Subnational Lobbying on National Policymaking: Evidence from Germany
Anonymous
2023-05-14
1. Packages
library(foreign)
#install.packages("ggplot2")
library(ggplot2)
#install.packages("tidyverse")
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ lubridate 1.9.2 ✔ tibble 3.2.1
## ✔ purrr 1.0.2 ✔ tidyr 1.3.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors#install.packages("plotly")
library(plotly)##
## Attaching package: 'plotly'
##
## The following object is masked from 'package:ggplot2':
##
## last_plot
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following object is masked from 'package:graphics':
##
## layout#install.packages("gapminder")
library(gapminder)
#install.packages("psych")
library(psych)##
## Attaching package: 'psych'
##
## The following objects are masked from 'package:ggplot2':
##
## %+%, alpha#install.packages("car")
library(car)## Loading required package: carData
##
## Attaching package: 'car'
##
## The following object is masked from 'package:psych':
##
## logit
##
## The following object is masked from 'package:dplyr':
##
## recode
##
## The following object is masked from 'package:purrr':
##
## somelibrary(carData)
#install.packages("forcats")
library(forcats)
#install.packages("DescTools")
library(DescTools)##
## Attaching package: 'DescTools'
##
## The following object is masked from 'package:car':
##
## Recode
##
## The following objects are masked from 'package:psych':
##
## AUC, ICC, SD#install.packages("e1071")
library(e1071)
#install.packages("sjPlot")
#install.packages("patchwork")
library(patchwork)
#install.packages("gridExtra")
library(gridExtra)##
## Attaching package: 'gridExtra'
##
## The following object is masked from 'package:dplyr':
##
## combine#install.packages("QuantPsyc")
#install.packages("lm.beta")
library(lm.beta)
library(sjPlot)
library(glmmTMB)## Warning in checkMatrixPackageVersion(): Package version inconsistency detected.
## TMB was built with Matrix version 1.6.0
## Current Matrix version is 1.6.1
## Please re-install 'TMB' from source using install.packages('TMB', type = 'source') or ask CRAN for a binary version of 'TMB' matching CRAN's 'Matrix' package## Warning in checkDepPackageVersion(dep_pkg = "TMB"): Package version inconsistency detected.
## glmmTMB was built with TMB version 1.9.4
## Current TMB version is 1.9.6
## Please re-install glmmTMB from source or restore original 'TMB' package (see '?reinstalling' for more information)#install.packages("tinytext")
library(tinytex)
#tinytex::install_tinytex()
#install_tinytex()
#install.packages("modelsummary")
library(modelsummary)##
## Attaching package: 'modelsummary'
##
## The following objects are masked from 'package:DescTools':
##
## Format, Mean, Median, N, SD, Var
##
## The following object is masked from 'package:psych':
##
## SD#install.packages("stargazer")
library(stargazer)##
## Please cite as:
##
## Hlavac, Marek (2022). stargazer: Well-Formatted Regression and Summary Statistics Tables.
## R package version 5.2.3. https://CRAN.R-project.org/package=stargazer#install.packages("webshot")
library(webshot)
#install.packages("Hmisc")
library(Hmisc)##
## Attaching package: 'Hmisc'
##
## The following object is masked from 'package:modelsummary':
##
## Mean
##
## The following object is masked from 'package:e1071':
##
## impute
##
## The following objects are masked from 'package:DescTools':
##
## %nin%, Label, Mean, Quantile
##
## The following object is masked from 'package:psych':
##
## describe
##
## The following object is masked from 'package:plotly':
##
## subplot
##
## The following objects are masked from 'package:dplyr':
##
## src, summarize
##
## The following objects are masked from 'package:base':
##
## format.pval, units#install.packages("dplyr")
library(dplyr)
#install.packages("VIM", dependencies = TRUE)
library(VIM)## Loading required package: colorspace
## Loading required package: grid
## The legacy packages maptools, rgdal, and rgeos, underpinning the sp package,
## which was just loaded, will retire in October 2023.
## Please refer to R-spatial evolution reports for details, especially
## https://r-spatial.org/r/2023/05/15/evolution4.html.
## It may be desirable to make the sf package available;
## package maintainers should consider adding sf to Suggests:.
## The sp package is now running under evolution status 2
## (status 2 uses the sf package in place of rgdal)
## VIM is ready to use.
##
## Suggestions and bug-reports can be submitted at: https://github.com/statistikat/VIM/issues
##
## Attaching package: 'VIM'
##
## The following object is masked from 'package:datasets':
##
## sleep#install.packages("mice")
library(mice)##
## Attaching package: 'mice'
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following objects are masked from 'package:base':
##
## cbind, rbind#install.packages("ggpubr")
library(ggpubr)
#install.packages("vtable")
library(vtable)## Loading required package: kableExtra
##
## Attaching package: 'kableExtra'
##
## The following object is masked from 'package:dplyr':
##
## group_rows
##
##
## Attaching package: 'vtable'
##
## The following object is masked from 'package:VIM':
##
## countNA#install.packages("lme4")
library(lme4)## Loading required package: Matrix
##
## Attaching package: 'Matrix'
##
## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpack#install.packages("easystats")
library(easystats)## # Attaching packages: easystats 0.6.0 (red = needs update)
## ✖ bayestestR 0.13.1 ✔ correlation 0.8.4
## ✖ datawizard 0.9.1 ✖ effectsize 0.8.6
## ✖ insight 0.19.8 ✖ modelbased 0.8.6
## ✖ performance 0.10.5 ✖ parameters 0.21.5
## ✖ report 0.5.7 ✖ see 0.8.0
##
## Restart the R-Session and update packages in red with `easystats::easystats_update()`.#install.packages("esquisse")
library(esquisse)
#install.packages("devtools")
library(openai)
require(devtools)## Loading required package: devtools
## Loading required package: usethis#install.packages("pander")
library(pander)
#install.packages("lmtest")
library(lmtest)## Loading required package: zoo
##
## Attaching package: 'zoo'
##
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric#install.packages("sandwich")
library(sandwich)
#install.packages("miceadds")
library(miceadds)## * miceadds 3.16-18 (2023-01-06 10:54:00)#install.packages("expss")
library(expss)## Loading required package: maditr
##
## To aggregate data: take(mtcars, mean_mpg = mean(mpg), by = am)
##
##
## Attaching package: 'maditr'
##
## The following object is masked from 'package:DescTools':
##
## %like%
##
## The following objects are masked from 'package:dplyr':
##
## between, coalesce, first, last
##
## The following object is masked from 'package:purrr':
##
## transpose
##
## The following object is masked from 'package:readr':
##
## cols
##
## Registered S3 methods overwritten by 'expss':
## method from
## [.labelled Hmisc
## as.data.frame.labelled base
## print.labelled Hmisc
##
## Attaching package: 'expss'
##
## The following object is masked from 'package:lme4':
##
## dummy
##
## The following object is masked from 'package:ggpubr':
##
## compare_means
##
## The following object is masked from 'package:car':
##
## recode
##
## The following objects are masked from 'package:stringr':
##
## fixed, regex
##
## The following objects are masked from 'package:dplyr':
##
## compute, contains, na_if, recode, vars, where
##
## The following objects are masked from 'package:purrr':
##
## keep, modify, modify_if, when
##
## The following objects are masked from 'package:tidyr':
##
## contains, nest
##
## The following object is masked from 'package:ggplot2':
##
## vars#install.packages("logistf")
library(logistf)
#install.packages("parameters")
library(parameters)
install.packages## function (pkgs, lib, repos = getOption("repos"), contriburl = contrib.url(repos,
## type), method, available = NULL, destdir = NULL, dependencies = NA,
## type = getOption("pkgType"), configure.args = getOption("configure.args"),
## configure.vars = getOption("configure.vars"), clean = FALSE,
## Ncpus = getOption("Ncpus", 1L), verbose = getOption("verbose"),
## libs_only = FALSE, INSTALL_opts, quiet = FALSE, keep_outputs = FALSE,
## ...)
## {
## if (!is.character(type))
## stop("invalid 'type'; must be a character string")
## type2 <- .Platform$pkgType
## if (type == "binary") {
## if (type2 == "source")
## stop("type 'binary' is not supported on this platform")
## else type <- type2
## if (type == "both" && (!missing(contriburl) || !is.null(available)))
## stop("specifying 'contriburl' or 'available' requires a single type, not type = \"both\"")
## }
## if (is.logical(clean) && clean)
## clean <- "--clean"
## if (is.logical(dependencies) && is.na(dependencies))
## dependencies <- if (!missing(lib) && length(lib) > 1L)
## FALSE
## else c("Depends", "Imports", "LinkingTo")
## get_package_name <- function(pkg) {
## gsub("_[.](zip|tar[.]gz|tar[.]bzip2|tar[.]xz)", "", gsub(.standard_regexps()$valid_package_version,
## "", basename(pkg)))
## }
## getConfigureArgs <- function(pkg) {
## if (.Platform$OS.type == "windows")
## return(character())
## if (length(pkgs) == 1L && length(configure.args) && length(names(configure.args)) ==
## 0L)
## return(paste0("--configure-args=", shQuote(paste(configure.args,
## collapse = " "))))
## pkg <- get_package_name(pkg)
## if (length(configure.args) && length(names(configure.args)) &&
## pkg %in% names(configure.args))
## config <- paste0("--configure-args=", shQuote(paste(configure.args[[pkg]],
## collapse = " ")))
## else config <- character()
## config
## }
## getConfigureVars <- function(pkg) {
## if (.Platform$OS.type == "windows")
## return(character())
## if (length(pkgs) == 1L && length(configure.vars) && length(names(configure.vars)) ==
## 0L)
## return(paste0("--configure-vars=", shQuote(paste(configure.vars,
## collapse = " "))))
## pkg <- get_package_name(pkg)
## if (length(configure.vars) && length(names(configure.vars)) &&
## pkg %in% names(configure.vars))
## config <- paste0("--configure-vars=", shQuote(paste(configure.vars[[pkg]],
## collapse = " ")))
## else config <- character()
## config
## }
## get_install_opts <- function(pkg) {
## if (!length(INSTALL_opts))
## character()
## else paste(INSTALL_opts[[get_package_name(pkg)]], collapse = " ")
## }
## if (missing(pkgs)) {
## if (!interactive())
## stop("no packages were specified")
## if (.Platform$OS.type == "windows" || .Platform$GUI ==
## "AQUA" || (capabilities("tcltk") && capabilities("X11") &&
## suppressWarnings(tcltk::.TkUp))) {
## }
## else stop("no packages were specified")
## if (is.null(available)) {
## av <- available.packages(contriburl = contriburl,
## method = method, ...)
## if (missing(repos))
## repos <- getOption("repos")
## if (type != "both")
## available <- av
## }
## else av <- available
## if (NROW(av)) {
## pkgs <- select.list(sort(unique(rownames(av))), multiple = TRUE,
## title = "Packages", graphics = TRUE)
## }
## }
## if (.Platform$OS.type == "windows" && length(pkgs)) {
## pkgnames <- get_package_name(pkgs)
## inuse <- search()
## inuse <- sub("^package:", "", inuse[grep("^package:",
## inuse)])
## inuse <- pkgnames %in% inuse
## if (any(inuse)) {
## warning(sprintf(ngettext(sum(inuse), "package %s is in use and will not be installed",
## "packages %s are in use and will not be installed"),
## paste(sQuote(pkgnames[inuse]), collapse = ", ")),
## call. = FALSE, domain = NA, immediate. = TRUE)
## pkgs <- pkgs[!inuse]
## }
## }
## if (!length(pkgs))
## return(invisible())
## if (missing(lib) || is.null(lib)) {
## lib <- .libPaths()[1L]
## if (!quiet && length(.libPaths()) > 1L)
## message(sprintf(ngettext(length(pkgs), "Installing package into %s\n(as %s is unspecified)",
## "Installing packages into %s\n(as %s is unspecified)"),
## sQuote(lib), sQuote("lib")), domain = NA)
## }
## ok <- dir.exists(lib) & (file.access(lib, 2) == 0L)
## if (length(lib) > 1 && any(!ok))
## stop(sprintf(ngettext(sum(!ok), "'lib' element %s is not a writable directory",
## "'lib' elements %s are not writable directories"),
## paste(sQuote(lib[!ok]), collapse = ", ")), domain = NA)
## if (length(lib) == 1L && .Platform$OS.type == "windows") {
## ok <- dir.exists(lib)
## if (ok) {
## fn <- file.path(lib, paste0("_test_dir_", Sys.getpid()))
## unlink(fn, recursive = TRUE)
## res <- try(dir.create(fn, showWarnings = FALSE))
## if (inherits(res, "try-error") || !res)
## ok <- FALSE
## else unlink(fn, recursive = TRUE)
## }
## }
## if (length(lib) == 1L && !ok) {
## warning(gettextf("'lib = \"%s\"' is not writable", lib),
## domain = NA, immediate. = TRUE)
## userdir <- unlist(strsplit(Sys.getenv("R_LIBS_USER"),
## .Platform$path.sep))[1L]
## if (interactive()) {
## ans <- askYesNo(gettext("Would you like to use a personal library instead?"),
## default = FALSE)
## if (!isTRUE(ans))
## stop("unable to install packages")
## lib <- userdir
## if (!file.exists(userdir)) {
## ans <- askYesNo(gettextf("Would you like to create a personal library\n%s\nto install packages into?",
## sQuote(userdir)), default = FALSE)
## if (!isTRUE(ans))
## stop("unable to install packages")
## if (!dir.create(userdir, recursive = TRUE))
## stop(gettextf("unable to create %s", sQuote(userdir)),
## domain = NA)
## .libPaths(c(userdir, .libPaths()))
## }
## }
## else stop("unable to install packages")
## }
## lib <- normalizePath(lib)
## if (length(pkgs) == 1L && missing(repos) && missing(contriburl)) {
## if ((type == "source" && any(grepl("[.]tar[.](gz|bz2|xz)$",
## pkgs))) || (type %in% "win.binary" && endsWith(pkgs,
## ".zip")) || (startsWith(type, "mac.binary") && endsWith(pkgs,
## ".tgz"))) {
## repos <- NULL
## message("inferring 'repos = NULL' from 'pkgs'")
## }
## if (type == "both") {
## if (type2 %in% "win.binary" && endsWith(pkgs, ".zip")) {
## repos <- NULL
## type <- type2
## message("inferring 'repos = NULL' from 'pkgs'")
## }
## else if (startsWith(type2, "mac.binary") && endsWith(pkgs,
## ".tgz")) {
## repos <- NULL
## type <- type2
## message("inferring 'repos = NULL' from 'pkgs'")
## }
## else if (grepl("[.]tar[.](gz|bz2|xz)$", pkgs)) {
## repos <- NULL
## type <- "source"
## message("inferring 'repos = NULL' from 'pkgs'")
## }
## }
## }
## if (length(pkgs) == 1L && is.null(repos) && type == "both") {
## if ((type2 %in% "win.binary" && endsWith(pkgs, ".zip")) ||
## (startsWith(type2, "mac.binary") && endsWith(pkgs,
## ".tgz"))) {
## type <- type2
## }
## else if (grepl("[.]tar[.](gz|bz2|xz)$", pkgs)) {
## type <- "source"
## }
## }
## if (is.null(repos) && missing(contriburl)) {
## tmpd <- destdir
## nonlocalrepos <- any(web <- grepl("^(http|https|ftp)://",
## pkgs))
## if (is.null(destdir) && nonlocalrepos) {
## tmpd <- file.path(tempdir(), "downloaded_packages")
## if (!file.exists(tmpd) && !dir.create(tmpd))
## stop(gettextf("unable to create temporary directory %s",
## sQuote(tmpd)), domain = NA)
## }
## if (nonlocalrepos) {
## df <- function(p, destfile, method, ...) download.file(p,
## destfile, method, mode = "wb", ...)
## urls <- pkgs[web]
## for (p in unique(urls)) {
## this <- pkgs == p
## destfile <- file.path(tmpd, basename(p))
## res <- try(df(p, destfile, method, ...))
## if (!inherits(res, "try-error") && res == 0L)
## pkgs[this] <- destfile
## else {
## pkgs[this] <- NA
## }
## }
## }
## }
## if (type == "both") {
## if (type2 == "source")
## stop("type == \"both\" can only be used on Windows or a CRAN build for macOS")
## if (!missing(contriburl) || !is.null(available))
## type <- type2
## }
## getDeps <- TRUE
## if (type == "both") {
## if (is.null(repos))
## stop("type == \"both\" cannot be used with 'repos = NULL'")
## type <- "source"
## contriburl <- contrib.url(repos, "source")
## if (missing(repos))
## repos <- getOption("repos")
## available <- available.packages(contriburl = contriburl,
## method = method, fields = "NeedsCompilation", ...)
## pkgs <- getDependencies(pkgs, dependencies, available,
## lib, ...)
## getDeps <- FALSE
## av2 <- available.packages(contriburl = contrib.url(repos,
## type2), method = method, ...)
## bins <- row.names(av2)
## bins <- pkgs[pkgs %in% bins]
## srcOnly <- pkgs[!pkgs %in% bins]
## binvers <- av2[bins, "Version"]
## hasArchs <- !is.na(av2[bins, "Archs"])
## needsCmp <- !(available[bins, "NeedsCompilation"] %in%
## "no")
## hasSrc <- hasArchs | needsCmp
## srcvers <- available[bins, "Version"]
## later <- as.numeric_version(binvers) < srcvers
## action <- getOption("install.packages.compile.from.source",
## "interactive")
## if (!nzchar(Sys.which(Sys.getenv("MAKE", "make"))))
## action <- "never"
## if (grepl("darwin", R.version$platform) && !length(srcOnly))
## later[later] <- FALSE
## if (any(later)) {
## msg <- ngettext(sum(later), "There is a binary version available but the source version is later",
## "There are binary versions available but the source versions are later")
## cat("\n", paste(strwrap(msg, indent = 2, exdent = 2),
## collapse = "\n"), ":\n", sep = "")
## out <- data.frame(binary = binvers, source = srcvers,
## needs_compilation = hasSrc, row.names = bins,
## check.names = FALSE)[later, ]
## print(out)
## cat("\n")
## if (any(later & hasSrc)) {
## if (action == "interactive" && interactive()) {
## msg <- ngettext(sum(later & hasSrc), "Do you want to install from sources the package which needs compilation?",
## "Do you want to install from sources the packages which need compilation?")
## res <- askYesNo(msg)
## if (is.na(res))
## stop("Cancelled by user")
## if (!isTRUE(res))
## later <- later & !hasSrc
## }
## else if (action == "never") {
## cat(" Binaries will be installed\n")
## later <- later & !hasSrc
## }
## }
## }
## bins <- bins[!later]
## if (length(srcOnly)) {
## s2 <- srcOnly[!(available[srcOnly, "NeedsCompilation"] %in%
## "no")]
## if (length(s2)) {
## msg <- ngettext(length(s2), "Package which is only available in source form, and may need compilation of C/C++/Fortran",
## "Packages which are only available in source form, and may need compilation of C/C++/Fortran")
## msg <- c(paste0(msg, ": "), sQuote(s2))
## msg <- strwrap(paste(msg, collapse = " "), exdent = 2)
## message(paste(msg, collapse = "\n"), domain = NA)
## if (action == "interactive" && interactive()) {
## res <- askYesNo("Do you want to attempt to install these from sources?")
## if (is.na(res))
## stop("Cancelled by user")
## if (!isTRUE(res))
## pkgs <- setdiff(pkgs, s2)
## }
## else if (action == "never") {
## cat(" These will not be installed\n")
## pkgs <- setdiff(pkgs, s2)
## }
## }
## }
## if (length(bins)) {
## if (type2 == "win.binary")
## .install.winbinary(pkgs = bins, lib = lib, contriburl = contrib.url(repos,
## type2), method = method, available = av2, destdir = destdir,
## dependencies = NULL, libs_only = libs_only,
## quiet = quiet, ...)
## else .install.macbinary(pkgs = bins, lib = lib, contriburl = contrib.url(repos,
## type2), method = method, available = av2, destdir = destdir,
## dependencies = NULL, quiet = quiet, ...)
## }
## pkgs <- setdiff(pkgs, bins)
## if (!length(pkgs))
## return(invisible())
## message(sprintf(ngettext(length(pkgs), "installing the source package %s",
## "installing the source packages %s"), paste(sQuote(pkgs),
## collapse = ", ")), "\n", domain = NA)
## flush.console()
## }
## else if (getOption("install.packages.check.source", "yes") %in%
## "yes" && (type %in% "win.binary" || startsWith(type,
## "mac.binary"))) {
## if (missing(contriburl) && is.null(available) && !is.null(repos)) {
## contriburl2 <- contrib.url(repos, "source")
## if (missing(repos))
## repos <- getOption("repos")
## av1 <- tryCatch(suppressWarnings(available.packages(contriburl = contriburl2,
## method = method, ...)), error = function(e) e)
## if (inherits(av1, "error")) {
## message("source repository is unavailable to check versions")
## available <- available.packages(contriburl = contrib.url(repos,
## type), method = method, ...)
## }
## else {
## srcpkgs <- pkgs[pkgs %in% row.names(av1)]
## available <- available.packages(contriburl = contrib.url(repos,
## type), method = method, ...)
## bins <- pkgs[pkgs %in% row.names(available)]
## na <- srcpkgs[!srcpkgs %in% bins]
## if (length(na)) {
## msg <- sprintf(ngettext(length(na), "package %s is available as a source package but not as a binary",
## "packages %s are available as source packages but not as binaries"),
## paste(sQuote(na), collapse = ", "))
## cat("\n ", msg, "\n\n", sep = "")
## }
## binvers <- available[bins, "Version"]
## srcvers <- binvers
## OK <- bins %in% srcpkgs
## srcvers[OK] <- av1[bins[OK], "Version"]
## later <- as.numeric_version(binvers) < srcvers
## if (any(later)) {
## msg <- ngettext(sum(later), "There is a binary version available (and will be installed) but the source version is later",
## "There are binary versions available (and will be installed) but the source versions are later")
## cat("\n", paste(strwrap(msg, indent = 2, exdent = 2),
## collapse = "\n"), ":\n", sep = "")
## print(data.frame(binary = binvers, source = srcvers,
## row.names = bins, check.names = FALSE)[later,
## ])
## cat("\n")
## }
## }
## }
## }
## if (.Platform$OS.type == "windows") {
## if (startsWith(type, "mac.binary"))
## stop("cannot install macOS binary packages on Windows")
## if (type %in% "win.binary") {
## .install.winbinary(pkgs = pkgs, lib = lib, contriburl = contriburl,
## method = method, available = available, destdir = destdir,
## dependencies = dependencies, libs_only = libs_only,
## quiet = quiet, ...)
## return(invisible())
## }
## have_spaces <- grep(" ", pkgs)
## if (length(have_spaces)) {
## p <- pkgs[have_spaces]
## dirs <- shortPathName(dirname(p))
## pkgs[have_spaces] <- file.path(dirs, basename(p))
## }
## pkgs <- gsub("\\", "/", pkgs, fixed = TRUE)
## }
## else {
## if (startsWith(type, "mac.binary")) {
## if (!grepl("darwin", R.version$platform))
## stop("cannot install macOS binary packages on this platform")
## .install.macbinary(pkgs = pkgs, lib = lib, contriburl = contriburl,
## method = method, available = available, destdir = destdir,
## dependencies = dependencies, quiet = quiet, ...)
## return(invisible())
## }
## if (type %in% "win.binary")
## stop("cannot install Windows binary packages on this platform")
## if (!file.exists(file.path(R.home("bin"), "INSTALL")))
## stop("This version of R is not set up to install source packages\nIf it was installed from an RPM, you may need the R-devel RPM")
## }
## cmd0 <- file.path(R.home("bin"), "R")
## args0 <- c("CMD", "INSTALL")
## output <- if (quiet)
## FALSE
## else ""
## env <- character()
## tlim <- Sys.getenv("_R_INSTALL_PACKAGES_ELAPSED_TIMEOUT_")
## tlim <- if (!nzchar(tlim))
## 0
## else tools:::get_timeout(tlim)
## outdir <- getwd()
## if (is.logical(keep_outputs)) {
## if (is.na(keep_outputs))
## keep_outputs <- FALSE
## }
## else if (is.character(keep_outputs) && (length(keep_outputs) ==
## 1L)) {
## if (!dir.exists(keep_outputs) && !dir.create(keep_outputs,
## recursive = TRUE))
## stop(gettextf("unable to create %s", sQuote(keep_outputs)),
## domain = NA)
## outdir <- normalizePath(keep_outputs)
## keep_outputs <- TRUE
## }
## else stop(gettextf("invalid %s argument", sQuote("keep_outputs")),
## domain = NA)
## if (length(libpath <- .R_LIBS())) {
## if (.Platform$OS.type == "windows") {
## oldrlibs <- Sys.getenv("R_LIBS")
## Sys.setenv(R_LIBS = libpath)
## on.exit(Sys.setenv(R_LIBS = oldrlibs))
## }
## else env <- paste0("R_LIBS=", shQuote(libpath))
## }
## if (is.character(clean))
## args0 <- c(args0, clean)
## if (libs_only)
## args0 <- c(args0, "--libs-only")
## if (!missing(INSTALL_opts)) {
## if (!is.list(INSTALL_opts)) {
## args0 <- c(args0, paste(INSTALL_opts, collapse = " "))
## INSTALL_opts <- list()
## }
## }
## else {
## INSTALL_opts <- list()
## }
## if (verbose)
## message(gettextf("system (cmd0): %s", paste(c(cmd0, args0),
## collapse = " ")), domain = NA)
## if (is.null(repos) && missing(contriburl)) {
## update <- cbind(path.expand(pkgs), lib)
## for (i in seq_len(nrow(update))) {
## if (is.na(update[i, 1L]))
## next
## args <- c(args0, get_install_opts(update[i, 1L]),
## "-l", shQuote(update[i, 2L]), getConfigureArgs(update[i,
## 1L]), getConfigureVars(update[i, 1L]), shQuote(update[i,
## 1L]))
## status <- system2(cmd0, args, env = env, stdout = output,
## stderr = output, timeout = tlim)
## if (status > 0L)
## warning(gettextf("installation of package %s had non-zero exit status",
## sQuote(update[i, 1L])), domain = NA)
## else if (verbose) {
## cmd <- paste(c(cmd0, args), collapse = " ")
## message(sprintf("%d): succeeded '%s'", i, cmd),
## domain = NA)
## }
## }
## return(invisible())
## }
## tmpd <- destdir
## nonlocalrepos <- !all(startsWith(contriburl, "file:"))
## if (is.null(destdir) && nonlocalrepos) {
## tmpd <- file.path(tempdir(), "downloaded_packages")
## if (!file.exists(tmpd) && !dir.create(tmpd))
## stop(gettextf("unable to create temporary directory %s",
## sQuote(tmpd)), domain = NA)
## }
## av2 <- NULL
## if (is.null(available)) {
## filters <- getOption("available_packages_filters")
## if (!is.null(filters)) {
## available <- available.packages(contriburl = contriburl,
## method = method, ...)
## }
## else {
## f <- setdiff(available_packages_filters_default,
## c("R_version", "duplicates"))
## av2 <- available.packages(contriburl = contriburl,
## filters = f, method = method, ...)
## f <- available_packages_filters_db[["R_version"]]
## f2 <- available_packages_filters_db[["duplicates"]]
## available <- f2(f(av2))
## }
## }
## if (getDeps)
## pkgs <- getDependencies(pkgs, dependencies, available,
## lib, ..., av2 = av2)
## foundpkgs <- download.packages(pkgs, destdir = tmpd, available = available,
## contriburl = contriburl, method = method, type = "source",
## quiet = quiet, ...)
## if (length(foundpkgs)) {
## if (verbose)
## message(gettextf("foundpkgs: %s", paste(foundpkgs,
## collapse = ", ")), domain = NA)
## update <- unique(cbind(pkgs, lib))
## colnames(update) <- c("Package", "LibPath")
## found <- pkgs %in% foundpkgs[, 1L]
## files <- foundpkgs[match(pkgs[found], foundpkgs[, 1L]),
## 2L]
## if (verbose)
## message(gettextf("files: %s", paste(files, collapse = ", \n\t")),
## domain = NA)
## update <- cbind(update[found, , drop = FALSE], file = files)
## if (nrow(update) > 1L) {
## upkgs <- unique(pkgs <- update[, 1L])
## DL <- .make_dependency_list(upkgs, available)
## p0 <- .find_install_order(upkgs, DL)
## update <- update[sort.list(match(pkgs, p0)), ]
## }
## if (Ncpus > 1L && nrow(update) > 1L) {
## tlim_cmd <- character()
## if (tlim > 0) {
## if (.Platform$OS.type == "windows" && !nzchar(Sys.getenv("R_TIMEOUT")) &&
## grepl("\\windows\\system32\\", tolower(Sys.which("timeout")),
## fixed = TRUE)) {
## warning("Windows default 'timeout' command is not usable for parallel installs")
## }
## else if (nzchar(timeout <- Sys.which(Sys.getenv("R_TIMEOUT",
## "timeout")))) {
## tlim_cmd <- c(shQuote(timeout), "-s INT", tlim)
## }
## else warning("timeouts for parallel installs require the 'timeout' command")
## }
## args0 <- c(args0, "--pkglock")
## tmpd2 <- file.path(tempdir(), "make_packages")
## if (!file.exists(tmpd2) && !dir.create(tmpd2))
## stop(gettextf("unable to create temporary directory %s",
## sQuote(tmpd2)), domain = NA)
## mfile <- file.path(tmpd2, "Makefile")
## conn <- file(mfile, "wt")
## deps <- paste(paste0(update[, 1L], ".ts"), collapse = " ")
## deps <- strwrap(deps, width = 75, exdent = 2)
## deps <- paste(deps, collapse = " \\\n")
## cat("all: ", deps, "\n", sep = "", file = conn)
## aDL <- .make_dependency_list(upkgs, available, recursive = TRUE)
## for (i in seq_len(nrow(update))) {
## pkg <- update[i, 1L]
## fil <- update[i, 3L]
## args <- c(args0, get_install_opts(fil), "-l",
## shQuote(update[i, 2L]), getConfigureArgs(fil),
## getConfigureVars(fil), shQuote(fil), ">", paste0(pkg,
## ".out"), "2>&1")
## cmd <- paste(c("MAKEFLAGS=", tlim_cmd, shQuote(cmd0),
## args), collapse = " ")
## deps <- aDL[[pkg]]
## deps <- deps[deps %in% upkgs]
## deps <- if (length(deps))
## paste(paste0(deps, ".ts"), collapse = " ")
## else ""
## cat(paste0(pkg, ".ts: ", deps), paste("\t@echo begin installing package",
## sQuote(pkg)), paste0("\t@", cmd, " && touch ",
## pkg, ".ts"), paste0("\t@cat ", pkg, ".out"),
## "", sep = "\n", file = conn)
## }
## close(conn)
## cwd <- setwd(tmpd2)
## on.exit(setwd(cwd))
## status <- system2(Sys.getenv("MAKE", "make"), c("-k -j",
## Ncpus), stdout = output, stderr = output, env = env)
## if (status > 0L) {
## pkgs <- update[, 1L]
## tss <- sub("[.]ts$", "", dir(".", pattern = "[.]ts$"))
## failed <- pkgs[!pkgs %in% tss]
## for (pkg in failed) system(paste0("cat ", pkg,
## ".out"))
## n <- length(failed)
## if (n == 1L)
## warning(gettextf("installation of package %s failed",
## sQuote(failed)), domain = NA)
## else if (n > 1L) {
## msg <- paste(sQuote(failed), collapse = ", ")
## if (nchar(msg) < 40)
## warning(gettextf("installation of %d packages failed: %s",
## n, msg), domain = NA)
## else warning(gettextf("installation of %d packages failed:\n %s",
## n, msg), domain = NA)
## }
## }
## if (keep_outputs)
## file.copy(paste0(update[, 1L], ".out"), outdir)
## file.copy(Sys.glob(paste0(update[, 1L], "*.zip")),
## cwd)
## file.copy(Sys.glob(paste0(update[, 1L], "*.tgz")),
## cwd)
## file.copy(Sys.glob(paste0(update[, 1L], "*.tar.gz")),
## cwd)
## setwd(cwd)
## on.exit()
## unlink(tmpd2, recursive = TRUE)
## }
## else {
## tmpd2 <- tempfile()
## if (!dir.create(tmpd2))
## stop(gettextf("unable to create temporary directory %s",
## sQuote(tmpd2)), domain = NA)
## outfiles <- file.path(tmpd2, paste0(update[, 1L],
## ".out"))
## for (i in seq_len(nrow(update))) {
## outfile <- if (keep_outputs)
## outfiles[i]
## else output
## fil <- update[i, 3L]
## args <- c(args0, get_install_opts(fil), "-l",
## shQuote(update[i, 2L]), getConfigureArgs(fil),
## getConfigureVars(fil), shQuote(fil))
## status <- system2(cmd0, args, env = env, stdout = outfile,
## stderr = outfile, timeout = tlim)
## if (!quiet && keep_outputs)
## writeLines(readLines(outfile))
## if (status > 0L)
## warning(gettextf("installation of package %s had non-zero exit status",
## sQuote(update[i, 1L])), domain = NA)
## else if (verbose) {
## cmd <- paste(c(cmd0, args), collapse = " ")
## message(sprintf("%d): succeeded '%s'", i, cmd),
## domain = NA)
## }
## }
## if (keep_outputs)
## file.copy(outfiles, outdir)
## unlink(tmpd2, recursive = TRUE)
## }
## if (!quiet && nonlocalrepos && !is.null(tmpd) && is.null(destdir))
## cat("\n", gettextf("The downloaded source packages are in\n\t%s",
## sQuote(normalizePath(tmpd, mustWork = FALSE))),
## "\n", sep = "", file = stderr())
## libs_used <- unique(update[, 2L])
## if (.Platform$OS.type == "unix" && .Library %in% libs_used) {
## message("Updating HTML index of packages in '.Library'")
## make.packages.html(.Library)
## }
## }
## else if (!is.null(tmpd) && is.null(destdir))
## unlink(tmpd, TRUE)
## invisible()
## }
## <bytecode: 0x11ebda278>
## <environment: namespace:utils>2. Data
#Subset
#Business organizations (V179 ,21-26 + V178, 7)
only_business <- subset(data, data$v_178 == '7' | data$v_179 %in% c(21:26))
#Public Interest groups
public_interest <- subset(data, !(data$v_178 == '7' | data$v_179 %in% c(21:26)))
#sum of people who contacted the Bundesrat and the committee of of inquiries about the EU
sum(data$v_258 == 1 & data$v_100 == 1)## [1] 02.1 Adding value labels
- The labels are created with the expss package
- To view the variable lable simply use var_lab()
- To viw the value lable simply use val_lab()
- or simply with base R attributes(data$variable) or attr(data$variable, “value.labels”)
#list_arg = list( ID.Gesetz = "Number of Law",
# ID.Gesetz = num_lab("
# 2 Fachkräfteeinwanderungsgesetz
# 3 Starke-Familien-Gesetz
# 4 Gesetz für mehr Sicherheit in der Arzneimittelversorgung
# 5 Gesetz gegen illegale Beschäftigung und Sozialleistungsmissbrauch
# 22 Gesetz zur Änderung des Strafgesetzbuchs
# 23 Gesetz zur Beschleunigung von Investitionen
# 6 Achtes Gesetz zur Änderung des Hochschulrahmengesetzes
# 7 Gesetz zur Änderung der zweiten Aktionärsrichtlinie
# 8 Drittes Gesetz zur Änderung des Asylbewerberleistungsgesetzes
# 10 Gesetz zur Änderung des Grundsteuergesetzes zur Mobilisierung von baureifen Grundstücken für die Bebauung
# 11 Gesetz zur weiteren steuerlichen Förderung der Elektromobilität und zur Änderung weiterer steuerlicher Vorschriften
# 21 Wohungseigentumsmodernisierungsgesetz
# 12 Gesetz zur Stärkung der Vor-Ort-Apotheken
# 13 Gesetz zur Entlastung unterhaltspflichtiger Angehöriger in der Sozialhilfe und in der Eingliederungshilfe
# 14 Gesetz Strukturänderungsgesetz Kohleregion
# 16 Gesetz zur Änderung des Aufstiegsfortbildungsfördergesetzes
# 17 Gesetz zur Umsetzung des Klimaschutzprogramms 2030 im Steuerrecht
# 15 Gesetz zur Einführung und Verwendung eines Tierwohlkennzeichens
# 24 Jahressteuergesetz 2020
# 25 Gestz zur Stärkung von Kindern und Jugendlichen
# "),
# titel.Gesetz = "name of the law",
# Subnational_jurisdiction = "is second chamber approval nessacery",
# Subnational_jurisdiction = num_lab("
# 0 no approval needed
# 1 approval of second chamber needed"),
# EU.origin = "law is crafted because of prior EU legislation",
# EU.origin = num_lab("0 no EU legislation origin
# 1 EU legislation origin"),
# salience = "Media salience; How often the proposal was adressed in media articels; continues variable from 0-n",
# lfdn = "anonymized ID of the surveyed persons; numbers are randomly assigned and cannot be used for Information of the Person",
# organization_long = "name of the interest group; character variable",
# organization_short = "abbreviation of the organizations name",
# organization_short = num_lab("
# -99 no abbreviation available"),
# v_176 = "identifyer of the organzation for the informations collected by Bochum; numbered consecutively",
# v_178 = "Actor type of the organization",
# v_178 = num_lab("
# 1 national interest group, Includes all forms of associations of individuals, businesses, public authorities and organizations
# 2 Politician or party, includes external politicians giving evidence to the committee such as Members of the Parliament or Members of the European Parliament, who are not members of the committee
# 3 Experts, includes experts with professional knowledge and instituional independence. University employees, jduges and medical staff. However, not if teh committee deals with matters in which the perosn may have personal or institutional interests
# 4 Central government actor, Includes government entities. Staff in departments and agencies, when acting on behalf of the unit
# 5 Local government actor, includes individual municipalities and municipal politicians in casses where the agent does not represent a local or regional interest group
# 6 Institutions, includes public and private institutions and staff group
# 7 Private firm, includes individual businesses, not representing a larger organization
# 8 Individuals, includes individual person who are not linked to any of teh above mentioned categories
# 9 Public committees, including public commissions, boards, councils and committees
# 10 Local interest group, includes non-national organizations, eg. local civic groups, sports associations and the like
# 11 International group, includes all international groups, however, German affiliations of international groups are coded 01
# 12 Regional group, includes regional groups such as Bavarian groups
# 13 Regional government actor, includdes government entities at the Federal State level
# 14 International organization
# 15 EU-Institutions
# 16 Other actors"),
# v_179 = "National Interest Group Categorization; Only used of v_178 is '[...] interest group'",
# v_179 = num_lab("
# 10 Unions, Associations of employees
# 11 Blue-collar unions, unions affiliated with the DGB
# 12 Other unions, unions not affiliated with the DGB
# 13 Other labour groups, groups that clearly represent the interests of organized labour but do not fit in ohter categories
# 20 Business groups, Associations of firms
# 21 Peak-level business groups, business groups representing all or major sectors of production according to the ISIC scheme
# 22 Sectoral business groups
# 23 Breed associations, associations of farmers with a focus on the breeding of animals
# 24 Technical associations, associations of business with a focus on technical issues
# 25 Other business groups, groups that represent business interests but do not fit in other categories
# 26 Agricultural groups
# 30 Institutional associations, Associations of public authorities or institutions
# 31 Associations of local authorities, associations where members are local or regional authorities
# 32 Associations of other public institutions, associations of institutions formally within the public sector
# 33 Associatoins of directors of institutions, associations of directors of institutions where the association represents the instituional interst not terms and conditinos of directors
# 34 Other institutional associations, associations of other institutions such as non-public schools or theaters
# 40 Occupational associations, associations of employees not negotiating terms and conditions, associations negotiating work-related terms and conditions are categorized in 11-13, 41-44 divison into categories is based on what profession the organization organizes
# 41 Doctos' associations
# 42 Associations of other medical professions
# 43 Teachers' associations
# 44 Other occupational associations
# 50 Identity groups associations where members/supporters have a selective interest in group goals (not work related), 51-56 division into categories is based on which group the organization organizes
# 51 Groups of patients or disabled
# 52 Elderly groups
# 53 Student groups
# 54 Friendship groups
# 55 Racial or ethnic groups
# 56 other identity groups
# 57 Gender
# 60 Hobby/leisure groups, associations of people with a common sport/leisure interest
# 61 Sport associations, associations of people engaged in sports
# 62 Other hobby/leisure groups, associations of people engaged in ohter leisure activities
# 63 Other cultural or leisure related groups
# 70 Religious groups, associations of people sharing a religion
# 71 Groups associated with the state church, groups declaring themselves as related to the state church
# 72 Other religious groups, other churches or groups representing people sharing a religion
# 73 Groups related to the Christian churches
# 80 Public interst groups, associations where members/supporters do not have a selective interst in group goals
# 81 Environment and animal welfare groups, groups working for causes related to the enhancement or protection of the environment, endangered species or animal welfare
# 82 Humanitarian groups - international, groups working with international causes such as human rights, world peace or general development
# 83 Humanitarian groups - national, Groups working with national causes such as child welfare, ethnic integration or alcohol abuse
# 84 Consumer groups, groups organizing consumers of general or specific goods
# 85 Other public interest groups, groups working with other causes"),
# Business.organization = "Is the interest group a Business organization?",
# Business.organization = num_lab("
# 1 Group is business organization
# 0 Group is not business organization"),
# duration = "Time it took the participant in seconds, continues variable",
# duration = num_lab("
# -1 Survey was restarted"),
# v_257 = "Part of National route: Deutscher Bundestag",
# v_257 = num_lab("
# 1 Yes
# 0 No"),
# v_259 = "Part of National route: Bundesregierung",
# v_259 = num_lab("
# 1 Yes
# 0 No"),
# national_route = "Was the National route taken?, only one of the two parts necessary",
# national_route = num_lab("
# 1 Route was taken
# 0 Route was not taken"),
# v_262 = "Part of Brussels route: Europäisches Parlament",
# v_262 = num_lab("
# 1 Yes
# 0 No"),
# v_263 = "Part of Brussels route: Rat der EU",
# v_263 = num_lab("
# 1 Yes
# 0 No"),
# v_264 = "Part of Brussels route: Europäische Kommission",
# v_264 = num_lab("
# 1 Yes
# 0 No"),
# v_266 = "Part of Brussels route: EWASA",
# v_266 = num_lab("
# 1 Yes
# 0 No"),
# brussels_route = "Was the Brussels route taken?, only one of the parts neccessary",
# brussels_route = num_lab("
# 1 Route was taken
# 0 Route was not taken"),
# v_258 = "Part of Subnational Berlin route : Bundesrat",
# v_258 = num_lab("
# 1 Yes
# 0 No"),
# v_260 = "Part of Subnational Berlin route : Landsregierungen",
# v_260 = num_lab("
# 1 Yes
# 0 No"),
# v_267 = "Part of Subnational Berlin route : Fachministerkonferenz der deutschen Länder",
# v_267 = num_lab("
# 1 Yes
# 0 No"),
# v_271 = "Part of Subnational Berlin route : Gemeinsame Wissenschaftsknoferenz",
# v_271 = num_lab("
# 1 Yes
# 0 No"),
# v_268 = "Part of Subnational Berlin route : Vertretung der Länder beim Bund",
# v_268 = num_lab("
# 1 Yes
# 0 No"),
# second_chamber_route = "Was the Subnational Berlin route taken?, only one of the parts neccessary",
# second_chamber_route = num_lab("
# 1 Route was taken
# 0 Route was not taken"),
# v_265 = "Part of Subnational-Brussels route: Europäischer Auschuss der Regionen",
# v_265 = num_lab("
# 1 Yes
# 0 No"),
# v_269 = "Part of Subnational-Brussels route: Vertretungen der Länder bei der EU",
# v_269 = num_lab("
# 1 Yes
# 0 No"),
# v_270 = "Part of Subnational-Brussels route: Beobachter der Länder bei der EU",
# v_270 = num_lab("
# 1 Yes
# 0 No"),
# subnational_brussels_route = "Was the Subnational-Brussels route taken? only one of the parts neccessary",
# subnational_brussels_route = num_lab("
# 1 Route was taken
# 0 Route was not taken"),
# v_3 = "Access to national-level policymakers, metric scale 1-10",
# v_3 = num_lab("
# 1 not agree
# 10 fully agree"),
# v_4 = "National-level policymaker opposes the position of the interest group",
# v_4 = num_lab("
# 1 not agree
# 10 fully agree"),
# v_6 = "Mobilization bias (Conflict)",
# v_6 = num_lab("
# 1 not agree
# 10 fully agree"),
# v_256 = "Are there one ore more federal government which sympathizes with your own position?",
# v_256 = num_lab("
# 1 Yes
# 0 No
# 3 Don't Know/No Answer
# -77 Missing"),
# länder_collaboration = "Which federal government sympathizes with your own position, counting variable of the federal states",
# länder_collaboration = num_lab("
# 1-16 number of Länder close to own position
# -77 Missing"),
# salience_igs = "Perceived salience of questioned person, the topic was visibal in the public discurse",
# salience_igs = num_lab("
# 1 not agree
# 10 fully agree"),
# v_2 = "Position of the interest group, was there seen need for change on the law",
# v_2 = num_lab("
# 0 not agree
# 10 fully agree"),
# v_168 = "Comments on the survey by participants, characters",
# v_168 = num_lab("
# -99 no comments"),
# v_169 = "mail of participants, to mail them the findings"
# )
#data1 <- apply_labels(data, list_arg)
#attributes(data1$EU.origin)3. Descriptive Statistics
3.1 Dependend Variables
3.1.1 Brusselsroute
the route is constructed with the following institutions:
EU Parliament (v_262)
Council of the EU (v_263)
EU Commission (v_264)
EESC (v_266)
Desc(data$brussels_route)## ------------------------------------------------------------------------------
## data$brussels_route (integer - dichotomous)
##
## length n NAs unique
## 341 341 0 2
## 100.0% 0.0%
##
## freq perc lci.95 uci.95'
## 0 314 92.1% 88.7% 94.5%
## 1 27 7.9% 5.5% 11.3%
##
## ' 95%-CI (Wilson)
data$brussels_route_z <- scale(data$brussels_route)
#Frequency of used institution
# Create a new row for the sum of variables
sum_row1 <- data.frame(
Variable1 = sum(data$v_262),
Variable2 = sum(data$v_263),
Variable3 = sum(data$v_264),
Variable4 = sum(data$v_266)
)
# Print the resulting data frame
print(sum_row1)## Variable1 Variable2 Variable3 Variable4
## 1 18 4 18 1#Proportion to the total count of the variable (N=238)
#EU Parliament
(8 / 238) * 100## [1] 3.361345#Council of the EU
(1 / 238) * 100## [1] 0.4201681#EU Commission
(11 / 238) * 100## [1] 4.621849#EESC
(1 / 238) * 100## [1] 0.42016813.1.2 Subnational Berlin Route
the route is construced with the following institutions:
Bundesrat (v_258)
Länder Governments (v_260)
conferences of Länder ministers (v_267)
Joint Science Conference (v_271)
representations of the Länder in the federal republic (v_268)
Desc(data$second_chamber_route)## ------------------------------------------------------------------------------
## data$second_chamber_route (integer - dichotomous)
##
## length n NAs unique
## 341 341 0 2
## 100.0% 0.0%
##
## freq perc lci.95 uci.95'
## 0 221 64.8% 59.6% 69.7%
## 1 120 35.2% 30.3% 40.4%
##
## ' 95%-CI (Wilson)
data$second_chamber_route_z <- scale(data$second_chamber_route)
#Frequency of used institution
# Create a new row for the sum of variables
sum_row2 <- data.frame(
Variable1 = sum(data$v_258),
Variable2 = sum(data$v_260),
Variable3 = sum(data$v_267),
Variable4 = sum(data$v_271),
Variable5 = sum(data$v_268)
)
# Print the resulting data frame
print(sum_row2)## Variable1 Variable2 Variable3 Variable4 Variable5
## 1 37 92 46 2 31#Proportion to the total count of the variable (N=238)
#Bundesrat
(29 / 238) * 100## [1] 12.18487#Länder Governments
(68 / 238) * 100## [1] 28.57143#Conferences of Länder ministers
(34 / 238) * 100## [1] 14.28571#Joint Science Conference
(2 / 238) * 100## [1] 0.8403361#representations of the Länder in the federal republic
(25 / 238) * 100## [1] 10.50423.1.3 Subnational brussels route
the route is construced with the following institutions:
Committee of the Regions (v_265)
representations of the Länder at the EU (v_269)
Observer of the Länder at the EU (v_270)
Desc(data$subnational_brussels_route)## ------------------------------------------------------------------------------
## data$subnational_brussels_route (integer - dichotomous)
##
## length n NAs unique
## 341 341 0 2
## 100.0% 0.0%
##
## freq perc lci.95 uci.95'
## 0 313 91.8% 88.4% 94.3%
## 1 28 8.2% 5.7% 11.6%
##
## ' 95%-CI (Wilson)
data$subnational_brussels_route_z <- scale(data$subnational_brussels_route)
#Frequency of used institution
# Create a new row for the sum of variables
sum_row3 <- data.frame(
Variable1 = sum(data$v_265),
Variable2 = sum(data$v_269),
Variable3 = sum(data$v_270)
)
# Print the resulting data frame
print(sum_row3)## Variable1 Variable2 Variable3
## 1 2 19 7#Proportion to the total count of the variable (N=238)
#Committee of the Regions
(2 / 238) * 100## [1] 0.8403361#Representations of the Länder at the EU
(16 / 238) * 100## [1] 6.722689#Observer of the Länder at the EU
(7 / 238) * 100## [1] 2.9411763.1.4 table of depended variables
#Tabelle der deskriptiven Beschreibung:
sumtable(data, vars = c('second_chamber_route', 'subnational_brussels_route')
,summ = list(
c('notNA(x)', 'mean(x)', 'median(x)', 'sd(x)', 'min(x)', 'max(x)', 'pctile(x)[25]', 'pctile(x)[75]')
),
summ.names = list(
c('N', 'Mean', 'Median', 'Standard Error', 'Minimum', 'Maximum', '1 Quantil', '4 Quantil')
)
,title = "Descriptive Statistics DV"
,labels = c("Subnational Berlin route", "Subnational Brussels route"), file = 'Deskriptive Statistik AV')## Warning in sumtable(data, vars = c("second_chamber_route", "subnational_brussels_route"), : Factor variables ignore custom summ options. Cols 1 and 2 are count and percentage.
## Beware combining factors with a custom summ unless factor.numeric = TRUE.| Variable | N | Mean | Median | Standard Error | Minimum | Maximum | 1 Quantil | 4 Quantil |
|---|---|---|---|---|---|---|---|---|
| Subnational Berlin route | 341 | 0.35 | 0 | 0.48 | 0 | 1 | 0 | 1 |
| Subnational Brussels route | 341 | 0.082 | 0 | 0.27 | 0 | 1 | 0 | 0 |
3.2 Independent Variables
Level 1
access to national-level policymakers (v_3)
national-level policymaker opposes the position of the interest group (v_4)
mobilization bias (v_6)
subnational policymaker supports the position of the group (Eigenes.BL.profitiert)
Subnational organization (v_178 = 5, 10, 12)
Level 2
- Type of the proposal (Subnational jurisdiction)
3.2.1 Group Level
#access to national-level policymakers
Desc(data$v_3)## ------------------------------------------------------------------------------
## data$v_3 (integer)
##
## length n NAs unique 0s mean meanCI'
## 341 341 0 11 46 4.16 3.84
## 100.0% 0.0% 13.5% 4.49
##
## .05 .10 .25 median .75 .90 .95
## 0.00 0.00 1.00 4.00 6.00 9.00 10.00
##
## range sd vcoef mad IQR skew kurt
## 10.00 3.07 0.74 4.45 5.00 0.29 -1.07
##
##
## value freq perc cumfreq cumperc
## 1 0 46 13.5% 46 13.5%
## 2 1 46 13.5% 92 27.0%
## 3 2 31 9.1% 123 36.1%
## 4 3 36 10.6% 159 46.6%
## 5 4 23 6.7% 182 53.4%
## 6 5 48 14.1% 230 67.4%
## 7 6 26 7.6% 256 75.1%
## 8 7 19 5.6% 275 80.6%
## 9 8 31 9.1% 306 89.7%
## 10 9 15 4.4% 321 94.1%
## 11 10 20 5.9% 341 100.0%
##
## ' 95%-CI (classic)
data$v_3_z <- scale(data$v_3)
#national-level policymaker opposes the position of the interest group
Desc(data$v_4)## ------------------------------------------------------------------------------
## data$v_4 (integer)
##
## length n NAs unique 0s mean meanCI'
## 341 341 0 11 49 3.32 3.04
## 100.0% 0.0% 14.4% 3.60
##
## .05 .10 .25 median .75 .90 .95
## 0.00 0.00 1.00 3.00 5.00 7.00 8.00
##
## range sd vcoef mad IQR skew kurt
## 10.00 2.60 0.78 2.97 4.00 0.58 -0.46
##
##
## value freq perc cumfreq cumperc
## 1 0 49 14.4% 49 14.4%
## 2 1 63 18.5% 112 32.8%
## 3 2 36 10.6% 148 43.4%
## 4 3 48 14.1% 196 57.5%
## 5 4 29 8.5% 225 66.0%
## 6 5 46 13.5% 271 79.5%
## 7 6 31 9.1% 302 88.6%
## 8 7 12 3.5% 314 92.1%
## 9 8 13 3.8% 327 95.9%
## 10 9 7 2.1% 334 97.9%
## 11 10 7 2.1% 341 100.0%
##
## ' 95%-CI (classic)
data$v_4_z <- scale(data$v_4)
#mobilization bias
Desc(data$v_6)## ------------------------------------------------------------------------------
## data$v_6 (integer)
##
## length n NAs unique 0s mean meanCI'
## 341 341 0 11 51 4.50 4.12
## 100.0% 0.0% 15.0% 4.87
##
## .05 .10 .25 median .75 .90 .95
## 0.00 0.00 1.00 4.00 8.00 10.00 10.00
##
## range sd vcoef mad IQR skew kurt
## 10.00 3.52 0.78 4.45 7.00 0.24 -1.37
##
##
## value freq perc cumfreq cumperc
## 1 0 51 15.0% 51 15.0%
## 2 1 53 15.5% 104 30.5%
## 3 2 31 9.1% 135 39.6%
## 4 3 21 6.2% 156 45.7%
## 5 4 16 4.7% 172 50.4%
## 6 5 37 10.9% 209 61.3%
## 7 6 23 6.7% 232 68.0%
## 8 7 17 5.0% 249 73.0%
## 9 8 24 7.0% 273 80.1%
## 10 9 23 6.7% 296 86.8%
## 11 10 45 13.2% 341 100.0%
##
## ' 95%-CI (classic)
data$v_6_z <- scale(data$v_6)
#Land benefits from collaboration
Desc(data$Eigenes.BL.profitiert) #0 = 210 (88,2%), 1 = 28 (11,8%)## ------------------------------------------------------------------------------
## data$Eigenes.BL.profitiert (integer)
##
## length n NAs unique 0s mean meanCI'
## 341 341 0 3 27 -61.98 -65.25
## 100.0% 0.0% 7.9% -58.71
##
## .05 .10 .25 median .75 .90 .95
## -77.00 -77.00 -77.00 -77.00 -77.00 1.00 1.00
##
## range sd vcoef mad IQR skew kurt
## 78.00 30.70 -0.50 0.00 0.00 1.54 0.39
##
##
## value freq perc cumfreq cumperc
## 1 -77 275 80.6% 275 80.6%
## 2 0 27 7.9% 302 88.6%
## 3 1 39 11.4% 341 100.0%
##
## ' 95%-CI (classic)
prop.table(table(data$Eigenes.BL.profitiert))##
## -77 0 1
## 0.80645161 0.07917889 0.11436950data$Eigenes.BL.profitiert_z <- scale(data$Eigenes.BL.profitiert)
#Changing the Missings of variable Eigenes.BL.profitiert to 0
data$Eigenes.BL.profitiert[data$Eigenes.BL.profitiert == -77] <- 0
#Subnational organization
data$local_regional_actor <- ifelse(data$v_178 %in% c(5, 10, 12), 1, 0)
Desc(data$local_regional_actor)## ------------------------------------------------------------------------------
## data$local_regional_actor (numeric)
##
## length n NAs unique 0s mean meanCI'
## 341 341 0 2 300 0.12 0.09
## 100.0% 0.0% 88.0% 0.15
##
## .05 .10 .25 median .75 .90 .95
## 0.00 0.00 0.00 0.00 0.00 1.00 1.00
##
## range sd vcoef mad IQR skew kurt
## 1.00 0.33 2.71 0.00 0.00 2.33 3.42
##
##
## value freq perc cumfreq cumperc
## 1 0 300 88.0% 300 88.0%
## 2 1 41 12.0% 341 100.0%
##
## ' 95%-CI (classic)
3.2.2 Proposal Level
#EU origin of the proposal
Desc(data$EU.origin)## ------------------------------------------------------------------------------
## data$EU.origin (integer - dichotomous)
##
## length n NAs unique
## 341 341 0 2
## 100.0% 0.0%
##
## freq perc lci.95 uci.95'
## 0 218 63.9% 58.7% 68.8%
## 1 123 36.1% 31.2% 41.3%
##
## ' 95%-CI (Wilson)
data$EU.origin_z <- scale(data$EU.origin)
#Type of proposal
Desc((data$Zustimmungsgesetz)) #0 = 96 (40,3%), 1 = 142 (59,7%)## ------------------------------------------------------------------------------
## (data$Zustimmungsgesetz) (integer - dichotomous)
##
## length n NAs unique
## 341 341 0 2
## 100.0% 0.0%
##
## freq perc lci.95 uci.95'
## 0 176 51.6% 46.3% 56.9%
## 1 165 48.4% 43.1% 53.7%
##
## ' 95%-CI (Wilson)
data$Zustimmungsgesetz_z <- scale(data$Zustimmungsgesetz)3.2.3 Table of Independed Variables
#Tabelle der deskriptiven Beschreibung:
sumtable(data, vars = c('v_3', 'v_4', 'v_6', 'Eigenes.BL.profitiert','Zustimmungsgesetz', 'local_regional_actor')
,summ = list(
c('notNA(x)', 'mean(x)', 'median(x)', 'sd(x)', 'min(x)', 'max(x)', 'pctile(x)[25]', 'pctile(x)[75]')
),
summ.names = list(
c('N', 'Mean', 'Median', 'Standard Error', 'Minimum', 'Maximum', '1 Quantil', '4 Quantil')
)
,title = "Descriptive Statistics IV"
,labels = c("Access to national-level policymakers", "National-level policymaker oposses position of group", "Mobilization bias", "subnational policymaker supports the position of the group","Subnational jurisdiction", "Subnational organization" ), file = 'Deskriptive Statistik UV')## Warning in sumtable(data, vars = c("v_3", "v_4", "v_6", "Eigenes.BL.profitiert", : Factor variables ignore custom summ options. Cols 1 and 2 are count and percentage.
## Beware combining factors with a custom summ unless factor.numeric = TRUE.| Variable | N | Mean | Median | Standard Error | Minimum | Maximum | 1 Quantil | 4 Quantil |
|---|---|---|---|---|---|---|---|---|
| Access to national-level policymakers | 341 | 4.2 | 4 | 3.1 | 0 | 10 | 1 | 6 |
| National-level policymaker oposses position of group | 341 | 3.3 | 3 | 2.6 | 0 | 10 | 1 | 5 |
| Mobilization bias | 341 | 4.5 | 4 | 3.5 | 0 | 10 | 1 | 8 |
| subnational policymaker supports the position of the group | 341 | 0.11 | 0 | 0.32 | 0 | 1 | 0 | 0 |
| Subnational jurisdiction | 341 | 0.48 | 0 | 0.5 | 0 | 1 | 0 | 1 |
| Subnational organization | 341 | 0.12 | 0 | 0.33 | 0 | 1 | 0 | 0 |
3.3 Controll variables
the Control variables are constructed from the following variables:
EU origin of the proposal (EU.origin)
Position of the interest groups (v_2)
Business organization (Business.organization)
Perceived Salience (salience_igs)
Media Salience (salience)
all routes from 3.1 besids the one thats already been used as the depened variable
Ressources:
Number of Lobbyist within the organization
Lobbyingbudget of Organization (in 10K steps)
#National route = Reference is route was not taken
#Frequency of used institution
# Create a new row for the sum of variables
sum_row4 <- data.frame(
Variable1 = sum(data$v_257),
Variable2 = sum(data$v_259)
)
data$national_route_z <- scale(data$national_route)
# Print the resulting data frame
print(sum_row4)## Variable1 Variable2
## 1 181 155#Proportion to the total count of the variable (N=238)
#Deutscher Bundestag
(136 / 238) * 100## [1] 57.14286#Bundesregierung
(113 / 238) * 100## [1] 47.47899#Business organization
Desc(data$Business.organization) #0 = 219 (64,2%), 1 = 122 (35,8%)## ------------------------------------------------------------------------------
## data$Business.organization (integer - dichotomous)
##
## length n NAs unique
## 341 341 0 2
## 100.0% 0.0%
##
## freq perc lci.95 uci.95'
## 0 219 64.2% 59.0% 69.1%
## 1 122 35.8% 30.9% 41.0%
##
## ' 95%-CI (Wilson)
data$Business.organization_z <- scale(data$Business.organization)
#Perceived Salience
Desc(data$salience_igs)## ------------------------------------------------------------------------------
## data$salience_igs (integer)
##
## length n NAs unique 0s mean meanCI'
## 341 341 0 11 45 4.45 4.12
## 100.0% 0.0% 13.2% 4.77
##
## .05 .10 .25 median .75 .90 .95
## 0.00 0.00 2.00 4.00 7.00 9.00 10.00
##
## range sd vcoef mad IQR skew kurt
## 10.00 3.05 0.69 2.97 5.00 0.19 -1.06
##
##
## value freq perc cumfreq cumperc
## 1 0 45 13.2% 45 13.2%
## 2 1 25 7.3% 70 20.5%
## 3 2 35 10.3% 105 30.8%
## 4 3 38 11.1% 143 41.9%
## 5 4 35 10.3% 178 52.2%
## 6 5 40 11.7% 218 63.9%
## 7 6 25 7.3% 243 71.3%
## 8 7 29 8.5% 272 79.8%
## 9 8 29 8.5% 301 88.3%
## 10 9 17 5.0% 318 93.3%
## 11 10 23 6.7% 341 100.0%
##
## ' 95%-CI (classic)
data$salience_igs_z <- scale(data$salience_igs)
#Position of the interest groups
Desc(data$v_2)## ------------------------------------------------------------------------------
## data$v_2 (integer)
##
## length n NAs unique 0s mean meanCI'
## 341 341 0 11 42 7.03 6.65
## 100.0% 0.0% 12.3% 7.41
##
## .05 .10 .25 median .75 .90 .95
## 0.00 0.00 5.00 8.00 10.00 10.00 10.00
##
## range sd vcoef mad IQR skew kurt
## 10.00 3.56 0.51 2.97 5.00 -0.98 -0.52
##
##
## value freq perc cumfreq cumperc
## 1 0 42 12.3% 42 12.3%
## 2 1 11 3.2% 53 15.5%
## 3 2 7 2.1% 60 17.6%
## 4 3 11 3.2% 71 20.8%
## 5 4 3 0.9% 74 21.7%
## 6 5 22 6.5% 96 28.2%
## 7 6 11 3.2% 107 31.4%
## 8 7 22 6.5% 129 37.8%
## 9 8 44 12.9% 173 50.7%
## 10 9 36 10.6% 209 61.3%
## 11 10 132 38.7% 341 100.0%
##
## ' 95%-CI (classic)
data$v_2_z <- scale(data$v_2)
#Media Salience
Desc(data$salience)## ------------------------------------------------------------------------------
## data$salience (integer)
##
## length n NAs unique 0s mean meanCI'
## 341 341 0 21 12 166.13 138.32
## 100.0% 0.0% 3.5% 193.93
##
## .05 .10 .25 median .75 .90 .95
## 1.00 5.00 10.00 87.00 184.00 906.00 906.00
##
## range sd vcoef mad IQR skew kurt
## 906.00 261.03 1.57 114.16 174.00 2.24 3.68
##
## lowest : 0 (12), 1 (8), 2 (2), 3 (8), 5 (17)
## highest: 154 (21), 184 (45), 208 (15), 211 (14), 906 (35)
##
## heap(?): remarkable frequency (13.8%) for the mode(s) (= 10)
##
## ' 95%-CI (classic)
data$salience_z <- scale(data$salience)
#Number of Lobbyists
data$lobbyists <- data$Beschäftigte..die.Interessenvertretung.unmittelbar.ausüben
Desc(data$lobbyists)## ------------------------------------------------------------------------------
## data$lobbyists (integer)
##
## length n NAs unique 0s mean meanCI'
## 341 185 156 38 27 13.46 10.14
## 54.3% 45.7% 7.9% 16.79
##
## .05 .10 .25 median .75 .90 .95
## 0.00 0.00 1.00 5.00 12.00 43.40 62.80
##
## range sd vcoef mad IQR skew kurt
## 122.00 22.93 1.70 5.93 11.00 2.77 8.09
##
## lowest : 0 (27), 1 (23), 2 (17), 3 (9), 4 (11)
## highest: 63 (2), 67, 77, 86 (3), 122 (3)
##
## heap(?): remarkable frequency (14.6%) for the mode(s) (= 0)
##
## ' 95%-CI (classic)
#Lobbybudget of Organization
data$budget <- data$Jährliche.finanzielle.Aufwendungen.im.Bereich.der.Interessenvertretung
Desc(data$budget)## ------------------------------------------------------------------------------
## data$budget (integer)
##
## length n NAs unique 0s mean meanCI'
## 341 177 164 78 4 92.31 67.47
## 51.9% 48.1% 1.2% 117.14
##
## .05 .10 .25 median .75 .90 .95
## 1.00 1.00 3.00 25.00 93.00 277.60 444.00
##
## range sd vcoef mad IQR skew kurt
## 824.00 167.41 1.81 35.58 90.00 2.84 8.24
##
## lowest : 0 (4), 1 (29), 2 (6), 3 (8), 4 (5)
## highest: 720, 741 (3), 789, 817, 824
##
## heap(?): remarkable frequency (16.4%) for the mode(s) (= 1)
##
## ' 95%-CI (classic)
#descripitive statistic control
sumtable(data, vars = c('EU.origin', 'v_2', 'Business.organization', 'salience_igs', 'salience', 'Bundesratsinitiative', 'national_route', 'subnational_brussels_route', 'second_chamber_route', 'brussels_route', 'lobbyists', 'budget')
,summ = list(
c('notNA(x)', 'mean(x)', 'median(x)', 'sd(x)', 'min(x)', 'max(x)', 'pctile(x)[25]', 'pctile(x)[75]')
),
summ.names = list(
c('N', 'Mean', 'Median', 'Standard Error', 'Minimum', 'Maximum', '1 Quantil', '4 Quantil')
)
,title = "descriptive statistics control"
,labels = c("EU origin of the proposal", "Position of the interest groups", "Business organization", "Perceived salience", "Media Salience", "Second Chamber Initiative", "National route", "Subnational Brussels route", "Subnational Berlin route", "Brussels route", "Number of Lobbyists within the Organization", "Budget used for lobbying") ,file = "Deskriptive Statistic Control")## Warning in sumtable(data, vars = c("EU.origin", "v_2", "Business.organization", : Factor variables ignore custom summ options. Cols 1 and 2 are count and percentage.
## Beware combining factors with a custom summ unless factor.numeric = TRUE.| Variable | N | Mean | Median | Standard Error | Minimum | Maximum | 1 Quantil | 4 Quantil |
|---|---|---|---|---|---|---|---|---|
| EU origin of the proposal | 341 | 0.36 | 0 | 0.48 | 0 | 1 | 0 | 1 |
| Position of the interest groups | 341 | 7 | 8 | 3.6 | 0 | 10 | 5 | 10 |
| Business organization | 341 | 0.36 | 0 | 0.48 | 0 | 1 | 0 | 1 |
| Perceived salience | 341 | 4.4 | 4 | 3.1 | 0 | 10 | 2 | 7 |
| Media Salience | 341 | 166 | 87 | 261 | 0 | 906 | 10 | 184 |
| Second Chamber Initiative | 341 | 0.21 | 0 | 0.4 | 0 | 1 | 0 | 0 |
| National route | 341 | 0.6 | 1 | 0.49 | 0 | 1 | 0 | 1 |
| Subnational Brussels route | 341 | 0.082 | 0 | 0.27 | 0 | 1 | 0 | 0 |
| Subnational Berlin route | 341 | 0.35 | 0 | 0.48 | 0 | 1 | 0 | 1 |
| Brussels route | 341 | 0.079 | 0 | 0.27 | 0 | 1 | 0 | 0 |
| Number of Lobbyists within the Organization | 185 | 13 | 5 | 23 | 0 | 122 | 1 | 12 |
| Budget used for lobbying | 177 | 92 | 25 | 167 | 0 | 824 | 3 | 93 |
5.Regression
- there will be calculated 3 different binominal regressions, for the different routes. The first three will be without the routes as control variables and the second three will be with the routes as control variables
5.1 null model
m0 <- glm(brussels_route ~ 1, data = data)
summary(m0)##
## Call:
## glm(formula = brussels_route ~ 1, data = data)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.07918 0.01464 5.407 1.21e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 0.07312403)
##
## Null deviance: 24.862 on 340 degrees of freedom
## Residual deviance: 24.862 on 340 degrees of freedom
## AIC: 78.796
##
## Number of Fisher Scoring iterations: 2#transform = Null noch hinzufügen damit logOdds angezeigt werden und nicht mehr Odds Ratios
tab_model(m0, transform = NULL)| brussels_route | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 0.08 | 0.05 – 0.11 | <0.001 |
| Observations | 341 | ||
| R2 | 0.000 | ||
# exp() / (1+exp())
PseudoR2(m0, which = "all")## McFadden McFaddenAdj CoxSnell Nagelkerke AldrichNelson
## 0.00000000 -0.02673954 0.00000000 0.00000000 0.00000000
## VeallZimmermann Efron McKelveyZavoina Tjur AIC
## 0.00000000 0.00000000 NA NA 78.79560964
## BIC logLik logLik0 G2
## 86.45937459 -37.39780482 -37.39780482 0.000000005.2 Level I (Group level)
5.2.1 Brusselsroute
m1 <- glm(brussels_route ~ 1 + v_3 + v_4 + v_6 + v_2 + salience_igs + Eigenes.BL.profitiert + Business.organization + EU.origin, data = data, family = binomial())
summary(m1)##
## Call:
## glm(formula = brussels_route ~ 1 + v_3 + v_4 + v_6 + v_2 + salience_igs +
## Eigenes.BL.profitiert + Business.organization + EU.origin,
## family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.40019 0.74181 -5.932 3e-09 ***
## v_3 0.01831 0.09020 0.203 0.839099
## v_4 0.04610 0.09904 0.465 0.641622
## v_6 0.08547 0.07003 1.221 0.222252
## v_2 0.05424 0.07771 0.698 0.485171
## salience_igs -0.11699 0.09416 -1.242 0.214084
## Eigenes.BL.profitiert 1.26478 0.52547 2.407 0.016086 *
## Business.organization 0.51612 0.43624 1.183 0.236774
## EU.origin 1.72312 0.48255 3.571 0.000356 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 188.75 on 340 degrees of freedom
## Residual deviance: 159.96 on 332 degrees of freedom
## AIC: 177.96
##
## Number of Fisher Scoring iterations: 6tab_model(m1, transform = NULL)| brussels_route | |||
|---|---|---|---|
| Predictors | Log-Odds | CI | p |
| (Intercept) | -4.40 | -6.03 – -3.09 | <0.001 |
| v 3 | 0.02 | -0.16 – 0.19 | 0.839 |
| v 4 | 0.05 | -0.15 – 0.24 | 0.642 |
| v 6 | 0.09 | -0.05 – 0.23 | 0.222 |
| v 2 | 0.05 | -0.09 – 0.22 | 0.485 |
| salience igs | -0.12 | -0.31 – 0.06 | 0.214 |
| Eigenes BL profitiert | 1.26 | 0.19 – 2.28 | 0.016 |
| Business organization | 0.52 | -0.34 – 1.38 | 0.237 |
| EU origin | 1.72 | 0.82 – 2.74 | <0.001 |
| Observations | 341 | ||
| R2 Tjur | 0.099 | ||
PseudoR2(m1, which = "all")## McFadden McFaddenAdj CoxSnell Nagelkerke AldrichNelson
## 0.15253785 0.05717354 0.08096635 0.19047469 0.07785873
## VeallZimmermann Efron McKelveyZavoina Tjur AIC
## 0.21852018 0.09360414 0.27824994 0.09886051 177.95836573
## BIC logLik logLik0 G2
## 212.44530803 -79.97918286 -94.37493180 28.79149786with routes as control variables
m1.1 <- glm(brussels_route ~ 1 + v_3 + v_4 + v_6 + v_2 + salience_igs + Eigenes.BL.profitiert + Business.organization + EU.origin + national_route + second_chamber_route + subnational_brussels_route, data = data, family = binomial())
summary(m1.1)##
## Call:
## glm(formula = brussels_route ~ 1 + v_3 + v_4 + v_6 + v_2 + salience_igs +
## Eigenes.BL.profitiert + Business.organization + EU.origin +
## national_route + second_chamber_route + subnational_brussels_route,
## family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -6.198315 1.062142 -5.836 5.36e-09 ***
## v_3 -0.053921 0.100549 -0.536 0.59178
## v_4 0.063795 0.107174 0.595 0.55168
## v_6 0.045898 0.078538 0.584 0.55894
## v_2 0.003515 0.089729 0.039 0.96875
## salience_igs -0.061859 0.104029 -0.595 0.55209
## Eigenes.BL.profitiert 0.271312 0.631431 0.430 0.66743
## Business.organization 0.467855 0.489868 0.955 0.33955
## EU.origin 2.173952 0.558503 3.892 9.92e-05 ***
## national_route 1.586786 0.816515 1.943 0.05197 .
## second_chamber_route 1.534518 0.575605 2.666 0.00768 **
## subnational_brussels_route 1.754138 0.708589 2.476 0.01330 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 188.75 on 340 degrees of freedom
## Residual deviance: 130.16 on 329 degrees of freedom
## AIC: 154.16
##
## Number of Fisher Scoring iterations: 7PseudoR2(m1.1, which = "all")## McFadden McFaddenAdj CoxSnell Nagelkerke AldrichNelson
## 0.3104177 0.1832653 0.1578709 0.3713939 0.1466281
## VeallZimmermann Efron McKelveyZavoina Tjur AIC
## 0.4115298 0.2645979 0.4942681 0.2584842 154.1585709
## BIC logLik logLik0 G2
## 200.1411606 -65.0792854 -94.3749318 58.59129275.2.2 Subnational Berlin route
m2 <- glm(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + v_2 + salience_igs + Eigenes.BL.profitiert + Business.organization + EU.origin, data = data, family = binomial())
summary(m2)##
## Call:
## glm(formula = second_chamber_route ~ 1 + v_3 + v_4 + v_6 + v_2 +
## salience_igs + Eigenes.BL.profitiert + Business.organization +
## EU.origin, family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.009093 0.383771 -5.235 1.65e-07 ***
## v_3 0.051187 0.053631 0.954 0.3399
## v_4 -0.005493 0.062024 -0.089 0.9294
## v_6 0.094536 0.040670 2.324 0.0201 *
## v_2 0.116344 0.046090 2.524 0.0116 *
## salience_igs -0.071524 0.051554 -1.387 0.1653
## Eigenes.BL.profitiert 2.041227 0.425596 4.796 1.62e-06 ***
## Business.organization 0.222421 0.267654 0.831 0.4060
## EU.origin -0.306807 0.269815 -1.137 0.2555
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 442.36 on 340 degrees of freedom
## Residual deviance: 382.86 on 332 degrees of freedom
## AIC: 400.86
##
## Number of Fisher Scoring iterations: 4PseudoR2(m2, which = "all")## McFadden McFaddenAdj CoxSnell Nagelkerke AldrichNelson
## 0.13449209 0.09380106 0.16009640 0.22030173 0.14855078
## VeallZimmermann Efron McKelveyZavoina Tjur AIC
## 0.26306396 0.16941802 0.22566597 0.16928685 400.86427535
## BIC logLik logLik0 G2
## 435.35121764 -191.43213767 -221.17895858 59.49364182with routes as control variables
m2.1 <- glm(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + v_2 + salience_igs + Eigenes.BL.profitiert + Business.organization + EU.origin + national_route + brussels_route + subnational_brussels_route , data = data, family = binomial())
summary(m2.1)##
## Call:
## glm(formula = second_chamber_route ~ 1 + v_3 + v_4 + v_6 + v_2 +
## salience_igs + Eigenes.BL.profitiert + Business.organization +
## EU.origin + national_route + brussels_route + subnational_brussels_route,
## family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.91095 0.48473 -6.005 1.91e-09 ***
## v_3 -0.03054 0.05922 -0.516 0.606074
## v_4 -0.00316 0.06912 -0.046 0.963533
## v_6 0.10546 0.04441 2.374 0.017576 *
## v_2 0.08726 0.05222 1.671 0.094685 .
## salience_igs -0.05246 0.05609 -0.935 0.349636
## Eigenes.BL.profitiert 2.11689 0.48106 4.400 1.08e-05 ***
## Business.organization 0.21824 0.29513 0.739 0.459636
## EU.origin -0.52307 0.31323 -1.670 0.094940 .
## national_route 1.63932 0.34146 4.801 1.58e-06 ***
## brussels_route 1.64874 0.55888 2.950 0.003177 **
## subnational_brussels_route 1.86869 0.56085 3.332 0.000863 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 442.36 on 340 degrees of freedom
## Residual deviance: 329.58 on 329 degrees of freedom
## AIC: 353.58
##
## Number of Fisher Scoring iterations: 5PseudoR2(m2.1, which = "all")## McFadden McFaddenAdj CoxSnell Nagelkerke AldrichNelson
## 0.2549572 0.2007025 0.2816081 0.3875087 0.2485384
## VeallZimmermann Efron McKelveyZavoina Tjur AIC
## 0.4401290 0.3001337 0.4515256 0.2994960 353.5755753
## BIC logLik logLik0 G2
## 399.5581651 -164.7877877 -221.1789586 112.7823418tab_model(m2.1, p.style = "stars", transform = NULL)| second_chamber_route | ||
|---|---|---|
| Predictors | Log-Odds | CI |
| (Intercept) | -2.91 *** | -3.93 – -2.02 |
| v 3 | -0.03 | -0.15 – 0.09 |
| v 4 | -0.00 | -0.14 – 0.13 |
| v 6 | 0.11 * | 0.02 – 0.19 |
| v 2 | 0.09 | -0.01 – 0.19 |
| salience igs | -0.05 | -0.16 – 0.06 |
| Eigenes BL profitiert | 2.12 *** | 1.22 – 3.12 |
| Business organization | 0.22 | -0.36 – 0.80 |
| EU origin | -0.52 | -1.15 – 0.08 |
| national route | 1.64 *** | 0.99 – 2.34 |
| brussels route | 1.65 ** | 0.59 – 2.81 |
|
subnational brussels route |
1.87 *** | 0.80 – 3.02 |
| Observations | 341 | |
| R2 Tjur | 0.299 | |
|
||
#without brussels route as control variable
m2.2 <- glm(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + v_2 + salience_igs + Eigenes.BL.profitiert + Business.organization + EU.origin + national_route + subnational_brussels_route , data = data, family = binomial())
tab_model(m2, m2.1, m2.2, p.style = "stars", transform = NULL)| second_chamber_route | second_chamber_route | second_chamber_route | ||||
|---|---|---|---|---|---|---|
| Predictors | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI |
| (Intercept) | -2.01 *** | -2.81 – -1.30 | -2.91 *** | -3.93 – -2.02 | -2.95 *** | -3.95 – -2.08 |
| v 3 | 0.05 | -0.05 – 0.16 | -0.03 | -0.15 – 0.09 | -0.04 | -0.15 – 0.08 |
| v 4 | -0.01 | -0.13 – 0.12 | -0.00 | -0.14 – 0.13 | 0.01 | -0.12 – 0.14 |
| v 6 | 0.09 * | 0.02 – 0.18 | 0.11 * | 0.02 – 0.19 | 0.11 * | 0.02 – 0.19 |
| v 2 | 0.12 * | 0.03 – 0.21 | 0.09 | -0.01 – 0.19 | 0.09 | -0.01 – 0.19 |
| salience igs | -0.07 | -0.17 – 0.03 | -0.05 | -0.16 – 0.06 | -0.06 | -0.17 – 0.04 |
| Eigenes BL profitiert | 2.04 *** | 1.25 – 2.94 | 2.12 *** | 1.22 – 3.12 | 2.07 *** | 1.19 – 3.06 |
| Business organization | 0.22 | -0.30 – 0.75 | 0.22 | -0.36 – 0.80 | 0.22 | -0.34 – 0.79 |
| EU origin | -0.31 | -0.84 – 0.22 | -0.52 | -1.15 – 0.08 | -0.27 | -0.85 – 0.30 |
| national route | 1.64 *** | 0.99 – 2.34 | 1.76 *** | 1.12 – 2.45 | ||
| brussels route | 1.65 ** | 0.59 – 2.81 | ||||
|
subnational brussels route |
1.87 *** | 0.80 – 3.02 | 1.99 *** | 0.96 – 3.10 | ||
| Observations | 341 | 341 | 341 | |||
| R2 Tjur | 0.169 | 0.299 | 0.272 | |||
|
||||||
5.2.3 Subnational_brussels_route
m3 <- glm(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + v_2 + salience_igs + Eigenes.BL.profitiert + Business.organization + EU.origin, data = data, family = binomial())
summary(m3)##
## Call:
## glm(formula = subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 +
## v_2 + salience_igs + Eigenes.BL.profitiert + Business.organization +
## EU.origin, family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.1202585 0.5166622 -4.104 4.06e-05 ***
## v_3 0.0812378 0.0865072 0.939 0.34769
## v_4 0.0181455 0.1093074 0.166 0.86815
## v_6 0.0005827 0.0699422 0.008 0.99335
## v_2 -0.0536790 0.0704732 -0.762 0.44624
## salience_igs -0.0593886 0.0854883 -0.695 0.48724
## Eigenes.BL.profitiert 1.4748924 0.4754194 3.102 0.00192 **
## Business.organization -0.4292384 0.4716046 -0.910 0.36274
## EU.origin -0.8792230 0.5245949 -1.676 0.09374 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 193.62 on 340 degrees of freedom
## Residual deviance: 176.67 on 332 degrees of freedom
## AIC: 194.67
##
## Number of Fisher Scoring iterations: 6PseudoR2(m3, which = "all")## McFadden McFaddenAdj CoxSnell Nagelkerke AldrichNelson
## 0.087541812 -0.005425135 0.048490467 0.111929134 0.047351919
## VeallZimmermann Efron McKelveyZavoina Tjur AIC
## 0.130748459 0.055226922 0.149502035 0.060113597 194.667599123
## BIC logLik logLik0 G2
## 229.154541419 -88.333799562 -96.808599830 16.949600536with routes as control variables
m3.1 <- glm(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + v_2 + salience_igs + Eigenes.BL.profitiert + Business.organization + EU.origin + national_route + second_chamber_route + brussels_route, data = data, family = binomial())
summary(m3.1)##
## Call:
## glm(formula = subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 +
## v_2 + salience_igs + Eigenes.BL.profitiert + Business.organization +
## EU.origin + national_route + second_chamber_route + brussels_route,
## family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.25163 0.56705 -3.971 7.16e-05 ***
## v_3 0.11939 0.09593 1.244 0.21333
## v_4 0.03204 0.11842 0.271 0.78670
## v_6 -0.03685 0.07374 -0.500 0.61723
## v_2 -0.05798 0.07447 -0.779 0.43622
## salience_igs -0.07471 0.09332 -0.801 0.42338
## Eigenes.BL.profitiert 0.79302 0.52753 1.503 0.13277
## Business.organization -0.63464 0.51719 -1.227 0.21978
## EU.origin -1.38983 0.62117 -2.237 0.02526 *
## national_route -1.24372 0.56355 -2.207 0.02732 *
## second_chamber_route 1.79442 0.57407 3.126 0.00177 **
## brussels_route 2.08644 0.69762 2.991 0.00278 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 193.62 on 340 degrees of freedom
## Residual deviance: 152.61 on 329 degrees of freedom
## AIC: 176.61
##
## Number of Fisher Scoring iterations: 6PseudoR2(m3.1, which = "all")## McFadden McFaddenAdj CoxSnell Nagelkerke AldrichNelson
## 0.21176958 0.08781365 0.11329342 0.26151190 0.10733506
## VeallZimmermann Efron McKelveyZavoina Tjur AIC
## 0.29637434 0.11450164 0.38127853 0.14238569 176.61496715
## BIC logLik logLik0 G2
## 222.59755688 -76.30748357 -96.80859983 41.00223251m3.2 <- glm(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + v_2 + salience_igs + Eigenes.BL.profitiert + Business.organization + EU.origin + national_route + second_chamber_route , data = data, family = binomial())
tab_model(m3, m3.1, m3.2, p.style = "stars", transform = NULL)| subnational_brussels_route | subnational_brussels_route | subnational_brussels_route | ||||
|---|---|---|---|---|---|---|
| Predictors | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI |
| (Intercept) | -2.12 *** | -3.24 – -1.19 | -2.25 *** | -3.48 – -1.23 | -2.24 *** | -3.43 – -1.25 |
| v 3 | 0.08 | -0.09 – 0.25 | 0.12 | -0.07 – 0.31 | 0.11 | -0.08 – 0.29 |
| v 4 | 0.02 | -0.20 – 0.23 | 0.03 | -0.21 – 0.26 | 0.02 | -0.21 – 0.25 |
| v 6 | 0.00 | -0.14 – 0.14 | -0.04 | -0.19 – 0.11 | -0.03 | -0.17 – 0.11 |
| v 2 | -0.05 | -0.19 – 0.09 | -0.06 | -0.21 – 0.09 | -0.08 | -0.22 – 0.06 |
| salience igs | -0.06 | -0.23 – 0.10 | -0.07 | -0.27 – 0.10 | -0.09 | -0.27 – 0.09 |
| Eigenes BL profitiert | 1.47 ** | 0.51 – 2.40 | 0.79 | -0.28 – 1.81 | 0.91 | -0.10 – 1.88 |
| Business organization | -0.43 | -1.42 – 0.45 | -0.63 | -1.73 – 0.33 | -0.51 | -1.53 – 0.41 |
| EU origin | -0.88 | -2.02 – 0.08 | -1.39 * | -2.75 – -0.27 | -0.87 | -2.02 – 0.12 |
| national route | -1.24 * | -2.38 – -0.16 | -0.86 | -1.89 – 0.15 | ||
| second chamber route | 1.79 ** | 0.71 – 2.98 | 1.98 *** | 0.95 – 3.12 | ||
| brussels route | 2.09 ** | 0.74 – 3.52 | ||||
| Observations | 341 | 341 | 341 | |||
| R2 Tjur | 0.060 | 0.142 | 0.108 | |||
|
||||||
Table with only Level 1 variables
tab_model(m1, m2, m3, p.style = "stars")| brussels_route | second_chamber_route | subnational_brussels_route | ||||
|---|---|---|---|---|---|---|
| Predictors | Odds Ratios | CI | Odds Ratios | CI | Odds Ratios | CI |
| (Intercept) | 0.01 *** | 0.00 – 0.05 | 0.13 *** | 0.06 – 0.27 | 0.12 *** | 0.04 – 0.31 |
| v 3 | 1.02 | 0.85 – 1.21 | 1.05 | 0.95 – 1.17 | 1.08 | 0.91 – 1.28 |
| v 4 | 1.05 | 0.86 – 1.27 | 0.99 | 0.88 – 1.12 | 1.02 | 0.82 – 1.26 |
| v 6 | 1.09 | 0.95 – 1.25 | 1.10 * | 1.02 – 1.19 | 1.00 | 0.87 – 1.15 |
| v 2 | 1.06 | 0.91 – 1.24 | 1.12 * | 1.03 – 1.23 | 0.95 | 0.83 – 1.09 |
| salience igs | 0.89 | 0.73 – 1.06 | 0.93 | 0.84 – 1.03 | 0.94 | 0.79 – 1.11 |
| Eigenes BL profitiert | 3.54 * | 1.21 – 9.77 | 7.70 *** | 3.49 – 18.89 | 4.37 ** | 1.67 – 10.98 |
| Business organization | 1.68 | 0.71 – 3.98 | 1.25 | 0.74 – 2.11 | 0.65 | 0.24 – 1.58 |
| EU origin | 5.60 *** | 2.27 – 15.45 | 0.74 | 0.43 – 1.24 | 0.42 | 0.13 – 1.08 |
| Observations | 341 | 341 | 341 | |||
| R2 Tjur | 0.099 | 0.169 | 0.060 | |||
|
||||||
5.3 Level I+II (Group + Proposal)
5.3.1 Brusselsroute
m4 <- glm(brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin, data = data, family = binomial())
summary(m4)##
## Call:
## glm(formula = brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert +
## Business.organization + salience_igs + Zustimmungsgesetz +
## salience + v_2 + EU.origin, family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -3.7495484 0.7794258 -4.811 1.5e-06 ***
## v_3 0.0331797 0.0927128 0.358 0.720436
## v_4 0.0362958 0.1005710 0.361 0.718176
## v_6 0.0566572 0.0733671 0.772 0.439971
## Eigenes.BL.profitiert 1.2334739 0.5402705 2.283 0.022426 *
## Business.organization 0.3177338 0.4464643 0.712 0.476671
## salience_igs -0.1255292 0.0954207 -1.316 0.188330
## Zustimmungsgesetz -1.1273576 0.5420011 -2.080 0.037526 *
## salience -0.0008789 0.0007880 -1.115 0.264706
## v_2 0.0723459 0.0809696 0.893 0.371593
## EU.origin 1.8360876 0.5046289 3.638 0.000274 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 188.75 on 340 degrees of freedom
## Residual deviance: 155.34 on 330 degrees of freedom
## AIC: 177.34
##
## Number of Fisher Scoring iterations: 6PseudoR2(m4, which = "all")## McFadden McFaddenAdj CoxSnell Nagelkerke AldrichNelson
## 0.17698278 0.06042641 0.09331780 0.21953166 0.08922272
## VeallZimmermann Efron McKelveyZavoina Tjur AIC
## 0.25041462 0.11762630 0.31500498 0.12253233 177.34438786
## BIC logLik logLik0 G2
## 219.49509511 -77.67219393 -94.37493180 33.40547574with routes as control variables
m4.1 <- glm(brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + national_route + subnational_brussels_route + second_chamber_route, data = data, family = binomial())
summary(m4.1)##
## Call:
## glm(formula = brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert +
## Business.organization + salience_igs + Zustimmungsgesetz +
## salience + v_2 + EU.origin + national_route + subnational_brussels_route +
## second_chamber_route, family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -5.3164474 1.0889206 -4.882 1.05e-06 ***
## v_3 -0.0760898 0.1054309 -0.722 0.47048
## v_4 0.0758524 0.1140737 0.665 0.50609
## v_6 -0.0147777 0.0838791 -0.176 0.86015
## Eigenes.BL.profitiert 0.0674617 0.6762788 0.100 0.92054
## Business.organization 0.0321747 0.5239201 0.061 0.95103
## salience_igs -0.0948979 0.1088624 -0.872 0.38336
## Zustimmungsgesetz -2.0098929 0.6779759 -2.965 0.00303 **
## salience -0.0013090 0.0009443 -1.386 0.16567
## v_2 0.0444930 0.0969348 0.459 0.64623
## EU.origin 2.4387689 0.6198370 3.935 8.34e-05 ***
## national_route 1.8894701 0.8539906 2.213 0.02693 *
## subnational_brussels_route 1.9397112 0.7859553 2.468 0.01359 *
## second_chamber_route 1.8056497 0.6131306 2.945 0.00323 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 188.75 on 340 degrees of freedom
## Residual deviance: 120.03 on 327 degrees of freedom
## AIC: 148.03
##
## Number of Fisher Scoring iterations: 7PseudoR2(m4.1, which = "all")## McFadden McFaddenAdj CoxSnell Nagelkerke AldrichNelson
## 0.3640663 0.2157218 0.1825107 0.4293595 0.1677191
## VeallZimmermann Efron McKelveyZavoina Tjur AIC
## 0.4707246 0.3536253 0.5667644 0.3315402 148.0324003
## BIC logLik logLik0 G2
## 201.6787550 -60.0162002 -94.3749318 68.71746335.3.2 Subnational Berlin route
m5 <- glm(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 + Business.organization + salience_igs + salience + Bundesratsinitiative + v_3:v_4, data = data, family = binomial())
summary(m5)##
## Call:
## glm(formula = second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert +
## Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 +
## Business.organization + salience_igs + salience + Bundesratsinitiative +
## v_3:v_4, family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.505e+00 4.955e-01 -5.055 4.29e-07 ***
## v_3 3.138e-02 8.265e-02 0.380 0.7042
## v_4 -7.009e-02 1.127e-01 -0.622 0.5338
## v_6 1.002e-01 4.242e-02 2.363 0.0181 *
## Eigenes.BL.profitiert 1.984e+00 4.350e-01 4.560 5.12e-06 ***
## Zustimmungsgesetz 6.534e-01 3.229e-01 2.024 0.0430 *
## local_regional_actor 9.908e-01 4.121e-01 2.404 0.0162 *
## EU.origin -2.559e-01 3.009e-01 -0.851 0.3950
## v_2 1.225e-01 4.997e-02 2.450 0.0143 *
## Business.organization 3.154e-01 2.813e-01 1.121 0.2621
## salience_igs -5.307e-02 5.410e-02 -0.981 0.3266
## salience 9.122e-05 6.090e-04 0.150 0.8809
## Bundesratsinitiative -2.128e-01 3.521e-01 -0.605 0.5455
## v_3:v_4 9.050e-03 1.754e-02 0.516 0.6059
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 442.36 on 340 degrees of freedom
## Residual deviance: 372.89 on 327 degrees of freedom
## AIC: 400.89
##
## Number of Fisher Scoring iterations: 4tab_model(m5, transform = NULL)| second_chamber_route | |||
|---|---|---|---|
| Predictors | Log-Odds | CI | p |
| (Intercept) | -2.51 | -3.53 – -1.58 | <0.001 |
| v 3 | 0.03 | -0.13 – 0.19 | 0.704 |
| v 4 | -0.07 | -0.30 – 0.15 | 0.534 |
| v 6 | 0.10 | 0.02 – 0.18 | 0.018 |
| Eigenes BL profitiert | 1.98 | 1.17 – 2.90 | <0.001 |
| Zustimmungsgesetz | 0.65 | 0.03 – 1.30 | 0.043 |
| local regional actor | 0.99 | 0.19 – 1.81 | 0.016 |
| EU origin | -0.26 | -0.85 – 0.33 | 0.395 |
| v 2 | 0.12 | 0.03 – 0.22 | 0.014 |
| Business organization | 0.32 | -0.24 – 0.87 | 0.262 |
| salience igs | -0.05 | -0.16 – 0.05 | 0.327 |
| salience | 0.00 | -0.00 – 0.00 | 0.881 |
| Bundesratsinitiative | -0.21 | -0.91 – 0.47 | 0.545 |
| v 3 × v 4 | 0.01 | -0.03 – 0.04 | 0.606 |
| Observations | 341 | ||
| R2 Tjur | 0.196 | ||
m5.z <- glm(second_chamber_route ~ 1 + v_3_z + v_4_z + v_6_z + Eigenes.BL.profitiert_z + Business.organization_z + salience_igs_z + Zustimmungsgesetz_z + salience_z + v_2_z + EU.origin_z + Business.organization_z:Eigenes.BL.profitiert_z + v_3_z:v_4_z, data = data, family = binomial())
summary(m5)##
## Call:
## glm(formula = second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert +
## Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 +
## Business.organization + salience_igs + salience + Bundesratsinitiative +
## v_3:v_4, family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.505e+00 4.955e-01 -5.055 4.29e-07 ***
## v_3 3.138e-02 8.265e-02 0.380 0.7042
## v_4 -7.009e-02 1.127e-01 -0.622 0.5338
## v_6 1.002e-01 4.242e-02 2.363 0.0181 *
## Eigenes.BL.profitiert 1.984e+00 4.350e-01 4.560 5.12e-06 ***
## Zustimmungsgesetz 6.534e-01 3.229e-01 2.024 0.0430 *
## local_regional_actor 9.908e-01 4.121e-01 2.404 0.0162 *
## EU.origin -2.559e-01 3.009e-01 -0.851 0.3950
## v_2 1.225e-01 4.997e-02 2.450 0.0143 *
## Business.organization 3.154e-01 2.813e-01 1.121 0.2621
## salience_igs -5.307e-02 5.410e-02 -0.981 0.3266
## salience 9.122e-05 6.090e-04 0.150 0.8809
## Bundesratsinitiative -2.128e-01 3.521e-01 -0.605 0.5455
## v_3:v_4 9.050e-03 1.754e-02 0.516 0.6059
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 442.36 on 340 degrees of freedom
## Residual deviance: 372.89 on 327 degrees of freedom
## AIC: 400.89
##
## Number of Fisher Scoring iterations: 4PseudoR2(m5, which = "all")## McFadden McFaddenAdj CoxSnell Nagelkerke AldrichNelson
## 0.15704532 0.09374816 0.18431338 0.25362566 0.16924550
## VeallZimmermann Efron McKelveyZavoina Tjur AIC
## 0.29971160 0.19621182 0.26241381 0.19584028 400.88767790
## BIC logLik logLik0 G2
## 454.53403258 -186.44383895 -221.17895858 69.47023927m5.r <- glm(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + local_regional_actor + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + budget + lobbyists + v_3:v_4, data = data, family = binomial())## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredsummary(m5.r)##
## Call:
## glm(formula = second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert +
## Business.organization + local_regional_actor + salience_igs +
## Zustimmungsgesetz + salience + v_2 + EU.origin + budget +
## lobbyists + v_3:v_4, family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.535e+00 7.752e-01 -3.270 0.00107 **
## v_3 2.277e-02 1.191e-01 0.191 0.84836
## v_4 -4.583e-02 1.659e-01 -0.276 0.78241
## v_6 8.588e-02 6.232e-02 1.378 0.16819
## Eigenes.BL.profitiert 1.937e+01 1.616e+03 0.012 0.99044
## Business.organization 5.966e-01 4.404e-01 1.355 0.17553
## local_regional_actor 1.924e+01 2.075e+03 0.009 0.99260
## salience_igs 2.525e-02 7.273e-02 0.347 0.72846
## Zustimmungsgesetz 4.680e-01 4.744e-01 0.987 0.32387
## salience 4.161e-04 8.870e-04 0.469 0.63899
## v_2 7.040e-02 7.345e-02 0.958 0.33783
## EU.origin -2.529e-01 4.300e-01 -0.588 0.55638
## budget -7.995e-05 1.711e-03 -0.047 0.96272
## lobbyists -7.905e-03 1.315e-02 -0.601 0.54758
## v_3:v_4 6.000e-03 2.413e-02 0.249 0.80365
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 225.33 on 176 degrees of freedom
## Residual deviance: 175.22 on 162 degrees of freedom
## (164 observations deleted due to missingness)
## AIC: 205.22
##
## Number of Fisher Scoring iterations: 17m5.r.robust <- logistf(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 + Business.organization + salience_igs + salience + lobbyists + budget + Bundesratsinitiative + v_3:v_4, data = data)
tab_model(m5, m5.r.robust, transform = NULL)| second_chamber_route | second_chamber_route | |||||
|---|---|---|---|---|---|---|
| Predictors | Log-Odds | CI | p | Log-Odds | CI | p |
| (Intercept) | -2.51 | -3.53 – -1.58 | <0.001 | -2.00 | -3.36 – -0.64 | 0.003 |
| v 3 | 0.03 | -0.13 – 0.19 | 0.704 | 0.02 | -0.19 – 0.24 | 0.833 |
| v 4 | -0.07 | -0.30 – 0.15 | 0.534 | -0.02 | -0.30 – 0.26 | 0.885 |
| v 6 | 0.10 | 0.02 – 0.18 | 0.018 | 0.07 | -0.04 – 0.18 | 0.227 |
| Eigenes BL profitiert | 1.98 | 1.17 – 2.90 | <0.001 | 4.11 | 1.38 – 6.85 | <0.001 |
| Zustimmungsgesetz | 0.65 | 0.03 – 1.30 | 0.043 | 0.54 | -0.32 – 1.41 | 0.230 |
| local regional actor | 0.99 | 0.19 – 1.81 | 0.016 | 3.41 | 0.35 – 6.47 | 0.007 |
| EU origin | -0.26 | -0.85 – 0.33 | 0.395 | -0.38 | -1.18 – 0.41 | 0.358 |
| v 2 | 0.12 | 0.03 – 0.22 | 0.014 | 0.05 | -0.08 – 0.18 | 0.431 |
| Business organization | 0.32 | -0.24 – 0.87 | 0.262 | 0.46 | -0.33 – 1.25 | 0.267 |
| salience igs | -0.05 | -0.16 – 0.05 | 0.327 | 0.02 | -0.11 – 0.16 | 0.729 |
| salience | 0.00 | -0.00 – 0.00 | 0.881 | 0.00 | -0.00 – 0.00 | 0.737 |
| Bundesratsinitiative | -0.21 | -0.91 – 0.47 | 0.545 | -0.81 | -1.75 – 0.14 | 0.093 |
| v 3 × v 4 | 0.01 | -0.03 – 0.04 | 0.606 | 0.00 | -0.04 – 0.05 | 0.882 |
| lobbyists | -0.01 | -0.03 – 0.01 | 0.484 | |||
| budget | 0.00 | -0.00 – 0.00 | 0.953 | |||
| Observations | 341 | 177 | ||||
| R2 Tjur | 0.196 | 0.261 | ||||
#m_interaction <- glm(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + Business.organization:Eigenes.BL.profitiert + v_3:v_4, data = data, family = binomial())with routes as control variables
m5.1 <- glm(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 + Business.organization + salience_igs + salience + Bundesratsinitiative + v_3:v_4 + national_route + subnational_brussels_route + brussels_route, data = data, family = binomial())
standardize_parameters( m5.1,
method = "sdy",
ci = 0.95,
robust = TRUE,
two_sd = FALSE,
include_response = TRUE,
verbose = TRUE
)## # Standardization method: sdy
##
## Parameter | Std. Coef. | 95% CI
## --------------------------------------------------------
## (Intercept) | -1.95 | [-2.67, -1.33]
## v_3 | -0.03 | [-0.11, 0.06]
## v_4 | -0.06 | [-0.19, 0.07]
## v_6 | 0.05 | [ 0.00, 0.09]
## Eigenes.BL.profitiert | 0.91 | [ 0.46, 1.42]
## Zustimmungsgesetz | 0.35 | [-0.01, 0.71]
## local_regional_actor | 1.09 | [ 0.61, 1.63]
## EU.origin | -0.29 | [-0.63, 0.04]
## v_2 | 0.04 | [-0.01, 0.10]
## Business.organization | 0.13 | [-0.17, 0.43]
## salience_igs | -8.23e-03 | [-0.07, 0.05]
## salience | 2.86e-04 | [ 0.00, 0.00]
## Bundesratsinitiative | -0.34 | [-0.76, 0.05]
## national_route | 1.13 | [ 0.73, 1.59]
## subnational_brussels_route | 1.31 | [ 0.68, 2.01]
## brussels_route | 0.93 | [ 0.38, 1.53]
## v_3:v_4 | 7.43e-03 | [-0.01, 0.03]
##
## - Scaled by one MAD from the median.
## - Response is unstandardized.summary(m5.1)##
## Call:
## glm(formula = second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert +
## Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 +
## Business.organization + salience_igs + salience + Bundesratsinitiative +
## v_3:v_4 + national_route + subnational_brussels_route + brussels_route,
## family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.0967860 0.7134178 -5.742 9.33e-09 ***
## v_3 -0.0539785 0.0932448 -0.579 0.562664
## v_4 -0.1165818 0.1397453 -0.834 0.404143
## v_6 0.0963187 0.0471207 2.044 0.040945 *
## Eigenes.BL.profitiert 1.9108059 0.5098937 3.747 0.000179 ***
## Zustimmungsgesetz 0.7248907 0.3816394 1.899 0.057510 .
## local_regional_actor 2.2974921 0.5416566 4.242 2.22e-05 ***
## EU.origin -0.6003149 0.3563889 -1.684 0.092097 .
## v_2 0.0917698 0.0585818 1.567 0.117226
## Business.organization 0.2765602 0.3201265 0.864 0.387638
## salience_igs -0.0172811 0.0615745 -0.281 0.778976
## salience 0.0006011 0.0007060 0.851 0.394528
## Bundesratsinitiative -0.7232394 0.4308214 -1.679 0.093202 .
## national_route 2.3674954 0.4572790 5.177 2.25e-07 ***
## subnational_brussels_route 2.7452638 0.7065904 3.885 0.000102 ***
## brussels_route 1.9483267 0.6039956 3.226 0.001257 **
## v_3:v_4 0.0156108 0.0210379 0.742 0.458066
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 442.36 on 340 degrees of freedom
## Residual deviance: 301.77 on 324 degrees of freedom
## AIC: 335.77
##
## Number of Fisher Scoring iterations: 6m5.1.r <- glm(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + local_regional_actor + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + budget + lobbyists + v_3:v_4 + national_route + subnational_brussels_route + brussels_route, data = data, family = binomial())## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredsummary(m5.1.r)##
## Call:
## glm(formula = second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert +
## Business.organization + local_regional_actor + salience_igs +
## Zustimmungsgesetz + salience + v_2 + EU.origin + budget +
## lobbyists + v_3:v_4 + national_route + subnational_brussels_route +
## brussels_route, family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -3.846e+00 1.043e+00 -3.687 0.000227 ***
## v_3 -1.887e-02 1.281e-01 -0.147 0.882868
## v_4 6.205e-03 1.957e-01 0.032 0.974709
## v_6 8.055e-02 6.846e-02 1.177 0.239348
## Eigenes.BL.profitiert 1.860e+01 1.484e+03 0.013 0.989994
## Business.organization 5.899e-01 4.766e-01 1.238 0.215817
## local_regional_actor 2.086e+01 2.029e+03 0.010 0.991797
## salience_igs -4.340e-03 8.227e-02 -0.053 0.957924
## Zustimmungsgesetz 2.760e-01 5.353e-01 0.516 0.606163
## salience 3.532e-04 1.013e-03 0.349 0.727293
## v_2 5.740e-03 8.615e-02 0.067 0.946874
## EU.origin -7.685e-01 4.987e-01 -1.541 0.123294
## budget 6.674e-04 1.887e-03 0.354 0.723587
## lobbyists -6.096e-03 1.410e-02 -0.432 0.665455
## national_route 2.446e+00 8.547e-01 2.862 0.004213 **
## subnational_brussels_route 1.632e+00 1.264e+00 1.291 0.196806
## brussels_route 1.797e+00 8.516e-01 2.110 0.034858 *
## v_3:v_4 3.117e-03 2.781e-02 0.112 0.910742
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 225.33 on 176 degrees of freedom
## Residual deviance: 152.49 on 159 degrees of freedom
## (164 observations deleted due to missingness)
## AIC: 188.49
##
## Number of Fisher Scoring iterations: 17m5.1.r.robust <- logistf(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 + Business.organization + salience_igs + salience + lobbyists + budget + Bundesratsinitiative + v_3:v_4 + national_route + subnational_brussels_route + brussels_route, data = data)
tab_model(m5.1, m5.1.r.robust, p.style = "stars", transform = NULL)| second_chamber_route | second_chamber_route | |||
|---|---|---|---|---|
| Predictors | Log-Odds | CI | Log-Odds | CI |
| (Intercept) | -4.10 *** | -5.60 – -2.79 | -2.91 *** | -4.58 – -1.23 |
| v 3 | -0.05 | -0.24 – 0.13 | -0.02 | -0.25 – 0.21 |
| v 4 | -0.12 | -0.39 – 0.16 | 0.05 | -0.28 – 0.39 |
| v 6 | 0.10 * | 0.00 – 0.19 | 0.06 | -0.06 – 0.18 |
| Eigenes BL profitiert | 1.91 *** | 0.96 – 2.97 | 3.74 *** | 0.84 – 6.64 |
| Zustimmungsgesetz | 0.72 | -0.01 – 1.49 | 0.41 | -0.54 – 1.36 |
| local regional actor | 2.30 *** | 1.28 – 3.42 | 4.85 ** | 1.37 – 8.33 |
| EU origin | -0.60 | -1.32 – 0.09 | -0.91 * | -1.80 – -0.02 |
| v 2 | 0.09 | -0.02 – 0.21 | -0.01 | -0.16 – 0.14 |
| Business organization | 0.28 | -0.35 – 0.91 | 0.40 | -0.43 – 1.23 |
| salience igs | -0.02 | -0.14 – 0.10 | 0.00 | -0.15 – 0.15 |
| salience | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 |
| Bundesratsinitiative | -0.72 | -1.60 – 0.10 | -1.19 * | -2.20 – -0.17 |
| national route | 2.37 *** | 1.53 – 3.35 | 2.10 *** | 0.77 – 3.42 |
|
subnational brussels route |
2.75 *** | 1.43 – 4.22 | 1.89 | -0.31 – 4.08 |
| brussels route | 1.95 ** | 0.81 – 3.20 | 1.57 * | 0.12 – 3.02 |
| v 3 × v 4 | 0.02 | -0.03 – 0.06 | -0.00 | -0.05 – 0.05 |
| lobbyists | -0.01 | -0.03 – 0.02 | ||
| budget | 0.00 | -0.00 – 0.00 | ||
| Observations | 341 | 177 | ||
| R2 Tjur | 0.360 | 0.378 | ||
|
||||
m5.1.z <- glm(second_chamber_route ~ 1 + v_3_z + v_4_z + v_6_z + Eigenes.BL.profitiert_z + Business.organization_z + salience_igs_z + Zustimmungsgesetz_z + salience_z + v_2_z + EU.origin_z + Business.organization_z:Eigenes.BL.profitiert_z + v_3_z:v_4_z + national_route_z + subnational_brussels_route_z + brussels_route_z, data = data, family = binomial())
PseudoR2(m5.1, which = "all")## McFadden McFaddenAdj CoxSnell Nagelkerke AldrichNelson
## 0.3178200 0.2409592 0.3378664 0.4649234 0.2919291
## VeallZimmermann Efron McKelveyZavoina Tjur AIC
## 0.5169682 0.3603301 0.5727925 0.3595990 335.7677113
## BIC logLik logLik0 G2
## 400.9097134 -150.8838556 -221.1789586 140.5902059m5.2 <- glm(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + national_route + subnational_brussels_route, data = data, family = binomial())
tab_model(m5, m5.1, m5.2, p.style = "stars", transform = NULL)| second_chamber_route | second_chamber_route | second_chamber_route | ||||
|---|---|---|---|---|---|---|
| Predictors | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI |
| (Intercept) | -2.51 *** | -3.53 – -1.58 | -4.10 *** | -5.60 – -2.79 | -3.18 *** | -4.32 – -2.16 |
| v 3 | 0.03 | -0.13 – 0.19 | -0.05 | -0.24 – 0.13 | -0.04 | -0.15 – 0.08 |
| v 4 | -0.07 | -0.30 – 0.15 | -0.12 | -0.39 – 0.16 | 0.01 | -0.12 – 0.14 |
| v 6 | 0.10 * | 0.02 – 0.18 | 0.10 * | 0.00 – 0.19 | 0.11 * | 0.03 – 0.20 |
| Eigenes BL profitiert | 1.98 *** | 1.17 – 2.90 | 1.91 *** | 0.96 – 2.97 | 2.04 *** | 1.16 – 3.03 |
| Zustimmungsgesetz | 0.65 * | 0.03 – 1.30 | 0.72 | -0.01 – 1.49 | 0.25 | -0.41 – 0.91 |
| local regional actor | 0.99 * | 0.19 – 1.81 | 2.30 *** | 1.28 – 3.42 | ||
| EU origin | -0.26 | -0.85 – 0.33 | -0.60 | -1.32 – 0.09 | -0.36 | -0.98 – 0.25 |
| v 2 | 0.12 * | 0.03 – 0.22 | 0.09 | -0.02 – 0.21 | 0.09 | -0.01 – 0.19 |
| Business organization | 0.32 | -0.24 – 0.87 | 0.28 | -0.35 – 0.91 | 0.28 | -0.30 – 0.86 |
| salience igs | -0.05 | -0.16 – 0.05 | -0.02 | -0.14 – 0.10 | -0.06 | -0.17 – 0.05 |
| salience | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 |
| Bundesratsinitiative | -0.21 | -0.91 – 0.47 | -0.72 | -1.60 – 0.10 | ||
| v 3 × v 4 | 0.01 | -0.03 – 0.04 | 0.02 | -0.03 – 0.06 | ||
| national route | 2.37 *** | 1.53 – 3.35 | 1.76 *** | 1.11 – 2.46 | ||
|
subnational brussels route |
2.75 *** | 1.43 – 4.22 | 1.95 *** | 0.92 – 3.08 | ||
| brussels route | 1.95 ** | 0.81 – 3.20 | ||||
| Observations | 341 | 341 | 341 | |||
| R2 Tjur | 0.196 | 0.360 | 0.273 | |||
|
||||||
#m_interaction <- glm(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + Business.organization:Eigenes.BL.profitiert + v_3:v_4 + national_route + subnational_brussels_route + brussels_route, data = data, family = binomial())5.3.3 Subnational brussels route
m6 <- glm(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 + Business.organization + salience_igs + salience + Bundesratsinitiative + v_3:v_4 , data = data, family = binomial())
tab_model(m6, p.style = "stars", transform = NULL)| subnational_brussels_route | ||
|---|---|---|
| Predictors | Log-Odds | CI |
| (Intercept) | -3.75 *** | -5.63 – -2.19 |
| v 3 | 0.11 | -0.18 – 0.39 |
| v 4 | -0.00 | -0.46 – 0.42 |
| v 6 | 0.04 | -0.11 – 0.20 |
| Eigenes BL profitiert | 2.13 *** | 1.01 – 3.30 |
| Zustimmungsgesetz | 0.12 | -1.07 – 1.37 |
| local regional actor | -1.14 | -4.12 – 0.67 |
| EU origin | -0.52 | -1.96 – 0.69 |
| v 2 | -0.08 | -0.25 – 0.10 |
| Business organization | 0.03 | -1.07 – 1.07 |
| salience igs | -0.01 | -0.22 – 0.18 |
| salience | 0.00 | -0.00 – 0.00 |
| Bundesratsinitiative | 2.46 *** | 1.37 – 3.70 |
| v 3 × v 4 | -0.01 | -0.07 – 0.06 |
| Observations | 341 | |
| R2 Tjur | 0.181 | |
|
||
m6.r <- glm(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + local_regional_actor + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + budget + lobbyists + v_3:v_4, data = data, family = binomial())
m6.r.robust <- logistf(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 + Business.organization + salience_igs + salience + lobbyists + budget + Bundesratsinitiative + v_3:v_4, data = data, control = logistf.control(maxit = 1000,maxstep = -1))## Warning in logistf(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 +
## Eigenes.BL.profitiert + : Nonconverged PL confidence limits: maximum number of
## iterations for variables: EU.origin exceeded. Try to increase the number of
## iterations by passing 'logistpl.control(maxit=...)' to parameter plcontrolsummary(m6.r)##
## Call:
## glm(formula = subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 +
## Eigenes.BL.profitiert + Business.organization + local_regional_actor +
## salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin +
## budget + lobbyists + v_3:v_4, family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.234e+00 1.339e+00 -1.668 0.095218 .
## v_3 2.102e-01 2.866e-01 0.733 0.463359
## v_4 2.276e-02 4.310e-01 0.053 0.957879
## v_6 -2.329e-03 1.335e-01 -0.017 0.986076
## Eigenes.BL.profitiert 4.933e+00 1.368e+00 3.604 0.000313 ***
## Business.organization -9.157e-01 9.650e-01 -0.949 0.342683
## local_regional_actor -1.899e+01 2.184e+03 -0.009 0.993064
## salience_igs 3.009e-01 1.793e-01 1.678 0.093374 .
## Zustimmungsgesetz 4.895e-01 1.099e+00 0.445 0.655966
## salience 2.577e-03 1.863e-03 1.384 0.166468
## v_2 -4.360e-01 1.736e-01 -2.512 0.012010 *
## EU.origin -3.786e-01 9.342e-01 -0.405 0.685324
## budget 7.237e-04 5.530e-03 0.131 0.895877
## lobbyists -6.348e-02 5.467e-02 -1.161 0.245579
## v_3:v_4 -3.461e-02 6.083e-02 -0.569 0.569320
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 76.895 on 176 degrees of freedom
## Residual deviance: 52.530 on 162 degrees of freedom
## (164 observations deleted due to missingness)
## AIC: 82.53
##
## Number of Fisher Scoring iterations: 17m6.z <- glm(subnational_brussels_route ~ 1 + v_3_z + v_4_z + v_6_z + Eigenes.BL.profitiert_z + Business.organization_z + salience_igs_z + Zustimmungsgesetz_z + salience_z + v_2_z + EU.origin_z + Business.organization_z:Eigenes.BL.profitiert_z + v_3_z:v_4_z, data = data, family = binomial())
m0.1 <- glm(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + brussels_route + national_route + subnational_brussels_route + Business.organization:Eigenes.BL.profitiert, data = data, family = binomial())## Warning in model.matrix.default(mt, mf, contrasts): the response appeared on
## the right-hand side and was dropped## Warning in model.matrix.default(mt, mf, contrasts): problem with term 13 in
## model.matrix: no columns are assignedtab_model(m0.1, p.style = "stars", transform = NULL)| subnational_brussels_route | ||
|---|---|---|
| Predictors | Log-Odds | CI |
| (Intercept) | -3.30 *** | -5.06 – -1.81 |
| v 3 | 0.08 | -0.11 – 0.28 |
| v 4 | 0.00 | -0.24 – 0.24 |
| v 6 | 0.03 | -0.11 – 0.18 |
| Eigenes BL profitiert | 0.82 | -0.53 – 2.07 |
| Business organization | -0.93 | -2.49 – 0.30 |
| salience igs | 0.00 | -0.19 – 0.18 |
| Zustimmungsgesetz | 1.73 ** | 0.55 – 3.12 |
| salience | -0.00 | -0.00 – 0.00 |
| v 2 | -0.04 | -0.19 – 0.11 |
| EU origin | -1.38 * | -2.89 – -0.16 |
| brussels route | 2.97 *** | 1.51 – 4.56 |
| national route | -0.89 | -1.93 – 0.13 |
|
Eigenes BL profitiert × Business organization |
2.09 | -0.18 – 4.49 |
| Observations | 341 | |
| R2 Tjur | 0.156 | |
|
||
#GLMM (sind ja zwei Ebenen, vlt wäre das korrekter als Berechnung)
m6.2 <- glmer(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + brussels_route + national_route + subnational_brussels_route + Business.organization:Eigenes.BL.profitiert + (1 | ID.Gesetz), data = data, family = binomial())## Warning in model.matrix.default(fixedform, fr, contrasts): the response
## appeared on the right-hand side and was dropped## Warning in model.matrix.default(fixedform, fr, contrasts): problem with term 13
## in model.matrix: no columns are assigned## Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, :
## Model failed to converge with max|grad| = 0.0843791 (tol = 0.002, component 1)tab_model(m6.2, p.style = "stars", transform = NULL)| subnational_brussels_route | ||
|---|---|---|
| Predictors | Log-Odds | CI |
| (Intercept) | -4.86 *** | -7.72 – -1.99 |
| v 3 | 0.13 | -0.11 – 0.37 |
| v 4 | -0.18 | -0.49 – 0.12 |
| v 6 | 0.07 | -0.12 – 0.26 |
| Eigenes BL profitiert | 1.67 | -0.02 – 3.36 |
| Business organization | 0.10 | -1.56 – 1.75 |
| salience igs | 0.05 | -0.19 – 0.29 |
| Zustimmungsgesetz | 0.48 | -2.18 – 3.13 |
| salience | 0.00 | -0.00 – 0.01 |
| v 2 | -0.05 | -0.24 – 0.14 |
| EU origin | -1.05 | -3.63 – 1.53 |
| brussels route | 3.62 *** | 1.73 – 5.50 |
| national route | -0.72 | -1.89 – 0.45 |
|
Eigenes BL profitiert × Business organization |
1.03 | -1.71 – 3.77 |
| Random Effects | ||
| σ2 | 3.29 | |
| τ00 ID.Gesetz | 2.91 | |
| ICC | 0.47 | |
| N ID.Gesetz | 23 | |
| Observations | 341 | |
| Marginal R2 / Conditional R2 | 0.221 / 0.587 | |
|
||
summary(m6)##
## Call:
## glm(formula = subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 +
## Eigenes.BL.profitiert + Zustimmungsgesetz + local_regional_actor +
## EU.origin + v_2 + Business.organization + salience_igs +
## salience + Bundesratsinitiative + v_3:v_4, family = binomial(),
## data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -3.7548216 0.8709862 -4.311 1.63e-05 ***
## v_3 0.1121891 0.1458263 0.769 0.441695
## v_4 -0.0041715 0.2249161 -0.019 0.985202
## v_6 0.0417084 0.0779666 0.535 0.592683
## Eigenes.BL.profitiert 2.1339750 0.5783295 3.690 0.000224 ***
## Zustimmungsgesetz 0.1198258 0.6135788 0.195 0.845166
## local_regional_actor -1.1419497 1.1125115 -1.026 0.304674
## EU.origin -0.5234739 0.6572705 -0.796 0.425779
## v_2 -0.0759020 0.0878362 -0.864 0.387516
## Business.organization 0.0271866 0.5377913 0.051 0.959682
## salience_igs -0.0138844 0.1010254 -0.137 0.890687
## salience 0.0009697 0.0013637 0.711 0.477061
## Bundesratsinitiative 2.4629147 0.5891425 4.181 2.91e-05 ***
## v_3:v_4 -0.0055141 0.0329348 -0.167 0.867036
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 193.62 on 340 degrees of freedom
## Residual deviance: 147.55 on 327 degrees of freedom
## AIC: 175.55
##
## Number of Fisher Scoring iterations: 6PseudoR2(m6, which = "all")## McFadden McFaddenAdj CoxSnell Nagelkerke AldrichNelson
## 0.23792789 0.09331264 0.12636590 0.29168673 0.11901541
## VeallZimmermann Efron McKelveyZavoina Tjur AIC
## 0.32862622 0.17218762 0.34937494 0.18054544 175.55026818
## BIC logLik logLik0 G2
## 229.19662286 -73.77513409 -96.80859983 46.06693148nulmodell <- glmer(subnational_brussels_route ~ 1 + (1 | ID.Gesetz), data = data, family = binomial())
tab_model(nulmodell, p.style = "stars", transform = NULL)| subnational_brussels_route | ||
|---|---|---|
| Predictors | Log-Odds | CI |
| (Intercept) | -3.74 *** | -4.94 – -2.53 |
| Random Effects | ||
| σ2 | 3.29 | |
| τ00 ID.Gesetz | 2.11 | |
| ICC | 0.39 | |
| N ID.Gesetz | 23 | |
| Observations | 341 | |
| Marginal R2 / Conditional R2 | 0.000 / 0.391 | |
|
||
#m_interaction <- glm(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + Business.organization:Eigenes.BL.profitiert + v_3:v_4, data = data, family = binomial())with routes as control variables
m6.1 <- glm(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 + Business.organization + salience_igs + salience + Bundesratsinitiative + v_3:v_4 + national_route + second_chamber_route + brussels_route, data = data, family = binomial())
m6.1.r <- glm(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + local_regional_actor + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + budget + lobbyists + v_3:v_4 + national_route + second_chamber_route + brussels_route, data = data, family = binomial())
summary(m6.1.r)##
## Call:
## glm(formula = subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 +
## Eigenes.BL.profitiert + Business.organization + local_regional_actor +
## salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin +
## budget + lobbyists + v_3:v_4 + national_route + second_chamber_route +
## brussels_route, family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -3.360e+00 2.323e+00 -1.447 0.14799
## v_3 5.299e-01 4.839e-01 1.095 0.27348
## v_4 5.428e-01 5.682e-01 0.955 0.33942
## v_6 -1.327e-01 2.259e-01 -0.588 0.55673
## Eigenes.BL.profitiert 4.895e+00 2.201e+00 2.224 0.02613 *
## Business.organization -2.582e+00 1.870e+00 -1.381 0.16724
## local_regional_actor -2.046e+01 2.306e+03 -0.009 0.99292
## salience_igs 5.267e-01 3.765e-01 1.399 0.16181
## Zustimmungsgesetz 1.995e+00 1.898e+00 1.051 0.29316
## salience 3.711e-03 2.879e-03 1.289 0.19750
## v_2 -6.944e-01 3.194e-01 -2.174 0.02969 *
## EU.origin -9.004e-01 1.382e+00 -0.652 0.51466
## budget 2.323e-03 6.295e-03 0.369 0.71216
## lobbyists -7.775e-02 9.825e-02 -0.791 0.42876
## national_route -2.226e+00 1.813e+00 -1.228 0.21948
## second_chamber_route 1.188e+00 1.777e+00 0.669 0.50366
## brussels_route 6.073e+00 2.332e+00 2.604 0.00921 **
## v_3:v_4 -1.434e-01 1.173e-01 -1.222 0.22161
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 76.895 on 176 degrees of freedom
## Residual deviance: 32.736 on 159 degrees of freedom
## (164 observations deleted due to missingness)
## AIC: 68.736
##
## Number of Fisher Scoring iterations: 17m6.1.r.robust <- logistf(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 + Business.organization + salience_igs + salience + lobbyists + budget + Bundesratsinitiative + v_3:v_4 + national_route + second_chamber_route + brussels_route, data = data, plcontrol = logistf.control(maxit = 1000, maxstep = -1))## Warning in logistf(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 +
## Eigenes.BL.profitiert + : logistf.fit: Maximum number of iterations for full
## model exceeded. Try to increase the number of iterations or alter step size by
## passing 'logistf.control(maxit=..., maxstep=...)' to parameter controlm6.1.z <- glm(subnational_brussels_route ~ 1 + v_3_z + v_4_z + v_6_z + Eigenes.BL.profitiert_z + Business.organization_z + salience_igs_z + Zustimmungsgesetz_z + salience_z + v_2_z + EU.origin_z + Business.organization_z:Eigenes.BL.profitiert_z + v_3_z:v_4_z + national_route_z + subnational_brussels_route_z + brussels_route_z, data = data, family = binomial())## Warning: glm.fit: algorithm did not convergesummary(m6.1)##
## Call:
## glm(formula = subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 +
## Eigenes.BL.profitiert + Zustimmungsgesetz + local_regional_actor +
## EU.origin + v_2 + Business.organization + salience_igs +
## salience + Bundesratsinitiative + v_3:v_4 + national_route +
## second_chamber_route + brussels_route, family = binomial(),
## data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -5.057904 1.100366 -4.597 4.30e-06 ***
## v_3 0.270760 0.176517 1.534 0.125052
## v_4 0.044745 0.285332 0.157 0.875389
## v_6 -0.024257 0.098495 -0.246 0.805465
## Eigenes.BL.profitiert 1.670758 0.671683 2.487 0.012867 *
## Zustimmungsgesetz 0.822201 0.771110 1.066 0.286308
## local_regional_actor -2.586485 1.349034 -1.917 0.055202 .
## EU.origin -1.140810 0.820804 -1.390 0.164569
## v_2 -0.130076 0.108798 -1.196 0.231865
## Business.organization -0.303114 0.632814 -0.479 0.631943
## salience_igs 0.031192 0.127151 0.245 0.806215
## salience 0.001922 0.001530 1.256 0.209044
## Bundesratsinitiative 3.281807 0.758709 4.326 1.52e-05 ***
## national_route -2.145991 0.775771 -2.766 0.005670 **
## second_chamber_route 2.834204 0.793061 3.574 0.000352 ***
## brussels_route 3.422191 0.891261 3.840 0.000123 ***
## v_3:v_4 -0.025731 0.042713 -0.602 0.546899
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 193.62 on 340 degrees of freedom
## Residual deviance: 108.65 on 324 degrees of freedom
## AIC: 142.65
##
## Number of Fisher Scoring iterations: 7PseudoR2(m6.1, which = "all")## McFadden McFaddenAdj CoxSnell Nagelkerke AldrichNelson
## 0.4388554 0.2632512 0.2205594 0.5091108 0.1994741
## VeallZimmermann Efron McKelveyZavoina Tjur AIC
## 0.5507892 0.3713236 0.6587894 0.3717573 142.6472381
## BIC logLik logLik0 G2
## 207.7892402 -54.3236190 -96.8085998 84.9699616m6.2 <- glm(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + national_route + second_chamber_route + Business.organization:Eigenes.BL.profitiert, data = data, family = binomial())
tab_model(m6, m6.1, m6.2, p.style = "stars", transform = NULL)| subnational_brussels_route | subnational_brussels_route | subnational_brussels_route | ||||
|---|---|---|---|---|---|---|
| Predictors | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI |
| (Intercept) | -3.75 *** | -5.63 – -2.19 | -5.06 *** | -7.45 – -3.10 | -2.93 *** | -4.63 – -1.48 |
| v 3 | 0.11 | -0.18 – 0.39 | 0.27 | -0.08 – 0.62 | 0.10 | -0.10 – 0.29 |
| v 4 | -0.00 | -0.46 – 0.42 | 0.04 | -0.54 – 0.59 | 0.00 | -0.24 – 0.25 |
| v 6 | 0.04 | -0.11 – 0.20 | -0.02 | -0.22 – 0.17 | -0.01 | -0.16 – 0.14 |
| Eigenes BL profitiert | 2.13 *** | 1.01 – 3.30 | 1.67 * | 0.36 – 3.03 | 0.35 | -0.99 – 1.57 |
| Zustimmungsgesetz | 0.12 | -1.07 – 1.37 | 0.82 | -0.64 – 2.43 | 1.13 | 0.02 – 2.40 |
| local regional actor | -1.14 | -4.12 – 0.67 | -2.59 | -5.94 – -0.35 | ||
| EU origin | -0.52 | -1.96 – 0.69 | -1.14 | -2.92 – 0.37 | -0.70 | -1.94 – 0.35 |
| v 2 | -0.08 | -0.25 – 0.10 | -0.13 | -0.35 – 0.08 | -0.10 | -0.25 – 0.05 |
| Business organization | 0.03 | -1.07 – 1.07 | -0.30 | -1.61 – 0.91 | -0.94 | -2.46 – 0.28 |
| salience igs | -0.01 | -0.22 – 0.18 | 0.03 | -0.22 – 0.28 | -0.02 | -0.22 – 0.17 |
| salience | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | -0.00 | -0.00 – 0.00 |
| Bundesratsinitiative | 2.46 *** | 1.37 – 3.70 | 3.28 *** | 1.91 – 4.93 | ||
| v 3 × v 4 | -0.01 | -0.07 – 0.06 | -0.03 | -0.11 – 0.06 | ||
| national route | -2.15 ** | -3.81 – -0.72 | -0.92 | -1.97 – 0.10 | ||
| second chamber route | 2.83 *** | 1.41 – 4.56 | 1.91 *** | 0.86 – 3.08 | ||
| brussels route | 3.42 *** | 1.76 – 5.32 | ||||
|
Eigenes BL profitiert × Business organization |
2.21 | 0.04 – 4.54 | ||||
| Observations | 341 | 341 | 341 | |||
| R2 Tjur | 0.181 | 0.372 | 0.141 | |||
|
||||||
#m_interaction <- glm(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + Business.organization:Eigenes.BL.profitiert + v_3:v_4 + national_route + second_chamber_route + brussels_route, data = data, family = binomial())table with Level I+II+interaction term
tab_model(m4, m5, m6, p.style = "stars", transform = NULL)| brussels_route | second_chamber_route | subnational_brussels_route | ||||
|---|---|---|---|---|---|---|
| Predictors | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI |
| (Intercept) | -3.75 *** | -5.44 – -2.35 | -2.51 *** | -3.53 – -1.58 | -3.75 *** | -5.63 – -2.19 |
| v 3 | 0.03 | -0.15 – 0.21 | 0.03 | -0.13 – 0.19 | 0.11 | -0.18 – 0.39 |
| v 4 | 0.04 | -0.17 – 0.23 | -0.07 | -0.30 – 0.15 | -0.00 | -0.46 – 0.42 |
| v 6 | 0.06 | -0.09 – 0.20 | 0.10 * | 0.02 – 0.18 | 0.04 | -0.11 – 0.20 |
| Eigenes BL profitiert | 1.23 * | 0.13 – 2.28 | 1.98 *** | 1.17 – 2.90 | 2.13 *** | 1.01 – 3.30 |
| Business organization | 0.32 | -0.57 – 1.20 | 0.32 | -0.24 – 0.87 | 0.03 | -1.07 – 1.07 |
| salience igs | -0.13 | -0.32 – 0.06 | -0.05 | -0.16 – 0.05 | -0.01 | -0.22 – 0.18 |
| Zustimmungsgesetz | -1.13 * | -2.24 – -0.09 | 0.65 * | 0.03 – 1.30 | 0.12 | -1.07 – 1.37 |
| salience | -0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 |
| v 2 | 0.07 | -0.08 – 0.24 | 0.12 * | 0.03 – 0.22 | -0.08 | -0.25 – 0.10 |
| EU origin | 1.84 *** | 0.88 – 2.89 | -0.26 | -0.85 – 0.33 | -0.52 | -1.96 – 0.69 |
| local regional actor | 0.99 * | 0.19 – 1.81 | -1.14 | -4.12 – 0.67 | ||
| Bundesratsinitiative | -0.21 | -0.91 – 0.47 | 2.46 *** | 1.37 – 3.70 | ||
| v 3 × v 4 | 0.01 | -0.03 – 0.04 | -0.01 | -0.07 – 0.06 | ||
| Observations | 341 | 341 | 341 | |||
| R2 Tjur | 0.123 | 0.196 | 0.181 | |||
|
||||||
5.3.4 Tables
tab_model(m1, m2, m3, m4, m5, m6, transform = NULL,
show.aic = T,
show.dev = T,
show.fstat = T,
p.style = "stars",
title = "Routes",
dv.labels = c("Brussels route", "Subnational Berlin route ", "subnational Brussels route", "Brussels route", "Subnational Berlin route ", "subnational Brussels route"),
pred.labels = c("Intercept", "Access to national-level policymakers", "National-level policymaker oposses position of group", "Mobilization bias", "Land benefits from collaboration", "Business organization", "Perceived salience", "Subnational jurisdiction", "Media salience", "Position of group", "EU origin", "Interaction Land benefits x Business organization", "Second Chamber initiative","Interaction national policy makers opposes position of group x group has no access to national level policy-maker", "National route", "Subnational Brussels route", "Subnational Berlin route ", "Brussels route"),
file = "Regression_komplett.html")## Length of `pred.labels` does not equal number of predictors, no labelling applied.| Brussels route | Subnational Berlin route | subnational Brussels route | Brussels route | Subnational Berlin route | subnational Brussels route | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Predictors | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI |
| (Intercept) | -4.40 *** | -6.03 – -3.09 | -2.01 *** | -2.81 – -1.30 | -2.12 *** | -3.24 – -1.19 | -3.75 *** | -5.44 – -2.35 | -2.51 *** | -3.53 – -1.58 | -3.75 *** | -5.63 – -2.19 |
| v_3 | 0.02 | -0.16 – 0.19 | 0.05 | -0.05 – 0.16 | 0.08 | -0.09 – 0.25 | 0.03 | -0.15 – 0.21 | 0.03 | -0.13 – 0.19 | 0.11 | -0.18 – 0.39 |
| v_4 | 0.05 | -0.15 – 0.24 | -0.01 | -0.13 – 0.12 | 0.02 | -0.20 – 0.23 | 0.04 | -0.17 – 0.23 | -0.07 | -0.30 – 0.15 | -0.00 | -0.46 – 0.42 |
| v_6 | 0.09 | -0.05 – 0.23 | 0.09 * | 0.02 – 0.18 | 0.00 | -0.14 – 0.14 | 0.06 | -0.09 – 0.20 | 0.10 * | 0.02 – 0.18 | 0.04 | -0.11 – 0.20 |
| v_2 | 0.05 | -0.09 – 0.22 | 0.12 * | 0.03 – 0.21 | -0.05 | -0.19 – 0.09 | 0.07 | -0.08 – 0.24 | 0.12 * | 0.03 – 0.22 | -0.08 | -0.25 – 0.10 |
| salience_igs | -0.12 | -0.31 – 0.06 | -0.07 | -0.17 – 0.03 | -0.06 | -0.23 – 0.10 | -0.13 | -0.32 – 0.06 | -0.05 | -0.16 – 0.05 | -0.01 | -0.22 – 0.18 |
| Eigenes.BL.profitiert | 1.26 * | 0.19 – 2.28 | 2.04 *** | 1.25 – 2.94 | 1.47 ** | 0.51 – 2.40 | 1.23 * | 0.13 – 2.28 | 1.98 *** | 1.17 – 2.90 | 2.13 *** | 1.01 – 3.30 |
| Business.organization | 0.52 | -0.34 – 1.38 | 0.22 | -0.30 – 0.75 | -0.43 | -1.42 – 0.45 | 0.32 | -0.57 – 1.20 | 0.32 | -0.24 – 0.87 | 0.03 | -1.07 – 1.07 |
| EU.origin | 1.72 *** | 0.82 – 2.74 | -0.31 | -0.84 – 0.22 | -0.88 | -2.02 – 0.08 | 1.84 *** | 0.88 – 2.89 | -0.26 | -0.85 – 0.33 | -0.52 | -1.96 – 0.69 |
| Zustimmungsgesetz | -1.13 * | -2.24 – -0.09 | 0.65 * | 0.03 – 1.30 | 0.12 | -1.07 – 1.37 | ||||||
| salience | -0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | ||||||
| local_regional_actor | 0.99 * | 0.19 – 1.81 | -1.14 | -4.12 – 0.67 | ||||||||
| Bundesratsinitiative | -0.21 | -0.91 – 0.47 | 2.46 *** | 1.37 – 3.70 | ||||||||
| v_3:v_4 | 0.01 | -0.03 – 0.04 | -0.01 | -0.07 – 0.06 | ||||||||
| Observations | 341 | 341 | 341 | 341 | 341 | 341 | ||||||
| R2 Tjur | 0.099 | 0.169 | 0.060 | 0.123 | 0.196 | 0.181 | ||||||
| Deviance | 159.958 | 382.864 | 176.668 | 155.344 | 372.888 | 147.550 | ||||||
| AIC | 177.958 | 400.864 | 194.668 | 177.344 | 400.888 | 175.550 | ||||||
|
||||||||||||
with routes as control variables
tab_model(m4, m5, m6, m4.1, m5.1, m6.1, transform = NULL,
show.aic = T,
show.dev = T,
show.fstat = T,
p.style = "stars",
title = "Routes",
dv.labels = c("Brussels route", "Subnational Berlin route", "subnational Brussels route", "Brussels route", "Subnational Berlin route", "subnational Brussels route"),
pred.labels = c("Intercept", "Access to national-level policymakers", "National-level policymaker oposses position of group", "Mobilization bias", "Land benefits from collaboration", "Business organization", "Perceived salience", "Subnational jurisdiction", "Media salience", "Position of group", "EU origin", "Interaction Land benefits x Business organization", "Interaction national policy makers opposes position of group x group has no access to national level policy-maker", "National route", "Subnational Brussels route", "Subnational Berlin route ", "Brussels route"),
file = "Regression_paper.html")## Length of `pred.labels` does not equal number of predictors, no labelling applied.| Brussels route | Subnational Berlin route | subnational Brussels route | Brussels route | Subnational Berlin route | subnational Brussels route | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Predictors | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI |
| (Intercept) | -3.75 *** | -5.44 – -2.35 | -2.51 *** | -3.53 – -1.58 | -3.75 *** | -5.63 – -2.19 | -5.32 *** | -7.79 – -3.44 | -4.10 *** | -5.60 – -2.79 | -5.06 *** | -7.45 – -3.10 |
| v_3 | 0.03 | -0.15 – 0.21 | 0.03 | -0.13 – 0.19 | 0.11 | -0.18 – 0.39 | -0.08 | -0.29 – 0.13 | -0.05 | -0.24 – 0.13 | 0.27 | -0.08 – 0.62 |
| v_4 | 0.04 | -0.17 – 0.23 | -0.07 | -0.30 – 0.15 | -0.00 | -0.46 – 0.42 | 0.08 | -0.15 – 0.30 | -0.12 | -0.39 – 0.16 | 0.04 | -0.54 – 0.59 |
| v_6 | 0.06 | -0.09 – 0.20 | 0.10 * | 0.02 – 0.18 | 0.04 | -0.11 – 0.20 | -0.01 | -0.18 – 0.15 | 0.10 * | 0.00 – 0.19 | -0.02 | -0.22 – 0.17 |
| Eigenes.BL.profitiert | 1.23 * | 0.13 – 2.28 | 1.98 *** | 1.17 – 2.90 | 2.13 *** | 1.01 – 3.30 | 0.07 | -1.34 – 1.35 | 1.91 *** | 0.96 – 2.97 | 1.67 * | 0.36 – 3.03 |
| Business.organization | 0.32 | -0.57 – 1.20 | 0.32 | -0.24 – 0.87 | 0.03 | -1.07 – 1.07 | 0.03 | -1.02 – 1.06 | 0.28 | -0.35 – 0.91 | -0.30 | -1.61 – 0.91 |
| salience_igs | -0.13 | -0.32 – 0.06 | -0.05 | -0.16 – 0.05 | -0.01 | -0.22 – 0.18 | -0.09 | -0.32 – 0.11 | -0.02 | -0.14 – 0.10 | 0.03 | -0.22 – 0.28 |
| Zustimmungsgesetz | -1.13 * | -2.24 – -0.09 | 0.65 * | 0.03 – 1.30 | 0.12 | -1.07 – 1.37 | -2.01 ** | -3.43 – -0.75 | 0.72 | -0.01 – 1.49 | 0.82 | -0.64 – 2.43 |
| salience | -0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | -0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 |
| v_2 | 0.07 | -0.08 – 0.24 | 0.12 * | 0.03 – 0.22 | -0.08 | -0.25 – 0.10 | 0.04 | -0.14 – 0.25 | 0.09 | -0.02 – 0.21 | -0.13 | -0.35 – 0.08 |
| EU.origin | 1.84 *** | 0.88 – 2.89 | -0.26 | -0.85 – 0.33 | -0.52 | -1.96 – 0.69 | 2.44 *** | 1.29 – 3.76 | -0.60 | -1.32 – 0.09 | -1.14 | -2.92 – 0.37 |
| local_regional_actor | 0.99 * | 0.19 – 1.81 | -1.14 | -4.12 – 0.67 | 2.30 *** | 1.28 – 3.42 | -2.59 | -5.94 – -0.35 | ||||
| Bundesratsinitiative | -0.21 | -0.91 – 0.47 | 2.46 *** | 1.37 – 3.70 | -0.72 | -1.60 – 0.10 | 3.28 *** | 1.91 – 4.93 | ||||
| v_3:v_4 | 0.01 | -0.03 – 0.04 | -0.01 | -0.07 – 0.06 | 0.02 | -0.03 – 0.06 | -0.03 | -0.11 – 0.06 | ||||
| national_route | 1.89 * | 0.39 – 3.88 | 2.37 *** | 1.53 – 3.35 | -2.15 ** | -3.81 – -0.72 | ||||||
| subnational_brussels_route | 1.94 * | 0.40 – 3.54 | 2.75 *** | 1.43 – 4.22 | ||||||||
| second_chamber_route | 1.81 ** | 0.65 – 3.09 | 2.83 *** | 1.41 – 4.56 | ||||||||
| brussels_route | 1.95 ** | 0.81 – 3.20 | 3.42 *** | 1.76 – 5.32 | ||||||||
| Observations | 341 | 341 | 341 | 341 | 341 | 341 | ||||||
| R2 Tjur | 0.123 | 0.196 | 0.181 | 0.332 | 0.360 | 0.372 | ||||||
| Deviance | 155.344 | 372.888 | 147.550 | 120.032 | 301.768 | 108.647 | ||||||
| AIC | 177.344 | 400.888 | 175.550 | 148.032 | 335.768 | 142.647 | ||||||
|
||||||||||||
Table for Paper
tab_model(m5, m6, m5.1, m6.1, transform = NULL,
show.aic = T,
show.dev = T,
show.fstat = T,
p.style = "stars",
title = "Routes",
dv.labels = c("Subnational Berlin route ", "subnational Brussels route", "Subnational Berlin route", "subnational Brussels route"),
pred.labels = c("Intercept", "Access to national-level policymakers",
"National-level policymaker oposses position of group", "Mobilization bias", "subnational policymaker supports the position of the group", "Subnational jurisdiction", "Subnational organization", "EU origin", "Position of interest group", "Business organization", "Perceived salience", "Media salience", "Second Chamber Initiative","Interaction national policy makers opposes position of group x group has no access to national level policy-maker", "National route", "Subnational Brussels route", "Subnational Berlin route ", "Brussels route"),
file = "Regression_paper.html")| Subnational Berlin route | subnational Brussels route | Subnational Berlin route | subnational Brussels route | |||||
|---|---|---|---|---|---|---|---|---|
| Predictors | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI |
| Intercept | -2.51 *** | -3.53 – -1.58 | -3.75 *** | -5.63 – -2.19 | -4.10 *** | -5.60 – -2.79 | -5.06 *** | -7.45 – -3.10 |
| Access to national-level policymakers | 0.03 | -0.13 – 0.19 | 0.11 | -0.18 – 0.39 | -0.05 | -0.24 – 0.13 | 0.27 | -0.08 – 0.62 |
| National-level policymaker oposses position of group | -0.07 | -0.30 – 0.15 | -0.00 | -0.46 – 0.42 | -0.12 | -0.39 – 0.16 | 0.04 | -0.54 – 0.59 |
| Mobilization bias | 0.10 * | 0.02 – 0.18 | 0.04 | -0.11 – 0.20 | 0.10 * | 0.00 – 0.19 | -0.02 | -0.22 – 0.17 |
| subnational policymaker supports the position of the group | 1.98 *** | 1.17 – 2.90 | 2.13 *** | 1.01 – 3.30 | 1.91 *** | 0.96 – 2.97 | 1.67 * | 0.36 – 3.03 |
| Subnational jurisdiction | 0.65 * | 0.03 – 1.30 | 0.12 | -1.07 – 1.37 | 0.72 | -0.01 – 1.49 | 0.82 | -0.64 – 2.43 |
| Subnational organization | 0.99 * | 0.19 – 1.81 | -1.14 | -4.12 – 0.67 | 2.30 *** | 1.28 – 3.42 | -2.59 | -5.94 – -0.35 |
| EU origin | -0.26 | -0.85 – 0.33 | -0.52 | -1.96 – 0.69 | -0.60 | -1.32 – 0.09 | -1.14 | -2.92 – 0.37 |
| Position of interest group | 0.12 * | 0.03 – 0.22 | -0.08 | -0.25 – 0.10 | 0.09 | -0.02 – 0.21 | -0.13 | -0.35 – 0.08 |
| Business organization | 0.32 | -0.24 – 0.87 | 0.03 | -1.07 – 1.07 | 0.28 | -0.35 – 0.91 | -0.30 | -1.61 – 0.91 |
| Perceived salience | -0.05 | -0.16 – 0.05 | -0.01 | -0.22 – 0.18 | -0.02 | -0.14 – 0.10 | 0.03 | -0.22 – 0.28 |
| Media salience | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 |
| Second Chamber Initiative | -0.21 | -0.91 – 0.47 | 2.46 *** | 1.37 – 3.70 | -0.72 | -1.60 – 0.10 | 3.28 *** | 1.91 – 4.93 |
| Interaction national policy makers opposes position of group x group has no access to national level policy-maker | 0.01 | -0.03 – 0.04 | -0.01 | -0.07 – 0.06 | 0.02 | -0.03 – 0.06 | -0.03 | -0.11 – 0.06 |
| National route | 2.37 *** | 1.53 – 3.35 | -2.15 ** | -3.81 – -0.72 | ||||
| Subnational Brussels route | 2.75 *** | 1.43 – 4.22 | ||||||
| Subnational Berlin route | 1.95 ** | 0.81 – 3.20 | 3.42 *** | 1.76 – 5.32 | ||||
| Brussels route | 2.83 *** | 1.41 – 4.56 | ||||||
| Observations | 341 | 341 | 341 | 341 | ||||
| R2 Tjur | 0.196 | 0.181 | 0.360 | 0.372 | ||||
| Deviance | 372.888 | 147.550 | 301.768 | 108.647 | ||||
| AIC | 400.888 | 175.550 | 335.768 | 142.647 | ||||
|
||||||||
#with ressources
tab_model(m5, m5.r.robust, m6, m6.r.robust, m5.1, m5.1.r.robust, m6.1, m6.1.r.robust, transform = NULL,
show.aic = T,
show.dev = T,
show.fstat = T,
p.style = "stars",
title = "Routes",
dv.labels = c("Subnational Berlin route", "Subnational Berlin route + Ressources", "subnational Brussels route", "subnational Brussels route + Ressources", "Subnational Berlin route", "Subnational Berlin route + Ressources", "subnational Brussels route", "subnational Brussels route + Ressources"),
pred.labels = c("Intercept", "Access to national-level policymakers",
"National-level policymaker oposses position of group", "Mobilization bias", "subnational policymaker supports the position of the group", "Subnational jurisdiction", "Subnational organization", "EU origin", "Position of interest group", "Business organization", "Perceived salience", "Media salience","Number of Lobbyists within the organization", "Lobbybudget of organization (10K € steps)", "Second Chamber Initiative","Interaction national policy makers opposes position of group x group has no access to national level policy-maker", "National route", "Subnational Brussels route", "Subnational Berlin route ", "Brussels route"),
file = "Regression_paper_Ressources.html")| Subnational Berlin route | Subnational Berlin route + Ressources | subnational Brussels route | subnational Brussels route + Ressources | Subnational Berlin route | Subnational Berlin route + Ressources | subnational Brussels route | subnational Brussels route + Ressources | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Predictors | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI |
| Intercept | -2.51 *** | -3.53 – -1.58 | -2.00 ** | -3.36 – -0.64 | -3.75 *** | -5.63 – -2.19 | -2.57 * | -4.61 – -0.54 | -4.10 *** | -5.60 – -2.79 | -2.91 *** | -4.58 – -1.23 | -5.06 *** | -7.45 – -3.10 | -2.85 * | -5.01 – -0.69 |
| Access to national-level policymakers | 0.03 | -0.13 – 0.19 | 0.02 | -0.19 – 0.24 | 0.11 | -0.18 – 0.39 | 0.20 | -0.20 – 0.59 | -0.05 | -0.24 – 0.13 | -0.02 | -0.25 – 0.21 | 0.27 | -0.08 – 0.62 | 0.37 | -0.13 – 0.87 |
| National-level policymaker oposses position of group | -0.07 | -0.30 – 0.15 | -0.02 | -0.30 – 0.26 | -0.00 | -0.46 – 0.42 | -0.02 | -0.59 – 0.54 | -0.12 | -0.39 – 0.16 | 0.05 | -0.28 – 0.39 | 0.04 | -0.54 – 0.59 | 0.18 | -0.32 – 0.69 |
| Mobilization bias | 0.10 * | 0.02 – 0.18 | 0.07 | -0.04 – 0.18 | 0.04 | -0.11 – 0.20 | 0.03 | -0.16 – 0.22 | 0.10 * | 0.00 – 0.19 | 0.06 | -0.06 – 0.18 | -0.02 | -0.22 – 0.17 | -0.08 | -0.30 – 0.14 |
| subnational policymaker supports the position of the group | 1.98 *** | 1.17 – 2.90 | 4.11 *** | 1.38 – 6.85 | 2.13 *** | 1.01 – 3.30 | 3.70 *** | 1.88 – 5.52 | 1.91 *** | 0.96 – 2.97 | 3.74 *** | 0.84 – 6.64 | 1.67 * | 0.36 – 3.03 | 2.52 * | 0.56 – 4.48 |
| Subnational jurisdiction | 0.65 * | 0.03 – 1.30 | 0.54 | -0.32 – 1.41 | 0.12 | -1.07 – 1.37 | -0.26 | -1.76 – 1.23 | 0.72 | -0.01 – 1.49 | 0.41 | -0.54 – 1.36 | 0.82 | -0.64 – 2.43 | -0.45 | -2.16 – 1.27 |
| Subnational organization | 0.99 * | 0.19 – 1.81 | 3.41 ** | 0.35 – 6.47 | -1.14 | -4.12 – 0.67 | -1.71 | -5.12 – 1.71 | 2.30 *** | 1.28 – 3.42 | 4.85 ** | 1.37 – 8.33 | -2.59 | -5.94 – -0.35 | -1.75 | -4.94 – 1.44 |
| EU origin | -0.26 | -0.85 – 0.33 | -0.38 | -1.18 – 0.41 | -0.52 | -1.96 – 0.69 | 0.01 | -1.38 – 1.41 | -0.60 | -1.32 – 0.09 | -0.91 * | -1.80 – -0.02 | -1.14 | -2.92 – 0.37 | -0.27 | -1.98 – 1.43 |
| Position of interest group | 0.12 * | 0.03 – 0.22 | 0.05 | -0.08 – 0.18 | -0.08 | -0.25 – 0.10 | -0.31 * | -0.54 – -0.08 | 0.09 | -0.02 – 0.21 | -0.01 | -0.16 – 0.14 | -0.13 | -0.35 – 0.08 | -0.34 | -0.62 – -0.06 |
| Business organization | 0.32 | -0.24 – 0.87 | 0.46 | -0.33 – 1.25 | 0.03 | -1.07 – 1.07 | -0.64 | -2.02 – 0.75 | 0.28 | -0.35 – 0.91 | 0.40 | -0.43 – 1.23 | -0.30 | -1.61 – 0.91 | -1.54 | -3.20 – 0.12 |
| Perceived salience | -0.05 | -0.16 – 0.05 | 0.02 | -0.11 – 0.16 | -0.01 | -0.22 – 0.18 | 0.17 | -0.07 – 0.41 | -0.02 | -0.14 – 0.10 | 0.00 | -0.15 – 0.15 | 0.03 | -0.22 – 0.28 | 0.18 | -0.10 – 0.47 |
| Media salience | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 |
| Number of Lobbyists within the organization | -0.21 | -0.91 – 0.47 | -0.81 | -1.75 – 0.14 | 2.46 *** | 1.37 – 3.70 | 1.52 | 0.00 – 3.04 | -0.72 | -1.60 – 0.10 | -1.19 * | -2.20 – -0.17 | 3.28 *** | 1.91 – 4.93 | 2.28 * | 0.44 – 4.13 |
| Lobbybudget of organization (10K € steps) | 0.01 | -0.03 – 0.04 | 0.00 | -0.04 – 0.05 | -0.01 | -0.07 – 0.06 | -0.01 | -0.09 – 0.07 | 0.02 | -0.03 – 0.06 | -0.00 | -0.05 – 0.05 | -0.03 | -0.11 – 0.06 | -0.05 | -0.14 – 0.04 |
| Second Chamber Initiative | -0.01 | -0.03 – 0.01 | -0.02 | -0.07 – 0.02 | -0.01 | -0.03 – 0.02 | -0.01 | -0.04 – 0.03 | ||||||||
| Interaction national policy makers opposes position of group x group has no access to national level policy-maker | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.01 | 0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.01 | ||||||||
| National route | 2.37 *** | 1.53 – 3.35 | 2.10 *** | 0.77 – 3.42 | -2.15 ** | -3.81 – -0.72 | -1.54 | -3.38 – 0.30 | ||||||||
| Subnational Brussels route | 2.75 *** | 1.43 – 4.22 | 1.89 | -0.31 – 4.08 | ||||||||||||
| Subnational Berlin route | 1.95 ** | 0.81 – 3.20 | 1.57 * | 0.12 – 3.02 | 3.42 *** | 1.76 – 5.32 | 3.35 *** | 1.47 – 5.23 | ||||||||
| Brussels route | 2.83 *** | 1.41 – 4.56 | 1.44 | -0.33 – 3.21 | ||||||||||||
| Observations | 341 | 177 | 341 | 177 | 341 | 177 | 341 | 177 | ||||||||
| R2 Tjur | 0.196 | 0.261 | 0.181 | 0.207 | 0.360 | 0.378 | 0.372 | 0.524 | ||||||||
| Deviance | 372.888 | 147.550 | 301.768 | 108.647 | ||||||||||||
| AIC | 400.888 | 175.550 | 335.768 | 142.647 | ||||||||||||
|
||||||||||||||||
#Marginal effects of the IV's
#Moblization Bias
g_1 <- plot_model(m5, type = "pred", terms = "v_6",
title = "Marginal effect of mobilization bias on choosing Subnational Berlin route",
axis.title = c("Mobilization Bias", "Subnational Berlin Route"))
ggsave("./Marginal_Effect_1.png", plot = g_1, units = "cm", width = 40, height = 20)
g_2 <- plot_model(m6, type = "pred", terms = "v_6",
title = "Marginal effect of moblization bias on choosing Subnational Brussels route",
axis.title = c("Mobilization Bias", "Subnational Brussels Route"))
ggsave("./Marginal_Effect_2.png", plot = g_2, units = "cm", width = 40, height = 20)
g_3 <- plot_model(m5.1, type = "pred", terms = "v_6",
title = "Marginal effect of mobilization bias on choosing Subnational Berlin route + routes as control",
axis.title = c("Mobilization Bias", "Subnational Berlin Route"))
ggsave("./Marginal_Effect_3.png", plot = g_3, units = "cm", width = 40, height = 20)
g_4 <- plot_model(m6.1, type = "pred", terms = "v_6",
title = "Marginal effect of moblization bias on choosing Subnational Brussels route + routes as control",
axis.title = c("Mobilization Bias", "Subnational Brussels Route"))
ggsave("./Marginal_Effect_4.png", plot = g_4, units = "cm", width = 40, height = 20)
#subnational policymaker supports the position of the group
g_5 <- plot_model(m5, type = "pred", terms = "Eigenes.BL.profitiert",
title = "Marginal effect of subnational policymaker supports the position of the group on choosing Subnational Berlin route",
axis.title = c("subnational policymaker supports the position of the group", "Subnational Berlin Route"))
ggsave("./Marginal_Effect_5.png", plot = g_5, units = "cm", width = 40, height = 20)
g_6 <- plot_model(m6, type = "pred", terms = "Eigenes.BL.profitiert",
title = "Marginal effect of subnational policymaker supports the position of the group on choosing Subnational Brussels route",
axis.title = c("subnational policymaker supports the position of the group", "Subnational Brussels Route"))
ggsave("./Marginal_Effects_6.png", plot = g_6, units = "cm", width = 40, height = 20)
g_7 <- plot_model(m5.1, type = "pred", terms = "Eigenes.BL.profitiert",
title = "Marginal effect of subnational policymaker supports the position of the group on choosing Subnational Berlin route + routes as control",
axis.title = c("subnational policymaker supports the position of the group", "Subnational Berlin Route"))
ggsave("./Marginal_Effects_7.png", plot = g_7, units = "cm", width = 40, height = 20)
g_8 <- plot_model(m6.1, type = "pred", terms = "Eigenes.BL.profitiert",
title = "Marginal effect of subnational policymaker supports the position of the group on choosing Subnational Brussels route + routes as control",
axis.title = c("subnational policymaker supports the position of the group", "Subnational Brussels Route"))
ggsave("./Marginal_Effects_8.png", plot = g_8, units = "cm", width = 40, height = 20)
#Subnational organization
g_9 <- plot_model(m5, type = "pred", terms = "local_regional_actor",
title = "Marginal effect of Subnational organization choosing Subnational Berlin route",
axis.title = c("local_regional_actor", "Subnational Berlin Route"))
ggsave("./Marginal_Effects_9.png", plot = g_9, units = "cm", width = 40, height = 20)
g_10 <- plot_model(m6, type = "pred", terms = "local_regional_actor",
title = "Marginal effect of Subnational organization choosing Subnational Brussels route",
axis.title = c("local_regional_actor", "Subnational Brussels Route"))
ggsave("./Marginal_Effects_10.png", plot = g_10, units = "cm", width = 40, height = 20)
g_11 <- plot_model(m5.1, type = "pred", terms = "local_regional_actor",
title = "Marginal effect of Subnational organization choosing Subnational Berlin route + routes as control",
axis.title = c("local_regional_actor", "Subnational Berlin Route"))
ggsave("./Marginal_Effects_11.png", plot = g_11, units = "cm", width = 40, height = 20)
g_12 <- plot_model(m6.1, type = "pred", terms = "local_regional_actor",
title = "Marginal effect of Subnational organization choosing Subnational Brussels route + routes as control",
axis.title = c("local_regional_actor", "Subnational Brussels Route"))
ggsave("./Marginal_Effects_12.png", plot = g_12, units = "cm", width = 40, height = 20)6. Plots for Paper
6.1 Model 1
g1 <- plot_model(m5, transform = NULL,
show.p = TRUE,
show.values = TRUE,
value.offset = 0.35,
dot.size = 2,
show.intercept = TRUE,
colors = c("darkred", "darkgreen" ),
vline.color = "black",
title = "Subnational Berlin route", axis.title = "Log-Odds
N = 341",
axis.labels = c("Interaction national policy makers opposes position of group x group has no access to natonal level policy-maker", "Second Chamber Initiative", "Media salience", "Perceived salience", "Business organization", "Position of interest group", "EU origin", "Subnational organization", "Subnational jurisdiction", "Subnational policymaker supports the position of the group", "Mobilization bias", "National-level policymaker oposses position of group", "Access to national-level policymaker", "Intercept"))
g1
6.2 Model 2
g2 <- plot_model(m5.1, transform = NULL,
show.p = TRUE,
show.values = TRUE,
value.offset = 0.35,
dot.size = 2,
show.intercept = TRUE,
colors = c("darkred", "darkgreen" ),
vline.color = "black",
title = "Subnational Berlin route", axis.title = "Log-Odds
N = 341",
axis.labels = c("Interaction national government opposition x no access to national government", "Subnational Brussels route", "Brussels route","National route", "Second chamber initiative", "Media salience", "Perceived salience", "Business organization", "Position of interest group", "EU origin", "Subnational organization", "Subnational jurisdiction", "Subnational government support", "Mobilization bias", "National government opposition", "No access to national government", "Intercept"))
g2
6.3 Model 3
g3 <- plot_model(m6, transform = NULL,
show.p = TRUE,
show.values = TRUE,
value.offset = 0.35,
dot.size = 2,
show.intercept = TRUE,
colors = c("darkred", "darkgreen" ),
vline.color = "black",
title = "Subnational Brussels route", axis.title = "Log-Odds
N = 341",
axis.labels = c("Interaction national policy makers opposes position of group x group has no access to natonal level policy-maker", "Second Chamber Initiative", "Media salience", "Perceived salience", "Business organization", "Position of interest group", "EU origin", "Subnational organization", "Subnational jurisdiction", "Subnational policymaker supports the position of the group", "Mobilization bias", "National-level policymaker oposses position of group", "Access to national-level policymaker", "Intercept"))
g3
6.4 Model 4
g4 <- plot_model(m6.1, transform = NULL,
show.p = TRUE,
show.values = TRUE,
value.offset = 0.35,
dot.size = 2,
show.intercept = TRUE,
colors = c("darkred", "darkgreen" ),
vline.color = "black",
title = "Subnational Brussels route", axis.title = "Log-Odds
N = 341",
axis.labels = c("Interaction national government opposition x no access to national government", "Subnational Berlin route", "Brussels route","National route", "Second chamber initiative", "Media salience", "Perceived salience", "Business organization", "Position of interest group", "EU origin", "Subnational organization", "Subnational jurisdiction", "Subnational government support", "Mobilization bias", "National government opposition", "No access to national government", "Intercept"))
g4
6.5 Model 5 Ressources
g5 <- plot_model(m5.r.robust, transform = NULL,
show.p = TRUE,
show.values = TRUE,
value.offset = 0.35,
dot.size = 2,
show.intercept = TRUE,
colors = c("darkred", "darkgreen" ),
vline.color = "black",
title = "Subnational Berlin route + ressources", axis.title ="Log-Odds
N = 341",
axis.labels = c("Interaction national government opposition x no access to national government", "Second chamber initiative", "Lobbybudget of organization (steps in 10k €)", "Number of Lobbyists within the organization", "Media salience", "Perceived salience", "Business organization", "Position of interest group", "EU origin", "Subnational organization", "Subnational jurisdiction", "Subnational government support", "Mobilization bias", "National government opposition", "No access to national government", "Intercept"))
g5
6.6 Model 6 Ressources
g6 <- plot_model(m6.r.robust, transform = NULL,
show.p = TRUE,
show.values = TRUE,
value.offset = 0.35,
dot.size = 2,
show.intercept = TRUE,
colors = c("darkred", "darkgreen" ),
vline.color = "black",
title = "Subnational Brussels route + ressources", axis.title ="Log-Odds
N = 341",
axis.labels = c("Interaction national government opposition x no access to national government", "Second chamber initiative", "Lobbybudget of organization (steps in 10k €)", "Number of Lobbyists within the organization", "Media salience", "Perceived salience", "Business organization", "Position of interest group", "EU origin", "Subnational organization", "Subnational jurisdiction", "Subnational government support", "Mobilization bias", "National government opposition", "No access to national government", "Intercept"))
g6
6.7 Model 7 Ressources + Routes as control
g7 <- plot_model(m5.1.r.robust, transform = NULL,
show.p = TRUE,
show.values = TRUE,
value.offset = 0.35,
dot.size = 2,
show.intercept = TRUE,
colors = c("darkred", "darkgreen" ),
vline.color = "black",
title = "Subnational Berlin route + ressources + routes as control", axis.title ="Log-Odds
N = 341",
axis.labels = c("Interaction national government opposition x no access to national government", "Subnational Burssels route", "Brussels route", "National route","Second chamber initiative", "Lobbybudget of organization (steps in 10k €)", "Number of Lobbyists within the organization", "Media salience", "Perceived salience", "Business organization", "Position of interest group", "EU origin", "Subnational organization", "Subnational jurisdiction", "Subnational government support", "Mobilization bias", "National government opposition", "No access to national government", "Intercept"))
g7
6.8 Model 8 Ressources + Routes as control
g8 <- plot_model(m6.1.r.robust, transform = NULL,
show.p = TRUE,
show.values = TRUE,
value.offset = 0.35,
dot.size = 2,
show.intercept = TRUE,
colors = c("darkred", "darkgreen" ),
vline.color = "black",
title = "Subnational Brussels route + ressources + Routes as control", axis.title ="Log-Odds
N = 341",
axis.labels = c("Interaction national government opposition x no access to national government", "Subnational Berlin route", "Brussels route", "National route","Second chamber initiative", "Lobbybudget of organization (steps in 10k €)", "Number of Lobbyists within the organization", "Media salience", "Perceived salience", "Business organization", "Position of interest group", "EU origin", "Subnational organization", "Subnational jurisdiction", "Subnational government support", "Mobilization bias", "National government opposition", "No access to national government", "Intercept"))
g8
7.Robustness test and testing of the BLUE criteria
Checks for VIF: should be below 5 best is below 3
Independent variance part should be above 30%
artifical multicolinearity due to interaction effect is corrected by a z-transformation if present
#model_dashboard(m5)
#model_dashboard(m5.1)
#model_dashboard(m6)
#model_dashboard(m6.1)
#Check for Multicolinearity
#Mulcikolinearity
vif(m6)## there are higher-order terms (interactions) in this model
## consider setting type = 'predictor'; see ?vif## v_3 v_4 v_6
## 4.414651 6.795525 1.473968
## Eigenes.BL.profitiert Zustimmungsgesetz local_regional_actor
## 1.291453 1.754406 1.100304
## EU.origin v_2 Business.organization
## 1.472212 1.965001 1.236455
## salience_igs salience Bundesratsinitiative
## 1.782259 1.963461 1.775153
## v_3:v_4
## 10.832047#individual variance part
1/vif(m6)## there are higher-order terms (interactions) in this model
## consider setting type = 'predictor'; see ?vif## v_3 v_4 v_6
## 0.22651847 0.14715566 0.67844076
## Eigenes.BL.profitiert Zustimmungsgesetz local_regional_actor
## 0.77432148 0.56999338 0.90883943
## EU.origin v_2 Business.organization
## 0.67924985 0.50890549 0.80876361
## salience_igs salience Bundesratsinitiative
## 0.56108556 0.50930482 0.56333158
## v_3:v_4
## 0.09231866#Multicolinearity
vif(m6.1)## there are higher-order terms (interactions) in this model
## consider setting type = 'predictor'; see ?vif## v_3 v_4 v_6
## 4.887688 8.461826 1.741691
## Eigenes.BL.profitiert Zustimmungsgesetz local_regional_actor
## 1.389870 2.158587 1.268498
## EU.origin v_2 Business.organization
## 1.937209 2.336690 1.286879
## salience_igs salience Bundesratsinitiative
## 2.148333 2.051149 2.302192
## national_route second_chamber_route brussels_route
## 2.255219 2.375200 2.356395
## v_3:v_4
## 13.395344#individual variance part
1/vif(m6.1)## there are higher-order terms (interactions) in this model
## consider setting type = 'predictor'; see ?vif## v_3 v_4 v_6
## 0.2045957 0.1181778 0.5741547
## Eigenes.BL.profitiert Zustimmungsgesetz local_regional_actor
## 0.7194920 0.4632659 0.7883337
## EU.origin v_2 Business.organization
## 0.5162066 0.4279558 0.7770737
## salience_igs salience Bundesratsinitiative
## 0.4654772 0.4875316 0.4343686
## national_route second_chamber_route brussels_route
## 0.4434159 0.4210171 0.4243770
## v_3:v_4
## 0.0746528#Multicolinearity
vif(m5)## there are higher-order terms (interactions) in this model
## consider setting type = 'predictor'; see ?vif## v_3 v_4 v_6
## 3.868510 5.271620 1.349736
## Eigenes.BL.profitiert Zustimmungsgesetz local_regional_actor
## 1.023706 1.628718 1.161758
## EU.origin v_2 Business.organization
## 1.308123 1.492275 1.146235
## salience_igs salience Bundesratsinitiative
## 1.540418 1.549636 1.273057
## v_3:v_4
## 9.419772#individual variance part
1/vif(m5)## there are higher-order terms (interactions) in this model
## consider setting type = 'predictor'; see ?vif## v_3 v_4 v_6
## 0.2584975 0.1896950 0.7408856
## Eigenes.BL.profitiert Zustimmungsgesetz local_regional_actor
## 0.9768425 0.6139797 0.8607644
## EU.origin v_2 Business.organization
## 0.7644540 0.6701177 0.8724211
## salience_igs salience Bundesratsinitiative
## 0.6491746 0.6453128 0.7855107
## v_3:v_4
## 0.1061597#Multicolinearity
vif(m5.1)## there are higher-order terms (interactions) in this model
## consider setting type = 'predictor'; see ?vif## v_3 v_4
## 4.060711 6.250117
## v_6 Eigenes.BL.profitiert
## 1.328722 1.074957
## Zustimmungsgesetz local_regional_actor
## 1.806324 1.690145
## EU.origin v_2
## 1.441432 1.447393
## Business.organization salience_igs
## 1.183521 1.568334
## salience Bundesratsinitiative
## 1.665549 1.449678
## national_route subnational_brussels_route
## 1.873401 1.526742
## brussels_route v_3:v_4
## 1.159685 11.098047#independent variance part
1/vif(m5.1)## there are higher-order terms (interactions) in this model
## consider setting type = 'predictor'; see ?vif## v_3 v_4
## 0.24626228 0.15999700
## v_6 Eigenes.BL.profitiert
## 0.75260298 0.93026964
## Zustimmungsgesetz local_regional_actor
## 0.55361055 0.59166537
## EU.origin v_2
## 0.69375455 0.69089739
## Business.organization salience_igs
## 0.84493616 0.63761923
## salience Bundesratsinitiative
## 0.60040250 0.68980857
## national_route subnational_brussels_route
## 0.53378846 0.65498932
## brussels_route v_3:v_4
## 0.86230307 0.09010594anova(m6, m6.1)## Analysis of Deviance Table
##
## Model 1: subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert +
## Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 +
## Business.organization + salience_igs + salience + Bundesratsinitiative +
## v_3:v_4
## Model 2: subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert +
## Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 +
## Business.organization + salience_igs + salience + Bundesratsinitiative +
## v_3:v_4 + national_route + second_chamber_route + brussels_route
## Resid. Df Resid. Dev Df Deviance
## 1 327 147.55
## 2 324 108.65 3 38.903shapiro.test(residuals(m6))##
## Shapiro-Wilk normality test
##
## data: residuals(m6)
## W = 0.60634, p-value < 2.2e-16shapiro.test(residuals(m6.1))##
## Shapiro-Wilk normality test
##
## data: residuals(m6.1)
## W = 0.69844, p-value < 2.2e-16#Calculate robust standard errors
#Full model of subnational Brussels route
#Robust standard errors
hc3 <- car::hccm(m6.1)
#Teststatistics of coefficents
coeftest(m6.1, vcov. = hc3)##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -5.0579036 3.4649962 -1.4597 0.1444
## v_3 0.2707603 0.5310339 0.5099 0.6101
## v_4 0.0447451 0.8162589 0.0548 0.9563
## v_6 -0.0242574 0.4089631 -0.0593 0.9527
## Eigenes.BL.profitiert 1.6707580 2.0344679 0.8212 0.4115
## Zustimmungsgesetz 0.8222013 2.5633339 0.3208 0.7484
## local_regional_actor -2.5864851 4.1691953 -0.6204 0.5350
## EU.origin -1.1408103 2.5157844 -0.4535 0.6502
## v_2 -0.1300756 0.3418633 -0.3805 0.7036
## Business.organization -0.3031137 1.9028134 -0.1593 0.8734
## salience_igs 0.0311916 0.4279355 0.0729 0.9419
## salience 0.0019222 0.0048445 0.3968 0.6915
## Bundesratsinitiative 3.2818068 2.6225152 1.2514 0.2108
## national_route -2.1459907 2.2021166 -0.9745 0.3298
## second_chamber_route 2.8342040 2.2697279 1.2487 0.2118
## brussels_route 3.4221908 3.1813713 1.0757 0.2821
## v_3:v_4 -0.0257311 0.1237905 -0.2079 0.8353coeftest(m6.1)##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -5.0579036 1.1003657 -4.5966 4.295e-06 ***
## v_3 0.2707603 0.1765167 1.5339 0.1250523
## v_4 0.0447451 0.2853317 0.1568 0.8753885
## v_6 -0.0242574 0.0984951 -0.2463 0.8054653
## Eigenes.BL.profitiert 1.6707580 0.6716829 2.4874 0.0128673 *
## Zustimmungsgesetz 0.8222013 0.7711100 1.0663 0.2863076
## local_regional_actor -2.5864851 1.3490343 -1.9173 0.0552016 .
## EU.origin -1.1408103 0.8208040 -1.3899 0.1645686
## v_2 -0.1300756 0.1087981 -1.1956 0.2318650
## Business.organization -0.3031137 0.6328138 -0.4790 0.6319433
## salience_igs 0.0311916 0.1271508 0.2453 0.8062150
## salience 0.0019222 0.0015302 1.2562 0.2090436
## Bundesratsinitiative 3.2818068 0.7587089 4.3255 1.522e-05 ***
## national_route -2.1459907 0.7757705 -2.7663 0.0056702 **
## second_chamber_route 2.8342040 0.7930615 3.5738 0.0003519 ***
## brussels_route 3.4221908 0.8912608 3.8397 0.0001232 ***
## v_3:v_4 -0.0257311 0.0427134 -0.6024 0.5468994
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1coeftest(m6.1, vcov. = hc3)[, "Std. Error"]## (Intercept) v_3 v_4
## 3.464996247 0.531033863 0.816258895
## v_6 Eigenes.BL.profitiert Zustimmungsgesetz
## 0.408963123 2.034467863 2.563333938
## local_regional_actor EU.origin v_2
## 4.169195288 2.515784392 0.341863348
## Business.organization salience_igs salience
## 1.902813399 0.427935467 0.004844475
## Bundesratsinitiative national_route second_chamber_route
## 2.622515250 2.202116559 2.269727921
## brussels_route v_3:v_4
## 3.181371312 0.123790463coeftest(m6.1)##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -5.0579036 1.1003657 -4.5966 4.295e-06 ***
## v_3 0.2707603 0.1765167 1.5339 0.1250523
## v_4 0.0447451 0.2853317 0.1568 0.8753885
## v_6 -0.0242574 0.0984951 -0.2463 0.8054653
## Eigenes.BL.profitiert 1.6707580 0.6716829 2.4874 0.0128673 *
## Zustimmungsgesetz 0.8222013 0.7711100 1.0663 0.2863076
## local_regional_actor -2.5864851 1.3490343 -1.9173 0.0552016 .
## EU.origin -1.1408103 0.8208040 -1.3899 0.1645686
## v_2 -0.1300756 0.1087981 -1.1956 0.2318650
## Business.organization -0.3031137 0.6328138 -0.4790 0.6319433
## salience_igs 0.0311916 0.1271508 0.2453 0.8062150
## salience 0.0019222 0.0015302 1.2562 0.2090436
## Bundesratsinitiative 3.2818068 0.7587089 4.3255 1.522e-05 ***
## national_route -2.1459907 0.7757705 -2.7663 0.0056702 **
## second_chamber_route 2.8342040 0.7930615 3.5738 0.0003519 ***
## brussels_route 3.4221908 0.8912608 3.8397 0.0001232 ***
## v_3:v_4 -0.0257311 0.0427134 -0.6024 0.5468994
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1#How big is the difference
coeftest(m6.1)[, "Std. Error"] - coeftest(m6.1, vcov. = hc3)[, "Std. Error"]## (Intercept) v_3 v_4
## -2.364630547 -0.354517177 -0.530927188
## v_6 Eigenes.BL.profitiert Zustimmungsgesetz
## -0.310468046 -1.362784966 -1.792223892
## local_regional_actor EU.origin v_2
## -2.820160996 -1.694980414 -0.233065222
## Business.organization salience_igs salience
## -1.269999563 -0.300784713 -0.003314306
## Bundesratsinitiative national_route second_chamber_route
## -1.863806308 -1.426346023 -1.476666460
## brussels_route v_3:v_4
## -2.290110518 -0.081077014#clustered standard errors
summary(m6.1, transform = NULL)##
## Call:
## glm(formula = subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 +
## Eigenes.BL.profitiert + Zustimmungsgesetz + local_regional_actor +
## EU.origin + v_2 + Business.organization + salience_igs +
## salience + Bundesratsinitiative + v_3:v_4 + national_route +
## second_chamber_route + brussels_route, family = binomial(),
## data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -5.057904 1.100366 -4.597 4.30e-06 ***
## v_3 0.270760 0.176517 1.534 0.125052
## v_4 0.044745 0.285332 0.157 0.875389
## v_6 -0.024257 0.098495 -0.246 0.805465
## Eigenes.BL.profitiert 1.670758 0.671683 2.487 0.012867 *
## Zustimmungsgesetz 0.822201 0.771110 1.066 0.286308
## local_regional_actor -2.586485 1.349034 -1.917 0.055202 .
## EU.origin -1.140810 0.820804 -1.390 0.164569
## v_2 -0.130076 0.108798 -1.196 0.231865
## Business.organization -0.303114 0.632814 -0.479 0.631943
## salience_igs 0.031192 0.127151 0.245 0.806215
## salience 0.001922 0.001530 1.256 0.209044
## Bundesratsinitiative 3.281807 0.758709 4.326 1.52e-05 ***
## national_route -2.145991 0.775771 -2.766 0.005670 **
## second_chamber_route 2.834204 0.793061 3.574 0.000352 ***
## brussels_route 3.422191 0.891261 3.840 0.000123 ***
## v_3:v_4 -0.025731 0.042713 -0.602 0.546899
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 193.62 on 340 degrees of freedom
## Residual deviance: 108.65 on 324 degrees of freedom
## AIC: 142.65
##
## Number of Fisher Scoring iterations: 7coeftest(m6.1, vcov. = vcovCL(m6.1, cluster = data$ID.Gesetz, type = "HC2"))##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -5.0579036 5.4475544 -0.9285 0.3532
## v_3 0.2707603 0.3418478 0.7920 0.4283
## v_4 0.0447451 0.5710407 0.0784 0.9375
## v_6 -0.0242574 0.1618334 -0.1499 0.8809
## Eigenes.BL.profitiert 1.6707580 3.4431132 0.4852 0.6275
## Zustimmungsgesetz 0.8222013 3.4612508 0.2375 0.8122
## local_regional_actor -2.5864851 10.2323644 -0.2528 0.8004
## EU.origin -1.1408103 4.9944756 -0.2284 0.8193
## v_2 -0.1300756 0.1223700 -1.0630 0.2878
## Business.organization -0.3031137 0.7788286 -0.3892 0.6971
## salience_igs 0.0311916 0.3945854 0.0790 0.9370
## salience 0.0019222 0.0219345 0.0876 0.9302
## Bundesratsinitiative 3.2818068 2.4061276 1.3639 0.1726
## national_route -2.1459907 4.3381432 -0.4947 0.6208
## second_chamber_route 2.8342040 4.6360296 0.6113 0.5410
## brussels_route 3.4221908 10.6031729 0.3228 0.7469
## v_3:v_4 -0.0257311 0.0333653 -0.7712 0.4406model <- glm.cluster(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 + Business.organization + salience_igs + salience + lobbyists + budget + v_3:v_4 + national_route + second_chamber_route + brussels_route, cluster = "ID.Gesetz", data = data, family = "binomial")
summary(model)## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -3.359934410 1.107229099 -3.0345431 2.409003e-03
## v_3 0.529901717 0.225941698 2.3453029 1.901163e-02
## v_4 0.542769354 0.359853768 1.5083053 1.314764e-01
## v_6 -0.132746865 0.148592353 -0.8933627 3.716630e-01
## Eigenes.BL.profitiert 4.894760327 1.120712178 4.3675445 1.256512e-05
## Zustimmungsgesetz 1.995263780 1.264653975 1.5777152 1.146311e-01
## local_regional_actor -20.464496087 1.517242617 -13.4879523 1.841441e-41
## EU.origin -0.900436977 1.281731250 -0.7025162 4.823573e-01
## v_2 -0.694422226 0.204266908 -3.3995826 6.748879e-04
## Business.organization -2.582285151 2.104709631 -1.2269080 2.198572e-01
## salience_igs 0.526709469 0.115613222 4.5557892 5.218925e-06
## salience 0.003710587 0.001690640 2.1947820 2.817924e-02
## lobbyists -0.077748120 0.028130363 -2.7638506 5.712370e-03
## budget 0.002322684 0.002286411 1.0158648 3.096938e-01
## national_route -2.225851759 0.684882056 -3.2499782 1.154139e-03
## second_chamber_route 1.188012596 1.119727060 1.0609841 2.886971e-01
## brussels_route 6.072958124 1.253644912 4.8442410 1.270966e-06
## v_3:v_4 -0.143411913 0.068925921 -2.0806673 3.746437e-02#Calculate robust standard errors
#Full model of subnational Berlin route
#Robust standard errors
hc4 <- car::hccm(m5.1)
#Teststatistics of coefficents
coeftest(m5.1, vcov. = hc4)##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.09678600 1.95528702 -2.0952 0.03615 *
## v_3 -0.05397846 0.25128056 -0.2148 0.82991
## v_4 -0.11658180 0.35436816 -0.3290 0.74217
## v_6 0.09631872 0.13456696 0.7158 0.47413
## Eigenes.BL.profitiert 1.91080589 1.37116745 1.3936 0.16345
## Zustimmungsgesetz 0.72489066 0.98640850 0.7349 0.46241
## local_regional_actor 2.29749206 1.54144474 1.4905 0.13610
## EU.origin -0.60031488 0.88731267 -0.6766 0.49869
## v_2 0.09176981 0.16110471 0.5696 0.56893
## Business.organization 0.27656018 0.83579272 0.3309 0.74072
## salience_igs -0.01728112 0.15924331 -0.1085 0.91358
## salience 0.00060108 0.00177565 0.3385 0.73498
## Bundesratsinitiative -0.72323937 1.18147849 -0.6121 0.54044
## national_route 2.36749536 1.39255606 1.7001 0.08911 .
## subnational_brussels_route 2.74526376 1.79007597 1.5336 0.12513
## brussels_route 1.94832668 1.53808618 1.2667 0.20525
## v_3:v_4 0.01561084 0.05488161 0.2844 0.77607
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1coeftest(m5.1)##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.09678600 0.71341775 -5.7425 9.330e-09 ***
## v_3 -0.05397846 0.09324479 -0.5789 0.5626636
## v_4 -0.11658180 0.13974532 -0.8342 0.4041431
## v_6 0.09631872 0.04712070 2.0441 0.0409452 *
## Eigenes.BL.profitiert 1.91080589 0.50989369 3.7475 0.0001786 ***
## Zustimmungsgesetz 0.72489066 0.38163938 1.8994 0.0575102 .
## local_regional_actor 2.29749206 0.54165660 4.2416 2.219e-05 ***
## EU.origin -0.60031488 0.35638890 -1.6844 0.0920971 .
## v_2 0.09176981 0.05858183 1.5665 0.1172261
## Business.organization 0.27656018 0.32012653 0.8639 0.3876379
## salience_igs -0.01728112 0.06157454 -0.2807 0.7789760
## salience 0.00060108 0.00070596 0.8514 0.3945280
## Bundesratsinitiative -0.72323937 0.43082136 -1.6787 0.0932017 .
## national_route 2.36749536 0.45727901 5.1774 2.251e-07 ***
## subnational_brussels_route 2.74526376 0.70659043 3.8852 0.0001022 ***
## brussels_route 1.94832668 0.60399564 3.2257 0.0012565 **
## v_3:v_4 0.01561084 0.02103787 0.7420 0.4580661
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1coeftest(m5.1, vcov. = hc4)[, "Std. Error"]## (Intercept) v_3
## 1.955287016 0.251280558
## v_4 v_6
## 0.354368162 0.134566965
## Eigenes.BL.profitiert Zustimmungsgesetz
## 1.371167449 0.986408504
## local_regional_actor EU.origin
## 1.541444740 0.887312675
## v_2 Business.organization
## 0.161104709 0.835792715
## salience_igs salience
## 0.159243308 0.001775649
## Bundesratsinitiative national_route
## 1.181478490 1.392556059
## subnational_brussels_route brussels_route
## 1.790075971 1.538086182
## v_3:v_4
## 0.054881615coeftest(m5.1)##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.09678600 0.71341775 -5.7425 9.330e-09 ***
## v_3 -0.05397846 0.09324479 -0.5789 0.5626636
## v_4 -0.11658180 0.13974532 -0.8342 0.4041431
## v_6 0.09631872 0.04712070 2.0441 0.0409452 *
## Eigenes.BL.profitiert 1.91080589 0.50989369 3.7475 0.0001786 ***
## Zustimmungsgesetz 0.72489066 0.38163938 1.8994 0.0575102 .
## local_regional_actor 2.29749206 0.54165660 4.2416 2.219e-05 ***
## EU.origin -0.60031488 0.35638890 -1.6844 0.0920971 .
## v_2 0.09176981 0.05858183 1.5665 0.1172261
## Business.organization 0.27656018 0.32012653 0.8639 0.3876379
## salience_igs -0.01728112 0.06157454 -0.2807 0.7789760
## salience 0.00060108 0.00070596 0.8514 0.3945280
## Bundesratsinitiative -0.72323937 0.43082136 -1.6787 0.0932017 .
## national_route 2.36749536 0.45727901 5.1774 2.251e-07 ***
## subnational_brussels_route 2.74526376 0.70659043 3.8852 0.0001022 ***
## brussels_route 1.94832668 0.60399564 3.2257 0.0012565 **
## v_3:v_4 0.01561084 0.02103787 0.7420 0.4580661
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1#How big is the difference
coeftest(m5.1)[, "Std. Error"] - coeftest(m5.1, vcov. = hc4)[, "Std. Error"]## (Intercept) v_3
## -1.241869265 -0.158035766
## v_4 v_6
## -0.214622844 -0.087446263
## Eigenes.BL.profitiert Zustimmungsgesetz
## -0.861273760 -0.604769123
## local_regional_actor EU.origin
## -0.999788140 -0.530923770
## v_2 Business.organization
## -0.102522879 -0.515666182
## salience_igs salience
## -0.097668764 -0.001069686
## Bundesratsinitiative national_route
## -0.750657128 -0.935277051
## subnational_brussels_route brussels_route
## -1.083485536 -0.934090543
## v_3:v_4
## -0.033843744#clustered standard errors
summary(m5.1, transform = NULL)##
## Call:
## glm(formula = second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert +
## Zustimmungsgesetz + local_regional_actor + EU.origin + v_2 +
## Business.organization + salience_igs + salience + Bundesratsinitiative +
## v_3:v_4 + national_route + subnational_brussels_route + brussels_route,
## family = binomial(), data = data)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.0967860 0.7134178 -5.742 9.33e-09 ***
## v_3 -0.0539785 0.0932448 -0.579 0.562664
## v_4 -0.1165818 0.1397453 -0.834 0.404143
## v_6 0.0963187 0.0471207 2.044 0.040945 *
## Eigenes.BL.profitiert 1.9108059 0.5098937 3.747 0.000179 ***
## Zustimmungsgesetz 0.7248907 0.3816394 1.899 0.057510 .
## local_regional_actor 2.2974921 0.5416566 4.242 2.22e-05 ***
## EU.origin -0.6003149 0.3563889 -1.684 0.092097 .
## v_2 0.0917698 0.0585818 1.567 0.117226
## Business.organization 0.2765602 0.3201265 0.864 0.387638
## salience_igs -0.0172811 0.0615745 -0.281 0.778976
## salience 0.0006011 0.0007060 0.851 0.394528
## Bundesratsinitiative -0.7232394 0.4308214 -1.679 0.093202 .
## national_route 2.3674954 0.4572790 5.177 2.25e-07 ***
## subnational_brussels_route 2.7452638 0.7065904 3.885 0.000102 ***
## brussels_route 1.9483267 0.6039956 3.226 0.001257 **
## v_3:v_4 0.0156108 0.0210379 0.742 0.458066
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 442.36 on 340 degrees of freedom
## Residual deviance: 301.77 on 324 degrees of freedom
## AIC: 335.77
##
## Number of Fisher Scoring iterations: 6coeftest(m5.1, vcov. = vcovCL(m5.1, cluster = data$ID.Gesetz, type = "HC2"))##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.09678600 0.93030167 -4.4037 1.064e-05 ***
## v_3 -0.05397846 0.07930454 -0.6806 0.4960944
## v_4 -0.11658180 0.16258573 -0.7170 0.4733444
## v_6 0.09631872 0.05988115 1.6085 0.1077261
## Eigenes.BL.profitiert 1.91080589 0.53427876 3.5764 0.0003483 ***
## Zustimmungsgesetz 0.72489066 0.57244270 1.2663 0.2054016
## local_regional_actor 2.29749206 0.74964241 3.0648 0.0021783 **
## EU.origin -0.60031488 0.46347858 -1.2952 0.1952383
## v_2 0.09176981 0.05880309 1.5606 0.1186113
## Business.organization 0.27656018 0.34267730 0.8071 0.4196335
## salience_igs -0.01728112 0.07075766 -0.2442 0.8070529
## salience 0.00060108 0.00069101 0.8699 0.3843770
## Bundesratsinitiative -0.72323937 0.56745604 -1.2745 0.2024759
## national_route 2.36749536 0.41808635 5.6627 1.490e-08 ***
## subnational_brussels_route 2.74526376 0.50125541 5.4768 4.331e-08 ***
## brussels_route 1.94832668 0.51972849 3.7487 0.0001777 ***
## v_3:v_4 0.01561084 0.02668816 0.5849 0.5585914
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1model_2 <- glm.cluster(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + national_route + brussels_route + subnational_brussels_route + Business.organization:Eigenes.BL.profitiert, cluster = "ID.Gesetz", data = data, family = "binomial")
summary(model_2)## Estimate Std. Error
## (Intercept) -3.3217197063 0.5733196776
## v_3 -0.0271533124 0.0583395868
## v_4 -0.0094161146 0.0603504410
## v_6 0.1166928542 0.0520109936
## Eigenes.BL.profitiert 1.7361284008 0.5472507621
## Business.organization 0.2009171574 0.3027789090
## salience_igs -0.0372872112 0.0603681762
## Zustimmungsgesetz 0.4971043810 0.4448825180
## salience 0.0009150252 0.0005126581
## v_2 0.0782636879 0.0554842285
## EU.origin -0.6650288988 0.4037802868
## national_route 1.6524952141 0.2864604375
## brussels_route 1.7864789466 0.4379908159
## subnational_brussels_route 1.7774899670 0.3256233984
## Eigenes.BL.profitiert:Business.organization 1.6169518619 1.4918171214
## z value Pr(>|z|)
## (Intercept) -5.7938352 6.879699e-09
## v_3 -0.4654355 6.416196e-01
## v_4 -0.1560240 8.760141e-01
## v_6 2.2436190 2.485692e-02
## Eigenes.BL.profitiert 3.1724550 1.511560e-03
## Business.organization 0.6635771 5.069610e-01
## salience_igs -0.6176634 5.367973e-01
## Zustimmungsgesetz 1.1173835 2.638304e-01
## salience 1.7848644 7.428331e-02
## v_2 1.4105574 1.583752e-01
## EU.origin -1.6470069 9.955664e-02
## national_route 5.7686682 7.990044e-09
## brussels_route 4.0788046 4.526787e-05
## subnational_brussels_route 5.4587292 4.795544e-08
## Eigenes.BL.profitiert:Business.organization 1.0838808 2.784177e-01Table for robustness check 1
#tab_model(model, model_2, transform = NULL,
# show.aic = T,
# show.dev = T,
# show.fstat = T,
# p.style = "stars",
# title = "Routes",
# dv.labels = c("Subnational Berlin route - clustered standard errors", "Subnational Brussels route - clustered standard errors"),
# pred.labels = c("Intercept", "Access to national-level policymakers",
# "National-level policymaker oposses position of group", "Mobilization bias", "subnational policymaker supports the position of the group", "Subnational jurisdiction", "Subnational organization", "EU origin", "Position of interest group", "Business organization", "Perceived salience", "Media salience", "Number of Lobbyists within the organization", "Lobbybudget of organization (10K € steps)", "Interaction national policy makers opposes position of group x group has no access to national level policy-maker", "National route", "Subnational Brussels route", "Subnational Berlin route ", "Brussels route"))#,
# file = "Regression_paper_Ressources.html")7.1 Differentiating between business groups and public interest groups
7.1.1 Business groups
#Brussels route
a <- glm(brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + national_route + subnational_brussels_route + second_chamber_route, data = only_business, family = binomial())## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred#Subnational Berlin route
b <- glm(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + brussels_route + national_route + subnational_brussels_route, data = only_business, family = binomial())
#Subnational brussels route
c <- glm(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + brussels_route + national_route + second_chamber_route + Business.organization:Eigenes.BL.profitiert, data = only_business, family = binomial())
#tab_model(a, b, c, p.style = "stars") N ist noch zu klein um eine Berechnung durchführen zu können 7.1.2 Public interest groups
#Brussels route
a1 <- glm(brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + national_route + subnational_brussels_route + second_chamber_route, data = public_interest, family = binomial())
#Subnational Berlin route
b1 <- glm(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + brussels_route + national_route + subnational_brussels_route, data = public_interest, family = binomial())
#Subnational brussels route
c1 <- glm(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + brussels_route + national_route + second_chamber_route, data = public_interest, family = binomial())## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred#Brussels route
a2 <- glm(brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + national_route + subnational_brussels_route + second_chamber_route, data = data, family = binomial())
#Subnational Berlin route
b2 <- glm(second_chamber_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + brussels_route + national_route + subnational_brussels_route, data = data, family = binomial())
#Subnational brussels route
c2 <- glm(subnational_brussels_route ~ 1 + v_3 + v_4 + v_6 + Eigenes.BL.profitiert + Business.organization + salience_igs + Zustimmungsgesetz + salience + v_2 + EU.origin + brussels_route + national_route + second_chamber_route, data = data, family = binomial())
tab_model(a1, b1, c1, a2, b2, c2, transform = NULL,
show.aic = T,
show.dev = T,
show.fstat = T,
p.style = "stars",
title = " Only Public interest groups (first 3 models), All interest groups",
dv.labels = c("Brussels route", "Subnational Berlin route ", "subnational Brussels route", "Brussels route", "Subnational Berlin route ", "subnational Brussels route"),
pred.labels = c("Intercept", "Access to national-level policymakers", "National-level policymaker oposses position of group", "Mobilization bias", "Land benefits from collaboration", "Business organization", "Perceived salience", "Subnational jurisdiction", "Media salience", "Position of group", "EU origin", "National route", "Subnational Brussels route", "Subnational Berlin route ", "Brussels route"),
file = "Regression_public_interest.html")| Brussels route | Subnational Berlin route | subnational Brussels route | Brussels route | Subnational Berlin route | subnational Brussels route | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Predictors | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI | Log-Odds | CI |
| Intercept | -3.60 ** | -6.47 – -1.28 | -2.37 ** | -3.99 – -0.90 | 0.55 | -2.21 – 3.14 | -5.32 *** | -7.79 – -3.44 | -3.30 *** | -4.49 – -2.25 | -3.34 *** | -5.11 – -1.82 |
| Access to national-level policymakers | -0.14 | -0.42 – 0.12 | -0.08 | -0.23 – 0.06 | 0.17 | -0.09 – 0.45 | -0.08 | -0.29 – 0.13 | -0.03 | -0.15 – 0.08 | 0.10 | -0.09 – 0.30 |
| National-level policymaker oposses position of group | -0.04 | -0.37 – 0.25 | 0.08 | -0.09 – 0.25 | -0.01 | -0.30 – 0.27 | 0.08 | -0.15 – 0.30 | -0.01 | -0.15 – 0.13 | 0.01 | -0.24 – 0.25 |
| Mobilization bias | -0.06 | -0.26 – 0.14 | 0.11 * | 0.00 – 0.21 | -0.09 | -0.31 – 0.12 | -0.01 | -0.18 – 0.15 | 0.12 * | 0.03 – 0.21 | -0.01 | -0.16 – 0.14 |
| Land benefits from collaboration | 0.01 | -0.01 – 0.03 | 0.02 ** | 0.00 – 0.03 | 0.02 | 0.00 – 0.04 | 0.07 | -1.34 – 1.35 | 2.09 *** | 1.19 – 3.11 | 0.94 | -0.17 – 2.02 |
| Business organization | 0.33 | -1.83 – 2.15 | 0.33 | -1.16 – 1.73 | -0.02 | -3.89 – 3.05 | 0.03 | -1.02 – 1.06 | 0.31 | -0.28 – 0.91 | -0.35 | -1.48 – 0.67 |
| Perceived salience | -0.00 | -0.28 – 0.26 | -0.05 | -0.19 – 0.09 | -0.04 | -0.34 – 0.23 | -0.09 | -0.32 – 0.11 | -0.04 | -0.16 – 0.07 | -0.02 | -0.22 – 0.17 |
| Subnational jurisdiction | -2.00 * | -3.80 – -0.43 | 0.73 | -0.10 – 1.60 | -0.18 | -1.76 – 1.57 | -2.01 ** | -3.43 – -0.75 | 0.45 | -0.23 – 1.16 | 1.45 * | 0.30 – 2.77 |
| Media salience | -0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | -0.04 ** | -0.07 – -0.02 | -0.00 | -0.00 – 0.00 | 0.00 | -0.00 – 0.00 | -0.00 | -0.00 – 0.00 |
| Position of group | 0.01 | -0.21 – 0.25 | 0.08 | -0.04 – 0.21 | 0.02 | -0.19 – 0.24 | 0.04 | -0.14 – 0.25 | 0.08 | -0.02 – 0.19 | -0.07 | -0.22 – 0.08 |
| EU origin | 1.95 ** | 0.60 – 3.49 | -0.18 | -1.01 – 0.61 | -3.28 ** | -6.06 – -1.31 | 2.44 *** | 1.29 – 3.76 | -0.68 * | -1.37 – -0.02 | -1.25 | -2.69 – -0.06 |
| National route | 1.76 | 0.07 – 3.91 | 1.46 *** | 0.69 – 2.29 | -2.39 ** | -4.18 – -0.90 | 1.89 * | 0.39 – 3.88 | 1.62 *** | 0.96 – 2.33 | -1.47 * | -2.67 – -0.35 |
| Subnational Brussels route | 1.14 | -1.01 – 3.18 | 1.76 ** | 0.61 – 3.02 | 1.94 * | 0.40 – 3.54 | 1.78 ** | 0.70 – 2.95 | ||||
| Subnational Berlin route | 1.70 * | 0.24 – 3.33 | 2.38 ** | 0.95 – 4.09 | 1.81 ** | 0.65 – 3.09 | 1.75 ** | 0.65 – 2.96 | ||||
| Brussels route | 1.43 * | 0.11 – 2.90 | 2.32 * | 0.12 – 4.80 | 1.79 ** | 0.71 – 2.98 | 2.66 *** | 1.21 – 4.22 | ||||
| Observations | 234 | 234 | 234 | 341 | 341 | 341 | ||||||
| R2 Tjur | 0.249 | 0.280 | 0.351 | 0.332 | 0.303 | 0.171 | ||||||
| Deviance | 80.590 | 229.329 | 80.756 | 120.032 | 327.409 | 144.592 | ||||||
| AIC | 108.590 | 257.329 | 108.756 | 148.032 | 355.409 | 172.592 | ||||||
|
||||||||||||