Codebook
library(codebook)
library(readxl)
library(here)## here() starts at C:/Users/Daniel/surfdrive/R/reproducing_registered_reportslibrary(rio)
codebook_data <- read_excel("Data_for_Analysis_of_Open_Data_and_Computational_Reproducibility_in_Registered_Reports_in_Psychology.xlsx", n_max = 62)
#Read codebook from second sheet in excel file.
dict <- read_excel("Data_for_Analysis_of_Open_Data_and_Computational_Reproducibility_in_Registered_Reports_in_Psychology.xlsx", sheet = "Codebook")
#Add variable labels to data
var_label(codebook_data) <- dict_to_list(dict)
#Add meta data
metadata(codebook_data)$name <- "Reproducibility of Registered Reports in psychology"
metadata(codebook_data)$description <- "Coded variables to examine data and code sharing and the computational reproducibility for Registered Reports in psychology"
metadata(codebook_data)$creator <- "Pepijn Obels, Daniel Lakens, Nicholas A. Coles, Jaroslav Gottfried"
metadata(codebook_data)$temporalCoverage <- "Spring 2018"
#Export codebook
rio::export(codebook_data, "reproducing_registered_reports_codebook.rds") # to R data structure filecodebook(codebook_data)knitr::asis_output(data_info)Metadata
Description
if (exists("name", meta)) {
glue::glue(
"__Dataset name__: {name}",
.envir = meta)
}Dataset name: Reproducibility of Registered Reports in psychology
cat(description)Coded variables to examine data and code sharing and the computational reproducibility for Registered Reports in psychology
Metadata for search engines
Temporal Coverage: Spring 2018
Date published: 2019-05-22
Creator:Pepijn Obels, Daniel Lakens, Nicholas A. Coles, Jaroslav Gottfried
meta <- meta[setdiff(names(meta),
c("creator", "datePublished", "identifier",
"url", "citation", "spatialCoverage",
"temporalCoverage", "description", "name"))]
pander::pander(meta)- keywords: doi, study, registered_report, domain, journal, replication, linked, url_dataset, file_format, availability, data_statement, comments_data_po, understandable, data_complete, codebook, not_software_specific, analysis_script_included, programming_language, included_language, url_scripts, run_script_final, reproducible_final, run_script_po, reproducible_po, comments_on_reproducibility_po, time_reproducing_po, run_script_jg, reproducible_jg, comments_on_reproducibility_jg, time_reproducing_jg, run_script_nc, reproducible_nc, comments_on_reproducibility_nc, time_reproducing_nc, run_script_dl, reproducible_dl, comments_on_reproducibility_dl, time_reproducing_dl and resolving_disagreements_between_coders
knitr::asis_output(survey_overview)Variables
if (detailed_variables || detailed_scales) {
knitr::asis_output(paste0(scales_items, sep = "\n\n\n", collapse = "\n\n\n"))
}doi
Digital Object Identifier
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)0 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| doi | Digital Object Identifier | character | 0 | 62 | 62 | 0 | 62 | 16 | 32 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}study
First author name and Year
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)0 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| study | First author name and Year | character | 0 | 62 | 62 | 0 | 60 | 8 | 18 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}registered_report
True if the paper is a registered report / False if it is not a registered report
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)0 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| registered_report | True if the paper is a registered report / False if it is not a registered report | logical | 0 | 62 | 62 | TRU: 62, NA: 0 | 1 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}domain
The domain where the paper is published in (e.g. Psychology , Biology, Political Science)
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)0 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| domain | The domain where the paper is published in (e.g. Psychology , Biology, Political Science) | character | 0 | 62 | 62 | 0 | 1 | 10 | 10 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}journal
The journal where the paper is published in
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)0 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| journal | The journal where the paper is published in | character | 0 | 62 | 62 | 0 | 12 | 17 | 42 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}replication
True if the paper is a replication / False if the paper is not a replication
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)0 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| replication | True if the paper is a replication / False if the paper is not a replication | logical | 0 | 62 | 62 | FAL: 32, TRU: 30, NA: 0 | 0.48 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}linked
True if there is a link to the dataset(s) and/or script(s) / False if there is no link in the paper
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)0 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| linked | True if there is a link to the dataset(s) and/or script(s) / False if there is no link in the paper | logical | 0 | 62 | 62 | TRU: 45, FAL: 17, NA: 0 | 0.73 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}url_dataset
URL to the dataset of the paper
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)18 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| url_dataset | URL to the dataset of the paper | character | 18 | 44 | 62 | 0 | 44 | 21 | 64 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}file_format
The format of the datafiles (e.g. .csv , .txt)
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)20 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| file_format | The format of the datafiles (e.g. .csv , .txt) | character | 20 | 42 | 62 | 0 | 12 | 4 | 19 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}availability
True if the data of the paper is available (linked or searched on osf)/ False if there is no data available
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)0 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| availability | True if the data of the paper is available (linked or searched on osf)/ False if there is no data available | logical | 0 | 62 | 62 | TRU: 43, FAL: 19, NA: 0 | 0.69 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}data_statement
Statement about the data in the paper (e.g. linked to osf, link is dead//empty)
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)0 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| data_statement | Statement about the data in the paper (e.g. linked to osf, link is dead//empty) | character | 0 | 62 | 62 | 0 | 18 | 13 | 114 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}understandable
True if the provided data is understandable(are the variables described /clear what they mean) / False if the data is incomprehensible
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)20 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| understandable | True if the provided data is understandable(are the variables described /clear what they mean) / False if the data is incomprehensible | logical | 20 | 42 | 62 | FAL: 21, TRU: 21, NA: 20 | 0.5 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}data_complete
True if all the data is there / False if there are other files mentioned in the paper/script that are not there
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)20 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| data_complete | True if all the data is there / False if there are other files mentioned in the paper/script that are not there | logical | 20 | 42 | 62 | TRU: 39, NA: 20, FAL: 3 | 0.93 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}codebook
True if there is a codebook included / False if there is no codebook
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)19 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| codebook | True if there is a codebook included / False if there is no codebook | logical | 19 | 43 | 62 | FAL: 32, NA: 19, TRU: 11 | 0.26 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}not_software_specific
True if the data is not software specific (relatively easy to load with free software) / False if the data is software-specific
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)19 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| not_software_specific | True if the data is not software specific (relatively easy to load with free software) / False if the data is software-specific | logical | 19 | 43 | 62 | TRU: 42, NA: 19, FAL: 1 | 0.98 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}analysis_script_included
True if there is a script included with the paper / False if there is no script included
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)17 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| analysis_script_included | True if there is a script included with the paper / False if there is no script included | logical | 17 | 45 | 62 | TRU: 40, NA: 17, FAL: 5 | 0.89 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}programming_language
The programming language that is used (e.g. SPSS,. R)
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)22 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| programming_language | The programming language that is used (e.g. SPSS,. R) | character | 22 | 40 | 62 | 0 | 7 | 1 | 11 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}included_language
Does the programming language match our inclusion criteria due to our expertise and is it included in the final dataset.
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)22 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| included_language | Does the programming language match our inclusion criteria due to our expertise and is it included in the final dataset. | logical | 22 | 40 | 62 | TRU: 35, NA: 22, FAL: 5 | 0.88 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}url_scripts
URL to the script of the paper
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)27 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| url_scripts | URL to the script of the paper | character | 27 | 35 | 62 | 0 | 35 | 21 | 84 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}run_script_final
Final decision if the script can run; True if the script runs / False if the script does not run
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)27 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| run_script_final | Final decision if the script can run; True if the script runs / False if the script does not run | logical | 27 | 35 | 62 | TRU: 30, NA: 27, FAL: 5 | 0.86 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}reproducible_final
Final decision if the paper is reproducible; True if it is reproducible / False if not reproducible
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)27 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| reproducible_final | Final decision if the paper is reproducible; True if it is reproducible / False if not reproducible | logical | 27 | 35 | 62 | NA: 27, TRU: 19, FAL: 16 | 0.54 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}run_script_po
Coder (P. Obels) decision on if the script can run; True if the script runs / False if the script does not run
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)27 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| run_script_po | Coder (P. Obels) decision on if the script can run; True if the script runs / False if the script does not run | logical | 27 | 35 | 62 | NA: 27, TRU: 26, FAL: 9 | 0.74 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}reproducible_po
Coder (P. Obels) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)27 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| reproducible_po | Coder (P. Obels) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible | logical | 27 | 35 | 62 | NA: 27, TRU: 19, FAL: 16 | 0.54 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}comments_on_reproducibility_po
Coder (P. Obels) comments on his own reproducibility process
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)25 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| comments_on_reproducibility_po | Coder (P. Obels) comments on his own reproducibility process | character | 25 | 37 | 62 | 0 | 36 | 16 | 483 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}time_reproducing_po
Time it took to reproduce for Coder (P. Obels)
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)27 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| time_reproducing_po | Time it took to reproduce for Coder (P. Obels) | numeric | 27 | 35 | 62 | 20.57 | 19.43 | 0 | 10 | 15 | 25 | 120 | ▇▆▁▁▁▁▁▁ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}run_script_jg
Coder (J. Gottfried) decision on if the script can run; True if the script runs / False if the script does not run
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)42 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| run_script_jg | Coder (J. Gottfried) decision on if the script can run; True if the script runs / False if the script does not run | character | 42 | 20 | 62 | 0 | 3 | 4 | 9 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}reproducible_jg
Coder (J. Gottfried) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)42 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| reproducible_jg | Coder (J. Gottfried) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible | character | 42 | 20 | 62 | 0 | 4 | 4 | 9 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}comments_on_reproducibility_jg
Coder (J. Gottfried) comments on his own reproducibility process
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)42 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| comments_on_reproducibility_jg | Coder (J. Gottfried) comments on his own reproducibility process | character | 42 | 20 | 62 | 0 | 20 | 26 | 382 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}time_reproducing_jg
Time it took to reproduce for Coder (J. Gottfried)
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)42 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| time_reproducing_jg | Time it took to reproduce for Coder (J. Gottfried) | numeric | 42 | 20 | 62 | 25.5 | 9.72 | 5 | 20 | 25 | 31.25 | 40 | ▂▂▂▇▆▅▃▅ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}run_script_nc
Coder (N. A. Coles) decision on if the script can run; True if the script runs / False if the script does not run
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)46 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| run_script_nc | Coder (N. A. Coles) decision on if the script can run; True if the script runs / False if the script does not run | logical | 46 | 16 | 62 | NA: 46, TRU: 12, FAL: 4 | 0.75 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}reproducible_nc
Coder (N. A. Coles) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)46 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| reproducible_nc | Coder (N. A. Coles) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible | character | 46 | 16 | 62 | 0 | 3 | 4 | 9 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}comments_on_reproducibility_nc
Coder (N. A. Coles) comments on his own reproducibility process
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)46 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| comments_on_reproducibility_nc | Coder (N. A. Coles) comments on his own reproducibility process | character | 46 | 16 | 62 | 0 | 16 | 37 | 1787 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}time_reproducing_nc
Time it took to reproduce for Coder (N. A. Coles)
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)46 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| time_reproducing_nc | Time it took to reproduce for Coder (N. A. Coles) | numeric | 46 | 16 | 62 | 32.5 | 20.95 | 3 | 21.25 | 30 | 42.75 | 81 | ▆▁▇▅▃▂▁▂ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}run_script_dl
Coder (D. Lakens) decision on if the script can run; True if the script runs / False if the script does not run
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)60 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| run_script_dl | Coder (D. Lakens) decision on if the script can run; True if the script runs / False if the script does not run | logical | 60 | 2 | 62 | NA: 60, TRU: 2 | 1 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}reproducible_dl
Coder (D. Lakens) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)60 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | count | mean |
|---|---|---|---|---|---|---|---|
| reproducible_dl | Coder (D. Lakens) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible | logical | 60 | 2 | 62 | NA: 60, TRU: 2 | 1 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}comments_on_reproducibility_dl
Coder (D. Lakens) comments on his own reproducibility process
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)60 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| comments_on_reproducibility_dl | Coder (D. Lakens) comments on his own reproducibility process | character | 60 | 2 | 62 | 0 | 2 | 115 | 154 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}time_reproducing_dl
Time it took to reproduce for Coder (D. Lakens)
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)60 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| time_reproducing_dl | Time it took to reproduce for Coder (D. Lakens) | numeric | 60 | 2 | 62 | 15 | 7.07 | 10 | 12.5 | 15 | 17.5 | 20 | ▇▁▁▁▁▁▁▇ |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}resolving_disagreements_between_coders
how the disagreements between the coders where resolved after a closer look together
Distribution
show_missing_values <- FALSE
if (has_labels(item)) {
missing_values <- item[is.na(haven::zap_missing(item))]
attributes(missing_values) <- attributes(item)
if (!is.null(attributes(item)$labels)) {
attributes(missing_values)$labels <- attributes(missing_values)$labels[is.na(attributes(missing_values)$labels)]
attributes(item)$labels <- attributes(item)$labels[!is.na(attributes(item)$labels)]
}
if (is.double(item)) {
show_missing_values <- length(unique(haven::na_tag(missing_values))) > 1
item <- haven::zap_missing(item)
}
if (length(item_attributes$labels) == 0 && is.numeric(item)) {
item <- haven::zap_labels(item)
}
}
item_nomiss <- item[!is.na(item)]
# unnest mc_multiple and so on
if (
is.character(item_nomiss) &&
any(stringr::str_detect(item_nomiss, stringr::fixed(", "))) &&
!is.null(item_info) &&
(exists("type", item_info) &&
any(stringr::str_detect(item_info$type,
pattern = stringr::fixed("multiple"))))
) {
item_nomiss <- unlist(stringr::str_split(item_nomiss, pattern = stringr::fixed(", ")))
}
attributes(item_nomiss) <- attributes(item)
old_height <- knitr::opts_chunk$get("fig.height")
non_missing_choices <- item_attributes[["labels"]]
many_labels <- length(non_missing_choices) > 7
go_vertical <- !is_numeric_or_time_var(item_nomiss) || many_labels
if ( go_vertical ) {
# numeric items are plotted horizontally (because that's what usually expected)
# categorical items are plotted vertically because we can use the screen real estate better this way
if (is.null(choices) ||
dplyr::n_distinct(item_nomiss) > length(non_missing_choices)) {
non_missing_choices <- unique(item_nomiss)
names(non_missing_choices) <- non_missing_choices
}
choice_multiplier <- old_height/6.5
new_height <- 2 + choice_multiplier * length(non_missing_choices)
new_height <- ifelse(new_height > 20, 20, new_height)
new_height <- ifelse(new_height < 1, 1, new_height)
if(could_disclose_unique_values(item_nomiss) && is.character(item_nomiss)) {
new_height <- old_height
}
knitr::opts_chunk$set(fig.height = new_height)
}
wrap_at <- knitr::opts_chunk$get("fig.width") * 10# todo: if there are free-text choices mingled in with the pre-defined ones, don't show
# todo: show rare items if they are pre-defined
# todo: bin rare responses into "other category"
if (!length(item_nomiss)) {
cat("No non-missing values to show.")
} else if (!could_disclose_unique_values(item_nomiss)) {
plot_labelled(item_nomiss, item_name, wrap_at, go_vertical)
} else {
if (is.character(item_nomiss)) {
char_count <- stringr::str_count(item_nomiss)
attributes(char_count)$label <- item_label
plot_labelled(char_count,
item_name, wrap_at, FALSE, trans = "log1p", "characters")
} else {
cat(dplyr::n_distinct(item_nomiss), " unique, categorical values, so not shown.")
}
}
knitr::opts_chunk$set(fig.height = old_height)39 missing values.
Summary statistics
attributes(item) <- item_attributes
df = data.frame(item, stringsAsFactors = FALSE)
names(df) = html_item_name
escaped_table(codebook_table(df))| name | label | data_type | missing | complete | n | empty | n_unique | min | max |
|---|---|---|---|---|---|---|---|---|---|
| resolving_disagreements_between_coders | how the disagreements between the coders where resolved after a closer look together | character | 39 | 23 | 62 | 0 | 23 | 67 | 321 |
if (show_missing_values) {
plot_labelled(missing_values, item_name, wrap_at)
}if (!is.null(item_info)) {
# don't show choices again, if they're basically same thing as value labels
if (!is.null(choices) && !is.null(item_info$choices) &&
all(names(na.omit(choices)) == item_info$choices) &&
all(na.omit(choices) == names(item_info$choices))) {
item_info$choices <- NULL
}
item_info$label_parsed <-
item_info$choice_list <- item_info$study_id <- item_info$id <- NULL
pander::pander(item_info)
}if (!is.null(choices) && length(choices) && length(choices) < 30) {
pander::pander(as.list(choices))
}missingness_reportMissingness report
if (length(md_pattern)) {
if (knitr::is_html_output()) {
rmarkdown::paged_table(md_pattern, options = list(rows.print = 10))
} else {
knitr::kable(md_pattern)
}
}itemsCodebook table
export_table(metadata_table)jsonldJSON-LD metadata
The following JSON-LD can be found by search engines, if you share this codebook publicly on the web.
{
"name": "Reproducibility of Registered Reports in psychology",
"description": "Coded variables to examine data and code sharing and the computational reproducibility for Registered Reports in psychology\n\n\n## Table of variables\nThis table contains variable names, labels, their central tendencies and other attributes.\n\n|name |label |data_type |missing |complete |n |empty |n_unique |count |min |max |mean |sd |p0 |p25 |p50 |p75 |p100 |hist |\n|:--------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------|:---------|:-------|:--------|:--|:-----|:--------|:------------------------|:---|:----|:-----|:-----|:--|:-----|:---|:-----|:----|:--------|\n|doi |Digital Object Identifier |character |0 |62 |62 |0 |62 |NA |16 |32 |NA |NA |NA |NA |NA |NA |NA |NA |\n|study |First author name and Year |character |0 |62 |62 |0 |60 |NA |8 |18 |NA |NA |NA |NA |NA |NA |NA |NA |\n|registered_report |True if the paper is a registered report / False if it is not a registered report |logical |0 |62 |62 |NA |NA |TRU: 62, NA: 0 |NA |NA |1 |NA |NA |NA |NA |NA |NA |NA |\n|domain |The domain where the paper is published in (e.g. Psychology , Biology, Political Science) |character |0 |62 |62 |0 |1 |NA |10 |10 |NA |NA |NA |NA |NA |NA |NA |NA |\n|journal |The journal where the paper is published in |character |0 |62 |62 |0 |12 |NA |17 |42 |NA |NA |NA |NA |NA |NA |NA |NA |\n|replication |True if the paper is a replication / False if the paper is not a replication |logical |0 |62 |62 |NA |NA |FAL: 32, TRU: 30, NA: 0 |NA |NA |0.48 |NA |NA |NA |NA |NA |NA |NA |\n|linked |True if there is a link to the dataset(s) and/or script(s) / False if there is no link in the paper |logical |0 |62 |62 |NA |NA |TRU: 45, FAL: 17, NA: 0 |NA |NA |0.73 |NA |NA |NA |NA |NA |NA |NA |\n|url_dataset |URL to the dataset of the paper |character |18 |44 |62 |0 |44 |NA |21 |64 |NA |NA |NA |NA |NA |NA |NA |NA |\n|file_format |The format of the datafiles (e.g. .csv , .txt) |character |20 |42 |62 |0 |12 |NA |4 |19 |NA |NA |NA |NA |NA |NA |NA |NA |\n|availability |True if the data of the paper is available (linked or searched on osf)/ False if there is no data available |logical |0 |62 |62 |NA |NA |TRU: 43, FAL: 19, NA: 0 |NA |NA |0.69 |NA |NA |NA |NA |NA |NA |NA |\n|data_statement |Statement about the data in the paper (e.g. linked to osf, link is dead//empty) |character |0 |62 |62 |0 |18 |NA |13 |114 |NA |NA |NA |NA |NA |NA |NA |NA |\n|comments_data_po |Comments about the data that is provided by the paper (e.g. data is unclear / clearly described in codebook) |character |21 |41 |62 |0 |37 |NA |17 |183 |NA |NA |NA |NA |NA |NA |NA |NA |\n|understandable |True if the provided data is understandable(are the variables described /clear what they mean) / False if the data is incomprehensible |logical |20 |42 |62 |NA |NA |FAL: 21, TRU: 21, NA: 20 |NA |NA |0.5 |NA |NA |NA |NA |NA |NA |NA |\n|data_complete |True if all the data is there / False if there are other files mentioned in the paper/script that are not there |logical |20 |42 |62 |NA |NA |TRU: 39, NA: 20, FAL: 3 |NA |NA |0.93 |NA |NA |NA |NA |NA |NA |NA |\n|codebook |True if there is a codebook included / False if there is no codebook |logical |19 |43 |62 |NA |NA |FAL: 32, NA: 19, TRU: 11 |NA |NA |0.26 |NA |NA |NA |NA |NA |NA |NA |\n|not_software_specific |True if the data is not software specific (relatively easy to load with free software) / False if the data is software-specific |logical |19 |43 |62 |NA |NA |TRU: 42, NA: 19, FAL: 1 |NA |NA |0.98 |NA |NA |NA |NA |NA |NA |NA |\n|analysis_script_included |True if there is a script included with the paper / False if there is no script included |logical |17 |45 |62 |NA |NA |TRU: 40, NA: 17, FAL: 5 |NA |NA |0.89 |NA |NA |NA |NA |NA |NA |NA |\n|programming_language |The programming language that is used (e.g. SPSS,. R) |character |22 |40 |62 |0 |7 |NA |1 |11 |NA |NA |NA |NA |NA |NA |NA |NA |\n|included_language |Does the programming language match our inclusion criteria due to our expertise and is it included in the final dataset. |logical |22 |40 |62 |NA |NA |TRU: 35, NA: 22, FAL: 5 |NA |NA |0.88 |NA |NA |NA |NA |NA |NA |NA |\n|url_scripts |URL to the script of the paper |character |27 |35 |62 |0 |35 |NA |21 |84 |NA |NA |NA |NA |NA |NA |NA |NA |\n|run_script_final |Final decision if the script can run; True if the script runs / False if the script does not run |logical |27 |35 |62 |NA |NA |TRU: 30, NA: 27, FAL: 5 |NA |NA |0.86 |NA |NA |NA |NA |NA |NA |NA |\n|reproducible_final |Final decision if the paper is reproducible; True if it is reproducible / False if not reproducible |logical |27 |35 |62 |NA |NA |NA: 27, TRU: 19, FAL: 16 |NA |NA |0.54 |NA |NA |NA |NA |NA |NA |NA |\n|run_script_po |Coder (P. Obels) decision on if the script can run; True if the script runs / False if the script does not run |logical |27 |35 |62 |NA |NA |NA: 27, TRU: 26, FAL: 9 |NA |NA |0.74 |NA |NA |NA |NA |NA |NA |NA |\n|reproducible_po |Coder (P. Obels) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible |logical |27 |35 |62 |NA |NA |NA: 27, TRU: 19, FAL: 16 |NA |NA |0.54 |NA |NA |NA |NA |NA |NA |NA |\n|comments_on_reproducibility_po |Coder (P. Obels) comments on his own reproducibility process |character |25 |37 |62 |0 |36 |NA |16 |483 |NA |NA |NA |NA |NA |NA |NA |NA |\n|time_reproducing_po |Time it took to reproduce for Coder (P. Obels) |numeric |27 |35 |62 |NA |NA |NA |NA |NA |20.57 |19.43 |0 |10 |15 |25 |120 |▇▆▁▁▁▁▁▁ |\n|run_script_jg |Coder (J. Gottfried) decision on if the script can run; True if the script runs / False if the script does not run |character |42 |20 |62 |0 |3 |NA |4 |9 |NA |NA |NA |NA |NA |NA |NA |NA |\n|reproducible_jg |Coder (J. Gottfried) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible |character |42 |20 |62 |0 |4 |NA |4 |9 |NA |NA |NA |NA |NA |NA |NA |NA |\n|comments_on_reproducibility_jg |Coder (J. Gottfried) comments on his own reproducibility process |character |42 |20 |62 |0 |20 |NA |26 |382 |NA |NA |NA |NA |NA |NA |NA |NA |\n|time_reproducing_jg |Time it took to reproduce for Coder (J. Gottfried) |numeric |42 |20 |62 |NA |NA |NA |NA |NA |25.5 |9.72 |5 |20 |25 |31.25 |40 |▂▂▂▇▆▅▃▅ |\n|run_script_nc |Coder (N. A. Coles) decision on if the script can run; True if the script runs / False if the script does not run |logical |46 |16 |62 |NA |NA |NA: 46, TRU: 12, FAL: 4 |NA |NA |0.75 |NA |NA |NA |NA |NA |NA |NA |\n|reproducible_nc |Coder (N. A. Coles) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible |character |46 |16 |62 |0 |3 |NA |4 |9 |NA |NA |NA |NA |NA |NA |NA |NA |\n|comments_on_reproducibility_nc |Coder (N. A. Coles) comments on his own reproducibility process |character |46 |16 |62 |0 |16 |NA |37 |1787 |NA |NA |NA |NA |NA |NA |NA |NA |\n|time_reproducing_nc |Time it took to reproduce for Coder (N. A. Coles) |numeric |46 |16 |62 |NA |NA |NA |NA |NA |32.5 |20.95 |3 |21.25 |30 |42.75 |81 |▆▁▇▅▃▂▁▂ |\n|run_script_dl |Coder (D. Lakens) decision on if the script can run; True if the script runs / False if the script does not run |logical |60 |2 |62 |NA |NA |NA: 60, TRU: 2 |NA |NA |1 |NA |NA |NA |NA |NA |NA |NA |\n|reproducible_dl |Coder (D. Lakens) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible |logical |60 |2 |62 |NA |NA |NA: 60, TRU: 2 |NA |NA |1 |NA |NA |NA |NA |NA |NA |NA |\n|comments_on_reproducibility_dl |Coder (D. Lakens) comments on his own reproducibility process |character |60 |2 |62 |0 |2 |NA |115 |154 |NA |NA |NA |NA |NA |NA |NA |NA |\n|time_reproducing_dl |Time it took to reproduce for Coder (D. Lakens) |numeric |60 |2 |62 |NA |NA |NA |NA |NA |15 |7.07 |10 |12.5 |15 |17.5 |20 |▇▁▁▁▁▁▁▇ |\n|resolving_disagreements_between_coders |how the disagreements between the coders where resolved after a closer look together |character |39 |23 |62 |0 |23 |NA |67 |321 |NA |NA |NA |NA |NA |NA |NA |NA |\n\n### Note\nThis dataset was automatically described using the [codebook R package](https://rubenarslan.github.io/codebook/) (version 0.8.1).",
"creator": "Pepijn Obels, Daniel Lakens, Nicholas A. Coles, Jaroslav Gottfried",
"temporalCoverage": "Spring 2018",
"datePublished": "2019-05-22",
"keywords": ["doi", "study", "registered_report", "domain", "journal", "replication", "linked", "url_dataset", "file_format", "availability", "data_statement", "comments_data_po", "understandable", "data_complete", "codebook", "not_software_specific", "analysis_script_included", "programming_language", "included_language", "url_scripts", "run_script_final", "reproducible_final", "run_script_po", "reproducible_po", "comments_on_reproducibility_po", "time_reproducing_po", "run_script_jg", "reproducible_jg", "comments_on_reproducibility_jg", "time_reproducing_jg", "run_script_nc", "reproducible_nc", "comments_on_reproducibility_nc", "time_reproducing_nc", "run_script_dl", "reproducible_dl", "comments_on_reproducibility_dl", "time_reproducing_dl", "resolving_disagreements_between_coders"],
"@context": "http://schema.org/",
"@type": "Dataset",
"variableMeasured": [
{
"name": "doi",
"description": "Digital Object Identifier",
"@type": "propertyValue"
},
{
"name": "study",
"description": "First author name and Year",
"@type": "propertyValue"
},
{
"name": "registered_report",
"description": "True if the paper is a registered report / False if it is not a registered report",
"@type": "propertyValue"
},
{
"name": "domain",
"description": "The domain where the paper is published in (e.g. Psychology , Biology, Political Science)",
"@type": "propertyValue"
},
{
"name": "journal",
"description": "The journal where the paper is published in",
"@type": "propertyValue"
},
{
"name": "replication",
"description": "True if the paper is a replication / False if the paper is not a replication",
"@type": "propertyValue"
},
{
"name": "linked",
"description": "True if there is a link to the dataset(s) and/or script(s) / False if there is no link in the paper",
"@type": "propertyValue"
},
{
"name": "url_dataset",
"description": "URL to the dataset of the paper",
"@type": "propertyValue"
},
{
"name": "file_format",
"description": "The format of the datafiles (e.g. .csv , .txt)",
"@type": "propertyValue"
},
{
"name": "availability",
"description": "True if the data of the paper is available (linked or searched on osf)/ False if there is no data available",
"@type": "propertyValue"
},
{
"name": "data_statement",
"description": "Statement about the data in the paper (e.g. linked to osf, link is dead//empty)",
"@type": "propertyValue"
},
{
"name": "comments_data_po",
"description": "Comments about the data that is provided by the paper (e.g. data is unclear / clearly described in codebook)",
"@type": "propertyValue"
},
{
"name": "understandable",
"description": "True if the provided data is understandable(are the variables described /clear what they mean) / False if the data is incomprehensible",
"@type": "propertyValue"
},
{
"name": "data_complete",
"description": "True if all the data is there / False if there are other files mentioned in the paper/script that are not there",
"@type": "propertyValue"
},
{
"name": "codebook",
"description": "True if there is a codebook included / False if there is no codebook",
"@type": "propertyValue"
},
{
"name": "not_software_specific",
"description": "True if the data is not software specific (relatively easy to load with free software) / False if the data is software-specific",
"@type": "propertyValue"
},
{
"name": "analysis_script_included",
"description": "True if there is a script included with the paper / False if there is no script included",
"@type": "propertyValue"
},
{
"name": "programming_language",
"description": "The programming language that is used (e.g. SPSS,. R)",
"@type": "propertyValue"
},
{
"name": "included_language",
"description": "Does the programming language match our inclusion criteria due to our expertise and is it included in the final dataset.",
"@type": "propertyValue"
},
{
"name": "url_scripts",
"description": "URL to the script of the paper",
"@type": "propertyValue"
},
{
"name": "run_script_final",
"description": "Final decision if the script can run; True if the script runs / False if the script does not run",
"@type": "propertyValue"
},
{
"name": "reproducible_final",
"description": "Final decision if the paper is reproducible; True if it is reproducible / False if not reproducible",
"@type": "propertyValue"
},
{
"name": "run_script_po",
"description": "Coder (P. Obels) decision on if the script can run; True if the script runs / False if the script does not run",
"@type": "propertyValue"
},
{
"name": "reproducible_po",
"description": "Coder (P. Obels) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible",
"@type": "propertyValue"
},
{
"name": "comments_on_reproducibility_po",
"description": "Coder (P. Obels) comments on his own reproducibility process",
"@type": "propertyValue"
},
{
"name": "time_reproducing_po",
"description": "Time it took to reproduce for Coder (P. Obels)",
"@type": "propertyValue"
},
{
"name": "run_script_jg",
"description": "Coder (J. Gottfried) decision on if the script can run; True if the script runs / False if the script does not run",
"@type": "propertyValue"
},
{
"name": "reproducible_jg",
"description": "Coder (J. Gottfried) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible",
"@type": "propertyValue"
},
{
"name": "comments_on_reproducibility_jg",
"description": "Coder (J. Gottfried) comments on his own reproducibility process",
"@type": "propertyValue"
},
{
"name": "time_reproducing_jg",
"description": "Time it took to reproduce for Coder (J. Gottfried)",
"@type": "propertyValue"
},
{
"name": "run_script_nc",
"description": "Coder (N. A. Coles) decision on if the script can run; True if the script runs / False if the script does not run",
"@type": "propertyValue"
},
{
"name": "reproducible_nc",
"description": "Coder (N. A. Coles) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible",
"@type": "propertyValue"
},
{
"name": "comments_on_reproducibility_nc",
"description": "Coder (N. A. Coles) comments on his own reproducibility process",
"@type": "propertyValue"
},
{
"name": "time_reproducing_nc",
"description": "Time it took to reproduce for Coder (N. A. Coles)",
"@type": "propertyValue"
},
{
"name": "run_script_dl",
"description": "Coder (D. Lakens) decision on if the script can run; True if the script runs / False if the script does not run",
"@type": "propertyValue"
},
{
"name": "reproducible_dl",
"description": "Coder (D. Lakens) decision on if the paper is reproducible; True if it is reproducible / False if not reproducible",
"@type": "propertyValue"
},
{
"name": "comments_on_reproducibility_dl",
"description": "Coder (D. Lakens) comments on his own reproducibility process",
"@type": "propertyValue"
},
{
"name": "time_reproducing_dl",
"description": "Time it took to reproduce for Coder (D. Lakens)",
"@type": "propertyValue"
},
{
"name": "resolving_disagreements_between_coders",
"description": "how the disagreements between the coders where resolved after a closer look together",
"@type": "propertyValue"
}
]
}`
comments_data_po
Comments about the data that is provided by the paper (e.g. data is unclear / clearly described in codebook)
Distribution
21 missing values.
Summary statistics