sjPlot
sjp.lmer
#devtools::install_github("sjPlot/sjmisc")
library(sjPlot)## Warning: replacing previous import by 'grid::unit' when loading 'sjPlot'library(lme4)## Loading required package: Matrixfit <- lmer(Reaction ~ Days + (Days | Subject), sleepstudy)
fit## Linear mixed model fit by REML ['lmerMod']
## Formula: Reaction ~ Days + (Days | Subject)
## Data: sleepstudy
## REML criterion at convergence: 1743.628
## Random effects:
## Groups Name Std.Dev. Corr
## Subject (Intercept) 24.740
## Days 5.922 0.07
## Residual 25.592
## Number of obs: 180, groups: Subject, 18
## Fixed Effects:
## (Intercept) Days
## 251.41 10.47sjp.lmer(fit)################!!## Plotting random effects...
# sort by predictor Days
sjp.lmer(fit, sort.coef = "Days")## Plotting random effects...
#sjp.lmer(fit, sort.coef = "intercept")
# sort all predictors
sjp.lmer(fit,
facet.grid = FALSE,
sort.coef = "sort.all")
sjp.lmer(fit,
facet.grid = TRUE,
sort.coef = "sort.all")## Sorting each group of random intercept ('sort.all') is not possible when 'facet.grid = TRUE'.
## Sorting each group of random intercept ('sort.all') is not possible when 'facet.grid = TRUE'.
## Plotting random effects...
sjp.lmer
#For the next examples, we fit another model.
library(lme4)
# for sample data and tool functions
library(sjmisc)
data(efc)
head(efc)## c12hour e15relat e16sex e17age e42dep c82cop1 c83cop2 c84cop3 c85cop4
## 1 16 2 2 83 3 3 2 2 2
## 2 148 2 2 88 3 3 3 3 3
## 3 70 1 2 82 3 2 2 1 4
## 4 168 1 2 67 4 4 1 3 1
## 5 168 2 2 84 4 3 2 1 2
## 6 16 2 2 85 4 2 2 3 3
## c86cop5 c87cop6 c88cop7 c89cop8 c90cop9 c160age c161sex c172code
## 1 1 1 2 3 3 56 2 2
## 2 4 1 3 2 2 54 2 2
## 3 1 1 1 4 3 80 1 1
## 4 1 1 1 2 4 69 1 2
## 5 2 2 1 4 4 47 2 2
## 6 3 2 2 1 1 56 1 2
## c175empl barthtot neg_c_7 pos_v_4 quol_5 resttotn tot_sc_e n4pstu
## 1 1 75 12 12 14 0 4 0
## 2 1 75 20 11 10 4 0 0
## 3 0 35 11 13 7 0 1 2
## 4 0 0 10 15 12 2 0 3
## 5 0 25 12 15 19 2 1 2
## 6 1 60 19 9 8 1 3 2
## nur_pst
## 1 NA
## 2 NA
## 3 2
## 4 3
## 5 2
## 6 2# prepare group variable
efc$grp = as.factor(efc$e15relat)
levels(x = efc$grp) <- get_val_labels(efc$e15relat)##### Warning: 'get_val_labels' is deprecated.
## Use 'get_labels' instead.
## See help("Deprecated")head(efc$grp)## [1] child child spouse/partner spouse/partner
## [5] child child
## 8 Levels: spouse/partner child sibling ... other, specify# data frame for fitted model
mydf <- data.frame(neg_c_7 = as.numeric(efc$neg_c_7),
sex = as.factor(efc$c161sex),
c12hour = as.numeric(efc$c12hour),
barthel = as.numeric(efc$barthtot),
grp = efc$grp)
head(mydf)## neg_c_7 sex c12hour barthel grp
## 1 12 2 16 75 child
## 2 20 2 148 75 child
## 3 11 1 70 35 spouse/partner
## 4 10 1 168 0 spouse/partner
## 5 12 2 168 25 child
## 6 19 1 16 60 child# fit glmer
fit2 <- lmer(neg_c_7 ~ sex + c12hour +
barthel + (1|grp),data = mydf)#With the type parameter, you can decide which effects to plot. type = "fe" plots the fixed effects.
# plot fixed effects
sjp.lmer(fit2, type = "fe")## Computing approximate p-values via Wald chi-squared test...
## plot standardized fixed effects
sjp.lmer(fit2, type = "fe.std")## Computing approximate p-values via Wald chi-squared test...
#Plotting slopes of fixed effects
# plot fixed effects slopes
sjp.lmer(fit2, type = "fe.pred")
#Plotting fixed effects slopes for each random intercept (group levels)
# random intercepts
ranef(fit2)## $grp
## (Intercept)
## spouse/partner 0.62318882
## child 0.42390010
## sibling -0.05435509
## daughter or son -in-law 0.05759517
## ancle/aunt -0.10111187
## nephew/niece -0.55060421
## cousin -0.11383605
## other, specify -0.28477688# fixed effects
fixef(fit2)## (Intercept) sex2 c12hour barthel
## 14.135947298 0.478500191 0.003365667 -0.047946653# plot fixed effects depending on group levels
sjp.lmer(fit2, type = "fe.ri")
# plot fixed effects depending on group levels
# emphasize group levels 1, 2 and 5
sjp.lmer(fit2,
type = "fe.ri",
emph.grp = c(1, 2, 5),
facet.grid = FALSE)
sjp.lmer(fit2,
type = "fe.ri",
emph.grp = c(1, 2, 5),
facet.grid = TRUE)## Emphasizing groups only works in non-faceted plots. Use 'facet.grid = FALSE' to enable group emphasizing. 'emph.grp' was set to NULL.
#Grouping levels can also be specified via their names.
# plot fixed effects depending on group levels
# emphasize groups child and cousin
# only for predictor barthel
sjp.lmer(fit2,
type = "fe.ri",
emph.grp = c("child", "cousin"),
facet.grid = FALSE,
vars = "barthel")
## plot fixed effect "c12hour" only,
# depending on group levels
sjp.lmer(fit2,
type = "fe.ri",
vars = "c12hour")
# plot fixed effects correlation matrix
sjp.lmer(fit2, type = "fe.cor")## Computing correlation using spearman-method with listwise-deletion...## Warning: Removed 6 rows containing missing values (geom_point).
## plot qq-plot of random effects
sjp.lmer(fit2, type = "re.qq")## Testing for normal distribution. Dots should be plotted along the line.
sjc.qclus
#Examples
## Not run:
# k-means clustering of mtcars-dataset
sjc.qclus(mtcars)## Clustering Gap statistic ["clusGap"].
## B=100 simulated reference sets, k = 1..10
##
## --> Number of clusters (method 'Tibs2001SEmax', SE.factor=1): 2## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
# k-means clustering of mtcars-dataset with 4 pre-defined
# groups in a faceted panel
sjc.qclus(airquality,
groupcount = 4,
facetCluster = TRUE)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
#sjc.qclus(iris,
# groupcount = 3,
# facetCluster = TRUE)
## End(Not run)
# k-means clustering of airquality data
# and saving the results. most likely, 3 cluster
# groups have been found (see below).
airgrp <- sjc.qclus(airquality)## Clustering Gap statistic ["clusGap"].
## B=100 simulated reference sets, k = 1..10
##
## --> Number of clusters (method 'Tibs2001SEmax', SE.factor=1): 3## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
# "re-plot" cluster groups, without computing
# new k-means cluster analysis.
#sjc.qclus(airquality,
# groupcount = 3,
# groups = airgrp$classification)sjp.aov1
#Examples
library(sjmisc)
data(efc)
# note: "grpVar" does not need to be a factor.
# coercion to factor is done by the function
sjp.aov1(efc$c12hour, efc$e42dep)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
data(efc)
head(efc)## c12hour e15relat e16sex e17age e42dep c82cop1 c83cop2 c84cop3 c85cop4
## 1 16 2 2 83 3 3 2 2 2
## 2 148 2 2 88 3 3 3 3 3
## 3 70 1 2 82 3 2 2 1 4
## 4 168 1 2 67 4 4 1 3 1
## 5 168 2 2 84 4 3 2 1 2
## 6 16 2 2 85 4 2 2 3 3
## c86cop5 c87cop6 c88cop7 c89cop8 c90cop9 c160age c161sex c172code
## 1 1 1 2 3 3 56 2 2
## 2 4 1 3 2 2 54 2 2
## 3 1 1 1 4 3 80 1 1
## 4 1 1 1 2 4 69 1 2
## 5 2 2 1 4 4 47 2 2
## 6 3 2 2 1 1 56 1 2
## c175empl barthtot neg_c_7 pos_v_4 quol_5 resttotn tot_sc_e n4pstu
## 1 1 75 12 12 14 0 4 0
## 2 1 75 20 11 10 4 0 0
## 3 0 35 11 13 7 0 1 2
## 4 0 0 10 15 12 2 0 3
## 5 0 25 12 15 19 2 1 2
## 6 1 60 19 9 8 1 3 2
## nur_pst
## 1 NA
## 2 NA
## 3 2
## 4 3
## 5 2
## 6 2(efc.val <- get_labels(efc))## $c12hour
## NULL
##
## $e15relat
## [1] "spouse/partner" "child"
## [3] "sibling" "daughter or son -in-law"
## [5] "ancle/aunt" "nephew/niece"
## [7] "cousin" "other, specify"
##
## $e16sex
## [1] "male" "female"
##
## $e17age
## NULL
##
## $e42dep
## [1] "independent" "slightly dependent" "moderately dependent"
## [4] "severely dependent"
##
## $c82cop1
## [1] "never" "sometimes" "often" "always"
##
## $c83cop2
## [1] "Never" "Sometimes" "Often" "Always"
##
## $c84cop3
## [1] "Never" "Sometimes" "Often" "Always"
##
## $c85cop4
## [1] "Never" "Sometimes" "Often" "Always"
##
## $c86cop5
## [1] "Never" "Sometimes" "Often" "Always"
##
## $c87cop6
## [1] "Never" "Sometimes" "Often" "Always"
##
## $c88cop7
## [1] "Never" "Sometimes" "Often" "Always"
##
## $c89cop8
## [1] "never" "sometimes" "often" "always"
##
## $c90cop9
## [1] "never" "sometimes" "often" "always"
##
## $c160age
## NULL
##
## $c161sex
## [1] "Male" "Female"
##
## $c172code
## [1] "low level of education" "intermediate level of education"
## [3] "high level of education"
##
## $c175empl
## [1] "no" "yes"
##
## $barthtot
## NULL
##
## $neg_c_7
## NULL
##
## $pos_v_4
## NULL
##
## $quol_5
## NULL
##
## $resttotn
## NULL
##
## $tot_sc_e
## NULL
##
## $n4pstu
## [1] "No Care Level" "Care Level 1" "Care Level 2" "Care Level 3"
## [5] "Care Level 3+"
##
## $nur_pst
## [1] "Care Level 1" "Care Level 2" "Care Level 3/3+"(efc.var <- get_label(efc))## c12hour
## "average number of hours of care for the elder in a week"
## e15relat
## "relationship to elder"
## e16sex
## "elder's gender"
## e17age
## "elder' age"
## e42dep
## "how dependent is the elder? - subjective perception of carer"
## c82cop1
## "do you feel you cope well as caregiver?"
## c83cop2
## "do you find caregiving too demanding?"
## c84cop3
## "does caregiving cause difficulties in your relationship with your friends?"
## c85cop4
## "does caregiving have negative effect on your physical health?"
## c86cop5
## "does caregiving cause difficulties in your relationship with your family?"
## c87cop6
## "does caregiving cause financial difficulties?"
## c88cop7
## "do you feel trapped in your role as caregiver?"
## c89cop8
## "do you feel supported by friends/neighbours?"
## c90cop9
## "do you feel caregiving worthwhile?"
## c160age
## "carer' age"
## c161sex
## "carer's gender"
## c172code
## "carer's level of education: recoding of variable c172edu1"
## c175empl
## "are you currently employed?"
## barthtot
## "Total score BARTHEL INDEX"
## neg_c_7
## "Negative impact with 7 items"
## pos_v_4
## "Positive value with 4 items"
## quol_5
## "Quality of life 5 items"
## resttotn
## "Job restrictions"
## tot_sc_e
## "Services for elderly"
## n4pstu
## "Care level"
## nur_pst
## "Care level"sjp.aov1(efc$c12hour,
as.factor(efc$e42dep),
axisLabels.y = efc.val['e42dep'],
axisTitle.x = efc.var[['c12hour']],
showModelSummary = TRUE)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
# -------------------------------------------------
# auto-detection of value labels and variable names
# -------------------------------------------------
sjp.aov1(efc$c12hour,
efc$e42dep)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
# bar-plot, don't use this!
# however, if you dare to, adjust
# 'geom.size'...
sjp.aov1(efc$c12hour,
efc$c172code,
axisLabels.y = efc.val['c172code'],
title = efc.var[['c12hour']],
type = "bars",
geom.size = 0.5)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
sjp.chi2
#Examples
# create data frame with 5 dichotomous (dummy) variables
mydf <- data.frame(as.factor(sample(1:2, 100, replace=TRUE)),
as.factor(sample(1:2, 100, replace=TRUE)),
as.factor(sample(1:2, 100, replace=TRUE)),
as.factor(sample(1:2, 100, replace=TRUE)),
as.factor(sample(1:2, 100, replace=TRUE)))
# create variable labels
items <- list(c("Item 1", "Item 2", "Item 3", "Item 4", "Item 5"))
# plot Chi2-contingency-table
sjp.chi2(mydf, axisLabels = items)
sjp.corr
#Examples
# create data frame with 5 random variables
mydf <- data.frame(cbind(runif(10),
runif(10),
runif(10),
runif(10),
runif(10)))
# plot correlation matrix using circles
sjp.corr(mydf)## Computing correlation using spearman-method with listwise-deletion...## Warning: Removed 10 rows containing missing values (geom_point).
# plot correlation matrix using square tiles without diagram background
sjp.corr(mydf, type = "tile")## Computing correlation using spearman-method with listwise-deletion...
# -------------------------------
# Data from the EUROFAMCARE sample dataset
# -------------------------------
library(sjmisc)
data(efc)
# retrieve variable and value labels
varlabs <- get_label(efc)
# create data frame
vars.index <- c(1, 4, 15, 19, 20, 21, 22, 24, 25)
mydf <- data.frame(efc[, vars.index])
head(mydf)## c12hour e17age c160age barthtot neg_c_7 pos_v_4 quol_5 tot_sc_e n4pstu
## 1 16 83 56 75 12 12 14 4 0
## 2 148 88 54 75 20 11 10 0 0
## 3 70 82 80 35 11 13 7 1 2
## 4 168 67 69 0 10 15 12 0 3
## 5 168 84 47 25 12 15 19 1 2
## 6 16 85 56 60 19 9 8 3 2colnames(mydf) <- varlabs[vars.index]
# show legend
sjp.corr(mydf, type = "tile", hideLegend = FALSE)## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Computing correlation using spearman-method with listwise-deletion...
# -------------------------------
# auto-detection of labels
# -------------------------------
# blank theme
#sjp.setTheme(theme = "blank", axis.angle.x = 90)
sjp.corr(efc[, vars.index])## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Computing correlation using spearman-method with listwise-deletion...## Warning: Removed 36 rows containing missing values (geom_point).
sjt.df
data(efc)
head(efc)## c12hour e15relat e16sex e17age e42dep c82cop1 c83cop2 c84cop3 c85cop4
## 1 16 2 2 83 3 3 2 2 2
## 2 148 2 2 88 3 3 3 3 3
## 3 70 1 2 82 3 2 2 1 4
## 4 168 1 2 67 4 4 1 3 1
## 5 168 2 2 84 4 3 2 1 2
## 6 16 2 2 85 4 2 2 3 3
## c86cop5 c87cop6 c88cop7 c89cop8 c90cop9 c160age c161sex c172code
## 1 1 1 2 3 3 56 2 2
## 2 4 1 3 2 2 54 2 2
## 3 1 1 1 4 3 80 1 1
## 4 1 1 1 2 4 69 1 2
## 5 2 2 1 4 4 47 2 2
## 6 3 2 2 1 1 56 1 2
## c175empl barthtot neg_c_7 pos_v_4 quol_5 resttotn tot_sc_e n4pstu
## 1 1 75 12 12 14 0 4 0
## 2 1 75 20 11 10 4 0 0
## 3 0 35 11 13 7 0 1 2
## 4 0 0 10 15 12 2 0 3
## 5 0 25 12 15 19 2 1 2
## 6 1 60 19 9 8 1 3 2
## nur_pst
## 1 NA
## 2 NA
## 3 2
## 4 3
## 5 2
## 6 2#sji.viewSPSS(efc)
#Description and content of data frames
sjt.df(efc)##
|
| | 0%
|
|== | 4%
|
|===== | 8%
|
|======== | 12%
|
|========== | 15%
|
|============ | 19%
|
|=============== | 23%
|
|================== | 27%
|
|==================== | 31%
|
|====================== | 35%
|
|========================= | 38%
|
|============================ | 42%
|
|============================== | 46%
|
|================================ | 50%
|
|=================================== | 54%
|
|====================================== | 58%
|
|======================================== | 62%
|
|========================================== | 65%
|
|============================================= | 69%
|
|================================================ | 73%
|
|================================================== | 77%
|
|==================================================== | 81%
|
|======================================================= | 85%
|
|========================================================== | 88%
|
|============================================================ | 92%
|
|============================================================== | 96%
|
|=================================================================| 100%sjp.glm
#Examples
# prepare dichotomous dependent variable
data(swiss)
head(swiss)## Fertility Agriculture Examination Education Catholic
## Courtelary 80.2 17.0 15 12 9.96
## Delemont 83.1 45.1 6 9 84.84
## Franches-Mnt 92.5 39.7 5 5 93.40
## Moutier 85.8 36.5 12 7 33.77
## Neuveville 76.9 43.5 17 15 5.16
## Porrentruy 76.1 35.3 9 7 90.57
## Infant.Mortality
## Courtelary 22.2
## Delemont 22.2
## Franches-Mnt 20.2
## Moutier 20.3
## Neuveville 20.6
## Porrentruy 26.6y <- ifelse(swiss$Fertility < median(swiss$Fertility), 0, 1)
# fit model
fitOR <- glm(y ~ swiss$Education + swiss$Examination +
swiss$Infant.Mortality + swiss$Catholic,
family = binomial(link = "logit"))
# print Odds Ratios as dots
sjp.glm(fitOR)## Waiting for profiling to be done...
# print Odds Ratios as bars
sjp.glm(fitOR, type = "bars", geom.size = .3)## Waiting for profiling to be done...
# -------------------------------
# Predictors for negative impact
# of care. Data from the EUROFAMCARE
# sample dataset
# -------------------------------
library(sjmisc)
data(efc)
# retrieve predictor variable labels
labs <- get_label(efc)
predlab <- c(labs[['c161sex']],
paste0(labs[['e42dep']], " (slightly)"),
paste0(labs[['e42dep']], " (moderate)"),
paste0(labs[['e42dep']], " (severely)"),
labs[['barthtot']],
paste0(labs[['c172code']], " (mid)"),
paste0(labs[['c172code']], " (high)"))
# create binary response
y <- ifelse(efc$neg_c_7 < median(na.omit(efc$neg_c_7)), 0, 1)
# create dummy variables for educational status
edu.mid <- ifelse(efc$c172code == 2, 1, 0)
edu.high <- ifelse(efc$c172code == 3, 1, 0)
# create data frame for fitted model
mydf <- data.frame(y = as.factor(y),
sex = as.factor(efc$c161sex),
dep = as.factor(efc$e42dep),
barthel = as.numeric(efc$barthtot),
edu.mid = as.factor(edu.mid),
edu.hi = as.factor(edu.high))
# fit model
fit <- glm(y ~., data = mydf, family = binomial(link = "logit"))# plot odds
sjp.glm(fit,
title = labs[['neg_c_7']],
axisLabels.y = predlab)## Waiting for profiling to be done...
# plot probability curves (predicted probabilities)
# of coefficients
#sjp.glm(fit,
# title = labs[['neg_c_7']],
# axisLabels.y = predlab,
# type = "prob")sjp.glmer
#Examples
library(lme4)
library(sjmisc)
# create binary response
sleepstudy$Reaction.dicho <- dicho(sleepstudy$Reaction, dich.by = "md")
# fit model
fit <- glmer(Reaction.dicho ~ Days + (Days | Subject),
sleepstudy,
family = binomial("logit"))
# simple plot
sjp.glmer(fit)## Plotting random effects...
# sort by predictor Days
sjp.glmer(fit, sort.coef = "Days")## Plotting random effects...
data(efc)
# create binary response
efc$hi_qol <- dicho(efc$quol_5)
# prepare group variable
efc$grp = as.factor(efc$e15relat)
levels(x = efc$grp) <- get_labels(efc$e15relat)# data frame for fitted model
mydf <- data.frame(hi_qol = as.factor(efc$hi_qol),
sex = as.factor(efc$c161sex),
c12hour = as.numeric(efc$c12hour),
neg_c_7 = as.numeric(efc$neg_c_7),
grp = efc$grp)
# fit glmer
fit <- glmer(hi_qol ~ sex + c12hour + neg_c_7 + (1|grp),
data = mydf,
family = binomial("logit"))
# plot and sort fixed effects
sjp.glmer(fit,
type = "fe",
sort.coef = TRUE)
# plot probability curves (predicted probabilities)
# for each covariate, grouped by random intercepts
# in integrated plots, emphasizing groups 1 and 4
#sjp.glmer(fit,
# type = "ri.pc",
# emph.grp = c(1, 4),
# facet.grid = FALSE)
# plot probability curve (predicted probabilities)
# of fixed effect, only for coefficient "neg_c_7"
#sjp.glmer(fit,
# type = "fe.pc",
# vars = "neg_c_7")sjp.glmm
#Examples
# prepare dummy variables for binary logistic regression
y1 <- ifelse(swiss$Fertility < median(swiss$Fertility), 0, 1)
y2 <- ifelse(swiss$Infant.Mortality < median(swiss$Infant.Mortality), 0, 1)
y3 <- ifelse(swiss$Agriculture<median(swiss$Agriculture), 0, 1)
# Now fit the models. Note that all models share the same predictors
# and only differ in their dependent variable (y1, y2 and y3)
fitOR1 <- glm(y1 ~ swiss$Education + swiss$Examination + swiss$Catholic,
family = binomial(link = "logit"))
fitOR2 <- glm(y2 ~ swiss$Education + swiss$Examination + swiss$Catholic,
family = binomial(link = "logit"))
fitOR3 <- glm(y3 ~ swiss$Education + swiss$Examination + swiss$Catholic,
family = binomial(link = "logit"))
# plot multiple models
sjp.glmm(fitOR1, fitOR2, fitOR3, facet.grid = TRUE)## Waiting for profiling to be done...
## Waiting for profiling to be done...
## Waiting for profiling to be done...## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals
# plot multiple models with legend labels and point shapes instead of value labels
sjp.glmm(fitOR1, fitOR2, fitOR3,
labelDependentVariables = c("Fertility",
"Infant Mortality",
"Agriculture"),
showValueLabels = FALSE,
showPValueLabels = FALSE,
fade.ns = TRUE,
usePShapes = TRUE)## Waiting for profiling to be done...
## Waiting for profiling to be done...
## Waiting for profiling to be done...## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals
# plot multiple models from nested lists argument
all.models <- list()
all.models[[1]] <- fitOR1
all.models[[2]] <- fitOR2
all.models[[3]] <- fitOR3
sjp.glmm(all.models)## Waiting for profiling to be done...
## Waiting for profiling to be done...
## Waiting for profiling to be done...## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals
# -------------------------------
# Predictors for negative impact
# of care. Data from the EUROFAMCARE
# sample dataset
# -------------------------------
library(sjmisc)
data(efc)
# create binary response
y <- ifelse(efc$neg_c_7 < median(na.omit(efc$neg_c_7)), 0, 1)
# create dummy variables for educational status
edu.mid <- ifelse(efc$c172code == 2, 1, 0)
edu.high <- ifelse(efc$c172code == 3, 1, 0)
# create data frame for fitted model
mydat <- data.frame(y = as.factor(y),
sex = as.factor(efc$c161sex),
dep = as.factor(efc$e42dep),
barthel = as.numeric(efc$barthtot),
edu.mid = as.factor(edu.mid),
edu.hi = as.factor(edu.high))
fit1 <- glm(y ~ sex + edu.mid + edu.hi,
data = mydat,
family = binomial(link = "logit"))
fit2 <- update(fit1, . ~ . + barthel)
fit3 <- update(fit2, . ~ . + dep)
sjp.glmm(fit1, fit2, fit3)## Waiting for profiling to be done...
## Waiting for profiling to be done...
## Waiting for profiling to be done...## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals
sjp.gpt
#Examples
library(sjmisc)
data(efc)
# the proportion of dependency levels in female
# elderly, for each family carer's relationship
# to elderly
sjp.gpt(efc$e42dep, efc$e16sex, efc$e15relat)
# proportion of educational levels in highest
# dependency category of elderly, for different
# care levels
sjp.gpt(efc$c172code, efc$e42dep, efc$n4pstu)
sjp.grpfrq
#Examples
# histrogram with EUROFAMCARE sample dataset
library(sjmisc)
data(efc)
efc.val <- get_labels(efc)
efc.var <- get_label(efc)
sjp.grpfrq(efc$e17age,
efc$e16sex,
title = efc.var['e17age'],
type = "hist",
showValueLabels = FALSE,
showMeanIntercept = TRUE)
# boxplot
sjp.grpfrq(efc$e17age,
efc$e42dep,
type = "box")# -------------------------------------------------
# auto-detection of value labels and variable names
# -------------------------------------------------
# grouped bars using necessary y-limit
sjp.grpfrq(efc$e42dep,
efc$e16sex,
title = NULL)
# box plots with interaction variable
sjp.grpfrq(efc$e17age,
efc$e42dep,
interactionVar = efc$e16sex,
title = paste(efc.var['e17age'],
"by",
efc.var['e42dep'],
"and",
efc.var['e16sex']),
axisLabels.x = efc.val[['e17age']],
interactionVarLabels = efc.val[['e16sex']],
legendTitle = efc.var['e42dep'],
legendLabels = efc.val[['e42dep']],
type = "box")
# Grouped bar plot ranging from 1 to 28 (though scale starts with 7)
sjp.grpfrq(efc$neg_c_7,
efc$e42dep,
showValueLabels = FALSE,
startAxisAt = 1)
# Same grouped bar plot ranging from 7 to 28
sjp.grpfrq(efc$neg_c_7,
efc$e42dep,
showValueLabels = FALSE)sjp.int
#Examples
# Note that the data sets used in this example may not be perfectly suitable for
# fitting linear models. I just used them because they are part of the R-software.
# fit "dummy" model. Note that moderator should enter
# first the model, followed by predictor. Else, use
# argument "swapPredictors" to change predictor on
# x-axis with moderator
fit <- lm(weight ~ Diet * Time, data = ChickWeight)
# show summary to see significant interactions
summary(fit)##
## Call:
## lm(formula = weight ~ Diet * Time, data = ChickWeight)
##
## Residuals:
## Min 1Q Median 3Q Max
## -135.425 -13.757 -1.311 11.069 130.391
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 30.9310 4.2468 7.283 1.09e-12 ***
## Diet2 -2.2974 7.2672 -0.316 0.75202
## Diet3 -12.6807 7.2672 -1.745 0.08154 .
## Diet4 -0.1389 7.2865 -0.019 0.98480
## Time 6.8418 0.3408 20.076 < 2e-16 ***
## Diet2:Time 1.7673 0.5717 3.092 0.00209 **
## Diet3:Time 4.5811 0.5717 8.014 6.33e-15 ***
## Diet4:Time 2.8726 0.5781 4.969 8.92e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 34.07 on 570 degrees of freedom
## Multiple R-squared: 0.773, Adjusted R-squared: 0.7702
## F-statistic: 277.3 on 7 and 570 DF, p-value: < 2.2e-16# plot regression line of interaction terms, including value labels
sjp.int(fit, type = "eff", showValueLabels = TRUE)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
# load sample data set
library(sjmisc)
data(efc)
# create data frame with variables that should be included
# in the model
mydf <- data.frame(usage = efc$tot_sc_e,
sex = efc$c161sex,
education = efc$c172code,
burden = efc$neg_c_7,
dependency = efc$e42dep)
# convert gender predictor to factor
mydf$sex <- relevel(factor(mydf$sex), ref = "2")
# fit "dummy" model
fit <- lm(usage ~ .*., data = mydf)
summary(fit)##
## Call:
## lm(formula = usage ~ . * ., data = mydf)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4070 -0.8149 -0.2876 0.3931 8.2089
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.75061 0.71461 2.450 0.0145 *
## sex1 -0.09252 0.47518 -0.195 0.8457
## education -0.30402 0.27913 -1.089 0.2764
## burden -0.08038 0.05468 -1.470 0.1419
## dependency -0.45307 0.21478 -2.109 0.0352 *
## sex1:education -0.04657 0.15463 -0.301 0.7634
## sex1:burden -0.02251 0.02785 -0.808 0.4192
## sex1:dependency 0.16118 0.11559 1.394 0.1636
## education:burden 0.01110 0.01773 0.626 0.5316
## education:dependency 0.13983 0.08095 1.727 0.0845 .
## burden:dependency 0.02880 0.01245 2.314 0.0209 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.221 on 822 degrees of freedom
## (75 observations deleted due to missingness)
## Multiple R-squared: 0.06001, Adjusted R-squared: 0.04858
## F-statistic: 5.248 on 10 and 822 DF, p-value: 1.661e-07# plot interactions. note that type = "cond" only considers
# significant interactions by default. use "plevel" to
# adjust p-level sensivity
sjp.int(fit, type = "cond")## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
# plot only selected interaction term for
# type = "eff"
sjp.int(fit, type = "eff", int.term = "sex*education")
# plot interactions, using mean and sd as moderator
# values to calculate interaction effect
sjp.int(fit, type = "eff", moderatorValues = "meansd")
sjp.int(fit, type = "cond", moderatorValues = "meansd")## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
# plot interactions, including those with p-value up to 0.1
sjp.int(fit,
type = "cond",
plevel = 0.1,
showInterceptLines = TRUE)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
# -------------------------------
# Plot estimated marginal means
# -------------------------------
# load sample data set
library(sjmisc)
data(efc)
# create data frame with variables that should be included
# in the model
mydf <- data.frame(burden = efc$neg_c_7,
sex = efc$c161sex,
education = efc$c172code)
# convert gender predictor to factor
mydf$sex <- factor(mydf$sex)
mydf$education <- factor(mydf$education)
# name factor levels and dependent variable
levels(mydf$sex) <- c("female", "male")
levels(mydf$education) <- c("low", "mid", "high")
mydf$burden <- set_label(mydf$burden, "care burden")
# fit "dummy" model
fit <- lm(burden ~ .*., data = mydf)
summary(fit)##
## Call:
## lm(formula = burden ~ . * ., data = mydf)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.6321 -2.8491 -0.8491 2.1509 16.1509
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 11.0244 0.6068 18.169 <2e-16 ***
## sexmale 1.0632 0.6916 1.537 0.125
## educationmid 0.2524 0.7092 0.356 0.722
## educationhigh 0.6495 0.8344 0.778 0.437
## sexmale:educationmid -0.4909 0.8073 -0.608 0.543
## sexmale:educationhigh -0.1050 0.9741 -0.108 0.914
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.885 on 827 degrees of freedom
## (75 observations deleted due to missingness)
## Multiple R-squared: 0.01098, Adjusted R-squared: 0.005005
## F-statistic: 1.837 on 5 and 827 DF, p-value: 0.1032# plot marginal means of interactions, no interaction found
sjp.int(fit, type = "emm")## Warning: No significant interactions found...# plot marginal means of interactions, including those with p-value up to 1
sjp.int(fit, type = "emm", plevel = 1)
# swap predictors
sjp.int(fit,
type = "emm",
plevel = 1,
swapPredictors = TRUE)
# Predictors for negative impact of care.
# Data from the EUROFAMCARE sample datasetlibrary(sjmisc)
data(efc)
# create binary response
y <- ifelse(efc$neg_c_7 < median(stats::na.omit(efc$neg_c_7)), 0, 1)
# create data frame for fitted model
mydf <- data.frame(y = as.factor(y),
sex = as.factor(efc$c161sex),
barthel = as.numeric(efc$barthtot))
# fit model
fit <- glm(y ~ sex * barthel,
data = mydf,
family = binomial(link = "logit"))
# plot interaction, increase p-level sensivity
sjp.int(fit,
type = "eff",
legendLabels = get_labels(efc$c161sex),
plevel = 0.1)
sjp.int(fit,
type = "cond",
legendLabels = get_labels(efc$c161sex),
plevel = 0.1)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
## Not run:# -------------------------------
# Plot effects
# -------------------------------
# add continuous variable
mydf$barthel <- efc$barthtot
# re-fit model with continuous variable
fit <- lm(burden ~ .*., data = mydf)# plot effects
sjp.int(fit, type = "eff", showCI = TRUE)
# plot effects, facetedsjp.int(fit,
type = "eff",
int.plot.index = 3,
showCI = TRUE,
facet.grid = TRUE)
## End(Not run)sjp.likert
#Examples
# prepare data for dichotomous likert scale, 5 items
likert_2 <- data.frame(
as.factor(sample(1:2, 500, replace = TRUE, prob = c(0.3,0.7))),
as.factor(sample(1:2, 500, replace = TRUE, prob = c(0.6,0.4))),
as.factor(sample(1:2, 500, replace = TRUE, prob = c(0.25,0.75))),
as.factor(sample(1:2, 500, replace = TRUE, prob = c(0.9,0.1))),
as.factor(sample(1:2, 500, replace = TRUE, prob = c(0.35,0.65))))
# create labels
levels_2 <- c("Agree", "Disagree")
# prepare data for 4-category likert scale, with neutral category 5 items
Q1 <- as.factor(sample(1:4, 500, replace = TRUE, prob = c(0.2, 0.3, 0.1, 0.4)))
Q2 <- as.factor(sample(1:4, 500, replace = TRUE, prob = c(0.5, 0.25, 0.15, 0.1)))
Q3 <- as.factor(sample(1:4, 500, replace = TRUE, prob = c(0.25, 0.1, 0.4, 0.25)))
Q4 <- as.factor(sample(1:4, 500, replace = TRUE, prob = c(0.1, 0.4, 0.4, 0.1)))
Q5 <- as.factor(sample(1:4, 500, replace = TRUE, prob = c(0.35, 0.25, 0.15, 0.25)))
likert_4 <- data.frame(Q1, Q2, Q3, Q4, Q5)
# create labels
levels_4 <- c("Strongly agree",
"Agree",
"Disagree",
"Strongly Disagree",
"Don't know")# prepare data for 6-category likert scale, 5 items
likert_6 <- data.frame()
Q1 <- as.factor(sample(1:6, 500, replace = TRUE, prob = c(0.2,0.1,0.1,0.3,0.2,0.1)))
Q2 <- as.factor(sample(1:6, 500, replace = TRUE, prob = c(0.15,0.15,0.3,0.1,0.1,0.2)))
Q3 <- as.factor(sample(1:6, 500, replace = TRUE, prob = c(0.2,0.25,0.05,0.2,0.2,0.2)))
Q4 <- as.factor(sample(1:6, 500, replace = TRUE, prob = c(0.2,0.1,0.1,0.4,0.1,0.1)))
Q5 <- as.factor(sample(1:6, 500, replace = TRUE, prob = c(0.1,0.4,0.1,0.3,0.05,0.15)))
likert_6 <- data.frame(Q1, Q2, Q3, Q4, Q5)
# create labels
levels_6 <- c("Very strongly agree", "Strongly agree", "Agree",
"Disagree", "Strongly disagree", "Very strongly disagree")
# create item labels
items <- c("Q1", "Q2", "Q3", "Q4", "Q5")# plot dichotomous likert scale, ordered by "negative" values
sjp.likert(likert_2,
geom.colors = c("green", "red"),
legendLabels = levels_2,
axisLabels.y = items,
sort.frq = "neg.desc")## Warning: Stacking not well defined when ymin != 0
# plot 4-category-likert-scale, no order
sjp.likert(likert_4,
cat.neutral = 5,
legendLabels = levels_4,
axisLabels.y = items,
gridRange = 1.2,
expand.grid = FALSE,
value.labels = "sum.outside",
showPercentageSign = TRUE)## Warning in max(catcount): max の引数に有限な値がありません: -Inf を返します## Warning in min(catcount): min の引数に有限な値がありません: Inf を返します## Warning: Length of labels for item categories 'legendLabels' differs from
## detected amount of categories. Use 'catcount' argument to define amount of
## item categories, if plotting does not work.## Warning: Stacking not well defined when ymin != 0
# plot 6-category-likert-scale, ordered by positive values,
# in brown color scale
sjp.likert(likert_6,
legendLabels = levels_6,
axisLabels.y = items,
sort.frq = "pos.asc",
labelDigits = 0,
showPercentageSign = TRUE,
value.labels = "sum.inside")## Warning: Stacking not well defined when ymin != 0
sjp.lm
#Examples
# --------------------------------------------------
# plotting estimates of linear models as forest plot
# --------------------------------------------------
# fit linear model
fit <- lm(airquality$Ozone ~ airquality$Wind + airquality$Temp +
airquality$Solar.R)
# plot estimates with CI
sjp.lm(fit, gridBreaksAt = 2)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
# plot estimates with CI
# and with narrower tick marks
# (because "gridBreaksAt" was not specified)
sjp.lm(fit)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
# ---------------------------------------------------
# plotting regression line of linear model (done
# automatically if fitted model has only 1 predictor)
# ---------------------------------------------------
library(sjmisc)
data(efc)
# fit model
fit <- lm(neg_c_7 ~ quol_5, data=efc)
# plot regression line with label strings
sjp.lm(fit,
axisLabels.x = "Quality of life",
axisLabels.y = "Burden of care",
showLoess = TRUE)
# --------------------------------------------------
# plotting regression lines of each single predictor
# of a fitted model
# --------------------------------------------------
library(sjmisc)
data(efc)
# fit model
fit <- lm(tot_sc_e ~ c12hour + e17age + e42dep, data=efc)
# reression line and scatter plot
sjp.lm(fit, type = "pred")
# reression line w/o scatter plot
sjp.lm(fit,
type = "pred",
showScatterPlot = FALSE)
# --------------------------
# plotting model assumptions
# --------------------------
sjp.lm(fit, type = "ma")
## Not run:sjp.poly
# --------------------------
# plotting polynomial terms
# --------------------------
library(sjmisc)
data(efc)
# fit sample model
fit <- lm(tot_sc_e ~ c12hour + e17age + e42dep, data = efc)
# "e17age" does not seem to be linear correlated to response
# try to find appropiate polynomial. Grey line (loess smoothed)
# indicates best fit. Looks like x^3 has a good fit.
# (not checked for significance yet).
sjp.poly(fit, "e17age", 2:4, showScatterPlot = FALSE)## Polynomial degrees: 2
## ---------------------
## p(x^1): 0.734
## p(x^2): 0.721
##
## Polynomial degrees: 3
## ---------------------
## p(x^1): 0.010
## p(x^2): 0.011
## p(x^3): 0.011
##
## Polynomial degrees: 4
## ---------------------
## p(x^1): 0.234
## p(x^2): 0.267
## p(x^3): 0.303
## p(x^4): 0.343
# fit new model
fit <- lm(tot_sc_e ~ c12hour + e42dep +
e17age + I(e17age^2) + I(e17age^3),
data = efc)
# plot marginal effects of polynomial term
sjp.lm(fit, type = "poly", poly.term = "e17age")
library(splines)
# fit new model with "splines"-package, "bs"
fit <- lm(tot_sc_e ~ c12hour + e42dep + bs(e17age, 3), data = efc)
# plot marginal effects of polynomial term, same call as above
sjp.lm(fit, type = "poly", poly.term = "e17age")## NOTE: e17age does not appear in the model
## End(Not run)sjp.lmer
#Examples
# fit model
library(lme4)
fit <- lmer(Reaction ~ Days + (Days | Subject), sleepstudy)
# simple plot
sjp.lmer(fit)## Plotting random effects...
# plot fixed effects
sjp.lmer(fit, type = "fe")## Computing approximate p-values via Wald chi-squared test...
# sort by predictor Days
sjp.lmer(fit, sort.coef = "Days")## Plotting random effects...
# plot each predictor as own plot
# sort each plot
sjp.lmer(fit,
facet.grid = FALSE,
sort.coef = "sort.all")
library(sjmisc)
data(efc)
# prepare group variable
efc$grp = as.factor(efc$e15relat)
levels(x = efc$grp) <- get_labels(efc$e15relat)
# data frame for fitted model
mydf <- data.frame(neg_c_7 = as.numeric(efc$neg_c_7),
sex = as.factor(efc$c161sex),
c12hour = as.numeric(efc$c12hour),
barthel = as.numeric(efc$barthtot),
grp = efc$grp)
# fit lmer
fit <- lmer(neg_c_7 ~ sex + c12hour + barthel + (1|grp),
data = mydf)# plot fixed effects
sjp.lmer(fit, type = "fe")## Computing approximate p-values via Wald chi-squared test...
sjp.lmer(fit,
type = "fe.std",
sort.coef = TRUE)## Computing approximate p-values via Wald chi-squared test...
# plot fixed effects slopes for
# each random intercept, but only for
# coefficient "c12hour"
sjp.lmer(fit,
type = "fe.ri",
vars = "c12hour")
# highlight specific grouping levels
# in this case we compare spouses, children
# and children-in-law
sjp.lmer(fit,
type = "fe.ri",
emph.grp = c(1, 2, 4),
vars = "c12hour")## Emphasizing groups only works in non-faceted plots. Use 'facet.grid = FALSE' to enable group emphasizing. 'emph.grp' was set to NULL.
## Not run:# --------------------------
# plotting polynomial terms
# --------------------------
# check linear relation between predictors and response
sjp.lmer(fit, type = "fe.pred")
# "barthel" does not seem to be linear correlated to response
# try to find appropiate polynomial. Grey line (loess smoothed)
# indicates best fit. Looks like x^4 has the best fit,
# however, x^2 seems to be suitable according to p-values.
sjp.poly(fit, "barthel", 2:4, showScatterPlot = FALSE)## Polynomial degrees: 2
## ---------------------
## p(x^1): 0.178
## p(x^2): 0.000
##
## Polynomial degrees: 3
## ---------------------
## p(x^1): 0.107
## p(x^2): 0.053
## p(x^3): 0.240
##
## Polynomial degrees: 4
## ---------------------
## p(x^1): 0.819
## p(x^2): 0.530
## p(x^3): 0.280
## p(x^4): 0.216
# fit new model
fit <- lmer(neg_c_7 ~ sex + c12hour + barthel +
I(barthel^2) + (1|grp), data = mydf)## Warning: Some predictor variables are on very different scales: consider
## rescaling# plot marginal effects of polynomial term
sjp.lmer(fit, type = "poly", poly.term = "barthel")
# lme4 complaints about scale of polynomial term, so
# try centering this predictor
mydf$barthel_s <- scale(mydf$barthel, center = TRUE, scale = TRUE)
# re-fit model
fit_s <- lmer(neg_c_7 ~ sex + c12hour + barthel_s +
I(barthel_s^2) + (1|grp), data = mydf)
# plot marginal effects of centered, scaled polynomial term
sjp.lmer(fit_s, type = "poly", poly.term = "barthel_s")
# scaling also improved p-values
sjt.lmer(fit, fit_s)## Computing approximate p-values via Wald chi-squared test...
## Computing approximate p-values via Wald chi-squared test...## End(Not run)sjp.lmm
#Examples
# prepare dummy variables for binary logistic regression
# Now fit the models. Note that all models share the same predictors
# and only differ in their dependent variable
library(sjmisc)
data(efc)
# fit three models
fit1 <- lm(barthtot ~ c160age + c12hour + c161sex + c172code, data = efc)
fit2 <- lm(neg_c_7 ~ c160age + c12hour + c161sex + c172code, data = efc)
fit3 <- lm(tot_sc_e ~ c160age + c12hour + c161sex + c172code, data = efc)
# plot multiple models
sjp.lmm(fit1, fit2, fit3, facet.grid = TRUE)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals
# plot multiple models with legend labels and
# point shapes instead of value labels
sjp.lmm(fit1, fit2, fit3,
axisLabels.y = c("Carer's Age",
"Hours of Care",
"Carer's Sex",
"Educational Status"),
labelDependentVariables = c("Barthel Index",
"Negative Impact",
"Services used"),
showValueLabels = FALSE,
showPValueLabels = FALSE,
fade.ns = TRUE,
usePShapes = TRUE)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals
# ------------------------------
# plot multiple models from nested lists argument
# ------------------------------
all.models <- list()
all.models[[1]] <- fit1
all.models[[2]] <- fit2
all.models[[3]] <- fit3
sjp.lmm(all.models)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals
# ------------------------------
# plot multiple models with different
# predictors (stepwise inclusion),
# standardi estimates
# ------------------------------
fit1 <- lm(mpg ~ wt + cyl + disp + gear, data = mtcars)
fit2 <- update(fit1, . ~ . + hp)
fit3 <- update(fit2, . ~ . + am)
sjp.lmm(fit1, fit2, fit3, type = "std2")## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.## Warning: position_dodge requires non-overlapping x intervals## Warning: position_dodge requires non-overlapping x intervals
sjp.pca
#Examples
# randomly create data frame with 7 items, each consisting of 4 categories
likert_4 <- data.frame(sample(1:4,
500,
replace = TRUE,
prob = c(0.2, 0.3, 0.1, 0.4)),
sample(1:4,
500,
replace = TRUE,
prob = c(0.5, 0.25, 0.15, 0.1)),
sample(1:4,
500,
replace = TRUE,
prob = c(0.4, 0.15, 0.25, 0.2)),
sample(1:4,
500,
replace = TRUE,
prob = c(0.25, 0.1, 0.4, 0.25)),
sample(1:4,
500,
replace = TRUE,
prob = c(0.1, 0.4, 0.4, 0.1)),
sample(1:4,
500,
replace = TRUE),
sample(1:4,
500,
replace = TRUE,
prob = c(0.35, 0.25, 0.15, 0.25)))
# Create variable labels
colnames(likert_4) <- c("V1", "V2", "V3", "V4", "V5", "V6", "V7")
# plot results from PCA as square-tiled "heatmap"
sjp.pca(likert_4, type = "tile")
# plot results from PCA as bars
sjp.pca(likert_4, type = "bar")
# manually compute PCA
pca <- prcomp(na.omit(likert_4),
retx = TRUE,
center = TRUE,
scale. = TRUE)
# plot results from PCA as circles, including Eigenvalue-diagnostic.
# note that this plot does not compute the Cronbach's Alpha
sjp.pca(pca,
plotEigenvalues = TRUE,
type = "circle",
geom.size = 10)# -------------------------------
# Data from the EUROFAMCARE sample dataset
# -------------------------------
library(sjmisc)
data(efc)
# retrieve variable and value labels
varlabs <- get_label(efc)
# recveive first item of COPE-index scale
start <- which(colnames(efc) == "c82cop1")
# recveive last item of COPE-index scale
end <- which(colnames(efc) == "c90cop9")
# create data frame with COPE-index scale
mydf <- data.frame(efc[, c(start:end)])
colnames(mydf) <- varlabs[c(start:end)]
sjp.pca(mydf)## Following items have been removed:
## none.
sjp.pca(mydf, type = "tile")## Following items have been removed:
## none.
# -------------------------------
# auto-detection of labels
# -------------------------------
sjp.pca(efc[, c(start:end)], type = "circle", geom.size = 10)## Following items have been removed:
## none.
sjp.poly
library(sjmisc)
data(efc)
# linear fit. loess-smoothed line indicates a more
# or less cubic curve
sjp.poly(efc$c160age, efc$quol_5, 1)## Polynomial degrees: 1
## ---------------------
## p(x^1): 0.000
# quadratic fit
sjp.poly(efc$c160age, efc$quol_5, 2)## Polynomial degrees: 2
## ---------------------
## p(x^1): 0.078
## p(x^2): 0.533
# linear to cubic fit
sjp.poly(efc$c160age, efc$quol_5,
1:4, showScatterPlot = FALSE)## Polynomial degrees: 1
## ---------------------
## p(x^1): 0.000
##
## Polynomial degrees: 2
## ---------------------
## p(x^1): 0.078
## p(x^2): 0.533
##
## Polynomial degrees: 3
## ---------------------
## p(x^1): 0.012
## p(x^2): 0.001
## p(x^3): 0.000
##
## Polynomial degrees: 4
## ---------------------
## p(x^1): 0.777
## p(x^2): 0.913
## p(x^3): 0.505
## p(x^4): 0.254
library(sjmisc)
data(efc)
# fit sample model
fit <- lm(tot_sc_e ~ c12hour + e17age + e42dep, data = efc)
# inspect relationship between predictors and response
sjp.lm(fit, type = "pred",
showLoess = TRUE, showScatterPlot = FALSE)
## Warning in simpleLoess(y, x, w, span, degree, parametric, drop.square,
## normalize, : pseudoinverse used at 4.015## Warning in simpleLoess(y, x, w, span, degree, parametric, drop.square,
## normalize, : neighborhood radius 2.015## Warning in simpleLoess(y, x, w, span, degree, parametric, drop.square,
## normalize, : reciprocal condition number 3.6014e-017## Warning in simpleLoess(y, x, w, span, degree, parametric, drop.square,
## normalize, : There are other near singularities as well. 1
# "e17age" does not seem to be linear correlated to response
# try to find appropiate polynomial. Grey line (loess smoothed)
# indicates best fit. Looks like x^4 has the best fit,
# however, only x^3 has significant p-values.
sjp.poly(fit, "e17age", 2:4, showScatterPlot = FALSE)## Polynomial degrees: 2
## ---------------------
## p(x^1): 0.734
## p(x^2): 0.721
##
## Polynomial degrees: 3
## ---------------------
## p(x^1): 0.010
## p(x^2): 0.011
## p(x^3): 0.011
##
## Polynomial degrees: 4
## ---------------------
## p(x^1): 0.234
## p(x^2): 0.267
## p(x^3): 0.303
## p(x^4): 0.343
## Not run:
# fit new model
fit <- lm(tot_sc_e ~ c12hour + e42dep +
e17age + I(e17age^2) + I(e17age^3),
data = efc)
# plot marginal effects of polynomial term
sjp.lm(fit, type = "poly", poly.term = "e17age")
## End(Not run)sjp.scatter
#Examples
# load sample date
library(sjmisc)
data(efc)
# simple scatter plot, auto-jittering
sjp.scatter(efc$e16sex, efc$neg_c_7)## auto-jittering values...
# simple scatter plot, no jittering needed
sjp.scatter(efc$c160age, efc$e17age)
# grouped scatter plot
sjp.scatter(efc$c160age, efc$e17age, efc$e42dep)
# grouped and jittered scatter plot with marginal rug plot
sjp.scatter(efc$e16sex,efc$neg_c_7, efc$c172code, showRug = TRUE)## auto-jittering values...
# grouped and labelled scatter plot, not using the auto-detection
# of labels, but instead pass labels as arguments
sjp.scatter(efc$c160age, efc$e17age, efc$e42dep,
title = "Scatter Plot",
legendTitle = get_label(efc)['e42dep'],
legendLabels = get_labels(efc)[['e42dep']],
axisTitle.x = get_label(efc)['c160age'],
axisTitle.y = get_label(efc)['e17age'],
showGroupFitLine = TRUE)
# grouped and labelled scatter plot as facets
sjp.scatter(efc$c160age,efc$e17age, efc$e42dep,
showGroupFitLine = TRUE,
facet.grid = TRUE,
show.se = TRUE)
# plot residuals of fitted models
fit <- lm(neg_c_7 ~ quol_5, data = efc)
sjp.scatter(y = fit$residuals, showTotalFitLine = TRUE)
# "hide" axis titles
sjp.scatter(efc$c160age, efc$e17age, efc$e42dep,
title = "", axisTitle.x = "", axisTitle.y = "")
# plot text labels
pl <- c(1:10)
for (i in 1:10) pl[i] <- paste(sample(c(0:9, letters, LETTERS),
8, replace = TRUE),
collapse = "")
sjp.scatter(runif(10), runif(10), pointLabels = pl)
#Examples
## Not run:
library(sjmisc)
data(efc)
# set sjPlot-defaults, a slightly modification
# of the ggplot base theme
sjp.setTheme()
# legends of all plots inside
sjp.setTheme(legend.pos = "top left",
legend.inside = TRUE)
sjp.xtab(efc$e42dep, efc$e16sex)
# Use classic-theme. you may need to
# load the ggplot2-library.
library(ggplot2)
sjp.setTheme(theme = theme_classic())
sjp.frq(efc$e42dep)
# adjust value labels
sjp.setTheme(geom.label.size = 3.5,
geom.label.color = "#3366cc",
geom.label.angle = 90)
# hjust-aes needs adjustment for this
update_geom_defaults('text', list(hjust = -0.1))
sjp.xtab(efc$e42dep,
efc$e16sex,
labelPos = "center")
# Create own theme based on classic-theme
sjp.setTheme(base = theme_classic(),
axis.linecolor = "grey50",
axis.textcolor = "#6699cc")
sjp.frq(efc$e42dep)
# use theme pre-set
sjp.setTheme(theme = "538",
geom.alpha = 0.8)
library(ggplot2) # for custom base-line
sjp.frq(efc$e42dep,
geom.color = "#c0392b",
expand.grid = TRUE,
printPlot = FALSE)$plot +
geom_hline(yintercept = 0,
size = 0.5,
colour = "black")
## End(Not run)sjp.stackfrq
#Examples
# -------------------------------
# random sample
# -------------------------------
# prepare data for 4-category likert scale, 5 items
Q1 <- as.factor(sample(1:4, 500, replace = TRUE,
prob = c(0.2, 0.3, 0.1, 0.4)))
Q2 <- as.factor(sample(1:4, 500, replace = TRUE,
prob = c(0.5, 0.25, 0.15, 0.1)))
Q3 <- as.factor(sample(1:4, 500, replace = TRUE,
prob = c(0.25, 0.1, 0.4, 0.25)))
Q4 <- as.factor(sample(1:4, 500, replace = TRUE,
prob = c(0.1, 0.4, 0.4, 0.1)))
Q5 <- as.factor(sample(1:4, 500, replace = TRUE,
prob = c(0.35, 0.25, 0.15, 0.25)))
likert_4 <- data.frame(Q1, Q2, Q3, Q4, Q5)
# create labels
levels_4 <- c("Independent",
"Slightly dependent",
"Dependent",
"Severely dependent")
# plot stacked frequencies of 5 (ordered) item-scales
sjp.stackfrq(likert_4, legendLabels = levels_4)
# -------------------------------
# Data from the EUROFAMCARE sample dataset
# -------------------------------
library(sjmisc)
data(efc)
# recveive first item of COPE-index scale
start <- which(colnames(efc) == "c82cop1")
# recveive first item of COPE-index scale
end <- which(colnames(efc) == "c90cop9")
# retrieve variable and value labels
varlabs <- get_label(efc)
vallabs <- get_labels(efc)
# create value labels. We need just one variable of
# the COPE-index scale because they have all the same
# level / category / value labels
levels <- vallabs['c82cop1']
# create item labels
items <- varlabs[c(start:end)]
sjp.stackfrq(efc[, c(start:end)],
legendLabels = levels,
axisLabels.y = items,
jitterValueLabels = TRUE)
# -------------------------------
# auto-detection of labels
# -------------------------------
sjp.stackfrq(efc[, c(start:end)])
sjp.xtab
#Examples
# create 4-category-items
grp <- sample(1:4, 100, replace = TRUE)
# create 3-category-items
x <- sample(1:3, 100, replace = TRUE)
# plot "cross tablulation" of x and grp
sjp.xtab(x, grp)
# plot "cross tablulation" of x and y, including labels
sjp.xtab(x, grp,
axisLabels.x = c("low", "mid", "high"),
legendLabels = c("Grp 1", "Grp 2", "Grp 3", "Grp 4"))
# plot "cross tablulation" of x and grp
# as stacked proportional bars
sjp.xtab(x, grp,
tableIndex = "row",
barPosition = "stack",
showTableSummary = TRUE,
coord.flip = TRUE)
# example with vertical labels
library(sjmisc)
data(efc)
sjp.setTheme(geom.label.angle = 90)
# hjust-aes needs adjustment for this
library(ggplot2)
update_geom_defaults('text', list(hjust = -0.1))
sjp.xtab(efc$e42dep,
efc$e16sex,
labelPos = "center")
# grouped bars with EUROFAMCARE sample dataset
# dataset was importet from an SPSS-file,
# see ?sjmisc::read_spss
data(efc)
efc.val <- get_labels(efc)
efc.var <- get_label(efc)
sjp.xtab(efc$e42dep,
efc$e16sex,
title = efc.var['e42dep'],
axisLabels.x = efc.val[['e42dep']],
legendTitle = efc.var['e16sex'],
legendLabels = efc.val[['e16sex']])
sjp.xtab(efc$e16sex,
efc$e42dep,
title = efc.var['e16sex'],
axisLabels.x = efc.val[['e16sex']],
legendTitle = efc.var['e42dep'],
legendLabels = efc.val[['e42dep']])
# -------------------------------
# auto-detection of labels works here
# so no need to specify labels. For
# title-auto-detection, use NULL
# -------------------------------
sjp.xtab(efc$e16sex, efc$e42dep, title = NULL)
sjp.xtab(efc$e16sex,
efc$e42dep,
tableIndex = "row",
barPosition = "stack",
coord.flip = TRUE,
jitterValueLabels = TRUE)sjt.corr
## Not run:
# create data frame with 5 random variables
mydf <- data.frame(cbind(runif(10),
runif(10),
runif(10),
runif(10),
runif(10)))
# plot correlation matrix using circles
sjt.corr(mydf)# -------------------------------
# Data from the EUROFAMCARE sample dataset
# -------------------------------
library(sjmisc)
data(efc)
# retrieve variable and value labels
varlabs <- get_label(efc)
# recveive first item of COPE-index scale
start <- which(colnames(efc) == "c83cop2")
# recveive last item of COPE-index scale
end <- which(colnames(efc) == "c88cop7")
# create data frame with COPE-index scale
mydf <- data.frame(efc[, c(start:end)])
colnames(mydf) <- varlabs[c(start:end)]
# we have high correlations here, because all items
# belong to one factor. See example from "sjp.pca".
sjt.corr(mydf, pvaluesAsNumbers = TRUE)## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties# -------------------------------
# auto-detection of labels, only lower triangle
# -------------------------------
sjt.corr(efc[, c(start:end)], triangle = "lower")## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties# -------------------------------
# auto-detection of labels, only lower triangle,
# all correlation values smaller than 0.3 are not
# shown in the table
# -------------------------------
sjt.corr(efc[, c(start:end)],
triangle = "lower",
val.rm = 0.3)## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties# -------------------------------
# auto-detection of labels, only lower triangle,
# all correlation values smaller than 0.3 are printed
# in blue
# -------------------------------
sjt.corr(efc[, c(start:end)],
triangle = "lower",
val.rm = 0.3,
CSS = list(css.valueremove = 'color:blue;'))## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## End(Not run)sjt.df
#Examples
## Not run:
# init dataset
library(sjmisc)
data(efc)
# plot efc-data frame summary
sjt.df(efc, alternateRowColors = TRUE)##
|
| | 0%
|
|== | 4%
|
|===== | 8%
|
|======== | 12%
|
|========== | 15%
|
|============ | 19%
|
|=============== | 23%
|
|================== | 27%
|
|==================== | 31%
|
|====================== | 35%
|
|========================= | 38%
|
|============================ | 42%
|
|============================== | 46%
|
|================================ | 50%
|
|=================================== | 54%
|
|====================================== | 58%
|
|======================================== | 62%
|
|========================================== | 65%
|
|============================================= | 69%
|
|================================================ | 73%
|
|================================================== | 77%
|
|==================================================== | 81%
|
|======================================================= | 85%
|
|========================================================== | 88%
|
|============================================================ | 92%
|
|============================================================== | 96%
|
|=================================================================| 100%# plot content, first 50 rows of first 5 columns of example data set
sjt.df(efc[1:50, 1:5],
describe = FALSE,
stringVariable = "Observation")##
|
| | 0%
|
|= | 2%
|
|=== | 4%
|
|==== | 6%
|
|===== | 8%
|
|====== | 10%
|
|======== | 12%
|
|========= | 14%
|
|========== | 16%
|
|============ | 18%
|
|============= | 20%
|
|============== | 22%
|
|================ | 24%
|
|================= | 26%
|
|================== | 28%
|
|==================== | 30%
|
|===================== | 32%
|
|====================== | 34%
|
|======================= | 36%
|
|========================= | 38%
|
|========================== | 40%
|
|=========================== | 42%
|
|============================= | 44%
|
|============================== | 46%
|
|=============================== | 48%
|
|================================ | 50%
|
|================================== | 52%
|
|=================================== | 54%
|
|==================================== | 56%
|
|====================================== | 58%
|
|======================================= | 60%
|
|======================================== | 62%
|
|========================================== | 64%
|
|=========================================== | 66%
|
|============================================ | 68%
|
|============================================== | 70%
|
|=============================================== | 72%
|
|================================================ | 74%
|
|================================================= | 76%
|
|=================================================== | 78%
|
|==================================================== | 80%
|
|===================================================== | 82%
|
|======================================================= | 84%
|
|======================================================== | 86%
|
|========================================================= | 88%
|
|========================================================== | 90%
|
|============================================================ | 92%
|
|============================================================= | 94%
|
|============================================================== | 96%
|
|================================================================ | 98%
|
|=================================================================| 100%# plot efc-data frame summary, sorted descending by mean-column
sjt.df(efc,
orderColumn = "mean",
orderAscending = FALSE)##
|
| | 0%
|
|== | 4%
|
|===== | 8%
|
|======== | 12%
|
|========== | 15%
|
|============ | 19%
|
|=============== | 23%
|
|================== | 27%
|
|==================== | 31%
|
|====================== | 35%
|
|========================= | 38%
|
|============================ | 42%
|
|============================== | 46%
|
|================================ | 50%
|
|=================================== | 54%
|
|====================================== | 58%
|
|======================================== | 62%
|
|========================================== | 65%
|
|============================================= | 69%
|
|================================================ | 73%
|
|================================================== | 77%
|
|==================================================== | 81%
|
|======================================================= | 85%
|
|========================================================== | 88%
|
|============================================================ | 92%
|
|============================================================== | 96%
|
|=================================================================| 100%# plot first 20 rows of first 5 columns of example data set,
# sort by column "e42dep" with alternating row colors
sjt.df(efc[1:20, 1:5],
alternateRowColors = TRUE,
orderColumn = "e42dep",
describe = FALSE)##
|
| | 0%
|
|=== | 5%
|
|====== | 10%
|
|========== | 15%
|
|============= | 20%
|
|================ | 25%
|
|==================== | 30%
|
|======================= | 35%
|
|========================== | 40%
|
|============================= | 45%
|
|================================ | 50%
|
|==================================== | 55%
|
|======================================= | 60%
|
|========================================== | 65%
|
|============================================== | 70%
|
|================================================= | 75%
|
|==================================================== | 80%
|
|======================================================= | 85%
|
|========================================================== | 90%
|
|============================================================== | 95%
|
|=================================================================| 100%# plot first 20 rows of first 5 columns of example data set,
# sorted by 4th column in descending order.
sjt.df(efc[1:20, 1:5],
orderColumn = 4,
orderAscending = FALSE,
describe = FALSE)##
|
| | 0%
|
|=== | 5%
|
|====== | 10%
|
|========== | 15%
|
|============= | 20%
|
|================ | 25%
|
|==================== | 30%
|
|======================= | 35%
|
|========================== | 40%
|
|============================= | 45%
|
|================================ | 50%
|
|==================================== | 55%
|
|======================================= | 60%
|
|========================================== | 65%
|
|============================================== | 70%
|
|================================================= | 75%
|
|==================================================== | 80%
|
|======================================================= | 85%
|
|========================================================== | 90%
|
|============================================================== | 95%
|
|=================================================================| 100%# add big mark to thousands
library(datasets)
sjt.df(as.data.frame(WorldPhones), big.mark = ",")##
|
| | 0%
|
|========= | 14%
|
|=================== | 29%
|
|============================ | 43%
|
|===================================== | 57%
|
|============================================== | 71%
|
|======================================================== | 86%
|
|=================================================================| 100%# ----------------------------------------------------------------
# User defined style sheet
# ----------------------------------------------------------------
sjt.df(efc,
alternateRowColor = TRUE,
CSS = list(css.table = "border: 2px solid #999999;",
css.tdata = "border-top: 1px solid;",
css.arc = "color:blue;"))##
|
| | 0%
|
|== | 4%
|
|===== | 8%
|
|======== | 12%
|
|========== | 15%
|
|============ | 19%
|
|=============== | 23%
|
|================== | 27%
|
|==================== | 31%
|
|====================== | 35%
|
|========================= | 38%
|
|============================ | 42%
|
|============================== | 46%
|
|================================ | 50%
|
|=================================== | 54%
|
|====================================== | 58%
|
|======================================== | 62%
|
|========================================== | 65%
|
|============================================= | 69%
|
|================================================ | 73%
|
|================================================== | 77%
|
|==================================================== | 81%
|
|======================================================= | 85%
|
|========================================================== | 88%
|
|============================================================ | 92%
|
|============================================================== | 96%
|
|=================================================================| 100%## End(Not run)sjt.frq
#Examples
## Not run:
# load sample data
library(sjmisc)
data(efc)
# show frequencies of "e42dep" in RStudio Viewer Pane
# or default web browser
sjt.frq(efc$e42dep)
# plot and show frequency table of "e42dep" with labels
sjt.frq(efc$e42dep,
variableLabels = "Dependency",
valueLabels = c("independent",
"slightly dependent",
"moderately dependent",
"severely dependent"))
# plot frequencies of e42dep, e16sex and c172code in one HTML file
# and show table in RStudio Viewer Pane or default web browser
# Note that valueLabels of multiple variables have to be
# list-objects
sjt.frq(data.frame(efc$e42dep, efc$e16sex, efc$c172code),
variableLabels = c("Dependency",
"Gender",
"Education"),
valueLabels = list(c("independent",
"slightly dependent",
"moderately dependent",
"severely dependent"),
c("male", "female"),
c("low", "mid", "high")))# -------------------------------
# auto-detection of labels
# due to auto-detection of labels, this works as well
# -------------------------------
sjt.frq(data.frame(efc$e42dep, efc$e16sex, efc$c172code))
# plot larger scale including zero-counts
# indicating median and quartiles
sjt.frq(efc$neg_c_7,
highlightMedian = TRUE,
highlightQuartiles = TRUE)
# -------------------------------
# sort frequencies
# -------------------------------
sjt.frq(efc$e42dep, sort.frq = "desc")## Sorting may not work when data contains values with zero-counts.# --------------------------------
# User defined style sheet
# --------------------------------
sjt.frq(efc$e42dep,
CSS = list(css.table = "border: 2px solid;",
css.tdata = "border: 1px solid;",
css.firsttablecol = "color:#003399; font-weight:bold;"))
## End(Not run)sjt.glm
# prepare dummy variables for binary logistic regression
y1 <- ifelse(swiss$Fertility < median(swiss$Fertility), 0, 1)
y2 <- ifelse(swiss$Infant.Mortality < median(swiss$Infant.Mortality), 0, 1)
y3 <- ifelse(swiss$Agriculture < median(swiss$Agriculture), 0, 1)
# Now fit the models. Note that both models share the same predictors
# and only differ in their dependent variable (y1, y2 and y3)
fitOR1 <- glm(y1 ~ swiss$Education + swiss$Examination+swiss$Catholic,
family = binomial(link = "logit"))
fitOR2 <- glm(y2 ~ swiss$Education + swiss$Examination+swiss$Catholic,
family = binomial(link = "logit"))
fitOR3 <- glm(y3 ~ swiss$Education + swiss$Examination+swiss$Catholic,
family = binomial(link = "logit"))
# open HTML-table in RStudio Viewer Pane or web browser
## Not run:
sjt.glm(fitOR1,
fitOR2,
labelDependentVariables = c("Fertility",
"Infant Mortality"),
labelPredictors = c("Education",
"Examination",
"Catholic"),
ci.hyphen = " to ")## Waiting for profiling to be done...
## Waiting for profiling to be done...# open HTML-table in RStudio Viewer Pane or web browser,
# integrate CI in OR column
sjt.glm(fitOR1, fitOR2, fitOR3,
labelDependentVariables = c("Fertility",
"Infant Mortality",
"Agriculture"),
labelPredictors = c("Education", "Examination", "Catholic"),
separateConfColumn = FALSE)## Waiting for profiling to be done...
## Waiting for profiling to be done...
## Waiting for profiling to be done...## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred# open HTML-table in RStudio Viewer Pane or web browser,
# indicating p-values as numbers and printing CI in a separate column
sjt.glm(fitOR1, fitOR2, fitOR3,
labelDependentVariables = c("Fertility",
"Infant Mortality",
"Agriculture"),
labelPredictors = c("Education", "Examination", "Catholic"))## Waiting for profiling to be done...
## Waiting for profiling to be done...
## Waiting for profiling to be done...## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred# --------------------------------------------
# User defined style sheet
# --------------------------------------------
sjt.glm(fitOR1, fitOR2, fitOR3,
labelDependentVariables = c("Fertility",
"Infant Mortality",
"Agriculture"),
labelPredictors = c("Education", "Examination", "Catholic"),
showHeaderStrings = TRUE,
CSS = list(css.table = "border: 2px solid;",
css.tdata = "border: 1px solid;",
css.depvarhead = "color:#003399;"))## Waiting for profiling to be done...
## Waiting for profiling to be done...
## Waiting for profiling to be done...## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred# --------------------------------------------
# Compare models with different link functions,
# but same predictors and response
# --------------------------------------------
library(sjmisc)
# load efc sample data
data(efc)
# dichtomozize service usage by "service usage yes/no"
efc$services <- sjmisc::dicho(efc$tot_sc_e, "v", 0, as.num = TRUE)
# fit 3 models with different link-functions
fit1 <- glm(services ~ neg_c_7 + c161sex + e42dep,
data=efc,
family=binomial(link="logit"))
fit2 <- glm(services ~ neg_c_7 + c161sex + e42dep,
data=efc,
family=binomial(link="probit"))
fit3 <- glm(services ~ neg_c_7 + c161sex + e42dep,
data=efc,
family=poisson(link="log"))
# compare models
sjt.glm(fit1, fit2, fit3,
showAIC = TRUE,
showFamily = TRUE)## Waiting for profiling to be done...
## Waiting for profiling to be done...
## Waiting for profiling to be done...# --------------------------------------------
# Change style of p-values and CI-appearance
# --------------------------------------------
# open HTML-table in RStudio Viewer Pane or web browser,
# table indicating p-values as stars
sjt.glm(fit1, fit2, fit3,
pvaluesAsNumbers = FALSE,
showAIC = TRUE,
showFamily = TRUE)## Waiting for profiling to be done...
## Waiting for profiling to be done...
## Waiting for profiling to be done...# open HTML-table in RStudio Viewer Pane or web browser,
# indicating p-values as stars and integrate CI in OR column
sjt.glm(fit1, fit2, fit3,
pvaluesAsNumbers = FALSE,
separateConfColumn = FALSE,
showAIC = TRUE,
showFamily = TRUE,
showPseudoR = TRUE)## Waiting for profiling to be done...
## Waiting for profiling to be done...
## Waiting for profiling to be done...# ----------------------------------
# automatic grouping of predictors
# ----------------------------------
library(sjmisc)
# load efc sample data
data(efc)
# dichtomozize service usage by "service usage yes/no"
efc$services <- sjmisc::dicho(efc$tot_sc_e, "v", 0, as.num = TRUE)
# make dependency categorical
efc$e42dep <- to_fac(efc$e42dep)## Warning: 'to_fac' is deprecated.
## Use 'to_factor' instead.
## See help("Deprecated")# fit model with "grouped" predictor
fit <- glm(services ~ neg_c_7 + c161sex + e42dep, data = efc)
# automatic grouping of categorical predictors
sjt.glm(fit)## Waiting for profiling to be done...# ----------------------------------
# compare models with different predictors
# ----------------------------------
fit2 <- glm(services ~ neg_c_7 + c161sex + e42dep + c12hour, data = efc)
fit3 <- glm(services ~ neg_c_7 + c161sex + e42dep + c12hour + c172code,
data = efc)
# print models with different predictors
sjt.glm(fit, fit2, fit3)## Waiting for profiling to be done...
## Waiting for profiling to be done...
## Waiting for profiling to be done...
## Fitted models have different coefficients. Grouping may not work properly. Set 'group.pred = FALSE' if you encouter cluttered labelling.efc$c172code <- to_fac(efc$c172code)## Warning: 'to_fac' is deprecated.
## Use 'to_factor' instead.
## See help("Deprecated")fit2 <- glm(services ~ neg_c_7 + c161sex + c12hour, data = efc)
fit3 <- glm(services ~ neg_c_7 + c161sex + c172code, data = efc)
# print models with different predictors
sjt.glm(fit, fit2, fit3, group.pred = FALSE)## Waiting for profiling to be done...
## Waiting for profiling to be done...
## Waiting for profiling to be done...## End(Not run)sjt.glmer
#Examples
## Not run:
library(lme4)
library(sjmisc)
data(efc)
# create binary response
efc$hi_qol <- dicho(efc$quol_5)
# prepare group variable
efc$grp = as.factor(efc$e15relat)
levels(x = efc$grp) <- get_labels(efc$e15relat)
# data frame for fitted model
mydf <- data.frame(hi_qol = as.factor(efc$hi_qol),
sex = as.factor(efc$c161sex),
c12hour = as.numeric(efc$c12hour),
neg_c_7 = as.numeric(efc$neg_c_7),
education = as.factor(efc$c172code),
grp = efc$grp)
# fit glmer
fit1 <- glmer(hi_qol ~ sex + c12hour + neg_c_7 + (1|grp),
data = mydf,
family = binomial("logit"))
fit2 <- glmer(hi_qol ~ sex + c12hour + neg_c_7 + education + (1|grp),
data = mydf,
family = binomial("logit"))# print summary table
sjt.glmer(fit1, fit2,
ci.hyphen = " to ")
# print summary table, using different table layout
sjt.glmer(fit1, fit2,
showAIC = TRUE,
showConfInt = FALSE,
showStdError = TRUE,
pvaluesAsNumbers = FALSE)
# print summary table
sjt.glmer(fit1, fit2,
labelPredictors = c("Elder's gender (female)",
"Hours of care per week",
"Negative Impact",
"Educational level (mid)",
"Educational level (high)"))
## End(Not run)#Examples
## Not run:
library(sjmisc)
data(efc)
sjt.grpmean(efc$c12hour,
efc$e42dep)
## End(Not run)sjt.itemanalysis
#Examples
# -------------------------------
# Data from the EUROFAMCARE sample dataset
# -------------------------------
library(sjmisc)
data(efc)
# retrieve variable and value labels
varlabs <- get_label(efc)
# recveive first item of COPE-index scale
start <- which(colnames(efc) == "c82cop1")
# recveive last item of COPE-index scale
end <- which(colnames(efc) == "c90cop9")
# create data frame with COPE-index scale
mydf <- data.frame(efc[, c(start:end)])
colnames(mydf) <- varlabs[c(start:end)]
## Not run:
sjt.itemanalysis(mydf)##
|
| | 0%
|
|======= | 11%
|
|============== | 22%
|
|====================== | 33%
|
|============================= | 44%
|
|==================================== | 56%
|
|=========================================== | 67%
|
|=================================================== | 78%
|
|========================================================== | 89%
|
|=================================================================| 100%# -------------------------------
# auto-detection of labels
# -------------------------------
sjt.itemanalysis(efc[, c(start:end)])##
|
| | 0%
|
|======= | 11%
|
|============== | 22%
|
|====================== | 33%
|
|============================= | 44%
|
|==================================== | 56%
|
|=========================================== | 67%
|
|=================================================== | 78%
|
|========================================================== | 89%
|
|=================================================================| 100%# ---------------------------------------
# Compute PCA on Cope-Index, and perform a
# item analysis for each extracted factor.
# ---------------------------------------
factor.groups <- sjt.pca(mydf, no.output = TRUE)$factor.index
sjt.itemanalysis(mydf, factor.groups)##
|
| | 0%
|
|=========== | 17%
|
|====================== | 33%
|
|================================ | 50%
|
|=========================================== | 67%
|
|====================================================== | 83%
|
|=================================================================| 100%
##
|
| | 0%
|
|====================== | 33%
|
|=========================================== | 67%
|
|=================================================================| 100%## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## Warning in cor.test.default(df[[i]], df[[j]], alternative = "two.sided", :
## Cannot compute exact p-value with ties## End(Not run)sjt.lm
#Examples
## Not run:
# Now fit the models. Note that both models share the same predictors
# and only differ in their dependent variable. See examples of stepwise
# models below at the end.
library(sjmisc)
data(efc)
# fit first model
fit1 <- lm(barthtot ~ c160age + c12hour + c161sex + c172code,
data = efc)
# fit second model
fit2 <- lm(neg_c_7 ~ c160age + c12hour + c161sex + c172code, data = efc)
# create and open HTML-table in RStudio Viewer Pane or web browser
# note that we don't need to specify labels for the predictors,
# because these are automatically read
sjt.lm(fit1, fit2)
# create and open HTML-table in RStudio Viewer Pane or web browser
# in the following examples, we set labels via argument
sjt.lm(fit1,
fit2,
labelDependentVariables = c("Barthel-Index",
"Negative Impact"),
labelPredictors = c("Carer's Age",
"Hours of Care",
"Carer's Sex",
"Educational Status"))
# show HTML-table, indicating p-values as asterisks
sjt.lm(fit1,
fit2,
labelDependentVariables = c("Barthel-Index",
"Negative Impact"),
labelPredictors = c("Carer's Age",
"Hours of Care",
"Carer's Sex",
"Educational Status"),
showStdBeta = TRUE,
pvaluesAsNumbers = FALSE)# create and open HTML-table in RStudio Viewer Pane or web browser,
# integrate CI in estimate column
sjt.lm(fit1,
fit2,
labelDependentVariables = c("Barthel-Index",
"Negative Impact"),
labelPredictors = c("Carer's Age",
"Hours of Care",
"Carer's Sex",
"Educational Status"),
separateConfColumn = FALSE)
# show HTML-table, indicating p-values as numbers
# and printing CI in a separate column
sjt.lm(fit1,
fit2,
labelDependentVariables = c("Barthel-Index",
"Negative Impact"),
labelPredictors = c("Carer's Age",
"Hours of Care",
"Carer's Sex",
"Educational Status"),
showStdBeta = TRUE)
# show HTML-table, indicating p-values as stars
# and integrate CI in estimate column
sjt.lm(fit1,
fit2,
labelDependentVariables = c("Barthel-Index",
"Negative Impact"),
labelPredictors = c("Carer's Age",
"Hours of Care",
"Carer's Sex",
"Educational Status"),
showStdBeta = TRUE,
ci.hyphen = " to ",
minus.sign = "−",
pvaluesAsNumbers = FALSE,
separateConfColumn = FALSE)# ----------------------------------
# connecting two html-tables
# ----------------------------------
# fit two more models
fit3 <- lm(tot_sc_e ~ c160age + c12hour + c161sex + c172code, data=efc)
fit4 <- lm(e42dep ~ c160age + c12hour + c161sex + c172code, data=efc)
# create and save first HTML-table
part1 <- sjt.lm(fit1,
fit2,
labelDependentVariables = c("Barthel-Index",
"Negative Impact"),
labelPredictors = c("Carer's Age",
"Hours of Care",
"Carer's Sex",
"Educational Status"))
# create and save second HTML-table
part2 <- sjt.lm(fit3,
fit4,
labelDependentVariables = c("Service Usage",
"Elder's Dependency"),
labelPredictors = c("Carer's Age",
"Hours of Care",
"Carer's Sex",
"Educational Status"))
# browse temporary file
htmlFile <- tempfile(fileext=".html")
write(sprintf("<html><head>%s</head><body>%s<p></p>%s</body></html>",
part1$page.style,
part1$page.content,
part2$page.content),
file = htmlFile)
viewer <- getOption("viewer")
if (!is.null(viewer)) viewer(htmlFile) else utils::browseURL(htmlFile)# ----------------------------------
# User defined style sheet
# ----------------------------------
sjt.lm(fit1,
fit2,
labelDependentVariables = c("Barthel-Index", "Negative Impact"),
labelPredictors = c("Carer's Age",
"Hours of Care",
"Carer's Sex",
"Educational Status"),
CSS = list(css.table = "border: 2px solid;",
css.tdata = "border: 1px solid;",
css.depvarhead = "color:#003399;"))# ----------------------------------
# automatic grouping of predictors
# ----------------------------------
library(sjmisc)
data(efc)
# make education categorical
efc$c172code <- to_factor(efc$c172code)
# fit first model again (with c172code as factor)
fit1 <- lm(barthtot ~ c160age + c12hour + c172code + c161sex, data=efc)
# fit second model again (with c172code as factor)
fit2 <- lm(neg_c_7 ~ c160age + c12hour + c172code + c161sex, data=efc)
# plot models, but group by predictors
sjt.lm(fit1,
fit2,
group.pred = TRUE)# ----------------------------------------
# compare models with different predictors
# ----------------------------------------
library(sjmisc)
data(efc)
# make education categorical
efc$c172code <- to_factor(efc$c172code)
# make education categorical
efc$e42dep <- to_factor(efc$e42dep)
# fit first model
fit1 <- lm(neg_c_7 ~ c160age + c172code + c161sex, data = efc)
# fit second model
fit2 <- lm(neg_c_7 ~ c160age + c172code + c161sex + c12hour, data = efc)
# fit second model
fit3 <- lm(neg_c_7 ~ c160age + c172code + e42dep + tot_sc_e, data = efc)
sjt.lm(fit1, fit2, fit3)## Fitted models have different coefficients. Grouping may not work properly. Set 'group.pred = FALSE' if you encouter cluttered labelling.# ----------------------------------------
# compare models with different predictors
# and grouping
# ----------------------------------------
# make cope-index categorical
efc$c82cop1 <- to_fac(efc$c82cop1)## Warning: 'to_fac' is deprecated.
## Use 'to_factor' instead.
## See help("Deprecated")# fit another model
fit4 <- lm(neg_c_7 ~ c160age + c172code + e42dep + tot_sc_e + c82cop1,
data = efc)
sjt.lm(fit1, fit2, fit4, fit3)## Fitted models have different coefficients. Grouping may not work properly. Set 'group.pred = FALSE' if you encouter cluttered labelling.# show standardized beta only
sjt.lm(fit1, fit2, fit4, fit3,
showEst = FALSE,
showStdBeta = TRUE,
showAIC = TRUE,
showFStat = TRUE)## Fitted models have different coefficients. Grouping may not work properly. Set 'group.pred = FALSE' if you encouter cluttered labelling.# -----------------------------------------------------------
# color insanity. just to show that each column has an own
# CSS-tag, so - depending on the stats and values you show -
# you can define column spaces / margins, border etc. to
# visually separate your models in the table
# -----------------------------------------------------------
sjt.lm(fit1, fit2, fit4, fit3,
showStdBeta = TRUE,
showAIC = TRUE,
showFStat = TRUE,
showStdError = TRUE,
CSS = list(css.modelcolumn1 = 'color:blue;',
css.modelcolumn2 = 'color:red;',
css.modelcolumn3 = 'color:green;',
css.modelcolumn4 = 'color:#ffff00;',
css.modelcolumn5 = 'color:#777777;',
css.modelcolumn6 = 'color:#3399cc;'))## Fitted models have different coefficients. Grouping may not work properly. Set 'group.pred = FALSE' if you encouter cluttered labelling.sjt.lm(fit1, fit2, fit4, fit3,
showEst = FALSE,
showStdBeta = TRUE,
pvaluesAsNumbers = FALSE,
group.pred = FALSE,
CSS = list(css.modelcolumn4 = 'border-left:1px solid black;',
css.modelcolumn5 = 'padding-right:50px;'))
## End(Not run)sjt.stackfrq
#Examples
# -------------------------------
# random sample
# -------------------------------
# prepare data for 4-category likert scale, 5 items
likert_4 <- data.frame(as.factor(sample(1:4,
500,
replace = TRUE,
prob = c(0.2, 0.3, 0.1, 0.4))),
as.factor(sample(1:4,
500,
replace = TRUE,
prob = c(0.5, 0.25, 0.15, 0.1))),
as.factor(sample(1:4,
500,
replace = TRUE,
prob = c(0.25, 0.1, 0.4, 0.25))),
as.factor(sample(1:4,
500,
replace = TRUE,
prob = c(0.1, 0.4, 0.4, 0.1))),
as.factor(sample(1:4,
500,
replace = TRUE,
prob = c(0.35, 0.25, 0.15, 0.25))))
# create labels
levels_4 <- c("Independent",
"Slightly dependent",
"Dependent",
"Severely dependent")
# create item labels
items <- c("Q1", "Q2", "Q3", "Q4", "Q5")
# plot stacked frequencies of 5 (ordered) item-scales
## Not run:
sjt.stackfrq(likert_4, valuelabels = levels_4, varlabels = items)# -------------------------------
# Data from the EUROFAMCARE sample dataset
# Auto-detection of labels
# -------------------------------
library(sjmisc)
data(efc)
# recveive first item of COPE-index scale
start <- which(colnames(efc) == "c82cop1")
# recveive first item of COPE-index scale
end <- which(colnames(efc) == "c90cop9")
sjt.stackfrq(efc[, c(start:end)],
alternateRowColors = TRUE)
sjt.stackfrq(efc[, c(start:end)],
alternateRowColors = TRUE,
showN = TRUE,
showNA = TRUE)# --------------------------------
# User defined style sheet
# --------------------------------
sjt.stackfrq(efc[, c(start:end)],
alternateRowColors = TRUE,
showTotalN = TRUE,
showSkew = TRUE,
showKurtosis = TRUE,
CSS = list(css.ncol = "border-left:1px dotted black;",
css.summary = "font-style:italic;"))
## End(Not run)sjt.xtab
#Examples
# prepare sample data set
library(sjmisc)
data(efc)
efc.labels <- get_labels(efc)
# print simple cross table w/o labels
## Not run:
sjt.xtab(efc$e16sex, efc$e42dep)
# print cross table with manually set
# labels and expected values
sjt.xtab(efc$e16sex,
efc$e42dep,
variableLabels = c("Elder's gender",
"Elder's dependency"),
valueLabels = list(efc.labels[['e16sex']],
efc.labels[['e42dep']]),
showExpected = TRUE)
# print minimal cross table with labels, total col/row highlighted
sjt.xtab(efc$e16sex, efc$e42dep,
variableLabels = c("Elder's gender", "Elder's dependency"),
valueLabels = list(efc.labels[['e16sex']], efc.labels[['e42dep']]),
showHorizontalLine = FALSE,
showCellPerc = FALSE,
highlightTotal = TRUE)# -------------------------------
# auto-detection of labels
# -------------------------------
# print cross table with labels and all percentages
sjt.xtab(efc$e16sex, efc$e42dep,
showRowPerc = TRUE,
showColPerc = TRUE)
# print cross table with labels and all percentages, including
# grouping variable
sjt.xtab(efc$e16sex, efc$e42dep, efc$c161sex,
variableLabels=c("Elder's gender",
"Elder's dependency",
"Carer's gender"),
valueLabels=list(efc.labels[['e16sex']],
efc.labels[['e42dep']],
efc.labels[['c161sex']]),
showRowPerc = TRUE,
showColPerc = TRUE)## Warning in chisq.test(tab): Chi-squared approximation may be incorrect# ----------------------------------------------------------------
# User defined style sheet
# ----------------------------------------------------------------
sjt.xtab(efc$e16sex, efc$e42dep,
variableLabels = c("Elder's gender", "Elder's dependency"),
valueLabels = list(efc.labels[['e16sex']],
efc.labels[['e42dep']]),
CSS = list(css.table = "border: 2px solid;",
css.tdata = "border: 1px solid;",
css.horline = "border-bottom: double blue;"))
## End(Not run)view_df
## Not run:
# init dataset
library(sjmisc)
data(efc)
# view variables
view_df(efc)##
|
| | 0%
|
|== | 4%
|
|===== | 8%
|
|======== | 12%
|
|========== | 15%
|
|============ | 19%
|
|=============== | 23%
|
|================== | 27%
|
|==================== | 31%
|
|====================== | 35%
|
|========================= | 38%
|
|============================ | 42%
|
|============================== | 46%
|
|================================ | 50%
|
|=================================== | 54%
|
|====================================== | 58%
|
|======================================== | 62%
|
|========================================== | 65%
|
|============================================= | 69%
|
|================================================ | 73%
|
|================================================== | 77%
|
|==================================================== | 81%
|
|======================================================= | 85%
|
|========================================================== | 88%
|
|============================================================ | 92%
|
|============================================================== | 96%
|
|=================================================================| 100%# view variables w/o values and value labels
view_df(efc, showValues = FALSE, showValueLabels = FALSE)##
|
| | 0%
|
|== | 4%
|
|===== | 8%
|
|======== | 12%
|
|========== | 15%
|
|============ | 19%
|
|=============== | 23%
|
|================== | 27%
|
|==================== | 31%
|
|====================== | 35%
|
|========================= | 38%
|
|============================ | 42%
|
|============================== | 46%
|
|================================ | 50%
|
|=================================== | 54%
|
|====================================== | 58%
|
|======================================== | 62%
|
|========================================== | 65%
|
|============================================= | 69%
|
|================================================ | 73%
|
|================================================== | 77%
|
|==================================================== | 81%
|
|======================================================= | 85%
|
|========================================================== | 88%
|
|============================================================ | 92%
|
|============================================================== | 96%
|
|=================================================================| 100%# view variables including variable typed, orderd by name
view_df(efc, sortByName = TRUE, showType = TRUE)##
|
| | 0%
|
|== | 4%
|
|===== | 8%
|
|======== | 12%
|
|========== | 15%
|
|============ | 19%
|
|=============== | 23%
|
|================== | 27%
|
|==================== | 31%
|
|====================== | 35%
|
|========================= | 38%
|
|============================ | 42%
|
|============================== | 46%
|
|================================ | 50%
|
|=================================== | 54%
|
|====================================== | 58%
|
|======================================== | 62%
|
|========================================== | 65%
|
|============================================= | 69%
|
|================================================ | 73%
|
|================================================== | 77%
|
|==================================================== | 81%
|
|======================================================= | 85%
|
|========================================================== | 88%
|
|============================================================ | 92%
|
|============================================================== | 96%
|
|=================================================================| 100%# ----------------------------------------------------------------
# User defined style sheet
# ----------------------------------------------------------------
view_df(efc,
CSS = list(css.table = "border: 2px solid;",
css.tdata = "border: 1px solid;",
css.arc = "color:blue;"))##
|
| | 0%
|
|== | 4%
|
|===== | 8%
|
|======== | 12%
|
|========== | 15%
|
|============ | 19%
|
|=============== | 23%
|
|================== | 27%
|
|==================== | 31%
|
|====================== | 35%
|
|========================= | 38%
|
|============================ | 42%
|
|============================== | 46%
|
|================================ | 50%
|
|=================================== | 54%
|
|====================================== | 58%
|
|======================================== | 62%
|
|========================================== | 65%
|
|============================================= | 69%
|
|================================================ | 73%
|
|================================================== | 77%
|
|==================================================== | 81%
|
|======================================================= | 85%
|
|========================================================== | 88%
|
|============================================================ | 92%
|
|============================================================== | 96%
|
|=================================================================| 100%## End(Not run)
data(iris)
view_df(iris,
CSS = list(css.table = "border: 2px solid;",
css.tdata = "border: 1px solid;",
css.arc = "color:blue;"))##
|
| | 0%
|
|============= | 20%
|
|========================== | 40%
|
|======================================= | 60%
|
|==================================================== | 80%
|
|=================================================================| 100%adjust_plot_range
#Examples
# sample data set
library(sjmisc)
data(efc)
# show frequencies of relationship-variable and
# retrieve plot object
gp <- sjp.frq(efc$e15relat, printPlot = FALSE)
# show current plot
plot(gp$plot)
# show adjusted plot
adjust_plot_range(gp$plot)dist_chisq
#Examples
# a simple chi-squared distribution
# for 6 degrees of freedom
dist_chisq(deg.f = 6)
# a chi-squared distribution for 6 degrees of freedom,
# and a shaded area starting at chi-squared value of ten.
# With a df of 6, a chi-squared value of 12.59 would be "significant",
# thus the shaded area from 10 to 12.58 is filled as "non-significant",
# while the area starting from chi-squared value 12.59 is filled as
# "significant"
dist_chisq(chi2 = 10, deg.f = 6)
# a chi-squared distribution for 6 degrees of freedom,
# and a shaded area starting at that chi-squared value, which has
# a p-level of about 0.125 (which equals a chi-squared value of about 10).
# With a df of 6, a chi-squared value of 12.59 would be "significant",
# thus the shaded area from 10 to 12.58 (p-level 0.125 to p-level 0.05)
# is filled as "non-significant", while the area starting from chi-squared
# value 12.59 (p-level < 0.05) is filled as "significant".
dist_chisq(p = 0.125, deg.f = 6)
dist_f
#Examples
# a simple F distribution for 6 and 45 degrees of freedom
dist_f(deg.f1 = 6, deg.f2 = 45)
# F distribution for 6 and 45 degrees of freedom,
# and a shaded area starting at F value of two.
# F-values equal or greater than 2.31 are "significant"
dist_f(f = 2, deg.f1 = 6, deg.f2 = 45)
# F distribution for 6 and 45 degrees of freedom,
# and a shaded area starting at a p-level of 0.2
# (F-Value about 1.5).
dist_f(p = 0.2, deg.f1 = 6, deg.f2 = 45)
dist_norm
#Examples
# a simple normal distribution
dist_norm()
# a simple normal distribution with different mean and sd.
# note that curve looks similar to above plot, but axis range
# has changed.
dist_norm(mean = 2, sd = 4)
# a simple normal distribution
dist_norm(norm = 1)
# a simple normal distribution
dist_norm(p = 0.2)
dist_t
#Examples
# a simple t-distribution
# for 6 degrees of freedom
dist_t(deg.f = 6)
# a t-distribution for 6 degrees of freedom,
# and a shaded area starting at t-value of one.
# With a df of 6, a t-value of 1.94 would be "significant".
dist_t(t = 1, deg.f = 6)
# a t-distribution for 6 degrees of freedom,
# and a shaded area starting at p-level of 0.4
# (t-value of about 0.26).
dist_t(p = 0.4, deg.f = 6)
sjc.cluster
#Examples
# Hierarchical clustering of mtcars-dataset
groups <- sjc.cluster(mtcars, 5)
# K-means clustering of mtcars-dataset
groups <- sjc.cluster(mtcars, 5, method="k")sjc.dend
#Examples
# Plot dendrogram of hierarchical clustering of mtcars-dataset
# and show group classification
sjc.dend(mtcars, 5)
# Plot dendrogram of hierarchical clustering of mtcars-dataset
# and show group classification for 2 to 4 groups
sjc.dend(mtcars, 2:4)
sjc.elbow
#Examples
# plot elbow values of mtcars dataset
sjc.elbow(mtcars)
sjc.grpdisc
#Examples
# retrieve group classification from hierarchical cluster analysis
# on the mtcars data set (5 groups)
groups <- sjc.cluster(mtcars, 5)
# plot goodness of group classificatoin
sjc.grpdisc(mtcars, groups, 5)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
sjc.kgap
#Examples
## Not run:
# plot gap statistic and determine best number of clusters
# in mtcars dataset
sjc.kgap(mtcars)## Clustering Gap statistic ["clusGap"].
## B=100 simulated reference sets, k = 1..10
##
## --> Number of clusters (method 'Tibs2001SEmax', SE.factor=1): 2
# and in iris dataset
sjc.kgap(iris[,1:4])## Clustering Gap statistic ["clusGap"].
## B=100 simulated reference sets, k = 1..10
##
## --> Number of clusters (method 'Tibs2001SEmax', SE.factor=1): 3
## End(Not run)sjc.qclus
#Examples
## Not run:
# k-means clustering of mtcars-dataset
sjc.qclus(mtcars)## Clustering Gap statistic ["clusGap"].
## B=100 simulated reference sets, k = 1..10
##
## --> Number of clusters (method 'Tibs2001SEmax', SE.factor=1): 2## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
sjc.qclus(iris[,1:4])## Clustering Gap statistic ["clusGap"].
## B=100 simulated reference sets, k = 1..10
##
## --> Number of clusters (method 'Tibs2001SEmax', SE.factor=1): 3## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
# k-means clustering of mtcars-dataset with 4 pre-defined
# groups in a faceted panel
sjc.qclus(airquality,
groupcount = 4,
facetCluster = TRUE)## Warning: `show_guide` has been deprecated. Please use `show.legend`
## instead.
## End(Not run)k-means clustering of airquality data
and saving the results. most likely, 3 cluster
groups have been found (see below).
airgrp <- sjc.qclus(airquality) # “re-plot” cluster groups, without computing # new k-means cluster analysis. sjc.qclus(airquality, groupcount = 3, groups = airgrp$classification)