| GLESsmall {BTLLasso} | R Documentation |
This is a subset of the GLES data set from the German
Longitudinal Election Study (GLES), see Rattinger et al. (2014). The subset contains
only 200 of the 2003 observations and only a small part of the covariates. The GLES is
a long-term study of the German electoral process. It collects pre- and
post-election data for several federal elections, the data used here
originate from the pre-election study for 2013.
A list containing data from the German Longitudinal Election Study with 200 observations. The list contains both information on the response (paired comparisons) and different covariates.
A response.BTLLasso object for the GLES data including
response: Ordinal paired comparison response vector
first.object: Vector containing the first-named party per paired comparison
second.object: Vector containing the second-named party per paired comparison
subject: Vector containing a person identifier per paired comparison
with.order Automatically generated vector containing information on order effect. Irrelevant, because no order effect needs to be included in the analysis of GLES data.
Matrix containing all eight person-specific covariates
Age: Age in years
Gender (0: male, 1: female)
Matrix containing all four person-party-specific covariates
Climate: Self-perceived distance of each person to all five parties with respect to ones attitude towards climate change.
Immigration: Self-perceived distance of each person to all five parties with respect to ones attitude towards immigration.
Rattinger, H., S. Rossteutscher, R. Schmitt-Beck, B. Wessels, and C. Wolf (2014): Pre-election cross section (GLES 2013). GESIS Data Archive, Cologne ZA5700 Data file Version 2.0.0.
Schauberger, Gunther and Tutz, Gerhard (2019): BTLLasso - A Common Framework and Software Package for the Inclusion and Selection of Covariates in Bradley-Terry Models, Journal of Statistical Software, to appear
Schauberger, Gunther and Tutz, Gerhard (2017): Subject-specific modelling of paired comparison data: A lasso-type penalty approach, Statistical Modelling, 17(3), 223 - 243
## Not run:
op <- par(no.readonly = TRUE)
data(GLESsmall)
## extract data and center covariates for better interpretability
Y <- GLESsmall$Y
X <- scale(GLESsmall$X, scale = FALSE)
Z1 <- scale(GLESsmall$Z1, scale = FALSE)
## vector of subtitles, containing the coding of the X covariates
subs.X <- c('', 'female (1); male (0)')
## Cross-validate BTLLasso model
m.gles.cv <- cv.BTLLasso(Y = Y, X = X, Z1 = Z1)
m.gles.cv
coef(m.gles.cv)
logLik(m.gles.cv)
head(predict(m.gles.cv, type="response"))
head(predict(m.gles.cv, type="trait"))
par(xpd = TRUE, mar = c(5,4,4,6))
plot(m.gles.cv, subs.X = subs.X, plots_per_page = 4, which = 2:5)
paths(m.gles.cv, y.axis = 'L2')
par(op)
## End(Not run)