Perform hierarchical Bayesian Aldrich-McKelvey scaling using Hamiltonian Monte
Carlo via 'Stan'. Aldrich-McKelvey ('AM') scaling is a method for estimating the ideological
positions of survey respondents and political actors on a common scale using positional survey
data. The hierarchical versions of the Bayesian 'AM' model included in this package outperform
other versions both in terms of yielding meaningful posterior distributions for respondent
positions and in terms of recovering true respondent positions in simulations. The package
contains functions for preparing data, fitting models, extracting estimates, plotting key
results, and comparing models using cross-validation. The default model is described in
Bølstad (2023) <doi:10.1017/pan.2023.18>.
| Version: |
1.2.0 |
| Depends: |
R (≥ 3.4.0) |
| Imports: |
dplyr, ggplot2, loo, matrixStats, methods, parallel, pbmcapply, plyr, RColorBrewer, Rcpp (≥ 1.0.7), RcppParallel (≥ 5.1.4), rlang, rstan (≥ 2.26.1), rstantools (≥ 2.2.0), stats, tidyr |
| LinkingTo: |
BH (≥ 1.66.0), Rcpp (≥ 1.0.7), RcppEigen (≥ 0.3.3.9.1), RcppParallel (≥ 5.1.4), rstan (≥ 2.26.1), StanHeaders (≥
2.26.22) |
| Suggests: |
data.table, knitr, rmarkdown |
| Published: |
2023-09-25 |
| Author: |
Jørgen Bølstad 
[aut, cre] |
| Maintainer: |
Jørgen Bølstad <jorgen.bolstad at stv.uio.no> |
| License: |
GPL (≥ 3) |
| URL: |
https://github.com/jbolstad/hbamr/ |
| NeedsCompilation: |
yes |
| SystemRequirements: |
GNU make |
| CRAN checks: |
hbamr results |