Package: Rrepest 1.5.4
Rodolfo Ilizaliturri
Rrepest: An Analyzer of International Large Scale Assessments in Education
An easy way to analyze international large-scale assessments and surveys in education or any other dataset that includes replicated weights (Balanced Repeated Replication (BRR) weights, Jackknife replicate weights,...) while also allowing for analysis with multiply imputed variables (plausible values). It supports the estimation of univariate statistics (e.g. mean, variance, standard deviation, quantiles), frequencies, correlation, linear regression and any other model already implemented in R that takes a data frame and weights as parameters. It also includes options to prepare the results for publication, following the table formatting standards of the Organization for Economic Cooperation and Development (OECD).
Authors:
Rrepest_1.5.4.tar.gz
Rrepest_1.5.4.tar.gz(r-4.5-noble)Rrepest_1.5.4.tar.gz(r-4.4-noble)
Rrepest_1.5.4.tgz(r-4.4-emscripten)Rrepest_1.5.4.tgz(r-4.3-emscripten)
Rrepest.pdf |Rrepest.html✨
Rrepest/json (API)
| # Install 'Rrepest' in R: |
| install.packages('Rrepest', repos = 'https://cloud.r-project.org') |
- df_pisa18 - Program for International Student Assessment (PISA) 2018 noisy data subset
- df_talis18 - Teaching and Learning International Survey (TALIS) 2018 noisy data subset
- rrepest_pisa_age_gender - Rrepest table of results for PISA 2018 showing age and gender
- rrepest_pisa_age_isced - Rrepest table of results for PISA 2018 showing the age and completed schooling level of students' mothers
- talis18_tt3g23o_freq - Rrepest table of results for TALIS 2018 showing a frequency for other areas of professional development
This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.
Last updated 1 months agofrom:2d22eb13ce. Checks:2 OK, 1 NOTE. Indexed: yes.
| Target | Result | Latest binary |
|---|---|---|
| Doc / Vignettes | OK | Mar 21 2025 |
| R-4.5-linux | OK | Mar 21 2025 |
| R-4.4-linux | NOTE | Mar 21 2025 |
Exports:coverage_daggerscoverage_pctestformat_data_categ_varsformat_data_cont_varsformat_data_repestgrouped_sum_freqsgrpindep_diffinv_testis_primen_obs_xpaired_indep_diffRrepestweighted.corrweighted.corr.cov.nweighted.covweighted.iqrweighted.modeweighted.quantweighted.stdweighted.var
Dependencies:askpassbase64encbitbit64bslibcachemclicliprcodetoolscpp11crayondata.tabledigestdoParalleldplyrevaluatefansifastmapflextablefontawesomefontBitstreamVerafontLiberationfontquiverforcatsforeachfsgdtoolsgenericsgluehavenhighrhmshtmltoolsiteratorsjquerylibjsonliteknitrlabelledlifecyclemagrittrmemoisemimeofficeropensslpillarpkgconfigprettyunitsprogresspurrrR6raggrappdirsRcppreadrrlangrmarkdownsassstringistringrsyssystemfontstextshapingtibbletidyrtidyselecttinytextzdbutf8uuidvctrsvroomwithrxfunxml2yamlzip
Citation
To cite package ‘Rrepest’ in publications use:
Ilizaliturri R, Avvisati F, Keslair F (2025). Rrepest: An Analyzer of International Large Scale Assessments in Education. R package version 1.5.4, https://CRAN.R-project.org/package=Rrepest.
Corresponding BibTeX entry:
@Manual{,
title = {Rrepest: An Analyzer of International Large Scale
Assessments in Education},
author = {Rodolfo Ilizaliturri and Francesco Avvisati and Francois
Keslair},
year = {2025},
note = {R package version 1.5.4},
url = {https://CRAN.R-project.org/package=Rrepest},
}
Readme and manuals
Rrepest
A way to run estimations with weighted replicate samples and plausible values
Table of Contents
- Description
- Installation
- Documentation
- Examples of use cases
- Authors
- Contributing
Description
It estimates statistics using replicate weights (Balanced Repeated Replication (BRR) weights, Jackknife replicate weights,...), thus accounting for complex survey designs in the estimation of sampling variances. It is designed specifically for use with the international education datasets produced by the OECD (e.g. PIAAC, PISA, SSES, TALIS, etc.), but works for any educational large-scale assessment and survey that uses replicated weights (e.g. ICCS, ICILS, PIRLS, TIMSS - all produced by IEA). It also allows for analyses with multiply imputed variables (plausible values); where plausible values are used, the average estimator across plausible values is reported and the imputation error is added to the variance estimator.
Installation
Using CRAN (latest official version)
Run the following code:
install.packages("Rrepest")
Using tar.gz file (latest development version)
Download Rrepest, then run
Run the following code replacing "You_R_Name" with your username:
install.packages("C:/Users/You_R_Name/Downloads/Rrepest.tar.gz",
repos = NULL,
type ="source")
Run:
library(Rrepest)
Using a GitLab token (latest development version)
Run the following code replacing "MY_TOKEN" with your gitlab token:
remotes::install_gitlab("edu_data/rrepest", host = "https://algobank.oecd.org:4430", upgrade = "never", auth_token = "MY_TOKEN")
Note: It will take a few minutes to install.
Run:
library(Rrepest)
Note: Ensure you have the package data.table installed. For a complete list of the dependencies used, consult the Description file.
Documentation
-
Full documentation of
Rrepestis available here. -
Cheat sheet including an overview of the syntax and auxiliaries of
Rrepestis available here. - Information on how to incorporate analyses that are not pre-programmed into
Rrepestis available in the following wiki.
Examples of use cases
Rrepest supports summary statistics (i.e. mean, variance, standard deviation, quantiles, inter-quantile range), frequency count, correlation, linear regression and any other statistics that are not pre-programmed into Rrepest but take a data frame and weights as parameters (see General analysis below). Rrepest also has optional features that provide means, among others, to specify the level of analysis, obtain estimates for each level of a given categorical variable, test for differences, flag estimates that are based on fewer observations than required for reporting, compute averages. More detail on the optional features of Rrepest can be found here.
Summary statistics
# PISA 2018 Data
# df.qqq <- readRDS("//oecdmain/asgenedu/EDUCATION_DATALAKE/sources/PISA/PISA 2018/R/STU/CY07_MSU_STU_QQQ.rds")
Rrepest::Rrepest(data = df.qqq,
svy = "PISA2015",
est = est(c("mean","var","std","quant",0.5,"iqr",c(.9,.1)),"age"),
by = c("cnt"))
Frequency count
# TALIS 2018 Data
# df.t <- readRDS("//oecdmain/asgenedu/EDUCATION_DATALAKE/sources/TALIS/2018/R/International/TTGINTT3.rds")
Rrepest::Rrepest(data = df.t,
svy = "TALISTCH",
est = est("freq","tt3g01"),
by = "cntry")
Correlation
# PISA 2018 Data
# df.qqq <- readRDS("//oecdmain/asgenedu/EDUCATION_DATALAKE/sources/PISA/PISA 2018/R/STU/CY07_MSU_STU_QQQ.rds")
Rrepest::Rrepest(data = df.qqq,
svy = "PISA2015",
est = est("corr",c("pv@math","pv@read")),
by = c("cnt"))
Linear regression
# TALIS 2018 Data
# df.t <- readRDS("//oecdmain/asgenedu/EDUCATION_DATALAKE/sources/TALIS/2018/R/International/TTGINTT3.rds")
df.t <- df.t %>%
mutate(TT3G01_rec = case_when(TT3G01 == 2 ~ 1,
TT3G01 == 1 ~ 0))
Rrepest::Rrepest(data = df.t,
svy = "TALISTCH",
est = est("lm","tt3g01_rec","tt3g39c"),
by = "cntry")
Further examples can be found in the Examples.R file.
General analysis
To incorporate analyses that are not pre-programmed into Rrepest, you can utilize the 'gen' option within the est() function of Rrepest. Any line of code that takes a data frame and weights as parameters can be used with the 'gen' option. For more information, please see the following wiki.
Authors
Francesco Avvisati, Rodolfo Ilizaliturri and François Keslair.
Contact us if you want to join!
Contributing
Do you have suggestions or comments? Please open an issue.