In sophiestallasch/multides: R Tools for the MULTI-DES Project

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)
options(tibble.print_min = 20, tibble.print_max = 20)

multides

The multides package is a companion R package of the project "MULTI-DES: Multilevel Design Parameters and Effect Size Benchmarks for Students’ Competencies," as well as its follow-up project "MULTI-DES 2: Multilevel Design Parameters for Sample Size Planning of Randomized Intervention Studies in Preschool, Elementary and Secondary School."

multides compiles tools that were developed to facilitate the analyses conducted within the MULTI-DES project framework. The functions may be used to replicate the R code that accompanies the manuscripts prepared within MULTI-DES. All R scripts are shared via the Open Science Framework (OSF; see below).

Nevertheless, the application scope of multides is not limited to the analyses specific to MULTI-DES. The functions provided can also be used in other contexts of (multilevel) data analysis, for instance, to easily generate overviews of descriptive statistics, single- and multilevel correlation matrices, or--most importantly--to calculate (multilevel) design parameters such as intraclass correlation coefficients and explained variances by covariates at each hierarchical level with corresponding standard errors, based on the variance components estimated from single- or multilevel models.

The MULTI-DES Project

MULTI-DES is funded by the German Research Foundation (DFG) and aims at investigating (1) single- and multilevel design parameters that are needed to efficiently plan adequately powered individually and cluster randomized trials on various outcomes (viz., achievement/cognitive outcomes and socio-emotional learning outcomes) in preschool, elementary and secondary school, as well as (2) effect size benchmarks in terms of academic growth and performance gaps between schools or policy-relevant groups to appropriately interpret and communicate the results of such studies. In MULTI-DES, rich data from several German (longitudinal) large-scale assessments were used to apply multilevel and structural equation modeling. For more information on MULTI-DES, visit https://www.uni-potsdam.de/en/quantmethoden/forschung.

Publications and Preprints

Brunner, M., Stallasch, S. E., Artelt, C., Hedges, L. V., & Lüdtke, O. (2024). An individual participant data meta-analysis to support power analyses for randomized intervention studies in preschool: Cognitive and socio-emotional learning outcomes. PsyArXiv. https://doi.org/10.31234/osf.io/dkw42
Preprint

Brunner, M., Stallasch, S. E., & Lüdtke, O. (2023). Empirical benchmarks to interpret intervention effects on student achievement in elementary and secondary school: Meta-analytic results from Germany. Journal of Research on Educational Effectiveness, 17(1), 1–39. https://doi.org/10.1080/19345747.2023.2175753
R code

Stallasch, S. E., Lüdtke, O., Artelt, C., & Brunner, M. (2021). Multilevel design parameters to plan cluster-randomized intervention studies on student achievement in elementary and secondary school. Journal of Research on Educational Effectiveness, 14, 172–206. https://doi.org/10.1080/19345747.2020.1823539
R code

Stallasch, S. E., Lüdtke, O., Artelt, C., Hedges, L. V., & Brunner, M. (2024). Single- and multilevel perspectives on covariate selection in randomized intervention studies on student achievement. Educational Psychology Review, 36, 112. https://doi.org/10.1007/s10648-024-09898-7
R code

Installation

You can install the development version of multides from GitHub with:

# install.packages("devtools")
devtools::install_github("sophiestallasch/multides")

Usage

library(multides)

# calculate a range of descriptive statistics for a series of numeric variables,
# grouped by school type
describe_stats(studach, gender:read, ts_name)

# calculate multilevel correlations between group means at the school level
correlate_ml(studach, gender:read, id_sch)

Help & Suggestions

If you encounter a bug, have questions or suggestions for improvement, please file an issue on GitHub or email me, possibly including a minimal reproducible example.

sophiestallasch/multides documentation built on Oct. 20, 2024, 5:14 a.m.