Analysis of Covariance in Randomized Experiments with Heterogeneity of Regression and a Random Covariate
The Variance of the Estimated Treatment Effect at Selected Covariate Values
Bibliographic Data
| ID | 19290356 |
|---|---|
| Authors | Li Li (0000-0001-9700-9682, University of New Mexico), Christopher J McLouth (0000-0002-5434-9748, Department of Behavioral Science, University of Kentucky College of Medicine), Harold D Delaney (0000-0002-2794-0559, University of New Mexico, corresponding author) |
| Year | 2020 |
| Volume | 55 |
| Issue | 6 |
| Pages | 926-940 |
| Publication date | 2020-11-01 |
| Open Access | No |
| Type | ARTICLE |
| Venue | Multivariate Behavioral Research (JOURNAL) |
| Journal identifiers | ISSN: 0027-3171 • E-ISSN: 1532-7906 |
| Publisher | Informa UK Limited (PUBLISHER • GB) |
| DOI | 10.1080/00273171.2019.1693953 |
| PMID | 31795755 |
| OpenAlex | W2994153641 |
| Language | EN |
| References cited | 20 |
Researchers detecting heterogeneity of regression in a treatment outcome study including a covariate and random assignment to groups often want to investigate the simple treatment effect at the sample grand mean of the covariate and at points one standard deviation above and below that mean. The estimated variances of the simple treatment effect that have traditionally been used in such tests were derived under the assumption that the covariate values were fixed constants. We derive results appropriate for a two-group experiment that instead presume the covariate is a normally distributed random variable. A simulation study is used to confirm the validity of the analytical results and to compare error estimates and confidence intervals based on these results with those based on assuming a fixed covariate. Discrepancies between estimates for fixed and random covariates of the variability of treatment effects can be substantial. However, in situations where the extent of heterogeneity of regression is like that typically reported, presuming the covariate is random rather than fixed will generally result in only a modest increase in estimated standard errors, and in some circumstances can even result in a smaller estimated standard error. We illustrate the new methods with an empirical data set
Analysis of covariance · Covariance · Covariate · Econometrics · Meta-analysis · Population · Random effects model · Regression analysis · Simple random sample · Standard deviation · Standard error · Statistics · Advanced Causal Inference Techniques · Mathematics · Statistical Methods and Inference · Statistical Methods in Clinical Trials
Applied Bayesian Modeling and Causal Inference from Incomplete‐Data Perspectives
Personality, Interactive Relations, and Applied Psychology
Robustness?
Computational procedures for probing interactions in OLS and logistic regression
Effect Size and Power in Assessing Moderating Effects of Categorical Variables Using Multiple Regression
Correlational effect size benchmarks.
Computational Tools for Probing Interactions in Multiple Linear Regression, Multilevel Modeling, and Latent Curve Analysis
Pygmalion in the classroom
Tests of Simple Slopes in Multiple Regression Models with an Interaction
The Next Generation of Moderator Research in Personality Psychology
An empirical study of a proposed test of nonparametric analysis of covariance
The moderator–mediator variable distinction in social psychological research
The moderator-mediator variable distinction in social psychological research
Beyond the two disciplines of scientific psychology
Comparing nonparallel regression lines
| Highly cited | No |
|---|