Randomized controlled trials (RCTs) admit unconfounded design-based inference--randomization largely justifies the assumptions underlying statistical effect estimates--but often have limited sample sizes. However, researchers may have access to big observational data on covariates and outcomes from RCT non-participants. For example, data from A/B…

Multivariate analysis of variance (MANOVA) is widely used in educational research to compare means on multiple dependent variables across groups. Researchers faced with the problem of missing data often use multiple imputation of values in place of the missing observations. This study compares the performance of 2 methods for combining p values in…

In education research, small samples are common because of financial limitations, logistical challenges, or exploratory studies. With small samples, statistical principles on which researchers rely do not hold, leading to trust issues with model estimates and possible replication issues when scaling up. Researchers are generally aware of such…

The main objective of this study was to quantify the impact of failing to account for measurement error on school compositional effects. Multilevel structural equation models were incorporated to control for measurement error and/or sampling error. Study 1, a large sample of English primary students in Years 1 and 4, revealed a significantly…

Clustered data (e.g., students within schools) are often analyzed in educational research where data are naturally nested. As a consequence, multilevel modeling (MLM) has commonly been used to study the contextual or group-level (e.g., school) effects on individual outcomes. The current study investigates the use of an alternative procedure to…

Educational researchers commonly use the rule of thumb of "design effect smaller than 2" as the justification of not accounting for the multilevel or clustered structure in their data. The rule, however, has not yet been systematically studied in previous research. In the present study, we generated data from three different models…

Many classroom climate studies suffer from 2 critical problems: They (a) treat climate as a student-level (L1) variable in single-level analyses instead of a classroom-level (L2) construct in multilevel analyses; and (b) rely on manifest-variable models rather than on latent-variable models that control measurement error at L1 and L2, and sampling…

Classroom context and climate are inherently classroom-level (L2) constructs, but applied researchers sometimes--inappropriately--represent them by student-level (L1) responses in single-level models rather than more appropriate multilevel models. Here we focus on important conceptual issues (distinctions between climate and contextual variables;…

This report examines the differences in impact estimates and standard errors that arise when these are derived using state achievement tests only (as pre-tests and post-tests), study-administered tests only, or some combination of state- and study-administered tests. State tests may yield different evaluation results relative to a test that is…

Stepwise methods are frequently employed in educational and psychological research, both to select useful subsets of variables and to evaluate the order of importance of variables. Three problems with stepwise applications are explored in some detail. First, computer packages use incorrect degrees of freedom in their stepwise computations,…

Standard statistical methods are used to analyze data that is assumed to be collected using a simple random sampling scheme. These methods, however, tend to underestimate variance when the data is collected with a cluster design, which is often found in educational survey research. The purposes of this paper are to demonstrate how a cluster design…

Test reliability is a concept central to classical test theory and it is commonly stated as a requirement that a test attain a certain level of reliability before it be considered of sufficient quality for practical use. This article discusses the role of reliability in item response theory, and in particular the role of reliability in contexts…

Thirty-four papers on educational statistics which were presented at the 1971 AERA Conference are summarized. Six major interest areas are covered: (a) general information; (b) non-parametric methods; (c) errors of measurement and correlation techniques; (d) regression theory; (e) univariate and multivariate analysis; (f) factor analysis. (MS)

An empirical sampling approach was used to assess the accuracy of a Taylor approximation for the estimation of sampling errors. The sampling errors were in the statistics involved in estimating a path model based on medium-sized samples gathered using five sample designs commonly used in educational research. (TJH)

The serious problems associated with the use of stepwise methods are well documented. Various authors have leveled scathing criticisms against the use of stepwise techniques, yet it is not uncommon to find these methods continually employed in educational and psychological research. The three main problems with stepwise techniques are: (1)…