This paper examines some of the implications of testing for statistical significance. After considering methodological issues raised by two examples from the literature, the paper proceeds to look in detail at a variety of misunderstandings attached to the reporting of "significant" results. It is concluded that significance testing is of limited…

The present paper suggests that multivariate techniques are very important in social science research, and that canonical correlation analysis may be particularly useful. The logic of canonical analysis is explained and discussed. The necessity of using replicability/generalizability analyses is argued. It is suggested that cross-validation…

Identifies some errors commonly committed when educational research results are reported. (BR)

The application of a multivariate analytic technique for the analysis of data from longitudinal designs with multiple dependent variables is presented. The technigue is the multivariate generalization of univariate repeated measures ANOVA. An application of the technique to data collected using materials from the Asian Studies Curriculum Project…

Designed for use with Research for Better Schools' evaluation system, this guide focuses upon basic concepts and statistical procedures applicable to specific research hypotheses emerging from evaluation questions. The first of three sections presents a discussion of descriptive statistics in terms of frequency, central tendency, variability, and…

When examining a repeated measures design with independent groups for a significant group by trial interaction, classical analysis of variance or multivariate procedures can be used if the assumptions underlying the tests are met. Neither procedure may be justified for designs with small sample sizes and dichotomous dependent variables. An omnibus…

The purpose of this paper is to demonstrate the use of the general linear model (GLM) in problems with repeated measures on a dependent variable. Such problems include pretest-posttest designs, multitrial designs, and groups by trials designs. For each of these designs, a GLM analysis is demonstrated wherein full models are formed and restrictions…

Considerable thought, research, and concern has been expanded in an effort to determine whether the assumption of a quadratic relation between a single predictor and a criterion violated the assumptions which Johnson and Neyman (1936) state for calculating regions of significance about interacting regressions. In particular, there has been special…

When random assignment has been accomplished and an analysis of covariance (ANCOVA) is being used to correct for initial differences among treatment groups, use of unreliable covariables not only decreases the power of ANCOVA, but also causes ANCOVA to test biased treatment effects. Several correction procedures have been suggested for the single…

Attempts to distill a growing technical literature on repeated-measures analysis of variance into a few simple principles for selecting an analytic technique. Argues that researchers ought not opt for a general analysis strategy when current computer technology makes it possible to select the optimal analysis technique for a given data set. (RH)

This paper discusses the sample size problem and four factors affecting its solution: significance level, statistical power, analysis procedure, and effect size. The interrelationship between these factors is discussed and demonstrated by calculating minimal sample size requirements for a variety of research conditions. (Author)

A Bradley-Terry type model for paired comparisons is considered which allows for individual parameters and corresponding parameters for the choice-alternatives. Model is applied to data from a Danish investigation of blue collar attitudes towards alternative social gains. Model is compared to one suggested by Schonemann and Wang. (RC)

This paper describes two statistics (chi square and Kendall's S) which may be used to test hypotheses about the association between two variables when observations are cross-classified in a contingency table. (CK)