Biomedical subjects

S R Doyle

Publications and source records attributed to S R Doyle.

4 recordsLinked to original sources

PubMed1996

False-positive error rates in routine application of repeated measurements ANOVA.

Failure to recognize the serious implications of heterogeneous correlations and disregard of the multiple test problem in interpreting the results from repeated measurements ANOVA of any single primary outcome measure can produce false-positive error rates that are more than five times the alpha level that is reported. Alternative analyses that do not depend on the symmetry assumption, together with a Bonferroni correction of the multiple tests of significance that are routinely accomplished by the repeated measurements ANOVA, appropriately control the probability of statistical support for a false-positive claim. The magnitudes of error inflation and appropriate procedures for error control are examined in this article using simulated clinical trials data.

Analysis of Variance↗

PubMed1994

Estimating sample sizes for repeated measurement designs.

Formulas for estimating sample sizes that are required to provide specified power for analysis of variance (ANOVA) tests of significance in a two-group repeated measurements design are presented and evaluated. Power and sample size requirements depend on the pattern of treatment effects and the pattern of correlations among the repeated measurements, as well as on parameters common to sample size estimation for cross-sectional comparisons of treatment effects in simple randomized designs. Simplifying assumptions permit generation of these numerous parameter estimates from predictions of the magnitude of the standardized "effect size" at end of trial and the single correlation between the baseline and endpoint measurements. Monte Carlo methods are used to verify the actual power of different tests of significance for treatment effects in repeated measurement designs using sample sizes estimated by the formulas. The sample size implications of different patterns of treatment effects, levels of correlation, and numbers of repeated measurements are evaluated.

Analysis of Variance↗

PubMed1994

Implications of chance baseline differences in repeated measurement designs.

Datasets representing randomized, parallel-groups designs were analyzed by repeated measurements ANOVA and linear trend analysis with and without baseline values being covaried. ANOVA tests for the between-groups main effect, groups X times interaction, and differences in linear trends across time periods are shown to be seriously conservative or seriously nonconservative, depending on the direction and significance of chance baseline mean difference. Inclusion of baseline scores as a covariate in the repeated measurements ANOVA provides appropriate correction for the between-groups (average) effect across time, but the covariate provides no correction for the within-subject effects that are concerned with differences in the rates or patterns of change across time. If one desires to evaluate differences between patterns of treatment-induced change, tests of significance for differences in group means on composite trend scores with covariance correction for baseline are recommended. If covariance correction is not or cannot be employed, the potentially "favorable" or "unfavorable" influence of chance baseline differences on tests of significance needs to be explicitly recognized.

Analysis of Variance↗

PubMed1994

A comment on the importance of numerical evaluation of analytic solutions involving approximations.

An analytic solution proposed by Senn (1) for removing the effects of covariate imbalance in controlled clinical trials was subjected to Monte Carlo evaluation. For practical applications of his derivation, Senn proposed substitution of sample statistics for parameters of the bivariate normal model. Unfortunately, that substitution produces severe distortion in the size of tests of significance for treatment effects when covariate imbalance is present. Numerical verification of proposed substitutions into analytic models is recommended as a prudent approach.

Analysis of Variance↗