Search PubMed⌕ Search

Biomedical subjects

R J Grissom

Publications and source records attributed to R J Grissom.

5 recordsLinked to original sources
PubMed2001

Review of assumptions and problems in the appropriate conceptualization of effect size.

Estimation of the effect size parameter, D, the standardized difference between population means, is sensitive to heterogeneity of variance (heteroscedasticity), which seems to abound in psychological data. Pooling s2s assumes homoscedasticity, as do methods for constructing a confidence interval for D, estimating D from t or analysis of variance results, formulas that adjust estimates for inflation by main effects or covariates, and the Q statistic. The common language effect size statistic as an estimate of Pr(X1 > X2), the probability that a randomly sampled member of Population 1 will outscore a randomly sampled member of Population 2, also assumes normality and homoscedasticity. Various proposed solutions are reviewed, including measures that do not make these assumptions, such as the probability of superiority estimate of Pr(X1 > X2). Ways to reconceptualize effect size when treatments may affect moments such as the variance are also discussed.

Analysis of Variance↗
PubMed2000

Heterogeneity of variance in clinical data.

Traditional parametric (t, F) and nonparametric (Mann-Whitney-Wilcoxon U, Kruskal-Wallis H) statistics are sensitive to heterogeneity of variance (heteroscedasticity). Moreover, there are theoretical reasons to expect, and empirical results to document, the existence of heteroscedasticity in clinical data. Transformations to reduce heteroscedasticity are problematic. This article reviews the literature on robust methods that are available and that should be widely used to control rate of Type I error and maintain power. No one robust method is ideal for all situations, but such methods are superior to the traditional tests. Specific recommendations are made for application under various conditions of heteroscedasticity.

Analysis of Variance↗
PubMed1996

The magical number .7 +/- .2: meta-meta-analysis of the probability of superior outcome in comparisons involving therapy, placebo, and control.

The "probability of superiority estimate" (PS) estimates the probability that a randomly sampled client from a population given a treatment will have an outcome that is superior to that of a randomly sampled client from a population given another treatment. The meta-analytic clinical outcome literature was examined to calculate mean PS (PS) for comparisons involving therapy versus control, therapy versus placebo, therapy versus therapy, and placebo versus control. The range of PS was found to be approximately .7 +/- .2, with median PS greatest when therapy and control are compared (Mdn PSTC = .70, where T = therapy and C = control) and least when 2 therapies are compared (Mdn PSTT = .56). Results suggested that there is more to therapeutic success than placebo effects (Mdn PSTP = .66, where T = therapy and P = placebo) and that placebo is typically better than do-nothing control conditions (Mdn PSPC = .62). The present exceptionally large study, controlling for dependencies and confounding variables, may put to rest the question of the superiority of therapy to placebo. It also appears that the strength of effect of therapy is typically at least average among the effects of independent variables in psychology.

Adult↗
PubMed1994

Statistical analysis of ordinal categorical status after therapies.

Appropriate statistical analysis of clinical data based on ordinal categorical outcome scales is discussed. Chi-square analysis is inappropriate for testing the superiority of one therapy over another when outcome is ordinal categorical. Emphasized is estimation of clinically informative effect sizes after statistical significance has been attained with the Mann-Whitney U test. Little-used informative measures of effect size are related to estimation of the probability that a client given one therapy will have an outcome superior to that of a client given another therapy.

Amitriptyline↗