When t-tests or Wilcoxon-Mann-Whitney tests won't do

Abstract

t-Tests are widely used by researchers to compare the average values of a numeric outcome between two groups. If there are doubts about the suitability of the data for the requirements of a t-test, most notably the distribution being non-normal, the Wilcoxon-Mann-Whitney test may be used instead. However, although often applied, both tests may be invalid when discrete and/or extremely skew data are analyzed. In medicine, extremely skewed data having an excess of zeroes are often observed, representing a numeric outcome that does not occur for a large percentage of cases (so is often zero) but which also sometimes takes relatively large values. For data such as this, application of the t-test or Wilcoxon-Mann-Whitney test could lead researchers to draw incorrect conclusions. A valid alternative is regression modeling to quantify the characteristics of the data. The increased availability of software has simplified the application of these more complex statistical analyses and hence facilitates researchers to use them. In this article, we illustrate the methodology applied to a comparison of cyst counts taken from control and steroid-treated fetal mouse kidneys.

Consistency of Use and Effectiveness of Household Water Treatment Practices Among Urban and Rural Populations Claiming to Treat Their Drinking Water at Home: A Case Study in Zambia

“…34 We used raw mean counts of TTC, with outcomes expressed as risk ratios, estimating the change in the relative mean number of events between categories. 35,36 The analysis used robust variance estimation to adjust for clustering at the household level. All statistical analyses were conducted using STATA version 10 (Stata Corp., College Station, TX).…”

Bifactor Models of Religious and Spiritual Struggles: Distinct from Religiousness and Distress

“…We used the forestplot package [78] to visualize comparisons of effect size estimates and confidence intervals across all samples and the total sample. In the overall sample with 95% confidence based on a negative binomial regression model [79], we would expect the mean number of identical responses to be between 2.0 and 2.8 times larger among people who fail this attention check ( Figure 1a). Conversely, the odds of a participant failing the attention check increase by 19%-28% for every unit increase in the number of identical responses based on a logistic regression model with 95% confidence (Figure 1b) [80].…”

NAHR-mediated copy-number variants in a clinical population: Mechanistic insights into both genomic disorders and Mendelizing traits

“…This kind of regression analysis builds the model that explains the response variable assuming that it has a Poisson distribution, i.e., the logarithm of its expected value can be modeled by a linear combination of parameters. The advantage of the regression approach over standard hypotheses testing was discussed by McElduff et al (2010).…”