Which statistical test is appropriate for comparing slug abundance before and after a rain event?

• A. A paired t-test (or non-parametric equivalent)
• B. A chi-square test
• C. A one-way ANOVA
• D. A correlation coefficient

Answer: (A)

The main idea is comparing two related measurements to see if an event changes something. Since slug abundance is measured on the same plots before and after a rain, the data are paired. You want to know if the average difference in abundance between the two times is zero. The paired t-test does exactly this by analyzing the differences for each plot and testing whether their mean is different from zero. If those differences don’t look normally distributed, you can use the Wilcoxon signed-rank test, which is the non-parametric alternative for matched data.

Why the other tests don’t fit: a chi-square test is for categorical frequencies, not for comparing mean abundance between two related measurements. A one-way ANOVA compares means across independent groups, and with only two related measurements, a paired approach is more appropriate (a repeated-measures ANOVA would be used if there were more time points or a more complex design). A correlation coefficient looks at how two variables co-vary, not whether one condition changes the level of slug abundance on the same units.