Welch’s t-test 

  • Assumptions to check:

    • Each sample has been randomly selected from the populations from which the samples are derived. 

    • The distribution of data in the underlying population from each of the samples is derived is normal.

Normal distribution (testable by e.g. the Kolmogorov–Smirnov test, the Shapiro–Wilk test, Q-Q plot)

  • Report design in method section

    • One or two tails? Justify the use of one tail test, if applicable. 

    • Name the statistical package or program used in the analysis

  • Report statistics in result section

    •  the t-statistic, degrees of freedom and exact p-value. 

    • Strongly recommended: report effect size with confidence intervals.

    • Report on assumptions. 

  • Example: 

    • Methods section:  We checked the hypothesis with two tailed Welch’s t-test. We used GraphPad Prism (RRID:SCR_002798) to perform the  analysis. 

    • Results section: According to the Shapiro-Wilk test, the normality assumption was not violated (W=0.976, p=0.063). We used the independent samples t-test with corrections (Welch’s test) which indicated a significant difference between the groups (t(98) = 10.542, p < 0.001, d = 2.108, 95% CI=[110,156]).