Suppose, you have to test whether the participants of a training camp show different reaction times before and after the training. In order to check whether there is a significant difference between the two tests, we repeat the reaction test several times and perform a t-test to compare the reaction times. The t-test, however, has two requirements - the data has to be normally distributed, and the variance have to be the same. Thus we have to carry out three different tests - a Kolmogorov-Smirnov test for normality, an F-test for equal variances, and finally the t-test for equal reaction times.
All three tests can be carried out easily by DataLab. We first start the statistical tests and tag the data to be compared (shown in red and blue).
Next we perform the Kolmogorov-Smirnov test for normality, which shows that the requirement of normal distributions is fulfilled (the results of block B are not visible on the screen shot):
Now we have to check for equal variances by applying an F test:
Finally, we carry out the t-test which is not significant at the 5% level. Thus there is no reason to say that the reaction times before and after the training differ: