Single Sample T-Test Use Case

For more information about the single-sample t-test, see T-Test - Single Sample.

For an example of this test's usage, see the following sample data from a puppy training program that measures the skills of the puppies before they enter the program and after the program.

Suppose that for the above data, we want to ask whether the puppies that enter our training program are scored above average or below average. We know that in general puppies score an average of 10.0 on this test. In this case, we could run a single sample t-test on the Score Before Training column against the known mean of 10.0. Formally, we would say that our null hypothesis is that the puppies that enter our training program do not have a statistically higher or lower score on the skills test. We would reject the null hypothesis if the Two Tailed p-value is less than 0.05.

First, we draw a random sample from the population (the connected dataset) and then compare the sample mean with the population mean (the assumed mean here). We can use this to tell whether the sample mean is different from the population (assumed) mean.

For example, we can use this operator if we have election data from a state. We know the population mean (percent of voters who select a certain candidate), but we want to compare that with the sample mean of voters from a certain county. The Single Sample t-test can tell if this difference is statistically significant. (source)

In this example, we can determine whether the puppies score differently than average before and after the training program by selecting the Score Before Training and Score After Training columns for the Sample Columns parameter. We also set the Assumed Mean to 10.0, because we know that puppies in general score about 10.0.