One sample t-test
Use the one sample t-test to test whether the average of observations differs significantly from a test value.
- Select the variable of interest.
If the variable needs Logarithmic transformation, select the corresponding option.
- Optionally select a filter to include a subset of cases.
- Test value: the value to which you want to compare the sample mean.
The results include the summary statistics of the observations.
The One sample t-test panel shows:
- The test value
- The difference Sample mean - Test value
- The 95% Confidence Interval (CI) for this difference
- The Degrees of Freedom (DF), t-statistic, and corresponding (two-sided) P-value.
If the calculated P-value is less than 0.05, the conclusion is that, statistically, the sample mean is significantly different from the test value.
If you selected the Logarithmic transformation option, the program performs the calculations on the logarithms of the observations, but reports the back-transformed summary statistics.
For the One sample t-test, the difference between sample mean and test value, with 95% confidence interval, are given on the log-transformed scale.
Next, the results are transformed back and the interpretation is as follows: the back-transformed difference of the logs is ratio of the sample mean / test value on the original scale.
Go to One sample t-test.