Definition of T-Test
You can use t-test as a statistical measure which can be used to determine the difference between two groups of data which have some similar characteristics. The t-test measures the differences between the means of two groups, and is often used as a hypothesis testing tool.
The types of t-tests used are varied according to the type of data that is required to be analysed. You need to know certain data values for calculating the t-test.
These data values include the difference between the means of the groups used for the test, the standard deviation of each group and the number of data values of each group.
When is the t-test used?
The basic concept of t-test is that it considers the samples from each group involved in the testing by also considering the null hypothesis in which there are no differences between the mean of both the groups.
T-test is a parametric test and it can only be used when comparing between two groups. These groups need to meet certain parameters— data of both groups is independent, it is normally distributed and has a similar amount of variance.
If your data doesn’t fit these parameters it is not fit for the t-test and you may have to go for some other test.
What are the types of t-tests performed?
The two types of t-tests that are widely performed depend whether the two units compared are same or two completely different units. For example, two different factors may be tested in a similar population or two entirely different populations.
Depending on this the t-tests performed are— paired t-test and one-tailed or two-tailed t-test. Paired t-test is done when comparing the data from similar units or similar population whereas one-tailed and two-tailed t-tests are done when comparing the data from two different units or population.
