I have compared two groups on a certain variable and SPSS has produced a negative t-value. I have interpreted the results from p-value but the thing i want to know that whether the t-value be reported in negative or positive.
Look at the formula for the t value. The distribution is close to normal around zero. This just means that your sample avrg value is bigger or smaller from the other to which it is compared to, depending what is your m1 and m2
.
there is nothing wrong with a negative t-value
http://blog.minitab.com/blog/statistics-and-quality-data-analysis/what-are-t-values-and-p-values-in-statistics
.
Yes, it is indeed possible to obtain a negative t value. It eventually depends on the formulation of the test statistics. As pointed out by Etuk, the formula of the test statistics can be value from group 1 - value from group 2, or value from group 2 - value from group 1.
If you are not fond of a negative t value, you can change or define the original formula, so that you end up with a positive t value.
Dear t value can be reported as negative on the basis of P- value. However the possibility of negative t- value is rare.
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS