About t-values
A t-value is used for null hypothesis (H0) significance testing and as follows.
We first define H0, a critical p-value (pcritic), and the degrees of freedom υ. With pcritic and υ, a critical t-value (tcritic) is determined and then compared against a sample-calculated t-value (tsample), such that
- H0 is rejected if tsample > tcritic
- H0 is not rejected if tsample < tcritic
Statistical tables can be used to find a tcritic. These tables are compiled by solving the Inverse Cumulative Distribution Frequency (ICDF) of the Student's t Distribution. Solving the ICDF is done through numerical approximation algorithms (Hill, 1970; Shaw, 2005; Shaw 2006). These are precisely the types of algorithms used by our tool to generate a tcritic.
If H0 is rejected, the experiment was conclusive at the critical confidence level selected, meaning the data is sufficiently inconsistent with H0.
By contrast, if H0 is not rejected, the experiment is inconclusive at the chosen confidence level, so the data is sufficiently consistent with H0.
Evidently, tsample > tcritic suggests that the observed data is so sufficiently inconsistent with H0 that it may be rejected. On the other hand, tsample < tcritic does not prove that H0 can be accepted. It only means that it cannot be rejected with the sample data examined. We can do better by formulating an alternative hypothesis known to be true, H1 so if H0 is rejected, we could accept H1.
However, to accept H1, we must consistently reject H0. This can be done by increasing the statistical power of the test, by increasing pcritic then decreasing tcritic. Thus, if one end rejecting H0 more often, there is a greater chance of safely accepting H1 (Trochim, 2006).