Researchers and scientists often use statistical tests called t-tests to assess whether two groups significantly differ from one another. T-tests take into account the numbers on which the means are based to determine the amount of data overlap between two groups.
A t-value can be computed by dividing the difference between group means by the variability (called the standard error of difference) between the groups.
Calculating difference between group means simply involves subtraction of one mean from the other.
The standard error of difference can be calculated by subtracting the mean of one group from a unique sample in that same group, squaring that value, then dividing the value by the total number of samples in the group minus 1. This calculation should be performed for each unique sample, then all of those values should be added together.
A negative t-value simply indicates a reversal in the directionality of the effect, which has no bearing on the significance of the difference between groups. Analysis of a negative t-value requires examination of its absolute value in comparison to the value on a table of t-values and degrees of freedom (which quantifies the variability of the final estimated number). If the absolute value of the experimental t-value is smaller than the value found on the degrees of freedom chart, then the means of the two groups can be said to be significantly different.