Laptops for Teachers: An evaluation of the TELA scheme in Auckland schools

Statistics Glossary

Analysis of Variance (ANOVA)

A statistical procedure for deciding if the underlying mean values of several groups are really all the same, or if some are significantly different from others. It uses a calculated value known as an F statistic, which needs to be compared with tabulated ‘critical’ values.

Significant

The difference between the mean values of two groups is said to be (statistically) significant if the probability of the difference occurring by chance is less than a pre-set value (usually 5%).

Standard deviation

A measure of the variation of a set of numerical values around a central mean value. Usually, about 95% of cases will lie within twice the standard deviation of the mean.

T-test

A statistical procedure for deciding if the underlying mean values of two groups are really the same, or significantly different. It uses a calculated value known as a t statistic, which needs to be compared with tabulated ‘critical’ values.

Tukey post hoc test

Even if an ANOVA test indicates that group means are not all the same, it does not indicate which ones are different from which others. A ‘post hoc’ test provides this additional information, and Tukey’s test is one of several variants.