A2 - Psychology - Statistical tests

Statistical tests

Statistical tets are the only way to determine whether the results of a study are significant, i.e. a real effect has been demonstrated as opposed to a chance pattern that looks menaingful. There are a large number of statistical tests that are used by researchers and statisticians; however you only need to be concerned with the five in the specification. When deciding which test is appropriate in any situation you can sk yourself the questions described below:

Nominal data - Yes - Chi-square Test, Sign Test

Nominal data - No - Spearman's Test, Mann-Whitney U Test, Wilcoxon T Test

Nominal data - Yes - Frequency data - Yes - Chi-square Test 

Nominal data - Yes - Frequency data - No - Sign Test

Nominal data - No - Correlation - Yes - Spearman's Test

Nominal data - No - Correlation - No - Mann-Whitney U Test, Wilcoxon T Test

Nominal data - No - Correlation - No - Independent groups - Yes - Mann-whitney U Test 

Nominal data - No - Correlation - No - Independent groups - No - Wilcoxon T Test

Justifying your choice In an exam question, you may be asked to choose an appropriate statistical test and then justify your choice. Below is a variety of possible justifications that could be used. However, be warned that such justification need…