AQA A Level Psychology 3.2.3.2 and 3.2.3.3 Data Handling and Inferential Testing Exam Questions

About AQA A Level Psychology 3.2.3.2 and 3.2.3.3 Data Handling and Inferential Testing

Data Handling and Inferential Testing complete the AQA A Level Research Methods content on Paper 2, and this is where most of the course's maths skills are assessed. You need to distinguish quantitative and qualitative, primary and secondary data and meta-analysis, then calculate and interpret descriptive statistics and draw appropriate graphs. Inferential testing covers levels of measurement, probability and significance, Type I and Type II errors, choosing the right statistical test and calculating the sign test. Questions often give a small data set to analyse, ask you to justify a test choice or ask you to compare a calculated value with a critical value.

What you need to know

• Types of data Quantitative data are numerical and qualitative data are descriptive. Primary data are collected first hand; secondary data were collected by someone else. A meta-analysis combines the findings of several studies to produce an effect size.
• Descriptive statistics Measures of central tendency are mean, median and mode; measures of dispersion are range and standard deviation. A large standard deviation shows scores are widely spread around the mean.
• Presentation and distributions Use bar charts for discrete categories, histograms for continuous data, line graphs and scattergrams for correlations. In a normal distribution mean, median and mode are equal; in a positive skew the mean is greater than the median, and in a negative skew the mean is lower.
• Levels of measurement and probability Nominal data are categories, ordinal data are ranked, and interval data use equal units. Psychologists usually use p ≤ 0.05; a Type I error is a false positive (often from too lenient a level) and a Type II error is a false negative (often from too stringent a level).
• Choosing a test Choose by test of difference or correlation, design and level of data: chi-squared (nominal, unrelated), sign test (nominal, related), Mann-Whitney (ordinal, unrelated), Wilcoxon (ordinal, related), Spearman's rho (ordinal, correlation), unrelated t-test, related t-test and Pearson's r for interval data.
• The sign test Count plus and minus signs for each participant, ignore those with no change, so N is the number of remaining scores. S is the less frequent sign; the result is significant if S is equal to or less than the critical value.

Common mistakes in 3.2.3.2 and 3.2.3.3 Data Handling and Inferential Testing

• Including participants with no difference in N for the sign test; they must be removed first.
• Saying the observed value must be greater than the critical value for every test; for the sign test, Wilcoxon and Mann-Whitney it must be equal to or less than it.
• Using a histogram for categorical data; bar charts with gaps between bars are used for discrete categories.
• Getting the direction of skew wrong; in a positive skew the tail is on the right and most scores are at the lower end.
• Justifying a test choice without stating all three criteria: difference or correlation, related or unrelated design, and level of measurement.

Try three 3.2.3.2 and 3.2.3.3 Data Handling and Inferential Testing exam-style questions