What are Data?

Statistics for Psychologists – Data and the T-test

In this course, Dr Andrew Bell (Kings College London) introduces statistics for psychologists and the t-test. In the first lecture, we are introduced to the different types of data which might be analysed for a scientific study. In the second lecture, we think about descriptive statistics, specifically mean, variance, and standard deviation. In the third lecture, we explore data distributions, working through normal (or Gaussian), leftward skewed, and rightward skewed graphs. Next, we think about null hypothesis significance testing (NHST), highlighting the importance of understanding what is meant by rejecting and not rejecting a hypothesis. In the fifth lecture, we think about the t-test, outlining the similarities and differences between a one sample, independent samples, and paired samples test. In the sixth and final lecture, we work through an example of each of the three t-tests to solidify our understanding.

What are Data?

In this lecture, we think about types of data, focusing in particular on: (i) data as the cornerstone of all scientific disciplines; (ii) quantitative (or numerical) and qualitative (or categorical) data; (iii) discrete and continuous data as subsets of quantitative data, the former being that which can only be subdivided so much (e.g. the number of houses on a street) and the latter being that which can be continually subdivided (e.g. time); (iv) nominal and ordinal data as subsets of qualitative data, the former being that which has no natural order (e.g. colours) and the latter being that which does (e.g. days of the week); (v) population and sample datasets, using measuring the heights of 17-year-olds in the UK as an example study.