2. Statistical Testing

About this Lecture

Lecture

In this lecture, we think about statistical testing, focusing in particular on: (i) understanding statistical testing as a method of calculating the probability of an event against the null hypothesis; (ii) recognising that a rejection of the null hypothesis is simply an acknowledgment that the results present are deemed to be outside of the realm of random chance; (iii) returning to the coin flip example to discuss how many heads results it would take for one to decide that the coin is biased; (iv) returning also to the blood pressure example, to discuss how much of a drop in blood pressure could be deemed outside of the realm of random chance and therefore could be attributed to the effectiveness of the administered drug; (v) the vital element of a statistical test, which is the comparison of the calculated value to a critical value.

Course

In this course, Dr Ayoub Bouguettaya (University of Birmingham) explores probability within the field of statistics. In the first lecture, we look to understand what statistics are and why they matter. In the second lecture, we think about statistical testing as a function of the null hypothesis, and what it means to reject a null. In the third lecture, we think about significance and normality, including the importance of evaluating percentages and probability against the number of events/incidences being tested. Next, we think about types of statistical tests, with a focus on t-tests, Pearson’s correlation, Spearman’s Rho, and the Chi-squared test. In the fifth lecture, we think about the two main types of errors: type 1 and type 2, and their consequences in different settings. In the sixth and final lecture, we think about some controversies in the field of statistics, including p-hacking and the use of Bayesian statistics.

Lecturer

Dr Ayoub Bouguettaya is a lecturer in the School of Psychology at the University of Birmingham. Dr Bouguettaya’s research interests are in social psychology and how knowledge from that field can be applied to others, particularly health, including how we can apply social identity theory to societal problems, as well as investigating the different perspectives one might take on those issues. Some of Dr Bouguettaya’s recent publications include 'The relationship between gambling advertising and gambling attitudes, intentions and behaviours: a critical and meta-analytic review' (2020) and 'The Effect of a Food Addiction Explanation Model for Weight Control and Obesity on Weight Stigma' (2020).