Text Font Conventions

Key concepts - You will be responsible for knowing a number of definitions of key concepts. You may be asked to give an accurate definition and example of any of the key concepts. Key concepts are in italics, bolded and colored red throughout the notes.

Critical points - There are some points that require extra emphasis because they are fundamental to the example or concept being discussed. Critical points are bolded, in italics and colored orange.

Course learning objective questions - These are the questions given in the learning objectives document.

Lecture 9

We have made it to the last week of the course! This week,we look at a test statistic used to address questions relating to differences between 3 or more groups. This test statistic is called Analysis of Variance of ANOVA for short. The first place we need to start is with the basic set-up of the situation in which ANOVA is useful. Here goes...

1) ANOVA...the basic set up....here

Now we need to look at the calculations we would make in doing an ANOVA. We introduce the ideas of MS within and MS between and look at how they are relevant to the hypothesis test we do in the ANOVA situation and the extent to which the IV and DV are correlated with each other. Here goes...

2) ANOVA...calculation example....here

These last two videos give sufficient information to answer learning objectives questions 26 and 27.

That's it for new material in the course. Now I would just like to revisit some of the logical issues in hypothesis testing to make sure we do not loose our basic understanding of the purpose of hypothesis testing in working through the complexities of test statistics. Let's start with the question about why we do not make alpha 0...learning objectives question 21. Here goes...

3) Why we do not make alpha 0...here

In the next video, we take a closer look at the p-value. In my view, the p-value is the most important number in statistics (learning objectives question 20) because it is the only number we calculate that determines whether or not to reject the null hypothesis. Since rejecting the null hypothesis is the purpose of hypothesis testing, the only number we calculate that is relevant to our purpose is the p-value. The reason we have spent so much time on the logic of hypothesis testing, as opposed to looking at a wide variety of test statistics, is that all test statistics, no matter the complexity of the situation, exist for the purpose of producing a p-value. And, in all cases, just as in the simplest case, the p-value is the basis upon which we reject the null and the basis for our claim that we have "discovered" that the null is false. So, all research papers that employ hypothesis testing (about 95% of them in the social sciences) contain p-values as the basis for making the decision that something has been discovered. This is why p-values are so important to us. The following video contains a more broad analysis of the concept of a p-value that is relevant to learning objectives questions 20 and 22. Here goes...

4) Is P the probability the null is true....here

I would like to end this course by looking at the relationship between hypothesis testing and the aims of science. It turns out that there are a number of analytic approaches we can take to our data, only one of which is hypothesis testing. In this video, I look at the situations in which hypothesis testing is relevant and situations in which it is not relevant. The case of COVID-19 is used as an example. The question is an answer to learning objectives question 29. Here goes..

5) Where is hypothesis testing....here

That's it for psychology 2300 everyone. Thank you all for your patience and efforts to overcome the difficulties of taking this course Online at such short notice. All the best to you all...Jeremy