For a paper published in 2015 (for example, from the journal Psychological Science), where a key result apparently testing a theory comes from a t-test,  answer the following questions. Try to limit your total words to about 1000, so each answer will need to be very concise, while being informative.

  Section A. Popper (25 marks)

1) Concisely state the theory that the authors present as being put up to test?
2) What pattern of results, if any, would falsify the theory?
3) What background knowledge inspired this theory but is not being directly tested?
4) What background knowledge must be assumed in order for the test to be a test of the theory in (1)?
5) How safe is the background knowledge in (4)?

 Section B. Neyman Pearson (25 marks)

6) Have the authors determined what minimal difference  could be expected if the theory were true? If not, determine one yourself and state your reasons. Use it to construct a null region.
7) Calculate a confidence interval and use it and the null region to argue whether or not the data sensitively distinguished the alternative and null hypotheses.

Section C Lakatos (25 marks)

8) State the hard core of the research programme the authors are working in
9) Does the paper contribute to the research programme in a progressive or degenerating way? State your reasons.

Section D  Bayes (25 marks)

10) What was the mean difference obtained in the study?
11) What was the standard error of this difference?
12) Can you determine an expected value or a maximum value?
13) Specify a probability distribution for the difference expected by the theory and justify it.
14) What is the Bayes factor in favour of the theory over the null hypothesis?
15) What does this Bayes factor tell you that the t-test does not?

For some possible answers to previous versions of these questions:

Example answer1 (short model answers)

Example answer2 (detailed discussion of issues)

Here is a multiple choice version.