skip to primary navigationskip to content

Graduate Methods Class - Professor Mark Haggard

Five classes in Lent Term of 1.5+ hours’ duration. Graduates in all years are welcome, and some of the most knowledgeable students have found it worthwhile to re-attend in later years.

All courses start at 16.00 and are in the Department of Psychology Building on the Downing Site.

Wednesday 9 January 2019 - Nick Mackintosh Room

Wednesday 16 January 2019 - Nick Mackintosh Room

Wednesday 23 January 2019 - Nick Mackintosh Room

Wednesday 30 January 2019 - Nick Mackintosh Room

Wednesday 6 February 2019 - Nick Mackintosh Room

Wednesday 13 February 2019 - Nick Mackintosh Room

Detailed requirements for graduate projects in respect of methods are diverse. (‘Statistics’ is too narrow a term here, although ‘strategic uses of statistics’ comes close.)  After this taster Professor Haggard is available through the year for (unpaid!!) consultancy to those who have attended it.

The prevailing reading of the so-called Replication Crisis (RC) shows that decades of studies deemed publishable have done things wrongly. A more profound reading shows they have largely been attempting to do the wrong thing (to claim specious factoidality -- finding one example of existence of some effect that it is not an outrageous example to claim rather than specifying the affect.) Distributions can be important, but concentration on the mathematics of whether distributional assumptions make the third decimal place of a misleading number 0.XX8 or 0.XX7 is an activity misplaced. It is especially misplaced when the conclusion will be misleading in either instance, because the argument has attempted to do something wrong in the first place.

This course attempts to transferring understanding of statistical concepts, so that the self-deceptions of RC do not occur in the future. It emphases the scientific goals to be achieved by studies: generalisability, stability, power by error-reduction, parsimony and the explanation of worthwhile proportions of the variance (effect size). It includes some initial familiarisation with the necessary statistical techniques for data structures more complex than those met in undergraduate projects – the simple differences, correlations and ANOVA designs. The discussions are rooted in issues that make a difference: what are the specific (psychological AND statistical) advantages AND disadvantages of between- versus within-participant designs? What is the p-value and what should it be used for, if anything? For what reasons should you test for interaction and what do you next, especially if the interaction result is marginal as to ‘significance’? If you have a difference carried by a higher level of sampling unit such as school or hospitals, when do you need formally to test for generality across these (MLM) rather than for some effect across participants within the data?

Well, the glib answer to all these questions is that it depends on the exact expression for the study of the particular research question from the general research question or prediction. The course teaches that the generation of particular useful answers depends on having a set of methodological principles (eg that you must always show you have made use to the extent feasible of all relevant data obtained and should limit); and the implementation of an answer depends on sufficient understanding of statistics to design a study and design a good analysis of it.  In 5 weekly sessions we meet the various powerful extensions of the General Linear Model (that is basically, of ANOVA) such as Multiple Regression, Factor Analysis, Structural Equation modelling and Multi-level modelling; also logistic regression and computationally intensive non-parametric methods. The distinction between a legitimate and the most appropriate statistical test is introduced, with principles and precedents for how to make the choice.

Reading. PDFs of particular methodological answers are supplied, but no post-graduate in psychology should proceed without having read in their first few months:

P. Abelson. Statistics as Principled Argument, 1994

G. Cumming. Introduction to the New Statistics, 2012. (Beware, there is a more recent book of similar title by Geoff Cumming which is OK, but more an undergraduate workbook.)