|
ellen@ling.ed.ac.uk, AFB-322 office hours: Tues 10:30-11:30, Wed 15:30-16:30 |
|
horlock@cstr.ed.ac.uk |
page created on October 3, 2000
Aims
This course should teach you how to approach the design and analysis of scientific studies of human behaviour. It will impart general principles of experimental research, issues of importance in the design of studies, ways of thinking about and treating the results. The main goal of the scientific enterprise is to know more with more certainty and less effort. The course should have direct impact on your own project work, saving you much time and many lines of prose which you could otherwise waste in trying to understand what your own data mean.
Methods
The course will include lectures (Wednesday of every week; Friday of week 1) and tutorials (Friday 14:00-15:00 or 15:00-16:00). Lectures describe principles and methods. Tutorials show you how to use a statistical package to apply methods. You may use the PCs in the AFB-B12 to supplement the weekly tutorials. Tutorial assignments will always include a problem to solve on your own. In addition, you will be assigned design problems which involve thinking rather than calculation. These will help you think like a critical experimenter. They should improve your judgment as a consumer of experimental research and help you design good studies of your own.
Assessment
Honours students will be assessed by an end-of-term project and an end-of-year exam. MSc students will submit an end-of-term project as part of their December exam. These projects will comprise a series of questions about a new data set. All students intending to do Honours or MSc dissertations will be expected to propose work which is satisfactory with respect to its design and susceptible to rigorous analysis.
Reading
I will try to have copies of the assigned texts put on reserve, but note that the library is re-cataloguing and this may take some time.
Assigned texts:
Easy, funny or lovable for one reason or another:
Follow the link below to other very useful sites with statistics information, often themselves containing links to further sites.
Schedule
C = Coolican; G&D = Greene & D'Oliveira
|
|
Room AFB-B12 (except wk 1) |
||||
|
|
|||||
|
[11.x] Introduction: Science as a Research Method | C, ch. 1 (WE)
C, ch. 2-4 (FR) |
(AFB-B9) Experimental Design - assuring you can know more from less | |||
|
[18.x] Measurement Scales & Descriptive Statistics | C, ch. 10 | Lab 1: Descriptive Statistics & Data Exploration | |||
|
[25.x] Relationships between two variables: Ordinal vs interval measures of correlation | G&D, ch. 8;
C ch. 15 pp 346-59 |
Lab 2: Correlation | |||
|
[1.xi] Nominal Data: from description to statistical inference: Binomial/Sign test, Chi-Square | C, ch. 11-12 | Lab 3: Binomial/signTest, Chi-Square | |||
|
[8.xi] Ordinal Data: Wilcoxon, Friedman, Mann-Whitney, Kruskal-Wallis | G&D, ch. 5-7 | Lab 4: Wilcoxon, Friedman, Mann-Whitney, Kruskal-Wallis | |||
|
[15.xi] Interval/ratio data: z-scores again, t-tests | G&D, ch. 10-12. | Lab 5: t-tests | |||
|
[22.xi] Interval/ratio data: ANOVA - basic concepts | G&D, ch. 13-14 | Lab 6: ANOVA part 1 | |||
|
[29.xi] Interval/ratio data: ANOVA - within subjects designs: with bells and whistles | G&D, ch. 15; C, ch. 19 | Lab 7: ANOVA part 2 | |||
|
[6.xii] Interval/ratio data: Regression and Multiple Regression. | C, ch.. 15 | Lab 8: Regression & Multiple Regression. | |||
|
[13.xii] Sampling and people: special designs and considerations | C, ch. 3,
Papers by Clark and Raaijmakers et al |
Lab 9: Test or extend your SPSS skills. |