ComputerUseforStatisticsdoc.docVIP

PAGE  PAGE 2 Computer Use Classes Accompanying Statistics Lectures 2008-2009: Coordinator: Prof. Alan Pickering Tutors: Dr. Ian Tharp Weeks 16 -19 Autumn Term: Some Miscellaneous Techniques Time and venue: Monday 4-5.15 pm in WB304 (Psychology Department Computer Classroom) for all students. For students on the following courses: Computer Use (PS71021A) MSc Research Methods in Psychology Computer Use (PS81021A) Research Training for 1st Year PhD students WEEK 17: CLASSICAL TEST THEORY AND RELIABILITY Learning Outcomes: After the session students should be able to: Use SPSS to simulate data under classical test theory assumptions. Calculate expected values of means, standard deviations, correlations and reliabilities using classical test theory and compare these predictions with the actual values in the simulated data. Use SPSS to calculate Cronbach’s alpha for a scale score composed of items stored within the SPSS dataset. Dataset To Be Used: If you have access to the Goldsmiths computer network then the file can be downloaded from the J drive: J:\psycholo\APstats\comp_classes\cttdata.sav or these files can be downloaded from the web by clicking and following the relevant links at the following URLs:  HYPERLINK http://homepages.gold.ac.uk/aphome/misc.html http://homepages.gold.ac.uk/aphome/misc.html The dataset contains a simulated set of items obs1 to obs5. In line with the assumptions of classical test theory these items are formed from an individual’s true score (based on a random normal variable called true) plus a random error term (err1 to err5, as appropriate). Note that each of the error terms is independent of each other (i.e., they are uncorrelated) and are also independent of the true score. Specific Tasks and Questions: Look at the stored formulae for the variables and answer the following questions: What is the expected value for the means and standard deviations (s.d.) of the error terms? Are these error terms as they are assumed to be und