Statistical computing, statistical software packages; working with large data sets; exploratory data analysis; graphical methods; statistical consulting practice.
Tuesday 12:30-14:30, Thursday 12:30-13:20, in BSB-138
By appointment only.
All assignments must be submitted no later than noon on Tuesday 29 April 2002, the final day of the undergraduate examination period.
Assignment #1 - Using Splus or R, do a thorough data analysis for the Cervical Cancer Case Study.
Do an exploratory graphical analysis and a detailed survival analysis. Write your own program to plot the Kaplan Meier estimate of the survival function and to fit an exponential distribution, and use it to study the effect of tumour size (with size categorized into 3 classes). Using the survival library functions, fit exponential regression, Weibull regression and Cox Proportional Hazards regression. Determine which variables are useful for prognosis.
Write a report summarizing your results. There should be a plain-language consultant's report explaining your results in terms any educated person could understand, and technical appendices documenting the statistical methods and software used. The assignment will be graded on the quality of the write-up as well as on the appropriateness and correctess of the analysis.
Assignment #2 - Using SAS, complete S2MA3 Assignment #3. Include your SAS scripts in your report. Be careful with the wording of your conclusions.