title>Statistics 248 Spring 2000 D.R. Brillinger Statistics 248 (D. R. Brillinger) - Course Structure

Some specifics re the course:

1. Each Tuesday a homework exercise will be assigned. The solution is due the next Tuesday.

2. Due on Tuesday April 8, or earlier, is a proposal setting down -
a) a brief description of the data set you intend to analyse for the Project,
b) an indication of the source of the data set,
c) the objectives of your investigation,
d) the analyses you anticipate completing.

These are to be brief. The point is that I can interact with you a bit before you do a lot of work.

3. Due on Tuesday May 13 is the report on the Project - an analysis of a time series, image or some such random process data set. Carry through both time and frequency domain analyses.

4. The course grade will come from - the report, the homeworks, and the Tuesday April 8 material.

5. Exam. The Project will consititute the final.

The Reports

0. Set down the scientific questions you will be addressing.

1. Describe the important parts of your analyses.

2. Be specific, clear, factual.

3. Indicate details and sources of your data.

4. Provide conclusions and implications
i) with subject-matter interpretation as possible,
ii) that are properly qualified (for the sceptical reader - here, me)

5. Lay out any final models (with parameter estimate standard errors and confidence intervals as possible)

6. Mention especially important points (eg. model limitations, unexpected results, suggestions for future studies.)

7. Include important computer output and plots

8. Include a Summary

9. If necessary, include a list of references.

10. For each Project provide some comparative discussion of the time-side and the frequency-side and the nonlinear results.

Some Suggestions re the Projects

1. Check the basic assumptions (eg. stationarity, no outliers present) by plotting the data, getting stem-and-leafs, etc.

2. Think about re-expressing the data, eg. analysing log Y(t) instead of Y(t).

A Bit of Advice

Don't leave a lot of computations til the end of the semester. The computers break down and get very slow.

DON'T FORGET ABOUT THIS MATERIAL!

1/21/2003