Bio&Soc 202 Summer 1991

Statistical analysis includes the construction of observations (in experiments and in the field), summarizing data (statistics, distributions, correlation), testing hypotheses and other statistical inference (including Goodness of Fit). Concepts and methods will be introduced through lectures, practice classes and discussions. Real cases from the life sciences will be used, and the different interpretations, hidden assumptions, limitations and misuse of statistically derived results will be emphasized.

Assessment: Assignments 50%

Take-home exams 30%

Class participation and improvement 20%

Expectations: Emphasis will be placed on learning from assessed work. Students will be asked to resubmit work until it is mostly correct, at which time I will give them the answer sheet. The course builds on itself -- getting behind is unacceptable, because it will make it hard for you to follow current classes. All submitted work must be very legible.

Required Texts: Freedman,D., R. Pisani, R. Purves (& A. Adhikari) 1978/1991 Statistics N.Y.: Norton. (The 1st edition is OK, but will not have high resale value, because there is now a 2nd. edition. I will accommodate both editions.)

Huff,D. How to Lie with Statistics N.Y.: Norton.

In addition, I will circulate photocopied material, for which there is a $5 charge.

Required calculator: You will need to have a calculator which you can bring to each class. I have a $15 TI-30 solar-powered one, but it would probably be better if you had one with at least two memories.

SCHEDULE OF CLASSES

Classes will be part lecture, part discussion and part practice classes. I will distribute problem sets and handouts about which sections of the texts correspond to the classes.

(Note: In a fall or spring semester class these topics would be subdivided to fit shorter class periods, and there would be room for additional topics.)

1. Introduction: why do we want to be able to deal with statistics?

General scheme of statistics.

(Phenomenon--Elevation--Observation--Measurement--Data--Pattern--Prediction.....Causes?)

2. Observations

(Elevation of circumstances, categories and identity, control, resolution) (Measurement, precision and notation)

3. Population and sample ; Classes and frequency

(Distributions)

4. Graphical representation

(Exploratory data analysis, histograms & distributions)

5. Statistics

(Central tendency and dispersion; More graphics: box-and-whisper plots)

6. Distributions of statistics

7. Density Curves

(Normal, Chi-squared, fitting curves to histograms)

8. Statistical "machines"

(Probability or box models, central metaphor of statistics)

Mid-term take home exam (on classes 1-7)

9&10. Prediction

(Posterior density, confidence intervals)

(Hypothesis testing, comparison of means, decision rules)

11. Association I

(Experimental studies, G-test, goodness-of-fit)

12. Association II

(Observational studies, least squares fit, regression)

13. Correlation and causation

14. Analysis of variance

Final take-home exam distributed

15. Explanation and causality in the real world.

(Co-occurence, current factors vs. historical, proximate vs. background, internal vs. external, experimentally controlled vs. natural, unitary vs. multifactorial)

plus Review