THE DESIGN OF EXPERIMENTS

A. Overview

Statistics is the science of collecting, presenting, and interpreting data to answer questions.

Let's break it down.

There are four primary issues:

1. Determining the question and the data that will help you answer the question.

2. Collecting the data.

3. Summarizing and presenting the data graphically and numerically.

4. Making generalizations from the data and drawing conclusions. Frequently by making comparisons between groups.

B. Determining the Question

1. The first issue in statistics is always,

   "What question do we want to answer?"

   Example: If I use this new product will it work for me?

2. Data do not speak for themselves;

   so we must collect data with a purpose.

3. Not all questions can be answered or should be!

   a. "Data as they are" questions can be answered. These involve survey data.

   b. "What-if questions under replicable circumstances" can be answered. These involve experiments.

   c. Data from nonreplicable events, in general, can NOT be answered!

C. Collecting Data

Data collection may take the form of (a) guessing, yes, it's reasonable and you see frequently in disciplines such as history. For example, the question might be "how many people lived in Israel during the reign of Herod". There is no way to ask and written evidence may be scant, so one must guess (b) testimonials, anectdotal evidence -- these are stories. You see them in infomercials or in the newspaper. It's based on the experience of a very small number of people. While it may be valid for them, ask yourself, does it hold true for everyone else? (c) surveys -- collecting data as they are -- one goes out and talks to individuals or counts things or measures things. It's real information and it may be based on a number of people, things and it may have been done more than once, (d) experiments -- the strongest form of data collection.

D. Presenting Data

Numerically & Graphically

People often equate statistics with numbers. Numerical summaries are like averages (e.g. your grade point average) and graphically (e.g. a bar chart)

E. Interpretation and Generalization

The heart of statistics. Statistics is not just numbers. It's about the results for some small group of people (say 38 male twins who have used the "pheremone cologne") and knowing whether or not it will apply to men other than the 38 males in the study.