Memo - Babbie Chapter 16: Statistical Analysis

Chapter 16: Statistical Analyses

What is Descriptive Statistics (DS), and what is its objective?
- Descriptive statistics is a statistical computation describing ether the characteristics of a sample or the relationship among variables in a sample.
- Objective: DS summarizes a set of sample observations or the association between two variables into measures of proportionate reduction of error (PRE)

PRE – A logical model for assessing the strength of a relationship by asking how much knowing values on one variable would reduce our errors in guessing values in the other.

There are 3 models of PRE:

Nominal Variables – if two variables consist of nominal data (ex. Gender, religious affiliation, race) you can substitute each variable with a lambda (λ) to measure the exact value in proportion to the overall distribution.

Example: Of the group of 500 students, who attended the conference, 375 students are supporters of the Republican Party and 125 students were supporters of the Democratic Party. If you were to have guessed how many students are affiliated with the Republican Party or the Democratic Party, the exact value in proportion to the overall distribution of Democratic Students will be .25. λ = .25.

Ordinal Variables – Ordinal data (social class, religiosity, and alienation) measure a relationship between two variables, and uses the symbol gamma (γ) to guess values on one variable by knowing values on another.

Example from the book: Check for correlation. Are the variables showing a negative or positive relationship?

Let’s say you suspect that religiosity is positively related to political conservatism, and if Person A is more religious than Person B, you guess that A is also more conservative than B. In a negatively related correlation, Person A is more religious than Person B, but A is less conservative than B.

Interval / Ratio Variables – one measurement for interval/ratio variables is Pearson’s product-moment correlation (r), which is based on guessing the value of one variable by knowing another, or how closely you can guess the value of one variable through your knowledge of the value of another. For continuous interval or ratio variables, it is unlikely that you could predict the precise value of the variable.