PSY 307 Statistics for the Behavioral Sciences

1
PSY 307 Statistics for the Behavioral Sciences

• Chapter 1

2
What is Statistics

• A tool for discovering relationships and patterns
  in data.
• A way of describing and comparing behavior of
  groups.
• A way of presenting and supporting arguments
  empirically.

3
Two Kinds of Statistics

• Descriptive statistics tools for organizing and
  summarizing observations.
• Tables, graphs, averages
• Inferential statistics tools for generalizing
  beyond the actual observations.
• Hypothesis tests (t-test, ANOVA)

4
Two Types of Data

• The type of statistic used depends on whether
  data are numbers or words (or codes).
• Quantitative any single observation is an
  amount or a count.
• Ranks relative standing, order
• Qualitative any single observation is a class
  or category.

5
Numerical Codes

• When data consists of classes or categories,
  sometimes numbers can be used to replace category
  names.
• Male 1, Female 2
• Yes 1, No 2

6
What is a Variable

• Variable a characteristic or property that can
  take on different values.
• Constant an observation that has only one
  value.
• Any single observation in a data set.

7
Types of Variables

• Discrete isolated numbers separated by gaps.
• Most counts
• Continuous values have no restrictions.
• Weight, reaction times
• Rounded off continuous variables are approximate.
• Rounding creates gaps.

8
Variables in Research

• Independent variable the variable manipulated
  by the investigator.
• May be used to define groups.
• Used to test hypotheses about causation.
• Dependent variable the variable measured,
  counted, or recorded by the investigator.
• The outcome.
• Confound an uncontrolled variable that varies
  with the independent variable.

9
Multiple Dependent Variables

• Sometimes variables of interest cannot be
  manipulated (e.g., sex, poverty) but only
  measured.
• Correlation studies -- studies with multiple
  dependent variables.
• Goal is to identify relationships among the
  dependent variables measured.
• Often used in observational research.