You can not infer causation definitively

(i.e. draw causal conclusions)

- neither produce true experimental data

- neither manipulate variable

two groups and one outcome variable

(e.g. "Are there gender differences in kidergarteners fine motor skill prficiency?")

lack of randomization, manipulation, and control

it may be possible that the groups are different on some other major variable besides the target variable of interest, and this other variable may be the cause of the observed difference between the groups.

statistical adjustment of the dependent variable scores.

Analysis of covariance, or ANCOVA, is a statistical procedure used to equate groups for preexisting differences on the dependent measure.

(e.g. Lori is doing a causal-comparative study on whether valedictorians from private high schools are more likely to go to Ivy League colleges than valedictorians from public high schools. She believes that students from private schools have a financial advantage.)

self-confidence and popularity are related.

Although a relation is clear, causal conclusions cannot be drawn. Popularity may cause self-confidence, self-confidence may cause popularity, or something else may cause both self-confidence and popularity.

lack of randomization

Without random assignment, the groups are more likely to be different on some important variable (e.g., gender, experience, age) other than the variable under study. Matched groups control for this problem because they are similar with respect to the identified extraneous variable.

A major problem with pair-wise matching is that invariably some participants have no match and must therefore be eliminated from the study. If the population is small, finding an appropriately sized sample can be difficult.

the study is not generalizable to a larger population.

The concern when studying a homogeneous sample is that the results may not be generalizable to a larger population with more diverse characteristics.

causal-comparative research involves comparisons, whereas correlational research involves relations

causal-comparative studies involve two (or more) groups of participants and one grouping variable.

correlational studies typically involve two (or more) variables and one group of particpants

In causal-comparative research the groups are already formed and already differ in terms of the variable in question.

In experimental research the researcher can randomly form groups and manipulate in independent variable

the t test, which is used to determine whether the scores of two groups are significantly different from one another

analysis of variance, used to test for significant differences among the scores for three or more groups

chi square, used to see if an event occurs more frequently in one group than the other

The alleged cause-effect relation may be the effect, and vice versa, or a third factor may be the cause of both variables.

The way to determine the correct order of causality is to determine which one occured first.

1. matching

2. comparing homogenous groups or subgroups

3. analysis of covariance

"after the fact"

because both the effect and the alleged cause have already occured and must be studied in retrospect

a characteristic of a subject or organism

(e.g. age, sex, ethnicity)

variables are a characteristic of a subject or organism that cannot be directly controlled

Causal-comparative studies allow for group comparison on variables of interest

Causal-comparative research permits investigation of the potential effects of a number of educational variables that cannot be studied experimentally (e.g., intelligence, motivation, socio-economic status, gender).