NotesFAQContact Us
Search Tips
ERIC Number: ED171738
Record Type: RIE
Publication Date: 1978-Oct
Pages: 28
Abstractor: N/A
Reference Count: 0
Using Log Linear Analysis for Categorical Family Variables.
Moen, Phyllis
The Goodman technique of log linear analysis is ideal for family research, because it is designed for categorical (non-quantitative) variables. Variables are dichotomized (for example, married/divorced, childless/with children) or otherwise categorized (for example, level of permissiveness, life cycle stage). Contingency tables are then constructed and analyzed so that variables are cross-classified; estimates of the main effects of each variable, as well as interaction effects, are determined. This technique permits sophisticated (multivariate) analysis of quantitative data, testing of interactions, and examination of the relationships among variables, without designating one as the dependent variable. There are limitations to the Goodman technique, associated with the principal statistics used (Pearson's Chi-square and the likelihood ratio statistic), and with categorizing variables. Logit analysis, a type of log linear analysis, is used to predict a dependent variable. First, the relative importance of race, sex of family head, and life cycle stage in predicting the dependent variable, financial expectation, is examined; second, interaction effects are measured, that is, the existence of a conditional relationship among two or more predictor variables and the dependent variable. The best prediction model included the direct effects of life cycle stage and sex of breadwinner. (CP)
Publication Type: Speeches/Meeting Papers; Reports - Research
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A
Identifiers: Categorical Data; Log Linear Analysis
Note: Paper presented at the Annual Meeting of the National Council on Family Relations (Philadelphia, Pennsylvania, October, 1978)