Richard Breen Statistical Models of Association for Comparing Cross-Classifications Sociological Methods & Research 2008 36: 442-461.

February 7, 2010

In the analysis of cross-classified data, the quantities of interest are frequently odds ratios. Although odds ratios are functions of the interaction parameters in association models, the usual way of normalizing and identifying these parameters means that their relationship with the odds ratios of interest is indirect. This can lead to interpretative confusions. The author points to the benefits of defining the interaction parameters of a model to have a one-to-one relationship with the odds ratios of interest, thus overcoming problems of interpretation. Three examples are presented to illustrate the argument.

Key Words: log-linear and log-multiplicative models • odds ratios • crosstabulations • design matrices • comparative analysis

Iris Jerby, Moshe Semyonov, and Noah Lewin-Epstein, Capturing Gender-Based Microsegregation: A Modified Ratio Index for Comparative Analyses, Sociological Methods & Research 2005 34: 122-136.

February 7, 2010
Comparative studies of occupational sex segregation have employed a variety of measures to estimate the extent of segregation across labor markets. In this article, the authors focus on two intrinsic limitations of the ratio index, which is derived from the log-linear framework: singularity for totally segregated occupations and sensitivity near the extremes. To capture the real essence of gender occupational segregation, it is necessary to examine rather detailed occupational categories. Such detailed occupational classification poses a problem for the ratio index since small occupations are more likely to be mono-gender occupations. The authors propose an alternative modified index that resolves both the singularity and the sensitivity problems by employing the “first-order approximation” of the logarithmic function. The modified index makes it possible to compute measures of microsegregation for detailed occupational categories. The advantages of the proposed index for comparative microsegregation analyses are illustrated and discussed.

Key Words: segregation index • gender segregation • comparative analysis