Hypotheses shaped by family stress and resource theories about the impact of household economic indicators on the risk of violence against women in intimate relationships are tested with a data set built from the initial two waves of the National Survey of Families and Households (NSFH) and the 1990 U.S. Census. Measures of employment status, job conditions, and economic well‐being for male and female partners are examined with logistic regression analyses as predictors of the odds of male‐to‐female intimate violence. Results underline the importance that partners attach to each other's work performance and their feelings of financial well‐being in assessing whether job holding and household income serve to elevate or reduce the risk of intimate partner violence toward women.

This article attempted to identify neighborhood- partner- and individual-level factors that may lead to male-to-female partner violence. The relevant dimensions of community context were derived from social disorganization theory that indicates that disorganized areas lack formal and informal controls that inhibit street violence. Social disorganization theory predicts that there is a higher rate of violence and social isolation in disorganized areas. At the individual level, women who experience less social support will more likely be victimized by partner violence. This article investigates the direct and interactive effects of social disorganization measures and variables from social support theories on male-to-female partner violence. The data come from Wave 2 of the National Survey of Families and Households completed in 1994 and from the 1990 census. Logistic regression was used to assess variation in the independent and dependent variables between and within neighborhood types. Results indicate that neighborhood effects interact with partner- and individual-level characteristics for a more complete explanation for male-to-female partner violence.

Although widowhood has a strong depressive effect for older men, its effect for women is nonsignificant, and it explains a small proportion of the variation in depressive symptomatology. This suggests that most people, particularly women, adapt relatively well in the long run.

Many procedures in SAS/STAT ® can be used to perform logistic regression analysis: CATMOD, GENMOD,LOGISTIC, and PROBIT. Each procedure has special features that make it useful for certain applications. For most applications, PROC LOGISTIC is the preferred choice. It fits binary response or proportional odds models, provides various model-selection methods to identify important prognostic variables from a large number of candidate variables, and computes regression diagnostic statistics. This tutorial discusses some of the problems users encountered when they used the LOGISTIC procedure.

ࡗ Union Formation and Depression: Selection and Relationship EffectsMany studies have established that married people fare better than their never-married counterparts in terms of psychological well-being. It is still unclear, however, whether this advantage is due primarily to beneficial effects of marriage or to the selection of psychologically healthier individuals into marriage. This study employs data on young adults from both waves of the National Survey of Families and Households to test hypotheses based on both selection (N ϭ 878) and relationship (N ϭ 722) effects. Further, we differentiate union formation into cohabitation and marriage with and without prior cohabitation. Results indicate no evidence of selection of less depressed persons into either marriage or cohabitation, but a negative effect of entry into marriage on depression, particularly when marriage was not preceded by cohabitation.Many studies have demonstrated that married persons fare better than the never-married on psychological well-