USE OF A LOG-LINEAR MODEL TO COMPUTE THE EMPIRICAL SURVIVAL CURVE FROM INTERVAL-CENSORED DATA, WITH APPLICATION TO DATA ON TESTS FOR HIV POSITIVITY

We describe how a log-linear model can be used to compute the nonparametric maximum likelihood estimate of the survival curve from interval-censored data. This permits such computation to be performed with the aid of readily available statistical software such as GLIM or SAS. The method is illustrated with reference to data from a cohort of Danish homosexual men, each of whom was tested for HIV positivity on one or more of six possible follow-up times.     

Work–home conflict and facilitation across four different family structures in Norway

The purpose of this study was to examine how work–home conflict and facilitation vary among people living in different family structures in Norway, here conceptualized as: two-parent families; single parents; childless couples; and singles. The study used data from a Norwegian study on occupational health (N=2414). We hypothesized that respondents living in two-parent families experience more work–home conflict and facilitation than others due to more complex role expectations. Similarly, we hypothesized that the effect of workload and autonomy on work–home conflict and facilitation would be stronger among this group. The results indicate that conflict between work and home life are more profound among those living in two-parent families and among single parents than among childless couples and singles. Work-to-home facilitation did not vary by family structure, whereas the childless couples reported more home-to-work facilitation. Furthermore, with a few exceptions the effects of workload and autonomy on work–home conflict and facilitation did not differ by family structure.