Sexual functioning and practices in a multi-ethnic study of midlife women: baseline results from SWAN

This study examined the sexual practices and function of midlife women by ethnicity (African American, Caucasian, Chinese, Hispanic, Japanese) and menopausal status. Sexual behavior was compared in 3,262 women in the baseline cohort of SWAN. Participants were 42 to 52 years old, premenopausal or early perimenopausal, and not hysterectomized or using hormones. Analysis used multivariate proportional odds regression. In our sample, 79% had engaged in sex with a partner in the last 6 months, and a third considered sex to be very important. Common reasons for no sex (n = 676) were lack of partner (67%), lack of interest (33%), and fatigue (16%). Compared with Caucasians, Japanese and Chinese women were less likely, and African Americans more likely, to report sex as very important (p < 0.005). Significant ethnic differences were found for frequency of all practices. Perimenopause status was associated only with higher frequencies of masturbation and pain during intercourse.     

Bipolar disorder in children

This article presents an overview of bipolar disorder (BPD) in children, a condition that only recently has been recognized as a legitimate diagnosis. Bipolar disorder in children is underrecognized for many reasons including lack of awareness, diagnostic confusion, and the different clinical picture in children. Available data strongly suggest that prepubertal childhood BPD is a non-episodic, chronic, rapid cycling, mixed manic state. It may be comorbid with attention-deficit/hyperactivity disorder (ADHD) and conduct disorder (CD) or it may demonstrate features of ADHD and CD, further complicating recognition and subsequent treatment. Treatment issues are discussed, and some reasons for the urgency of early recognition and treatment are explained.     

Gradient boosting for distributional regression: faster tuning and improved variable selection via noncyclical updates

We present a new algorithm for boosting generalized additive models for location, scale and shape (GAMLSS) that allows to incorporate stability selection, an increasingly popular way to obtain stable sets of covariates while controlling the per-family error rate. The model is fitted repeatedly to subsampled data, and variables with high selection frequencies are extracted. To apply stability selection to boosted GAMLSS, we develop a new “noncyclical” fitting algorithm that incorporates an additional selection step of the best-fitting distribution parameter in each iteration. This new algorithm has the additional advantage that optimizing the tuning parameters of boosting is reduced from a multi-dimensional to a one-dimensional problem with vastly decreased complexity. The performance of the novel algorithm is evaluated in an extensive simulation study. We apply this new algorithm to a study to estimate abundance of common eider in Massachusetts, USA, featuring excess zeros, overdispersion, nonlinearity and spatiotemporal structures. Eider abundance is estimated via boosted GAMLSS, allowing both mean and overdispersion to be regressed on covariates. Stability selection is used to obtain a sparse set of stable predictors.     

Sociologists in the Press

Stimulated by debates on public sociology in the recent years I studied contributions of sociologists in daily newspapers in Austria. Although sociologists are rather present in the Austrian press, I argue this remains without noticeable effects on public opinion formation; the topics sociologists write and talk about are rather arbitrary and they lack factual content. Although my data refers to sociologists in the Austrian press, the study’s conclusions might be true to the wider sociological community: Through such exposure, a public profile of sociology cannot evolve. Furthermore, the article discusses criteria that prevent and complicate the relationship between sociologists and the press: avoidance of publicity, the problem of values and ideology, incompatibilities of language-games, divergence of relevance criteria, and deficient cultural empathy.     

Sectors of activity, topography, and parasitism in home areas of New Guinea coarse-haired rats, and Trombiculidae (Acarina)

Summary Home areas of hosts are, in effect the gardens in which parasite populations grow. The parasites flourish in response to the kind and amount of host activity modified, of course, by the habitat, and become microcommunities supported by their host and its artifacts. When scatter diagrams of points at which hosts have been observed are divided by median major and minor axes, and when the resulting four quarters, designated A, B, C, D, corresponding to concentration of points in the quarters, the relative concentration usually is: A>B>C>D. The concentration of observed points also is generally greatest nearest the major axis and frequently, but not always, near the median center. Nests of hosts, hence nest-parasites, appear generally to be near the center. For the host examined in detail here, the New Guinea coarse-haired rat, mostLeptotrombidium deliensis appear to have been acquired in the AB sector of the host's home areas but a greater diversity of chiggers is acquired in the CD sector. It is postulated that, ifL. akamushi had been present, it would have occurred in the CD sector where, though the observed concentration of host activity was least, the mixed grassforb and shrub habitat would have been more suitable than in the AB sector.Gahrliepia pingue, C. ewingi, Schoengastia blestowei andS. schueffneri, appear also to be more abundant in the CD sector than in the AB sector. The chiggers themselves have home clusters, or lairs, and adjacent areas of activity (home areas) somewhat resembling those of the hosts. This analysis of sectors of home areas was begun in 1965 under provision of a research grant (AI-03653) by the National Institutes of Health to the Division of Parasitology, University of California at Berkeley. It was completed during 1967.     

Compositional Tables Analysis in Coordinates

Compositional tables – a continuous counterpart to the contingency tables – carry relative information about relationships between row and column factors; thus, for their analysis, only ratios between cells of a table are informative. Consequently, the standard Euclidean geometry should be replaced by the Aitchison geometry on the simplex that enables decomposition of the table into its independent and interactive parts. The aim of the paper is to find interpretable coordinate representation for independent and interaction tables (in sense of balances and odds ratios of cells, respectively), where further statistical processing of compositional tables can be performed. Theoretical results are applied to real‐world problems from a health survey and in macroeconomics.