Search

A rapidly growing number of algorithms are available to researchers who apply statistical or machine learning methods to answer social science research questions. The unique advantages and limitations of each algorithm are relatively well known, but it is not possible to know in advance which algorithm is best suited for the particular research question and the data set at hand. Typically, researchers end up choosing, in a largely arbitrary fashion, one or a handful of algorithms. In this article, we present the Super Learner--a powerful new approach to statistical learning that leverages a variety of data-adaptive methods, such as random forests and spline regression, and systematically chooses the one, or a weighted combination of many, that produces the best forecasts. We illustrate the use of the Super Learner by predicting violence among inmates from the 2005 Census of State and Federal Adult Correctional Facilities. Over the past 40 years, mass incarceration has drastically weakened prisons' capacities to ensure inmate safety, yet we know little about the characteristics of prisons related to inmate victimization. We discuss the value of the Super Learner in social science research and the implications of our findings for understanding prison violence.

Abstract: Social network approach has conceptually and empirically improved research on HIV/ AIDS by counterbalancing the individualized concepts of sexual decision-making. In the current study, associations between the structural characteristics [...]

Using the National Comorbidity Survey Replication, this study explores the effects of incarceration on the subjective status of men, based on the MacArthur Scale of Subjective Social Status (or the ''ladder"). The study makes several crucial distinctions. First, it distinguishes subjective status in one's community and subjective status in the United States generally, thereby exploring differences between the local and global meanings of incarceration. Second, it distinguishes crime, arrest, and incarceration, thereby exploring the added effects of contact with the criminal justice system, apart from offending. The results reveal that contact with the criminal justice system results in progressively lower status: those who committed a crime report lower subjective status than those who did not, those who were arrested report lower status than those who only committed a crime, and those who were incarcerated report lower status than those who were only arrested. Although these differences along the crime-to-sentencing continuum are strong, the effects of crime, arrest, and incarceration are, if anything, even stronger among African Americans than whites. The results also suggest that the effects of incarceration are similar to-if not greater than-those of other stigmatizing statuses, including having spent time in a psychiatric hospital. The effects of arrest and incarceration are not driven entirely by the social or economic consequences of incarceration, although these consequences further deflate subjective status among former inmates. [ABSTRACT FROM AUTHOR]

Aim: To determine changes in sexual behaviors and other relevant characteristics related to human immunodeficiency virus (HIV) and sexually transmitted infection (STI) risks among young Croatian adults., Method: We surveyed adults aged 18-24 in 2005 (n=1092) and 18-25 in 2010 (n=1005). Both samples were probabilistic and stratified by county, settlement size, age, and gender. The samples were non-matched. Trained interviewers conducted structured face-to-face interviews in participants' households. The part of the questionnaire assessing sensitive information was self-administered., Results: A majority of participants at both survey points (85.2%-86.2%) were sexually active. Median age at sexual debut (17 years) remained unchanged. Lifetime number of sexual partners was also stable. More women than men reported only one lifetime sexual partner. The prevalence of condom use at first intercourse increased (from 62.6 to 70%, P=0.002), while the prevalence of condom use at most recent sexual intercourse remained stable (54% in 2005 and 54.7% in 2010). Consistent condom use also remained unchanged. Consistent condom use in the past year was reported by 19.2% participants in 2005 nad 20% in 2010.. At both survey points for both genders, consistent condom use was associated with age (odds ratio [OR] W2005=0.74, P=0.004; ORW2010=0.72, P<0.001; ORM2005=0.73, P<0.001; ORM2010=0.80,P=0.006), negative attitudes toward condom use (ORW2005=0.84, P=0.001; ORW2010=0.90, P=0.026; ORM2005=0.92, P=0.032; ORM2010=0.90, P=0.011)), and condom use at first intercourse (ORW2005=3.87, P<0.001; ORW2010=4.64, P<0.001; ORM2005=5.85, P<0.001; ORM2010=4.03, P<0.001). In the observed period, HIV/AIDS knowledge was stable., Conclusion: Risky sexual practices remain common among young Croatian adults. Given the recently reported STI prevalence rates in this age cohort, introduction of school-based sex education that would focus on protective behavioral and communication skills seems to be of crucial epidemiological importance.