Sociological computing: An opportunity missed?

Rapid advances in sociological computing are changing virtually every aspect of scholarly sociological work. These changes offer an opportunity for sociologists to improve the quality of their work and bring new insights and approaches to bear on important sociological problems. Nevertheless, sociologists display a profound ambivalence toward computer work by other sociologists. Left unchecked, this ambivalence threatens to turn sociological computing into an opportunity missed. Inadequate rewards, lack of training, and a general failure to understand the importance of computing in sociology threaten to stifle the development of quality soft-ware, push sociologists competent in computing into other fields, and jeopardize the quality of sociological scholarship. This article documents these ambivalent tendencies and proposes reasonable steps the discipline should take to assure that sociological computing does not become an opportunity missed.     

A structured framework for assessing sensitivity to missing data assumptions in longitudinal clinical trials

The objective of this research was to demonstrate a framework for drawing inference from sensitivity analyses of incomplete longitudinal clinical trial data via a re‐analysis of data from a confirmatory clinical trial in depression. A likelihood‐based approach that assumed missing at random (MAR) was the primary analysis. Robustness to departure from MAR was assessed by comparing the primary result to those from a series of analyses that employed varying missing not at random (MNAR) assumptions (selection models, pattern mixture models and shared parameter models) and to MAR methods that used inclusive models. The key sensitivity analysis used multiple imputation assuming that after dropout the trajectory of drug‐treated patients was that of placebo treated patients with a similar outcome history (placebo multiple imputation). This result was used as the worst reasonable case to define the lower limit of plausible values for the treatment contrast. The endpoint contrast from the primary analysis was ? 2.79 (p = .013). In placebo multiple imputation, the result was ? 2.17. Results from the other sensitivity analyses ranged from ? 2.21 to ? 3.87 and were symmetrically distributed around the primary result. Hence, no clear evidence of bias from missing not at random data was found. In the worst reasonable case scenario, the treatment effect was 80% of the magnitude of the primary result. Therefore, it was concluded that a treatment effect existed. The structured sensitivity framework of using a worst reasonable case result based on a controlled imputation approach with transparent and debatable assumptions supplemented a series of plausible alternative models under varying assumptions was useful in this specific situation and holds promise as a generally useful framework. Copyright © 2012 John Wiley & Sons, Ltd.     

A tutorial on rank-based coefficient estimation for censored data in small- and large-scale problems

The analysis of survival endpoints subject to right-censoring is an important research area in statistics, particularly among econometricians and biostatisticians. The two most popular semiparametric models are the proportional hazards model and the accelerated failure time (AFT) model. Rank-based estimation in the AFT model is computationally challenging due to optimization of a non-smooth loss function. Previous work has shown that rank-based estimators may be written as solutions to linear programming (LP) problems. However, the size of the LP problem is O(n ²+p) subject to n ² linear constraints, where n denotes sample size and p denotes the dimension of parameters. As n and/or p increases, the feasibility of such solution in practice becomes questionable. Among data mining and statistical learning enthusiasts, there is interest in extending ordinary regression coefficient estimators for low-dimensions into high-dimensional data mining tools through regularization. Applying this recipe to rank-based coefficient estimators leads to formidable optimization problems which may be avoided through smooth approximations to non-smooth functions. We review smooth approximations and quasi-Newton methods for rank-based estimation in AFT models. The computational cost of our method is substantially smaller than the corresponding LP problem and can be applied to small- or large-scale problems similarly. The algorithm described here allows one to couple rank-based estimation for censored data with virtually any regularization and is exemplified through four case studies.     

Comparing Equal-Tail Probability and Unbiased Confidence Intervals for the Intraclass Correlation Coefficient

The conventional confidence interval for the intraclass correlation coefficient assumes equal-tail probabilities. In general, the equal-tail probability interval is biased and other interval procedures should be considered. Unbiased confidence intervals for the intraclass correlation coefficient are readily available. The equal-tail probability and unbiased intervals have exact coverage as they are constructed using the pivotal quantity method. In this article, confidence intervals for the intraclass correlation coefficient are built using balanced and unbalanced one-way random effects models. The expected length of confidence intervals serves as a tool to compare the two procedures. The unbiased confidence interval outperforms the equal-tail probability interval if the intraclass correlation coefficient is small and the equal-tail probability interval outperforms the unbiased interval if the intraclass correlation coefficient is large.     

Urinary Excretion of Chromium Following Ingestion of Chromite-Ore Processing Residues in Humans: Implications for Biomonitoring

Biomonitoring programs for urinary chromium (Cr) typically attempt to evaluate occupational exposure via the inhalation route. This study investigated whether Cr can be detected in the urine of people following the ingestion of soils that contain relatively high concentrations of chromium in chromite ore processing residue (COPR). To evaluate the reasonableness of using urinary monitoring to assess environmental exposure, six volunteers ingested 400 mg of soil/day (low-dose group), two others ingested 2.0 g of soil/day (high-dose group) for 3 consecutive days, and one person ingested a placebo on each of 3 days. The soil and COPR mixture contained concentrations of total chromium (Cr) and hexavalent chromium [Cr(VI)] of 103 ± 20 and 9.3 ± 3.8 mg/kg, respectively. Therefore, the low-dose group ingested 41 μg Cr/day [including 3.7 μg Cr(VI)] and the high-dose group ingested 206 μg Cr/day [including 18.6 μg Cr(VI)] on each of 3 consecutive days. All urine samples were collected and analyzed individually for total Cr on the day prior to dosing, during the 3 days of dosing, and up to the first void 48 h after the last dose. No significant increases in urinary Cr excretion were found when background excretion data were compared with data following each of the 3 days of dosing or in daily mean urine concentrations of the high- vs the low-dose groups. It appears that Cr present in a soil and COPR mixture at Cr doses up to 200 μg/day is not sufficiently bioavailable for biomonitoring of urine to be informative. These results are consistent with previously published findings suggesting that incidental exposure to dusts and soils containing comparable levels of Cr will not result in increased concentrations of Cr in urine.     

Life Balance and Work Addiction Among NCAA Administrators and Coaches

Intercollegiate athletics represent an industry prone to challenges of work addiction and life balance. Work addiction and life balance domains in male and female intercollegiate athletic coaches and administrators (N = 245) were examined using multiple regression analysis. Higher levels of stress/anxiety, sleep disturbance, and career satisfaction and lower levels of quality of relationships and friendships were the strongest predictors of work addiction. Counseling focused on reducing the negative aspects of work addiction, while maintaining job performance, may benefit this population.     

Parents of Children with Attention Deficit/Hyperactivity Disorder: A Meta-Synthesis,Part II

In 2011 6.4 million children in the United States ages four to 17 years had a diagnosis of ADHD. Quantitative studies have indicated that parenting stress for parents of children diagnosed with ADHD is high. The purpose of the current meta-synthesis was to conduct a comprehensive review of both the published and unpublished qualitative studies involving the experience of parents raising children diagnosed with ADHD. Searches in online scholarly databases yielded an initial 1217 hits, which were narrowed down to eighty studies that met the criteria. A “meta-ethnography” framework was used for the synthesis. Results of the first part of the analysis were reported in Corcoran et al. (2016) and had to do with the personal impact on parents. The themes in Part II have to do with the processes parents go through in accepting the diagnosis of ADHD and in deciding whether their children should take medication. Parents struggled to make sense of their child’s problems and came to terms with the diagnosis in a series of stages. Regarding medication use, parental attitudes varied greatly, with both costs and benefits noted. Though there was considerable ambivalence towards medication use, some parents reported relief after their child began using medication. Implications from this study are that providers should recognize the processes involved in making decisions about an ADHD diagnosis and the use of medication. Social workers should allow sensitive exploration of parents’ attributions and understanding of their children’s behavior and level of acceptance of the diagnosis. Keeping an ethical and critical stance toward the use of medication, social workers should also have full exploration with parents around the potential benefits and risks associated with the treatment of their children’s ADHD, taking into account parents’ preferences.     

Maternal Lifetime Trauma Exposure,Prenatal Cortisol,and Infant Negative Affectivity

Little research has examined the impact of maternal lifetime trauma exposure on infant temperament. We examined associations between maternal trauma history and infant negative affectivity and modification by prenatal cortisol exposure in a sociodemographically diverse sample of mother–infant dyads. During pregnancy, mothers completed measures of lifetime trauma exposure and current stressors. Third‐trimester cortisol output was assessed from maternal hair. When infants were 6 months old, mothers completed the Infant Behavior Questionnaire‐Revised. In analyses that controlled for infant sex and maternal age, education, race/ethnicity, and stress during pregnancy, greater maternal trauma exposure was associated with increased infant distress to limitations and sadness. Higher and lower prenatal cortisol exposure modified the magnitude and direction of association between maternal trauma history and infant rate of recovery from arousal. The association between maternal trauma history and infant distress to limitations was somewhat stronger among infants exposed to higher levels of prenatal cortisol. The analyses suggested that maternal lifetime trauma exposure is associated with several domains of infant negative affectivity independently of maternal stress exposures during pregnancy and that some of these associations may be modified by prenatal cortisol exposure. The findings have implications for understanding the intergenerational impact of trauma exposure on child developmental outcomes.     

Risky Business: Is There an Association between Casual Sex and Mental Health among Emerging Adults?

A multiethnic sample of single, heterosexual, emerging-adult college students (N = 3,907) ages 18 to 25, from 30 institutions across the United States, participated in a study about identity, culture, psychological well-being, and risky behaviors. Given ongoing debates about the connection between casual sex and psychological adjustment, in the current study we assessed the cross-sectional association of participation in casual sex with psychological well-being and distress. A greater proportion of men (18.6%) compared to women (7.4%) reported having had casual sex in the month prior to assessment. Structural equation modeling indicated that casual sex was negatively associated with well-being (ß = .20, p < .001) and positively associated with psychological distress (ß = .16, p < .001). Gender did not moderate these associations. For emerging-adult college students, engaging in casual sex may elevate risk for negative psychological outcomes.     

Choice of the primary analysis in longitudinal clinical trials

Missing data, and the bias they can cause, are an almost ever‐present concern in clinical trials. The last observation carried forward (LOCF) approach has been frequently utilized to handle missing data in clinical trials, and is often specified in conjunction with analysis of variance (LOCF ANOVA) for the primary analysis. Considerable advances in statistical methodology, and in our ability to implement these methods, have been made in recent years. Likelihood‐based, mixed‐effects model approaches implemented under the missing at random (MAR) framework are now easy to implement, and are commonly used to analyse clinical trial data. Furthermore, such approaches are more robust to the biases from missing data, and provide better control of Type I and Type II errors than LOCF ANOVA. Empirical research and analytic proof have demonstrated that the behaviour of LOCF is uncertain, and in many situations it has not been conservative. Using LOCF as a composite measure of safety, tolerability and efficacy can lead to erroneous conclusions regarding the effectiveness of a drug. This approach also violates the fundamental basis of statistics as it involves testing an outcome that is not a physical parameter of the population, but rather a quantity that can be influenced by investigator behaviour, trial design, etc. Practice should shift away from using LOCF ANOVA as the primary analysis and focus on likelihood‐based, mixed‐effects model approaches developed under the MAR framework, with missing not at random methods used to assess robustness of the primary analysis. Copyright © 2004 John Wiley & Sons, Ltd.