Design and analysis considerations for comparing dynamic treatment regimens with binary outcomes from sequential multiple assignment randomized trials

In behavioral, educational and medical practice, interventions are often personalized over time using strategies that are based on individual behaviors and characteristics and changes in symptoms, severity, or adherence that are a result of one's treatment. Such strategies that more closely mimic real practice, are known as dynamic treatment regimens (DTRs). A sequential multiple assignment randomized trial (SMART) is a multi-stage trial design that can be used to construct effective DTRs. This article reviews a simple to use ‘weighted and replicated’ estimation technique for comparing DTRs embedded in a SMART design using logistic regression for a binary, end-of-study outcome variable. Based on a Wald test that compares two embedded DTRs of interest from the ‘weighted and replicated’ regression model, a sample size calculation is presented with a corresponding user-friendly applet to aid in the process of designing a SMART. The analytic models and sample size calculations are presented for three of the more commonly used two-stage SMART designs. Simulations for the sample size calculation show the empirical power reaches expected levels. A data analysis example with corresponding code is presented in the appendix using data from a SMART developing an effective DTR in autism.     

A joint model of cancer incidence,metastasis, and mortality

Many diseases, especially cancer, are not static, but rather can be summarized by a series of events or stages (e.g. diagnosis, remission, recurrence, metastasis, death). Most available methods to analyze multi-stage data ignore intermediate events and focus on the terminal event or consider (time to) multiple events as independent. Competing-risk or semi-competing-risk models are often deficient in describing the complex relationship between disease progression events which are driven by a shared progression stochastic process. A multi-stage model can only examine two stages at a time and thus fails to capture the effect of one stage on the time spent between other stages. Moreover, most models do not account for latent stages. We propose a semi-parametric joint model of diagnosis, latent metastasis, and cancer death and use nonparametric maximum likelihood to estimate covariate effects on the risks of intermediate events and death and the dependence between them. We illustrate the model with Monte Carlo simulations and analysis of real data on prostate cancer from the SEER database.     

A Texas Peasantry? Black Smallholders in the Texas Sugar Bowl, 1865–1890

This article examines a small community of former slaves in Texas's leading sugar-producing county and argues that local conditions fostered the growth of a Caribbean-style ‘reconstituted peasantry’. Using local sources to compile a database of 79 African American landowners, it traces the postwar decline of the sugar plantations, the process of black land acquisition and the smallholders' strategies for survival. The smallholders' position, however, was precarious, and most lost their lands at the close of the nineteenth century. The piece concludes by suggesting that more intensive local research into former-slave communities may force a reconsideration of the notion that all American slaves became landless wage labourers.     

Dimensions of mental health: Life satisfaction,positive affect,anxiety and depression

Psychological well-being and psychological distress are often regarded as distinct, if not orthogonal dimensions of mental health. Based on analyses in this paper, we consider the distinction misleading. Four dimensions seem worth measuring in general population surveys: life satisfaction, positive affect, anxiety and depression. Furthermore, one of the well-being dimensions, life satisfaction, is quite strongly correlated with a distress dimension, depression. A person is unlikely to be both satisfied with life and depressed, but may be satisfied and anxious. The paper is based on convergent validity (exploratory and confirmatory factor analyses) and divergent validity assessments of a range of widely used measures, which were included in the Victorian Quality of Life Panel Survey, 1987.     

Aggregate population and economic growth correlations: The role of the components of demographic change

The results of recent correlations showing a negative impact of population growth on economic development in cross-country data for the 1980s, versus “nonsignificant” correlations widely found for the 1960s and 1970s, are examined with contemporaneous and lagged components of demographic change, convergence-type economic modeling, and several statistical frameworks. The separate impacts of births and deaths are found to be notable but offsetting in the earlier periods. In contrast, the short-run costs (benefits) of births (mortality reduction) increase (decrease) significantly in the 1980s, and the favorable labor-force impacts of past births are not fully offsetting.     

Evolution of recent economic-demographic modeling: A synthesis

This paper develops a flexible framework for modeling population's role in economic growth by assessing and extending a rendering suggested by several Harvard economists. Our framework includes a ``productivity' model explaining output-per-worker growth and a ``translation' model translating that growth into per-capita terms. We specify a core economic model and several ``enriched' demographic variants that include dependency, size, and density. Regressions using a cross-country panel spanning the period 1960-1995 reveal that combined impacts of demographic change have accounted for approximately 20% of per capita output growth impacts, with larger shares in Asia and Europe. An earlier draft of this paper was presented at a conference on ``Population Change, Labor Market Transition and Economic Development in Asia,' Institute of Economics, Academia Sinica, Taipei, Taiwan, 6–9 December 2002. A pre-publication version of this paper will be presented at a joint conference (by COE/JEPA) entitled ``Towards a new economic paradigm: Declining population growth, labor market transition and economic development under globalization,' held at the Awaji Yumebutai International Conference Center, Kobe, Japan, 17–19 December 2005. We have benefited from comments by Michelle Connolly, Andrew Mason, Pietro Peretto, Warren Sanderson, Alessandro Tarozzi, Jeffrey Williamson, and two anonymous referees. Responsible editor: Junsen Zhang.     

Sexual attitudes and contraception among females across five college samples.

The relationships among sexual attitudes, sexual and contraceptive behavior, and responses to statements about sexual topics are explored using data obtained in the Sexual Opinion Survey concerning 772 women attending four midwestern U.S. universities in the period 1977-1979. "Associations generally occurred between the expression of more positive sexual attitudes and the reporting of behaviors and attitudes supportive of effective contraceptive activity."     

Feasibility and acceptability of using a web-based contraceptive support tool in a university health clinic

Abstract

Objective: To evaluate feasibility of integrating Bedsider.org, a web-based contraceptive decision support tool, at a university health clinic (UHC). Participants: Female students (ages 18–29) seeking contraceptive care at the UHC were enrolled in September 2015 (n?=?46). Methods: Providers recruited eligible patients during reproductive healthcare visits and introduced Bedsider. Surveys were administered immediately following the visit and a follow-up 2–4?weeks later. Electronic health records through 6?weeks post-enrollment were extracted. Results: Most patients had positive views toward Bedsider and appreciated receiving information during their UHC encounters. None were using long-acting reversible contraceptives (LARC) at enrollment. At follow-up, two patients self-reported IUD use. Among those recently sexually active, use of more effective contraceptive methods increased from 65% to 74%; 11% had initiated or were scheduled to receive a LARC. Conclusion: Bedsider can be feasibly integrated into UHC visits and may support women’s selection of more effective contraceptive methods, including LARCs.     

The Alliance in Relationship Education Programs

Couple relationship education (CRE) programs are associated with positive romantic relationship outcomes; however, the mechanisms by which these gains occur are less understood. The current study (122 couples) utilized actor–partner modeling to examine the association between the therapeutic alliance and dedication and negative and positive communication for racial/ethnic minority couples. Additionally, we examined whether gender and delivery format moderated these relationships. Results demonstrated that both men's and women's alliance scores were significantly related to their own outcomes. Higher ratings of alliance were related to partner outcomes for men only. The association between partners' alliance and dedication outcomes was stronger within the group format as compared to the couple format. Implications for leaders of CRE programs are offered.