Newest Articles

Structural nested mean models for assessing time-varying effect moderation

Almirall,D. — 2009

This article considers the problem of assessing causal effect moderation in longitudinal settings in which treatment (or exposure) is time varying and so are the covariates said to moderate its effect. Intermediate causal effects that describe time-varying causal effects of treatment conditional on past covariate history are introduced and considered as part of Robins' structural nested mean model. Two estimators of the intermediate causal effects, and their standard errors, are presented and discussed: The first is a proposed two-stage regression estimator. The second is Robins' G-estimator. The results of a small simulation study that begins to shed light on the small versus large sample performance of the estimators, and on the bias-variance trade-off between the two estimators are presented. The methodology is illustrated using longitudinal data from a depression study.

Lifestyle therapy changes and hypercholesterolemia: Identifying risk groups in a community sample of blacks and whites

BeLue,R. — 2009

OBJECTIVE: To examine diet and exercise lifestyle therapy change (LTC), behaviors and their relation to hypercholesterolemia in a community sample of Blacks and Whites. DESIGN: Latent class analysis (LCA) was employed to identify homogeneous subgroups of community dwelling Blacks and Whites related to LTC for hypercholesterolemia. LCA is a statistical technique used to identify subgroups of individuals who share a similar pattern of responses to a set of observations. The relation between hypercholesterolemia and latent class membership was assessed. PARTICIPANTS: Adults age 18 and over who participated in a county-level adaptation of the Behavioral Risk Factor Surveillance System. MAIN OUTCOME MEASURE: Hypercholesterolemia (absence or presence). RESULTS: Eleven unique latent classes of LTC behavior emerged from LCA models. Exercisers and Fat Reducers represented between 19% and 29% of each race-sex group. Latent class membership probabilities varied substantially across race and sex. Only Black women had a class of Contemplators (21.5%). Overall, men and Blacks with self reported hypercholesterolemia were more likely to engage only in fat reduction but not increase in vegetable consumption, reduction of fat or regular exercise (odds ratios range from 1.8-3.5). CONCLUSIONS: The distribution of diet and exercise related LTC behaviors in relation to self-reported hypercholesterolemia can help to identify, understand and tailor culturally and sex specific interventions based on the proportions of men and women in different latent classes.

A person-centered approach to individualizing a school-based universal prevention intervention

Caldwell,L. L. — 2009

Using item response theory to detect differential item functioning in health disparities research

Coffman,D. L. — 2009

Design of experiments with multiple independent variables: A resource management perspective on complete and reduced factorial designs

Collins,L. M. — 2009

An investigator who plans to conduct an experiment with multiple independent variables must decide whether to use a complete or reduced factorial design. This article advocates a resource management perspective on making this decision, in which the investigator seeks a strategic balance between service to scientific objectives and economy. Considerations in making design decisions include whether research questions are framed as main effects or simple effects; whether and which effects are aliased (confounded) in a particular design; the number of experimental conditions that must be implemented in a particular design and the number of experimental subjects the design requires to maintain the desired level of statistical power; and the costs associated with implementing experimental conditions and obtaining experimental subjects. In this article 4 design options are compared: complete factorial, individual experiments, single factor, and fractional factorial. Complete and fractional factorial designs and single-factor designs are generally more economical than conducting individual experiments on each factor. Although relatively unfamiliar to behavioral scientists, fractional factorial designs merit serious consideration because of their economy and versatility.

Sensitivities and specificities of diagnostic tests and infection prevalence of Schistosoma Haematobium estimated from data on adults in villages northwest of Accra, Ghana

Koukounari,A. — 2009

Substantial uncertainties surround the sensitivities and specificities of diagnostic techniques for urinary schistosomiasis. We used latent class (LC) modeling to address this problem. In this study, 220 adults in three villages northwest of Accra, Ghana were examined using five Schistosoma haematobium diagnostic measures: microscopic examination of urine for detection of S. haematobium eggs, dipsticks for detection of hematuria, tests for circulating antigens, antibody tests, and ultrasound scans of the urinary system. Testing of the LC model indicated non-invariance of the performance of the diagnostic tests across different age groups, and measurement invariance held for males and females and for the three villages. We therefore recommend the use of LC models for comparison between and the identification of the most accurate schistosomiasis diagnostic tests. Furthermore, microscopy and hematuria dipsticks were indicated through these models as the most appropriate techniques for detection of S. haematobium infection.

Transitions into and out of light and intermittent smoking during emerging adulthood

White,H. R. — 2009

INTRODUCTION: The purpose of this study was to examine transitions in smoking from adolescence into emerging adulthood and to identify factors that might influence these transitions, specifically, movement into and out of light and intermittent smoking. METHODS: This study used Markov models to examine movement across three stages of smoking (nonsmoking, light and intermittent smoking, and heavy smoking) from adolescence into emerging adulthood. Biannual data were collected from 990 young men and women from the 12th grade until 2 years after high school. RESULTS: At each timepoint, most youth were nonsmokers. Those who were heavy smokers in 12th grade had a 79% chance of also being heavy smokers 2 years after high school. Between 17% and 21% of participants were light and intermittent smokers at each timepoint, and the likelihood of remaining so at the next timepoint ranged from 56% to 72%. Less than one-half of the 12th-grade light and intermittent smokers were light and intermittent smokers 2 years later, and 3% of the sample were light and intermittent smokers across all assessments. Prevalence and transition rates did not differ by gender. College attendees reported less smoking than nonattendees before and after their transition to college, and attendees compared with nonattendees who smoked were less likely to transition from light and intermittent to heavy smoking and remain heavy smokers. Binge drinking was significantly related to 12th-grade smoking stage and to transitions from nonsmoking to smoking. Overall, few emerging adults maintained light and intermittent smoking consistently over time. DISCUSSION: Light and intermittent smoking during emerging adulthood may not be the same phenomenon as light and intermittent smoking in adulthood.

Variable selection for partially linear models with measurement errors

Liang,H. — 2009

This article focuses on variable selection for partially linear models when the covariates are measured with additive errors. We propose two classes of variable selection procedures. penalized least squares and penalized quantile regression, using the nonconvex penalized principle. The first procedure corrects the bias in the loss function caused by the measurement error by applying the so-called correction-for-attenuation approach. whereas the second procedure corrects the bias by using orthogonal regression. The sampling properties for the two procedures are investigated. The rate of convergence and the asymptotic normality of the resulting estimates are established. We further demonstrate that, with proper choices of the penalty functions and the regularization parameter. the resulting estimates perform asymptotically as well as an oracle property. Choice of smoothing parameters is also discussed. Finite sample performance of the proposed variable selection procedures is assessed by Monte Carlo simulation studies. We further illustrate the proposed procedures by an application.

A prospective longitudinal model of substance use onset among South African adolescents

Patrick,M. E. — 2009

Substance use onset among Colored adolescents between eighth and ninth grades in an urban area of Cape Town, South Africa was examined using latent transition analysis. Longitudinal self-report data regarding substance use (N= 1118, 50.9% female) were collected in 2004 and 2005. Results indicated that the pattern of onset was similar across genders; adolescents first tried either alcohol or cigarettes, followed by both, then dagga (cannabis), and then inhalants. The prevalence of lifetime cigarette use was slightly greater for females; dagga (cannabis) and inhalant use were greater for males. The similarity of developmental onset in the current sample to previous international work supports the promise of adapting prevention programs across contexts. The study's limitations are noted.

Comparison of a phased experimental approach and a single randomized clinical trial for developing multicomponent behavioral interventions

Collins,L. M. — 2009

BACKGROUND: Many interventions in today's health sciences are multicomponent, and often one or more of the components are behavioral. Two approaches to building behavioral interventions empirically can be identified. The more typically used approach, labeled here the classical approach, consists of constructing a likely best intervention a priori, and then evaluating the intervention in a standard randomized controlled trial (RCT). By contrast, the emergent phased experimental approach involves programmatic phases of empirical research and discovery aimed at identifying individual intervention component effects and the best combination of components and levels. PURPOSE: The purpose of this article is to provide a head-to-head comparison between the classical and phased experimental approaches and thereby highlight the relative advantages and disadvantages of these approaches when they are used to select program components and levels so as to arrive at the most potent intervention. METHODS: A computer simulation was performed in which the classical and phased experimental approaches to intervention development were applied to the same randomly generated data. RESULTS: The phased experimental approach resulted in better mean intervention outcomes when the intervention effect size was medium or large, whereas the classical approach resulted in better mean intervention outcomes when the effect size was small. The phased experimental approach led to identification of the correct set of intervention components and levels at a higher rate than the classical approach across all conditions. LIMITATIONS: Some potentially important factors were not varied in the simulation, for example the underlying structural model and the number of intervention components. CONCLUSIONS: The phased experimental approach merits serious consideration, because it has the potential to enable intervention scientists to develop more efficacious behavioral interventions.

Asian/Pacific islander youth violence prevention center: Community mobilization efforts to reduce and prevent youth violence

Lai,M. H. — 2008

Although youth violence is a serious concern in the United States, Asian American and Pacific Islander (AAPI) youth have generally been neglected as a demographic group for scholarly inquiry or community mobilization efforts. This lack of attention in the violence prevention field is indicative of two perceptual impediments with which AAPI communities have struggled for decades: (1) That AAPIs represent a relatively small portion of the United States population, and (2) That AAPIs are stereotyped as "model minorities" who do not encounter serious social obstacles and who lack ethnic heterogeneity. This paper challenges these concerns, and describes two community mobilization efforts to prevent youth violence in AAPI communities. Both of these efforts were carried out from 2000 to 2003 by the University of Hawaii, Asian/Pacific Islander Youth Violence Prevention Center. Findings from these mobilization efforts highlight the need for long-term university-community commitments, in which university entities take a leadership role in disaggregating AAPI juvenile justice data. Another critical need is to work with previously marginalized ethnic groups within the AAPI population.

How important are parents during the college years? A longitudinal perspective of indirect influences parents yield on their college teens' alcohol use

Abar,C. — 2008

Building on previous findings supporting the continuing influence of parents on their teens after they have gone to college [Turrisi, R., Jaccard, J., Taki, R., Dunnam, H., & Grimes, J. (2001). Examination of the short-term efficacy of a parent intervention to reduce college student drinking tendencies. Psychology of Addictive Behaviors, 15(4), 366-372.; Turrisi, R., Padilla, K., & Wiersma, K. (2000). College student drinking: An examination of theoretical models of drinking tendencies in freshman and upperclassmen. Journal of Studies on Alcohol, 61, 598-602.[28]], this study examined the possible indirect influence that parents may have on their teen's alcohol use through the selection of alcohol using peers in college. Friend use served as a mediator of the relationship between parenting characteristics and alcohol use in a longitudinal college sample. As part of a larger study, 392 incoming college freshmen were assessed for their perceptions of their parent's parenting practices, and peer alcohol use. Results from SEM indicated that friend alcohol use (first semester freshman year) mediated the relationship between parental knowledge about what their teen was doing in his/her free time (baseline pre-matriculation to college) and individual use in college (second semester freshman year). Findings suggest that even at this late stage of early adulthood parents continue to exhibit influence on the choices their teens make as far as friends, which in turn influences their teens' drinking in college. Implications for prevention are discussed.

Model misspecification in covariance structure models: Some implications for power and Type I error

Coffman,D. L. — 2008

This study investigated the degree to which violation of the parameter drift assumption affects the Type I error rate for the test of close fit and the power analysis procedures proposed by MacCallum et al. (1996) for both the test of close fit and the test of exact fit. The parameter drift assumption states that as sample size increases both sampling error and model error (i.e., the degree to which the model is an approximation in the population) decrease. Model error was introduced using a procedure proposed by Cudeck and Browne (1992). The empirical power for both the test of close fit, in which the null hypothesis specifies that the root mean square error of approximation (RMSEA) $ 0.05, and the test of exact fit, in which the null hypothesis specifies that RMSEA = 0, is compared with the theoretical power computed using the MacCallum et al. (1996) procedure. The empirical power and the theoretical power for both the test of close fit and the test of exact fit are nearly identical under violations of the assumption. The results also indicated that the test of close fit maintains the nominal Type I error rate under violations of the assumption.

Sex for you, but not for me: Discontinuity in undergraduate emerging adults' definitions of "having sex"

Gute,G. — 2008

The purpose of this study was to determine if undergraduates (N = 839) apply the same standard to themselves when labeling a behavior "having sex" as they apply to their significant others if those persons engage in the same behaviors outside the relationship. Using a between-participants design, one form asked participants if each of 11 behaviors constituted having sex if they engaged in the activity; the other form asked participants if each of the same behaviors constituted having sex if their significant other engaged in the activity outside their relationship. Participants answering for themselves were less likely to indicate a behavior was having sex for all behaviors except penile-anal and penile-vaginal intercourse. Men were also more likely than women to indicate most behaviors were having sex. The authors discuss what they define as a definitional discontinuity in undergraduate emerging adults' definitions of having sex. Fundamental attribution error (FAE) and emerging adulthood literature are used to explain the findings. Health and relationship implications are identified.