Fetene B. Tekle

Estimating the Association between Latent Class Membership and External Variables Using Bias-adjusted Three-step Approaches

Latent class analysis is a clustering method that is nowadays widely used in social science research. Researchers applying latent class analysis will typically not only construct a typology based on a set of observed variables but also investigate how the encountered clusters are related to other, external variables. Although it is possible to incorporate such external variables into the latent class model itself, researchers usually prefer using a three-step approach. This is the approach wherein after establishing the latent class model for clustering (step 1), one obtains predictions for the class membership scores (step 2) and subsequently uses these predicted scores to assess the relationship between class membership and other variables (step 3). Bolck, Croon, and Hagenaars (2004) showed that this approach leads to severely downward-biased estimates of the strength of the relationships studied in step 3. These authors and later also Vermunt (2010) developed methods to correct for this bias. In the current study, we extended these correction methods to situations where class membership is not predicted but used as an explanatory variable in the third step, a situation widely encountered in social science applications. A simulation study tested the performance of the proposed correction methods, and their practical use was illustrated with real data examples. The results showed that also when the latent class variable is used as a predictor of external variables, the uncorrected three-step approach leads to severely biased estimates. The proposed correction methods perform well under conditions encountered in practice.

Emotional distress, positive affect, and mortality in patients with an implantable cardioverter defibrillator

BACKGROUND Little is known about the relationship between emotional distress and mortality in patients with an implantable cardioverter defibrillator (ICD). Our aim was to examine the predictive value of general negative and positive affect, and depressive symptoms (including its components somatic symptoms and cognitive-affective symptoms) for mortality. METHODS ICD patients (N=591, 81% male, mean age=62.7 ± 10.1 years) completed the Global Mood Scale to measure the independent dimensions negative and positive mood, and the Beck Depression Inventory to measure depressive symptoms. Covariates consisted of demographic and clinical variables. RESULTS During the median follow-up of 3.2 years, 96 (16.2%) patients died. After controlling for covariates, negative affect was significantly related to all-cause mortality (HR=1.034, p=0.002), whereas positive affect was not (HR=1.007, p=0.61). Depressive symptoms were also independently associated with an increased mortality risk (HR=1.031, p=0.030) and somatic symptoms of depression in particular (HR=1.130, p=0.003), but cognitive-affective symptoms were not associated with mortality (HR=0.968, p=0.29). When entering both significant psychological predictors in a covariate-adjusted model, negative mood remained significant (HR=1.039, p=0.009), but somatic symptoms of depression did not (HR=0.988, p=0.78). Similar results were found for cardiac-related death. Of covariates, increased age, CRT, appropriate shocks were positively related to death. CONCLUSIONS Negative affect in general was related to mortality, but reduced positive affect was not. Depression, particularly its somatic symptoms, was also related to mortality, while cognitive-affective symptoms were not. Future research may further focus on the differential predictive value of emotional distress factors, as well as on mechanisms that relate emotional distress factors to mortality.

Shock and Patient Preimplantation Type D Personality Are Associated With Poor Health Status in Patients With Implantable Cardioverter-Defibrillator

Background— Implantable cardioverter-defibrillator (ICD) shock is a critical event to patients associated with well-being after implantation, although other factors may play an equally important role. We compared the association of shock and the patients preimplantation personality with health status, using a prospective study design. Methods and Results— Consecutively implanted ICD patients (n=383; 79% men) completed the Type D Scale at baseline and the Short-Form Health Survey 36 (SF-36) at baseline and 3, 6, and 12 months. Of all patients, 23.5% had a Type D personality and 13.8% received a shock during follow-up. Shocked patients reported significantly poorer health status, as did Type D patients. Health status patterns were poorest in patients with combined Type D personality and shock during follow-up. Shock during follow-up was a significant independent associate of poorer health status for 4 of 8 subscales of the SF-36 and the Mental Component Summary (all P<.05), with shocked patients scoring between 2.60 to 13.30 points lower than nonshocked patients. Type D personality was an independent associate of poor postimplantation health status for 6 of 8 of the SF-36 subscales and the Mental Component Summary, with Type D patients scoring between 2.12 to 8.02 points lower, adjusting for demographic and clinical characteristics. Conclusions— ICD shock and the patients preimplantation personality disposition were equally important associates of health status 12 months after implantation. Identification of the patients personality profile before ICD implantation may help identify subsets of patients who may need additional care, for example, with a psychosocial component.

Pregnancy rate after vasectomy reversal in a contemporary series: influence of smoking, semen quality and post-surgical use of assisted reproductive techniques.

Study Type – Outcomes (cohort series)

Too many cohorts and repeated measurements are a waste of resources

OBJECTIVE Researchers in Health Sciences and Medicine often use cohort designs to study treatment effects and changes of outcome variables over time period. The costs of these studies can be reduced by choosing an optimal number of repeated measurements over time and by selecting cohorts of subjects more efficiently with optimal design procedures. The objective of this study is to provide evidence on how to design large-scale cohort studies with budget constraints as efficiently as possible. STUDY DESIGN AND SETTING A linear cost function for repeated measurements is proposed, and this cost function is used in the optimization procedure. For a given budget/cost, different designs for linear mixed-effects models are compared by means of their efficiency. RESULTS We found that adding more repeated measures is only beneficiary if the costs of selecting and measuring a new subject are much higher than the costs of obtaining an additional measurement for an already recruited subject. However, this gain in efficiency and power is not very large. CONCLUSION Adding more cohorts or repeated measurements do not necessarily lead to a gain in efficiency of the estimated model parameters. A general guideline for the optimal choice of a cohort design in practice is required and we offer this guideline.

Age-Related Differences in the Effect of Psychological Distress on Mortality: Type D Personality in Younger versus Older Patients with Cardiac Arrhythmias

Background. Mixed findings in biobehavioral research on heart disease may partly be attributed to age-related differences in the prognostic value of psychological distress. This study sought to test the hypothesis that Type D (distressed) personality contributes to an increased mortality risk following implantable cardioverter defibrillator (ICD) treatment in younger patients but not in older patients. Methods. The Type D Scale (DS14) was used to assess general psychological distress in 455 younger (≤70 y, m = 59.1) and 134 older (>70 y, m = 74.3) ICD patients. End points were all-cause mortality and cardiac death after a median follow-up of 3.2 years. Results. Older patients had more advanced heart failure and a higher mortality rate (n = 34/25%) than younger patients (n = 60/13%), P = 0.001. Cardiac resynchronization therapy (CRT), but not Type D personality, was associated with increased mortality in older patients. Among younger patients, however, Type D personality was associated with an adjusted hazard ratio = 1.91 (95% CI 1.09–3.34) and 2.26 (95% CI 1.16–4.41) for all-cause and cardiac mortality; other predictors were increasing age, CRT, appropriate shocks, ACE-inhibitors, and smoking. Conclusion. Type D personality was independently associated with all-cause and cardiac mortality in younger ICD patients but not in older patients. Cardiovascular research needs to further explore age-related differences in psychosocial risk.

Power Analysis for the Likelihood-Ratio Test in Latent Markov Models: Shortcutting the Bootstrap p-Value-Based Method

ABSTRACT The latent Markov (LM) model is a popular method for identifying distinct unobserved states and transitions between these states over time in longitudinally observed responses. The bootstrap likelihood-ratio (BLR) test yields the most rigorous test for determining the number of latent states, yet little is known about power analysis for this test. Power could be computed as the proportion of the bootstrap p values (PBP) for which the null hypothesis is rejected. This requires performing the full bootstrap procedure for a large number of samples generated from the model under the alternative hypothesis, which is computationally infeasible in most situations. This article presents a computationally feasible shortcut method for power computation for the BLR test. The shortcut method involves the following simple steps: (1) obtaining the parameters of the model under the null hypothesis, (2) constructing the empirical distributions of the likelihood ratio under the null and alternative hypotheses via Monte Carlo simulations, and (3) using these empirical distributions to compute the power. We evaluate the performance of the shortcut method by comparing it to the PBP method and, moreover, show how the shortcut method can be used for sample-size determination.