Predictive Margins and Marginal Effects in Stata

Tables of estimated regression coefficients, usually accompanied by additional information such as standard errors, t-statistics, p-values, confidence intervals or significance stars, have long been the preferred way of communicating results from statistical models. In recent years, however, the limits of this form of exposition have been increasingly recognized. For example, interpretation of regression tables can be very challenging in the presence of complications such as interaction effects, categorical variables, or nonlinear functional forms. Furthermore, while these issues might still be manageable in the case of linear regression, interpretational difficulties can be overwhelming in nonlinear models such as logistic regression. To facilitate sensible interpretation of such models it is often necessary to compute additional results such as marginal effects, predictive margins, or contrasts. Moreover, smart graphical displays of results can be very valuable in making complex relations accessible. A number of helpful commands geared at supporting these tasks have been recently introduced in Stata, making elaborate interpretation and communication of regression results possible without much extra effort. Examples of such commands are -margins-, -contrasts-, and -marginsplot-. In my talk, I will discuss the capabilities of these commands and present a range of examples illustrating their use.

Survey estimation and marginal effects in Stata

Stata is a general purpose software package that has become popular among various disciplines such as epidemiology, economics, or social sciences. Users like Stata for its scientific approach, its robustness and reliability, and the ease with which its functionality can be extended by user written programs. In this talk I will first give a brief overview of the functionality of Stata and then discuss two specific features: survey estimation and predictive margins/marginal effects. Most surveys are based on complex samples that contain multiple sampling stages, are stratified or clustered, and feature unequal selection probabilities. Standard estimators can produce misleading results in such samples unless the peculiarities of the sampling plan are taken into account. Stata offers survey statistics for complex samples for a wide variety of estimators and supports several variance estimation procedures such as linearization, jackknife, and balanced repeated replication (see Kreuter and Valliant, 2007, Stata Journal 7: 1-21). In the talk I will illustrate these features using applied examples and I will also show how user written commands can be adapted to support complex samples. Complex can also be the models we fit to our data, making it difficult to interpret them, especially in case of nonlinear or non-additive models (Mood, 2010, European Sociological Review 26: 67-82). Stata provides a number of highly useful commands to make results of such models accessible by computing and displaying predictive margins and marginal effects. In my talk I will discuss these commands provide various examples demonstrating their use.

Vulnerability and Growth. Developmental dynamics and differential effects of the loss of an intimate partner in the second half of life. IP 12: Study outline and first results

This working report gives an overview of the Individual Project 12 “Vulnerability and growth. Developmental dynamics and differential effects of the loss of an intimate partner in the second half of life” of the Swiss National Centre of Competence in Research LIVES led by Pasqualina Perrig-Chiello, University of Bern. This longitudinal and interdisciplinary project aims at examining vulnerability and personal growth after a critical life event, namely the break-up of a long-term intimate relationship in the second half of life, be it due to divorce or due to bereavement. In this report we present details about the rationale, the main research questions, the hypotheses and the methods of the study. Special attention is given to the methodological approach. The authors give a first sample description and report on the validity of the data by comparing the sample with Swiss Labour Force Survey and Swiss Health Survey data.

Relaxing hydrotherapy WATSU (WaterShiatsu) and its effects in third trimester of pregnancy

Background WATSU (WaterShiatsu) is a bodywork-technique comprising buoyancy, passive stretches, massage, and acupressure that is administered in 35° C warm water. WATSU is believed to exert beneficial effects on pregnancy-related complaints. We conducted a pilot study to test the hypothesis that WATSU treatment during pregnancy can affect low back pain, everyday stress perception, quality of life, tonus of the uterus, amount of amniotic fluid, spontaneous course of breech presentations, and the success rate of external cephalic versions. Methods Healthy women with singleton pregnancies at gestational week 36 were included in our cohort control pilot trial. Participants in the treatment group (n = 8) received a standardized WATSU-treatment on their first and fourth day of study participation, while participants in the control group were in a waiting condition. Participants underwent ultrasound investigations and completed quantitative and qualitative questionnaires before and after intervention, as well as weekly until birth. Results In contrast to the control group, participants in the WATSU-treatment group reported significant relief of low back pain and stress. After WATSU treatment spontaneous version out of breech position occurred once in seven cases, and external cephalic version was successful in two out of three cases. As qualitative data indicate, WATSU was appreciated as a deep relaxing and enjoyable treatment method. No negative side-effects or adverse events were reported. Conclusion The findings from our pilot-study support the notion that WATSU might yield therapeutic benefits for pregnant women and warrant further research.

Cognitive and emotional effects of carotid stenosis

PRINCIPLES Patients with carotid artery stenosis (CAS) are at risk of ipsilateral stroke and chronic compromise of cerebral blood flow. It is under debate whether the hypo-perfusion or embolism in CAS is directly related to cognitive impairment. Alternatively, CAS may be a marker for underlying risk factors, which themselves influence cognition. We aimed to determine cognitive performance level and the emotional state of patients with CAS. We hypothesised that patients with high grade stenosis, bilateral stenosis, symptomatic patients and/or those with relevant risk factors would suffer impairment of their cognitive performance and emotional state. METHODS A total of 68 patients with CAS of ≥70% were included in a prospective exploratory study design. All patients underwent structured assessment of executive functions, language, verbal and visual memory, motor speed, anxiety and depression. RESULTS Significantly more patients with CAS showed cognitive impairments (executive functions, word production, verbal and visual memory, motor speed) and anxiety than expected in a normative sample. Bilateral and symptomatic stenosis was associated with slower processing speed. Cognitive performance and anxiety level were not influenced by the side and the degree of stenosis or the presence of collaterals. Factors associated with less cognitive impairment included higher education level, female gender, ambidexterity and treated hypercholesterolemia. CONCLUSIONS Cognitive impairment and increased level of anxiety are frequent in patients with carotid stenosis. The lack of a correlation between cognitive functioning and degree of stenosis or the presence of collaterals, challenges the view that CAS per se leads to cognitive impairment.

Developmental changes in sleep biology and potential effects on adolescent behavior and caffeine use

Adolescent development includes changes in the biological regulatory processes for the timing of sleep. Circadian rhythm changes and changes to the sleep-pressure system (sleep homeostasis) during adolescence both favor later timing of sleep. These changes, combined with prevailing social pressures, are responsible for most teens sleeping too late and too little; those who sleep least report consuming more caffeine. Although direct research findings are scarce, the likelihood of use and abuse of caffeine-laden products grows across the adolescent years due, in part, to excessive sleepiness

Comparative Behavioral and Neural Effects of Tryptophan and Catecholamine Depletion in Remitted Depression

Background: Despite immense efforts into development of new antidepressant drugs, the increases of serotoninergic and catechominergic neurotransmission have remained the two major pharmacodynamic principles of current drug treatments for depression. Consequently, psychopathological or biological markers that predict response to drugs that selectively increase serotonin and/or catecholamine neurotransmission hold the potential to optimize the prescriber’s selection among currently available treatment options. The aim of this study was to elucidate the differential symptomatology and neurophysiology in response to reductions in serotonergic versus catecholaminergic neurotransmission in subjects at high risk of depression recurrence. Methods: Using identical neuroimaging procedures with [18F] fluorodeoxyglucose positron emission tomography after tryptophan depletion (TD) and catecholamine depletion (CD), subjects with remitted depression were compared to healthy controls in a double-blind, randomized, crossover design. Results: While TD induced significantly more depressed mood, sadness and hopelessness than CD, CD induced more inactivity, concentration difficulties, lassitude and somatic anxiety than TD. CD specifically increased glucose metabolism in the bilateral ventral striatum and decreased glucose metabolism in the bilateral orbitofrontal cortex, whereas TD specifically increased metabolism in the right prefrontal cortex and the posterior cingulate cortex (PCC). While we found direct associations between changes in brain metabolism and induced depressive symptoms following CD, the relationship between neural activity and symptoms was less clear after TD. Conclusions: In conclusion, this study showed that serotonin and catecholamines play common and differential roles in the pathophysiology of depression.

Oral prophylaxis and its effects on halitosis-associated and inflammatory parameters in patients with chronic periodontitis

OBJECTIVE A controlled clinical trial was conducted to evaluate the effects of oral prophylaxis on halitosis-associated, immunological and microbiological parameters. METHODS Thirty subjects were included in this controlled clinical trial (patients with generalized chronic periodontitis and controls without clinical attachment loss; each n = 15). Before oral prophylaxis and 14 days after (including tongue cleaning) volatile sulphur compounds (VSC), organoleptic scores and a tongue coating index were evaluated. The levels of IL-1β, IL-8, IL-10 and MMP-8 were measured in GCF, and also major periodontal pathogens were detected. Data were statistically analysed using anova and paired t-test. RESULTS Supragingival plaque and calculus removal with combined tongue cleaning was able to reduce significantly (P < 0.05) the VSC values in both groups (no significant differences between both groups). Two weeks after periodontal debridement, the VSC values were observed in the periodontitis group, but not in the control group, similar to the baseline values. The difference between the groups was statistically significant (P < 0.05). Only a repeated prophylaxis session in the periodontitis group was able to reduce VSC values significantly in comparison with baseline (P < 0.05). Organoleptic scores (10 and 30 cm) were significantly different (P < 0.05) between both groups before and after the treatment. Periodontal pathogens and host-derived markers were not significantly affected by a single prophylaxis session. CONCLUSIONS Oral prophylaxis may result in a significant decrease in VSC values. However, in periodontal diseases, a more complex treatment seems to be necessary.