Time-varying covariance occurs when a covariate changes over time during the follow-up period. Such variable can be analyzed with the Cox regression model to estimate its effect on survival time. For this it is essential to organize the data in a counting process style. In situations when the proportional hazards assumption of the Cox regression model does not hold, we say that the effect of the covariate is time-varying. The proportional hazards assumption can be tested by examining the residuals of the model. The rejection of the null hypothesis induces the use of time varying coefficient to describe the data. The time varying coefficient can be described with a step function or a parametric time function. This article aims to illustrate how to carry out statistical analyses in the presence of time-varying covariates or coefficients with R.

No abstract

The differences in participation rates must be taken into account to avoid biased estimates because socio-economic position has also been shown to be strongly related to health, health behaviour and biological risk factors. Particular attention should be paid to the recruitment of the less-educated population groups.

The lifetime accumulation of risk factors and the observed changes in risk factor levels over time are strong predictors of CVD mortality. It is important to investigate different ways of using the longitudinal risk factor measurements to take full advantage of them.

Background Living alone has become more common in today’s societies. Despite the high number of the population living alone, research directed towards the mental wellbeing issues related to living alone has been limited. This systematic literature review aimed to assess the association between living alone and positive mental health. Methods We conducted searches in Medline, Web of Science, Cochrane Library, CINAHL, PsycINFO, and other complementary databases from January 1998 to May 2019. Randomised trials and observational studies investigating adults over 18 years of age and living alone (defined as living in a single household or a household size of one person) were eligible. The primary outcome was positive mental health, defined as comprising both hedonic and eudaimonic elements of mental wellbeing, and it was measured with the Warwick-Edinburgh Mental Well-being Scale and/or theWHO-5 Index. Two reviewers independently screened and selected data; one reviewer extracted data, and the second checked the extracted data. A narrative synthesis described the quality and content of the evidence. Included studies were appraised using relevant Joanna Briggs Institute checklist. Results A total of 4 cross-sectional studies (22,591 adult participants) were included after screening of 341 titles and abstracts and 46 full-text articles. These studies were conducted in Europe and were published between 2014 and 2017. The studies differed in their measurements of positive mental health (WHO-5 Well-Being Index, 3 studies; WEMWBS, 1 study), sources of data (1 regional, 1 national, and 2 European-level studies), and study populations (regional study, adults over 65 years of age; national-level study, mental health nurses over 21 years of age; European-level studies, employees between 15 and 65 years of age and adults over 18 years of age). A potential association between living alone and low positive mental health was found in three out of the four studies. Our findings were limited as the number of included studies was low and the quality of evidence varied across studies. Conclusions This review allows a limited look at the association between living alone and positive mental health. Because the number of included studies was low and the quality of evidence varied across studies, further research is warranted. Electronic supplementary material The online version of this article (10.1186/s13643-019-1057-x) contains supplementary material, which is available to authorized users.

Repeated covariate measurements bring important information on the timevarying risk factors in long epidemiological follow-up studies. However, due to budget limitations, it may be possible to carry out the repeated measurements only for a subset of the cohort. We study cost-efficient alternatives for the simple random sampling in the selection of the individuals to be remeasured. The proposed selection criteria are based on forms of the Doptimality. The selection methods are compared in simulation studies and illustrated with the data from the East-West study carried out in Finland from 1959 to 1999. The results indicate that cost savings can be achieved if the selection is focused on the individuals with high expected risk of the event and, on the other hand, on those with extreme covariate values in the previous measurements.

Aim: We aim to compare four different weighting methods to adjust for non-response in a survey on drinking habits and to examine whether the problem of under-coverage of survey estimates of alcohol use could be remedied by these methods in comparison to sales statistics. Method : The data from a general population survey of Finns aged 15–79 years in 2016 ( n =2285, response rate 60%) were used. Outcome measures were the annual volume of drinking and prevalence of hazardous drinking. A wide range of sociodemographic and regional variables from registers were available to model the non-response. Response propensities were modelled using logistic regression and random forest models to derive two sets of refined weights in addition to design weights and basic post-stratification weights. Results : Estimated annual consumption changed from 2.43 litres of 100% alcohol using design weights to 2.36–2.44 when using the other three weights and the estimated prevalence of hazardous drinkers changed from 11.4% to 11.4–11.8%, correspondingly. The use of weights derived by the random forest method generally provided smaller estimates than use of the logistic regression-based weights. Conclusions : The use of complex non-response weights derived from the logistic regression model or random forest are not likely to provide much added value over more simple weights in surveys on alcohol use. Surveys may not catch heavy drinkers and therefore are prone for under-reporting of alcohol use at the population level. Also, factors other than sociodemographic characteristics are likely to influence participation decisions.

OBJECTIVE Natriuretic peptide (NP) concentrations are increased in cardiovascular diseases (CVDs) but are associated with a lower diabetes risk. We investigated associations of N-terminal pro-B-type NP (NT-proBNP) and midregional proatrial NP (MR-proANP) with incident type 2 diabetes stratified by the presence of CVD. RESEARCH DESIGN AND METHODS Based on the Biomarkers for Cardiovascular Risk Assessment in Europe (BiomarCaRE) Consortium, we included 45,477 participants with NT-proBNP measurements (1,707 developed type 2 diabetes over 6.5 years of median follow-up; among these, 209 had CVD at baseline) and 11,537 participants with MR-proANP measurements (857 developed type 2 diabetes over 13.8 years of median follow-up; among these, 106 had CVD at baseline). The associations were estimated using multivariable Cox regression models. RESULTS Both NPs were inversely associated with incident type 2 diabetes (hazard ratios [95% CI] per 1-SD increase of log NP: 0.84 [0.79; 0.89] for NT-proBNP and 0.77 [0.71; 0.83] for MR-proANP). The inverse association between NT-proBNP and type 2 diabetes was significant in individuals without CVD but not in individuals with CVD (0.81 [0.76; 0.86] vs. 1.04 [0.90; 1.19]; P multiplicative interaction = 0.001). There was no significant difference in the association of MR-proANP with type 2 diabetes between individuals without and with CVD (0.75 [0.69; 0.82] vs. 0.81 [0.66; 0.99]; P multiplicative interaction = 0.236). CONCLUSIONS NT-proBNP and MR-proANP are inversely associated with incident type 2 diabetes. However, the inverse association of NT-proBNP seems to be modified by the presence of CVD. Further investigations are warranted to confirm our findings and to investigate the underlying mechanisms.