No abstract

13We examine the performance of the two rank order correlation coefficients (Spearman's rho 14 and Kendall's tau) for describing the strength of association between two continuously 15 measured traits. We begin by discussing when these measures should, and should not, be 16 preferred over Pearson's product moment correlation coefficient on conceptual grounds. For 17 testing the null hypothesis of no monotonic association, our simulation studies found both 18

Summary 1.Researchers often want to place a confidence interval around estimated parameter values calculated from a sample. This is commonly implemented by bootstrapping. There are several different frequently used bootstrapping methods for this purpose.2. Here we demonstrate that authors of recent papers frequently do not specify the method they have used and that different methods can produce markedly different confidence intervals for the same sample and parameter estimate. 3. We encourage authors to be more explicit about the method they use (and number of bootstrap resamples used). 4. We recommend the bias corrected and accelerated method as giving generally good performance; although researchers should be warned that coverage of bootstrap confidence intervals is characteristically less than the specified nominal level, and confidence interval evaluation by any method can be unreliable for small samples in some situations.

BackgroundMultimorbidity is one of the most important and challenging aspects in public health. Multimorbid people are associated with more hospital admissions, a large number of drug prescriptions and higher risks of mortality. As there is evidence that multimorbidity varies with age and socioeconomic disparity, the main objective aimed at determining age-specific prevalence rates as well as exploring educational differences relating to multimorbidity in Germany.MethodsThis cross-sectional analysis is based on the national telephone health interview survey “German Health Update” (GEDA2012) conducted between March 2012 and March 2013 with nearly 20,000 adults. GEDA2012 provides information on 17 self-reported health conditions along with sociodemographic characteristics. Multimorbidity was defined as the occurrence of two or more chronic conditions in one individual at the same time. Descriptive statistical analysis was used to examine multimorbidity according to age and education, which was defined by the International Standard Classification of Education (ISCED 1997).ResultsOverall, 39.6% (95% confidence interval (CI) 38.7%–40.6%) of the 19,294 participants were multimorbid and the proportion of adults with multimorbidity increased substantially with age: nearly half (49.2%, 95% CI 46.9%–51.5%) of the adults aged 50–59 years had already two or more chronic health conditions. Prevalence rates of multimorbidity differed considerably between the levels of education. Low-level educated adults aged 40–49 years were more likely to be multimorbid with a prevalence rate of 47.4% (95% CI 44.2%–50.5%) matching those of highly educated men and women aged about ten years older.ConclusionsOur findings demonstrate that both, age and education are associated with a higher risk of being multimorbid in Germany. Hence, special emphasis in the development of new approaches in national public health and prevention programs on multimorbidity should be given to low-level educated people aged <65 years.Electronic supplementary materialThe online version of this article (10.1186/s12889-017-4833-3) contains supplementary material, which is available to authorized users.