Related Experiment Video
Updated: Jun 19, 2026

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data
Published on: December 9, 2015
Suicide mortality in eastern and western Germany, 1952-2022: Construction and validation of time series using
Enno Nowossadeck1, Claudia Hövener1,2, Niels Michalski1
1Department of Epidemiology and Health Monitoring, Robert Koch Institute, Berlin, Germany.
Abstract:
Suicide mortality is a significant public health problem. Retrospective analyses can be helpful in better understanding temporal trends of suicide mortality and thus derive clues about causal and associated factors for the course. For this paper, we compiled suicide mortality rates for eastern and western Germany from 1952 to 2022 from various data sources, stratified by sex. The period encompasses events that could substantially alter the statistically recorded rates, such as the changes in versions of the International Classification of Diseases (ICD) in 1978 and 1997, but also the integration of the statistical system of the German Democratic Republic (GDR) into that of the Federal Republic of Germany (FRG) in 1990/91. These could cause methodologically induced breaks in the compiled time series. Using Joinpoint-Jump models, we tested whether at these defined points a jump, i.e., an abrupt change in the level of the time series, can be statistically detected or rejected. The empirical results show a high dynamism of suicide mortality in both parts of Germany, with very frequent increases and decreases of suicide mortality rates. However, the analyses do not point to systematic and substantial methodologically induced structural breaks resulting from ICD version changes or from transferring of the GDR statistical system to that of the FRG. The analysis results support the conclusion that the compiled long time series for eastern and western German women and men are largely consistent. It is unlikely that analyses of trends in suicide rates in Germany during that period are distorted by methodological artefacts examined. Some caution is warranted for women during periods of ICD code changes, although any methodological effects are likely small and within the range of typical annual fluctuations.
Related Concept Videos
Parametric Survival Analysis: Weibull and Exponential Methods
Weibull Distribution
The Weibull distribution is a flexible model used in parametric survival analysis. It can handle both increasing and decreasing hazard rates, depending on its shape parameter...
Assumptions of Survival Analysis
Introduction To Survival Analysis
The primary goal of survival analysis is to estimate survival time—the time until a...
Applications of Life Tables
Statistical Methods for Analyzing Epidemiological Data
Comparing the Survival Analysis of Two or More Groups