[Show abstract][Hide abstract] ABSTRACT: We present the rationale, the background and the structure for version 2.0 of the GENESTAT information portal (www.genestat.org) for statistical genetics. The fast methodological advances, coupled with a range of standalone software, makes it difficult for expert as well as non-expert users to orientate when designing and analysing their genetic studies. The ultimate ambition of GENESTAT is to guide on statistical methodology related to the broad spectrum of research in genetic epidemiology. GENESTAT 2.0 focuses on genetic association studies. Each entry provides a summary of a topic and gives links to key papers, websites and software. The flexibility of the internet is utilised for cross-referencing and for open editing. This paper gives an overview of GENESTAT and gives short introductions to the current main topics in GENESTAT, with additional entries on the website. Methods and software developers are invited to contribute to the portal, which is powered by a Wikipedia-type engine and allows easy additions and editing.
European journal of human genetics: EJHG 12/2008; 17(4):533-6. · 3.56 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: Some cognitive functions undergo transitions in old age, which motivates the use of a change point model for the individual trajectory. The age when the change occurs varies between individuals and is treated as random. We illustrate the properties of a random change point model and use it for data from a Swedish study of change in cognitive function in old age. Variance estimates are obtained from Markov chain Monte Carlo simulation using Gibbs sampling. The random change point model is compared with models within the family of linear random effects models. The focus is on the ability to capture variability in measures of cognitive function. The models make different assumptions about the variance over the age span, and we demonstrate that the random change point model has the most reasonable structure.
Statistics in Medicine 09/2008; 27(27):5786-98. · 2.04 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: Smoking is a primary risk factor for chronic bronchitis, emphysema, and chronic obstructive pulmonary disease, but since not all smokers develop disease, it has been suggested that some individuals may be more susceptible to exogenous factors, such as smoking, and that this susceptibility could be genetically determined.
The aim of the present study was to assess, in a population-based sample of twins, the following: (1) to what extent genetic factors contribute to the development of chronic bronchitis, including emphysema, taking sex into consideration, and (2) whether the genetic influences on chronic bronchitis, including emphysema, are separate from those for smoking behavior.
Disease cases and smoking habits were identified in 44,919 twins older than 40 years from the Swedish Twin Registry. Disease was defined as self-reported chronic bronchitis or emphysema, or recurrent cough with phlegm. Individuals who had smoked 10 pack-years or more were defined as smokers. Univariate and bivariate structural equation models were used to estimate the heritability specific for chronic bronchitis and that in common with smoking. Measurements and
The heritability estimate for chronic bronchitis was a moderate 40% and only 14% of the genetic influences were shared with smoking.
Genetic factors independent of those related to smoking habits play a role in the development of chronic bronchitis.
American Journal of Respiratory and Critical Care Medicine 04/2008; 177(5):486-90. · 11.04 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: Incomplete data on trait values may bias estimates of genetic and environmental variance components obtained from twin analyses. If the nonresponse mechanism is 'ignorable' then methods such as full information maximum likelihood estimation will produce consistent variance component estimates. If, however, nonresponse is 'nonignorable', then the situation is more complicated. We demonstrate that a within-pair correlation of nonresponse, possibly different for monozygotic (MZ) and dizygotic (DZ) twins, may well be compatible with 'ignorability'. By means of Monte Carlo simulation, we assess the potential bias in variance component estimates for different types of nonresponse mechanisms. The simulation results guide the interpretation of analyses of data on perceptual speed from the Swedish Adoption/Twin Study of Aging. The results suggest that the dramatic decrease in genetic influences on perceptual speed observed after 13 years of follow-up is not attributable solely to dropout from the study, and thus support the hypothesis that genetic influences on some cognitive abilities decrease with age in late life.
Twin Research and Human Genetics 05/2006; 9(2):185-93. · 1.64 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: The likelihood ratio test of nested models for family data plays an important role in the assessment of genetic and environmental influences on the variation in traits. The test is routinely based on the assumption that the test statistic follows a chi-square distribution under the null, with the number of restricted parameters as degrees of freedom. However, tests of variance components constrained to be non-negative correspond to tests of parameters on the boundary of the parameter space. In this situation the standard test procedure provides too large p-values and the use of the Akaike Information Criterion (AIC) or the Bayesian Information Criterion (BIC) for model selection is problematic. Focusing on the classical ACE twin model for univariate traits, we adapt existing theory to show that the asymptotic distribution for the likelihood ratio statistic is a mixture of chi-square distributions, and we derive the mixing probabilities. We conclude that when testing the AE or the CE model against the ACE model, the p-values obtained from using the chi(2)(1 df) as the reference distribution should be halved. When the E model is tested against the ACE model, a mixture of chi(2)(0 df), chi(2)(1 df) and chi(2)(2 df) should be used as the reference distribution, and we provide a simple formula to compute the mixing probabilities. Similar results for tests of the AE, DE and E models against the ADE model are also derived. Failing to use the appropriate reference distribution can lead to invalid conclusions.
[Show abstract][Hide abstract] ABSTRACT: Some cognitive functions exhibit multiple phases in old age, which mo- tivates the use of a change point model for the individual trajectory. The change point varies between individuals and is treated as random. Illus- trating with an application to cognitive function in a Swedish sample, we contrast the random change point model with models within the family of linear random eects models. The focus is on the ability to capture trait variability. We show that the models make dierent assumptions about the trait variance over the age distribution, and demonstrate that the random change point model is favourable in this respect. The performance of ap- proximate maximum likelihood estimation based on first-order linearization of the random change point model is evaluated. Through simulations we show that the first-order linearization can produce biased parameter esti- mates even in an ideal situation with many repeated measurements and a balanced study design. We contrast the results with a Bayesian analysis, based on Markov chain Monte Carlo simulation using Gibbs sampling.