Additive interaction in the presence of a mismeasured outcome.
Ontology highlight
ABSTRACT:
SUBMITTER: Jiang Z
PROVIDER: S-EPMC4334828 | biostudies-literature | 2015 Jan
REPOSITORIES: biostudies-literature
Publications
Additive interaction in the presence of a mismeasured outcome.
Jiang Zhichao Z VanderWeele Tyler J TJ
American journal of epidemiology 20141216 1
Similar Datasets
Project description:Interest in investigating gene-environment (GxE) interactions has rapidly increased over the last decade. Although GxE interactions have been extremely investigated in large studies, few such effects have been identified and replicated, highlighting the need to develop statistical GxE tests with greater statistical power. The reverse test has been proposed for testing the interaction effect between continuous exposure and genetic variants in relation to a binary disease outcome, which leverages the idea of linear discriminant analysis, significantly increasing statistical power comparing to the standard logistic regression approach. However, this reverse approach did not take into consideration adjustment for confounders. Since GxE interaction studies are inherently nonexperimental, adjusting for potential confounding effects is critical for valid evaluation of GxE interactions. In this study, we extend the reverse test to allow for confounders. The proposed reverse test also allows for exposure measurement errors as typically occurs. Extensive simulation experiments demonstrated that the proposed method not only provides greater statistical power under most simulation scenarios but also provides substantive computational efficiency, which achieves a computation time that is more than sevenfold less than that of the standard logistic regression test. In an illustrative example, we applied the proposed approach to the Veterans Aging Cohort Study (VACS) to search for genetic susceptibility loci modifying the smoking-HIV status association.
| S-EPMC8473983 | biostudies-literature
Project description:Interaction measured on the additive scale has been argued to be better correlated with biologic interaction than when measured on the multiplicative scale. Measures of interaction on the additive scale have been developed using risk ratios. However, in studies that use odds ratios as the sole measure of effect, the calculation of these measures of additive interaction is usually performed by directly substituting odds ratios for risk ratios. Yet assessing additive interaction based on replacing risk ratios by odds ratios in formulas that were derived using the former may be erroneous. In this paper, we evaluate the extent to which three measures of additive interaction - the interaction contrast ratio (ICR), the attributable proportion due to interaction (AP), and the synergy index (S), estimated using odds ratios versus using risk ratios differ as the incidence of the outcome of interest increases in the source population and/or as the magnitude of interaction increases. Our analysis shows that the difference between the two depends on the measure of interaction used, the type of interaction present, and the baseline incidence of the outcome. Substituting odds ratios for risk ratios, when calculating measures of additive interaction, may result in misleading conclusions. Of the three measures, AP appears to be the most robust to this direct substitution. Formulas that use stratum specific odds and odds ratios to accurately calculate measures of additive interaction are presented.
| S-EPMC1475799 | biostudies-other
Project description:Suppose we are interested in the effect of a binary treatment on an outcome where that relationship is confounded by an ordinal confounder. We assume that the true confounder is not observed, rather we observe a nondifferentially mismeasured version of it. We show that under certain monotonicity assumptions about its effect on the treatment and on the outcome, an effect measure controlling for the mismeasured confounder will fall between its corresponding crude and the true effect measures. We present results for coarsened, and, under further assumptions, for multiple misclassified confounders.
| S-EPMC3761876 | biostudies-literature
Project description:Motivated by data gathered in an oral health study, we propose a Bayesian nonparametric approach for population-averaged modeling of correlated time-to-event data, when the responses can only be determined to lie in an interval obtained from a sequence of examination times and the determination of the occurrence of the event is subject to misclassification. The joint model for the true, unobserved time-to-event data is defined semiparametrically; proportional hazards, proportional odds, and accelerated failure time (proportional quantiles) are all fit and compared. The baseline distribution is modeled as a flexible tailfree prior. The joint model is completed by considering a parametric copula function. A general misclassification model is discussed in detail, considering the possibility that different examiners were involved in the assessment of the occurrence of the events for a given subject across time. We provide empirical evidence that the model can be used to estimate the underlying time-to-event distribution and the misclassification parameters without any external information about the latter parameters. We also illustrate the effect on the statistical inferences of neglecting the presence of misclassification.
| S-EPMC6711609 | biostudies-literature
Project description:The interaction between the seed beetle Zabrotes subfasciatus and its parasitoid Stenocorse bruchivora, was investigated on seeds of two populations of wild lima bean, Phaseolus lunatus. By manipulating the number of beetle larvae per seed and the presence of parasitoids, we determined how factors related to beetle larvae density, the seed in which they feed and the parasitoid, may interact and affect host and parasitoid survival. Results showed that an increase in larval beetle density had a negative impact on beetle performance. This effect cascaded up to parasitoids, high larval density strongly reduced parasitoid emergence. Also, parasitoid presence resulted in faster beetle development and lower female weight. An interactive effect between larval host density and parasitoid presence affected the number of insects that emerged from the seeds. Beetle performance was better in the bean population with the largest seeds, while parasitoid emergence was the lowest in these seeds. This study shows that the impact of parasitoids on seed beetles is contingent on the interaction between density-mediated (direct mortality) and trait-mediated (e.g. non-consumptive) effects. Indirect trait-mediated effects of natural enemies are likely prevalent across insect communities, understanding their role in driving host-parasitoid interactions can have important implications for biological control.
| S-EPMC6901471 | biostudies-literature
Project description:Measuring rates and causes of mortalities is important in animal ecology and management. Observing the fates of known individuals is a common method of estimating life history variables, including mortality patterns. It has long been assumed that data lost when known animals disappear were unbiased. We test and reject this assumption under conditions common to most, if not all, studies using marked animals. We illustrate the bias for 4 endangered wolf populations in the United States by reanalyzing data and assumptions about the known and unknown fates of marked wolves to calculate the degree to which risks of different causes of death were mismeasured. We find that, when using traditional methods, the relative risk of mortality from legal killing measured as a proportion of all known fates was overestimated by 0.05-0.16 and the relative risk of poaching was underestimated by 0.17-0.44. We show that published government estimates are affected by these biases and, importantly, are underestimating the risk of poaching. The underestimates have obscured the magnitude of poaching as the major threat to endangered wolf populations. We offer methods to correct estimates of mortality risk for marked animals of any taxon and describe the conditions under which traditional methods produce more or less bias. We also show how correcting past and future estimates of mortality parameters can address uncertainty about wildlife populations and increase the predictability and sustainability of wildlife management interventions.
| S-EPMC6093422 | biostudies-literature
Project description:Whole genome duplications have played an important role in the evolution of angiosperms. These events often occur through hybridization between closely related species, resulting in an allopolyploid with multiple subgenomes. With the availability of affordable genotyping and a reference genome to locate markers, breeders of allopolyploids now have the opportunity to manipulate subgenomes independently. This also presents a unique opportunity to investigate epistatic interactions between homeologous orthologs across subgenomes. We present a statistical framework for partitioning genetic variance to the subgenomes of an allopolyploid, predicting breeding values for each subgenome, and determining the importance of inter-genomic epistasis. We demonstrate using an allohexaploid wheat breeding population evaluated in Ithaca, NY and an important wheat dataset from CIMMYT previously shown to demonstrate non-additive genetic variance. Subgenome covariance matrices were constructed and used to calculate subgenome interaction covariance matrices for variance component estimation and genomic prediction. We propose a method to extract population structure from all subgenomes at once before covariances are calculated to reduce collinearity between subgenome estimates. Variance parameter estimation was shown to be reliable for additive subgenome effects, but was less reliable for subgenome interaction components. Predictive ability was equivalent to current genomic prediction methods. Including only inter-genomic interactions resulted in the same increase in accuracy as modeling all pairwise marker interactions. Thus, we provide a new tool for breeders of allopolyploid crops to characterize the genetic architecture of existing populations, determine breeding goals, and develop new strategies for selection of additive effects and fixation of inter-genomic epistasis.
| S-EPMC6404612 | biostudies-other
Project description:Background and aimsThere is considerable interest in epidemiology to estimate an additive interaction effect between two risk factors in case-control studies. An additive interaction is defined as the differential reduction in absolute risk associated with one factor between different levels of the other factor. A stratified two-phase case-control design is commonly used in epidemiology to reduce the cost of assembling covariates. It is crucial to obtain valid estimates of the model parameters by accounting for the underlying stratification scheme to obtain accurate and precise estimates of additive interaction effects. The aim of this paper is to examine the properties of different methods for estimating model parameters and additive interaction effects under a stratified two-phase case-control design.MethodsUsing simulations, we investigate the properties of three existing methods, namely stratum-specific offset, inverse-probability weighting, and multiple imputation for estimating model parameters and additive interaction effects. We also illustrate these properties using data from two published epidemiology studies.ResultsSimulation studies show that the multiple imputation method performs well when both the true and analysis models are additive (i.e., does not include multiplicative interaction terms) but does not provide a discernible advantage over the offset method when the analysis models are non-additive (i.e., includes multiplicative interaction terms). The offset method exhibits the best overall properties when the analysis model contains multiplicative interaction effects.ConclusionWhen estimating additive interaction between risk factors in stratified two-phase case-control studies, we recommend estimating model parameters using multiple imputation when the analysis model is additive, and we recommend the offset method when the analysis model is non-additive.
| S-EPMC6925975 | biostudies-literature
Project description:MotivationThe use of single nucleotide polymorphism (SNP) interactions to predict complex diseases is getting more attention during the past decade, but related statistical methods are still immature. We previously proposed the SNP Interaction Pattern Identifier (SIPI) approach to evaluate 45 SNP interaction patterns/patterns. SIPI is statistically powerful but suffers from a large computation burden. For large-scale studies, it is necessary to use a powerful and computation-efficient method. The objective of this study is to develop an evidence-based mini-version of SIPI as the screening tool or solitary use and to evaluate the impact of inheritance mode and model structure on detecting SNP-SNP interactions.ResultsWe tested two candidate approaches: the 'Five-Full' and 'AA9int' method. The Five-Full approach is composed of the five full interaction models considering three inheritance modes (additive, dominant and recessive). The AA9int approach is composed of nine interaction models by considering non-hierarchical model structure and the additive mode. Our simulation results show that AA9int has similar statistical power compared to SIPI and is superior to the Five-Full approach, and the impact of the non-hierarchical model structure is greater than that of the inheritance mode in detecting SNP-SNP interactions. In summary, it is recommended that AA9int is a powerful tool to be used either alone or as the screening stage of a two-stage approach (AA9int+SIPI) for detecting SNP-SNP interactions in large-scale studies.Availability and implementationThe 'AA9int' and 'parAA9int' functions (standard and parallel computing version) are added in the SIPI R package, which is freely available at https://linhuiyi.github.io/LinHY_Software/.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC6289141 | biostudies-literature
Project description:In this paper, the influence of measurement errors in exposure doses in a regression model with binary response is studied. Recently, it has been recognized that uncertainty in exposure dose is characterized by errors of two types: classical additive errors and Berkson multiplicative errors. The combination of classical additive and Berkson multiplicative errors has not been considered in the literature previously. In a simulation study based on data from radio-epidemiological research of thyroid cancer in Ukraine caused by the Chornobyl accident, it is shown that ignoring measurement errors in doses leads to overestimation of background prevalence and underestimation of excess relative risk. In the work, several methods to reduce these biases are proposed. They are new regression calibration, an additive version of efficient SIMEX, and novel corrected score methods.
| S-EPMC4915607 | biostudies-literature