Control of confounding of genetic associations in stratified populations

To control for hidden population stratification in genetic-association studies, statistical methods that use marker genotype data to infer population structure have been proposed as a possible alternative to family-based designs. In principle, it is possible to infer population structure from associations between marker loci and from associations of markers with the trait, even when no information about the demographic background of the population is available. In a model in which the total population is formed by admixture between two or more subpopulations, confounding can be estimated and controlled. Current implementations of this approach have limitations, the most serious of which is that they do not allow for uncertainty in estimations of individual admixture proportions or for lack of identifiability of subpopulations in the model. We describe methods that overcome these limitations by a combination of Bayesian and classical approaches, and we demonstrate the methods by using data from three admixed populations--African American, African Caribbean, and Hispanic American--in which there is extreme confounding of trait-genotype associations because the trait under study (skin pigmentation) varies with admixture proportions. In these data sets, as many as one-third of marker loci show crude associations with the trait. Control for confounding by population stratification eliminates these associations, except at loci that are linked to candidate genes for the trait. With only 32 markers informative for ancestry, the efficiency of the analysis is 70%. These methods can deal with both confounding and selection bias in genetic-association studies, making family-based designs unnecessary.     

Optimal response-adaptive designs for continuous responses in phase III trials

Optimal response-adaptive designs in phase III clinical trial set up are gaining more interest. Most of the available designs are not based on any optimal consideration. An optimal design for binary responses is given by Rosenberger et al. (2001) and one for continuous responses is provided by Biswas and Mandal (2004). Recently, Zhang and Rosenberger (2006) proposed another design for normal responses. This paper illustrates that the Zhang and Rosenberger (2006) design is not suitable for normally distributed responses, in general. The approach cannot be extended for other continuous response cases, such as exponential or gamma. In this paper, we first describe when the optimal design of Zhang and Rosenberger (2006) fails. We then suggest the appropriate adjustments for designs in different continuous distributions. A unified framework to find optimal response-adaptive designs for two competing treatments is proposed. The proposed methods are illustrated using some real data.     

Integrating social science and genetics: news from the political front

There has been growing interest in the use of genetic models to expand the understanding of political preferences, attitudes, and behaviors. Researchers in the social sciences have begun incorporating these models and have revealed that genetic differences account for individual differences in political beliefs, behaviors, and responses to the political environment. The first Integrating Genetics and the Social Sciences Conference, held at Boulder, Colorado in May of 2010, brought together these researchers. As a result, we jointly review the last 5 years of research in this area. In doing so, we explicate the methods, findings, and limitations of behavior genetic approaches, including twin designs, association studies, and genome-wide analyses, in their application toward exploring political preferences.     

Statistical validation of surrogate endpoints: is bone density a valid surrogate for fracture?

In the treatment of osteoporosis using anti-resorptive agents there has been increasing interest in quantifying the relationship between fracture endpoints and surrogates such as bone mineral density (BMD) or bone turnover markers. Statistical methodology constitutes a critical component of assessing surrogate validity. Depending on study designs, data resources, and statistical methods used for analyses, one has to use caution when interpreting results from different analyses, especially when results are disparate. For example, analyses based on individual patient data reported that only a limited proportion of the anti-fracture efficacy was explained by BMD increases for agents such as alendronate, risedronate and raloxifene. Analyses employing meta-regression based on summary statistics, however, indicated that most of the anti-fracture benefits were due to improvements in BMD. In this paper, we review definitions of surrogate endpoints and requirements for their statistical validation. We evaluate whether BMD meets these requirements as a possible surrogate for fracture. Our review indicates that the actual BMD value is correlated with fracture risk and thus BMD is useful in identifying patients that might need treatment. There is limited evidence to support BMD increase with anti-resorptive agents as a reliable substitute for fracture risk reduction. Strengths and limitations for various statistical methods are discussed.     

Drop-the-losers design: normal case

Drop-the-losers designs are statistical designs which have two stages of a trial separated by a data based decision. In the first stage k experimental treatments and a control are administered. During a transition period, the empirically best experimental treatment is selected for continuation into the second phase, along with the control. At the study's end, inference focuses on the comparison of the selected treatment with the control using both stages' data. Traditional methods used to make inferences based on both stages' data can yield tests with higher than advertised levels of significance and confidence intervals with lower than advertised confidence. For normally distributed data, methods are provided to correct these deficiencies, providing confidence intervals with accurate levels of confidence. Drop-the-losers designs are particularly applicable to biopharmaceutical clinical trials where they can allow Phase II and Phase III clinical trials to be conducted under a single protocol with the use of all available data.     

Epidemiological designs for vaccine safety assessment: methods and pitfalls

Three commonly used designs for vaccine safety assessment post licensure are cohort, case-control and self-controlled case series. These methods are often used with routine health databases and immunisation registries. This paper considers the issues that may arise when designing an epidemiological study, such as understanding the vaccine safety question, case definition and finding, limitations of data sources, uncontrolled confounding, and pitfalls that apply to the individual designs. The example of MMR and autism, where all three designs have been used, is presented to help consider these issues.     

Sampling designs, field techniques and analytical methods for systematic plant population surveys

Summary Intense pressures on the use and management of land underscore the need for reliable and up-to-date information on the status of native species. The outcomes of the most recent plant population surveys commissioned by agencies are generally limited by faults or omissions in survey design. There is little guidance on how to design and implement field surveys of plant populations in ways that address the most pertinent gaps in our current knowledge and provide answers of known reliability. In this paper, I used the International Union for the Conservation of Nature (IUCN) Red List criteria as a framework to define the data required from surveys to assess the conservation status of potentially threatened species. The criteria address the location and geographical range of extant populations, aspects of species' life history, the size and structure of extant populations and rates of change in abundance and range. I have described survey designs and sampling techniques for estimating these parameters. Choices of appropriate methods that consider trade-offs between desired levels of precision and rigour and sampling effort are illustrated using surveys of 13 Tasmanian Epacris species as examples. Key elements of the approach are: (i) systematic approaches to field searches and recording both positive and negative search outcomes; (ii) construction and testing of intuitive or quantitative distribution models in an explicit experimental framework; (iii) rigorous cost-effective sampling designs, systematic field methodologies and simple analytical techniques to estimate both the magnitude and uncertainty of distribution and abundance; (iv) assessment of the merits and limitations of alternative sampling options; and (v) inference of changes in distribution and abundance by judicious use of historical data and field evidence of recent population processes.     

Systematic comparison of the empirical and factorial methods used to estimate the nutrient requirements of growing pigs

Empirical and factorial methods are currently used to estimate nutrient requirements for domestic animals. The purpose of this study was to estimate the nutrient requirements of a given pig population using the empirical and factorial methods; to establish the relationship between the requirements estimated with these two methods; and to study the limitations of the methods when used to determine the level of a nutrient needed to optimize individual and population responses of growing pigs. A systematic analysis was carried out on optimal lysine-to-net-energy (Lys : NE) ratios estimated by the empirical and factorial methods using a modified InraPorc® growth model. Sixty-eight pigs were individually simulated based on detailed experimental data. In the empirical method, population responses were estimated by feeding pigs with 11 diets of different Lys : NE ratios. Average daily gain and feed conversion ratio were the chosen performance criteria. These variables were combined with economic information to estimate the economic responses. In the factorial method, the Lys : NE ratio for each animal was estimated by model inversion. Optimal Lys : NE ratios estimated for growing pigs (25 to 105 kg) differed between the empirical and the factorial method. When the average pig is taken to represent a population, the factorial method does not permit estimation of the Lys : NE ratio that maximizes the response of heterogeneous populations in a given time or weight interval. Although optimal population responses are obtained by the empirical method, the estimated requirements are fixed and cannot be used for other growth periods or populations. This study demonstrates that the two methods commonly used to estimate nutrient requirements provide different nutrient recommendations and have important limitations that should be considered when the goal is to optimize the response of individuals or pig populations.     

On the use of cellular telephony for audio interaction with animals

Playback is an important method of surveying animals, assessing habitats and studying animal communication. However, conventional playback methods require on-site observers and therefore become labour-intensive when covering large areas. Such limitations could be circumvented by the use of cellular telephony, a ubiquitous technology with increasing biological applications. In addressing concerns about the low audio quality of cellular telephones, this paper presents experimental data to show that owls of two species (Strix varia and Megascops asio) respond similarly to calls played through cellular telephones as to calls played through conventional playback technology. In addition, the telephone audio recordings are of sufficient quality to detect most of the two owl species' responses. These findings are a first important step towards large-scale applications where networks of cellular phones conduct real-time monitoring tasks.     

Logistic regression for clustered data from environmental monitoring programs

Large-scale surveys, such as national forest inventories and vegetation monitoring programs, usually have complex sampling designs that include geographical stratification and units organized in clusters. When models are developed using data from such programs, a key question is whether or not to utilize design information when analyzing the relationship between a response variable and a set of covariates. Standard statistical regression methods often fail to account for complex sampling designs, which may lead to severely biased estimators of model coefficients. Furthermore, ignoring that data are spatially correlated within clusters may underestimate the standard errors of regression coefficient estimates, with a risk for drawing wrong conclusions. We first review general approaches that account for complex sampling designs, e.g. methods using probability weighting, and stress the need to explore the effects of the sampling design when applying logistic regression models. We then use Monte Carlo simulation to compare the performance of the standard logistic regression model with two approaches to model correlated binary responses, i.e. cluster-specific and population-averaged logistic regression models. As an example, we analyze the occurrence of epiphytic hair lichens in the genus Bryoria; an indicator of forest ecosystem integrity. Based on data from the National Forest Inventory (NFI) for the period 1993–2014 we generated a data set on hair lichen occurrence on  >100,000 Picea abies trees distributed throughout Sweden. The NFI data included ten covariates representing forest structure and climate variables potentially affecting lichen occurrence. Our analyses show the importance of taking complex sampling designs and correlated binary responses into account in logistic regression modeling to avoid the risk of obtaining notably biased parameter estimators and standard errors, and erroneous interpretations about factors affecting e.g. hair lichen occurrence. We recommend comparisons of unweighted and weighted logistic regression analyses as an essential step in development of models based on data from large-scale surveys.     

Genetic dissection methods: designs used for tests of gene-environment interaction

Given recent advances in the field of molecular genetics, many have recognized the need to exploit either study designs or analytical methods to test hypotheses with gene-by-environment (G x E) interactions. The partial-collection designs, including case-only, partial case-control, and case-parent trio designs, have been suggested as attractive alternatives to the complete case-control design both for increased statistical efficiency and reduced data needs. However, common problems in genetic epidemiology studies, such as, presence of G x E correlation in the population, population mixture, and genotyping error may reduce the validity of these designs. On the basis of previous simulation studies and empirical data and given the potential limitations and uncertainty of assumptions of partial-collection designs, the case-control design is the optimal choice versus partial-collection designs.     

Centronuclear (myotubular) myopathy

In recent years, the use of adaptive design methods in clinical research and development based on accrued data has become very popular due to its flexibility and efficiency. Based on adaptations applied, adaptive designs can be classified into three categories: prospective, concurrent (ad hoc), and retrospective adaptive designs. An adaptive design allows modifications made to trial and/or statistical procedures of ongoing clinical trials. However, it is a concern that the actual patient population after the adaptations could deviate from the originally target patient population and consequently the overall type I error (to erroneously claim efficacy for an infective drug) rate may not be controlled. In addition, major adaptations of trial and/or statistical procedures of on-going trials may result in a totally different trial that is unable to address the scientific/medical questions the trial intends to answer. In this article, several commonly considered adaptive designs in clinical trials are reviewed. Impacts of ad hoc adaptations (protocol amendments), challenges in by design (prospective) adaptations, and obstacles of retrospective adaptations are described. Strategies for the use of adaptive design in clinical development of rare diseases are discussed. Some examples concerning the development of Velcade intended for multiple myeloma and non-Hodgkin's lymphoma are given. Practical issues that are commonly encountered when implementing adaptive design methods in clinical trials are also discussed.     

LADES: A Software for Constructing and Analyzing Longitudinal Designs in Biomedical Research

One of the most important steps in biomedical longitudinal studies is choosing a good experimental design that can provide high accuracy in the analysis of results with a minimum sample size. Several methods for constructing efficient longitudinal designs have been developed based on power analysis and the statistical model used for analyzing the final results. However, development of this technology is not available to practitioners through user-friendly software. In this paper we introduce LADES (Longitudinal Analysis and Design of Experiments Software) as an alternative and easy-to-use tool for conducting longitudinal analysis and constructing efficient longitudinal designs. LADES incorporates methods for creating cost-efficient longitudinal designs, unequal longitudinal designs, and simple longitudinal designs. In addition, LADES includes different methods for analyzing longitudinal data such as linear mixed models, generalized estimating equations, among others. A study of European eels is reanalyzed in order to show LADES capabilities. Three treatments contained in three aquariums with five eels each were analyzed. Data were collected from 0 up to the 12th week post treatment for all the eels (complete design). The response under evaluation is sperm volume. A linear mixed model was fitted to the results using LADES. The complete design had a power of 88.7% using 15 eels. With LADES we propose the use of an unequal design with only 14 eels and 89.5% efficiency. LADES was developed as a powerful and simple tool to promote the use of statistical methods for analyzing and creating longitudinal experiments in biomedical research.     

Analyses of physiological evolutionary response

Selection studies are useful if they can provide us with insights into the patterns and processes of evolution in populations under controlled conditions. In this context it is particularly valuable to be able to analyze the limitations of and constraints on evolutionary responses to allow predictions concerning evolutionary change. The concept of a selection pathway is presented as a means of visualizing this predictive process and the constraints that help define the population's response to selection. As pointed out by Gould and Lewontin, history and chance are confounding forces that can mask or distort the adaptive response. Students of the evolutionary responses of organisms are very interested in the effects of these confounding forces, since they play a critical role not only in the laboratory but also in natural selection in the field. In this article, we describe some methods that are a bit different from those used in most studies for examining data from laboratory selection studies. These analytical methods are intended to provide insights into the physiological mechanisms by which evolutionary responses to the environment proceed. Interestingly, selection studies often exhibit disparate responses in replicate populations. We offer methods for analyzing these disparate responses in replicate populations to better understand this very important source of variability in the evolutionary response. We review the techniques of Travisano et al. and show that these approaches can be used to investigate the relative roles of adaptation, history, and chance in the evolutionary responses of populations of Drosophila melanogaster to selection for enhanced desiccation resistance. We anticipate that a wider application of these techniques will provide valuable insights into the organismal, genetic, and molecular nature of the constraints, as well as the factors that serve to enhance or, conversely, to mask the effects of chance. Such studies should help to provide a more detailed understanding of the processes producing evolutionary change in populations.     

Estimating individualized treatment regimes from crossover designs

The field of precision medicine aims to tailor treatment based on patient-specific factors in a reproducible way. To this end, estimating an optimal individualized treatment regime (ITR) that recommends treatment decisions based on patient characteristics to maximize the mean of a prespecified outcome is of particular interest. Several methods have been proposed for estimating an optimal ITR from clinical trial data in the parallel group setting where each subject is randomized to a single intervention. However, little work has been done in the area of estimating the optimal ITR from crossover study designs. Such designs naturally lend themselves to precision medicine since they allow for observing the response to multiple treatments for each patient. In this paper, we introduce a method for estimating the optimal ITR using data from a 2 × 2 crossover study with or without carryover effects. The proposed method is similar to policy search methods such as outcome weighted learning; however, we take advantage of the crossover design by using the difference in responses under each treatment as the observed reward. We establish Fisher and global consistency, present numerical experiments, and analyze data from a feeding trial to demonstrate the improved performance of the proposed method compared to standard methods for a parallel study design.     

Optimal designs for a multiresponse Emax model and efficient parameter estimation

The aim of dose finding studies is sometimes to estimate parameters in a fitted model. The precision of the parameter estimates should be as high as possible. This can be obtained by increasing the number of subjects in the study, N, choosing a good and efficient estimation approach, and by designing the dose finding study in an optimal way. Increasing the number of subjects is not always feasible because of increasing cost, time limitations, etc. In this paper, we assume fixed N and consider estimation approaches and study designs for multiresponse dose finding studies. We work with diabetes dose–response data and compare a system estimation approach that fits a multiresponse Emax model to the data to equation‐by‐equation estimation that fits uniresponse Emax models to the data. We then derive some optimal designs for estimating the parameters in the multi‐ and uniresponse Emax model and study the efficiency of these designs.     

Discriminant models for high-throughput proteomics mass spectrometer data

We use several different multivariate analysis methods to discriminate between diseased and healthy patients using protein mass spectrometer data provided by Duke University. Two problems were presented by the university; one in which the responses (diseased or healthy) of the patients were not known and second, when the responses were known. In the latter case, the data can be used as a 'training' set. We attempted both problems. In particular, we use principle component analysis along with clustering methods to discriminate for the first problem set and partial least squares coupled with logistic and discriminant methods when the responses were known. In addition, we were able to detect regions of interest in the spectrum where there were differences in the protein patterns between healthy and diseased patients. There was considerable effort involved in the preprocessing of the data. We used a binning approach to reduce the number of variables rather than peak heights or peak areas. We performed a square root transformation on the data to help stabilize the variance; this in turn made a significant improvement in clustering results.     

Possibilities and limits of dendrogeomorphic data as a basis for defining thresholds for landslide triggering

Dendrogeomorphic (tree-ring based) methods are an effective tool for determining the spatial and temporal activity of landslide movements. Moreover, the obtained chronological data can be used for the analysis of their potential triggers. However, the use of tree-ring based chronologies for defining trigger thresholds is very rare and has not yet been critically evaluated. Given the well-known limitations of dendrogeomorphic methods, this study aims to define the limitations and advantages of this approach for trigger threshold analysis. Thus, tree-ring based data on the activity of 26 landslides, originating from 2644 tree-ring series of disturbed trees (and 180 tree-ring series of reference trees), were used in this study. Total Water Content (TWC) as a combination of precipitation sum (PS) and snow water equivalent (SWE) was analyzed as landslide trigger. The obtained values of the range of trigger thresholds were relatively high. The considerable heterogeneity of the results seems to be largely influenced by the character of the data obtained by dendrogeomorphic methods. In the discussion section, all potential influences of the tree-ring based approach on the obtained results and the possibilities of their elimination are discussed. Among the most important ones can be considered the inertia of tree response to landslide movements, the ability of trees in general to capture landslide movements, as well as the use of the approach to define a landslide event. However, in addition to dendrogeomorphic influences, the heterogeneity of the landslides studied and their geological structure themselves must be taken into account.     

A general framework for two-stage analysis of genome-wide association studies and its application to case-control studies

Two-stage analyses of genome-wide association studies have been proposed as a means to improving power for designs including family-based association and gene-environment interaction testing. In these analyses, all markers are first screened via a statistic that may not be robust to an underlying assumption, and the markers thus selected are then analyzed in a second stage with a test that is independent from the first stage and is robust to the assumption in question. We give a general formulation of two-stage designs and show how one can use this formulation both to derive existing methods and to improve upon them, opening up a range of possible further applications. We show how using simple regression models in conjunction with external data such as average trait values can improve the power of genome-wide association studies. We focus on case-control studies and show how it is possible to use allele frequencies derived from an external reference to derive a powerful two-stage analysis. An illustration involving the Wellcome Trust Case-Control Consortium data shows several genome-wide-significant associations, subsequently validated, that were not significant in the standard analysis. We give some analytic properties of the methods and discuss some underlying principles.     

Generic framework for high-dimensional fixed-effects ANOVA

In functional genomics it is more rule than exception that experimental designs are used to generate the data. The samples of the resulting data sets are thus organized according to this design and for each sample many biochemical compounds are measured, e.g. typically thousands of gene-expressions or hundreds of metabolites. This results in high-dimensional data sets with an underlying experimental design. Several methods have recently become available for analyzing such data while utilizing the underlying design. We review these methods by putting them in a unifying and general framework to facilitate understanding the (dis-)similarities between the methods. The biological question dictates which method to use and the framework allows for building new methods to accommodate a range of such biological questions. The framework is built on well known fixed-effect ANOVA models and subsequent dimension reduction. We present the framework both in matrix algebra as well as in more insightful geometrical terms. We show the workings of the different special cases of our framework with a real-life metabolomics example from nutritional research and a gene-expression example from the field of virology.