Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “statistical inference”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,405 records · Page 78Linked to original sources
PubMed2026

Phylogenomic subsampling and upsampling for efficient evolutionary analyses of big data.

Long runtimes, high memory demands, and reliance on high-performance computing impede phylogenomic analyses. We review a scalable phylogenomic subsampling with upsampling (PSU) framework to address this challenge, which reduces runtime and memory requirements by orders of magnitude. In PSU, small subsamples of sites from a concatenated alignment are analyzed, which are expanded by upsampling before inference, and the resulting inferences are aggregated to obtain evolutionary estimates. PSU harnesses the fact that the computational cost of maximum likelihood analysis is strongly influenced by the number of distinct site patterns in the concatenated alignment, whereas statistical power depends primarily on the amount of evolutionary information represented by the total number of sites and substitutions. By reducing the former while restoring the latter through upsampling, PSU can approximate many full-alignment analyses at substantially lower computational cost. Analysis of simulated and empirical datasets shows that PSU can accurately estimate bootstrap support values, select the optimal substitution model, test evolutionary hypotheses, and infer branch lengths, divergence times, and associated uncertainty measures. PSU also provides distributions of inferred clade support across independent subsamples, enabling detection of conflicting phylogenetic signals that may remain hidden in conventional bootstrap analysis of concatenated alignments. Automated tuning of subsample size, the number of subsamples, and the number of upsampling replicates make PSU practical. We suggest that PSU is a general approach for scalable phylogenomic inference using a broad range of statistical methods. By enabling analyses of genome-scale alignments on commodity hardware, PSU broadens research access and reduces environmental and infrastructural costs of big-data phylogenomics.

Phylogeny↗
PubMed2003

Gene microarrays in hippocampal aging: statistical profiling identifies novel processes correlated with cognitive impairment.

Gene expression microarrays provide a powerful new tool for studying complex processes such as brain aging. However, inferences from microarray data are often hindered by multiple comparisons, small sample sizes, and uncertain relationships to functional endpoints. Here we sought gene expression correlates of aging-dependent cognitive decline, using statistical profiling of gene microarrays in well powered groups of young, mid-aged, and aged rats (n = 10 per group). Animals were trained on two memory tasks, and the hippocampal CA1 region of each was analyzed on an individual microarray (one chip per animal). Aging- and cognition-related genes were identified by testing each gene by ANOVA (for aging effects) and then by Pearson's test (correlating expression with memory). Genes identified by this algorithm were associated with several phenomena known to be aging-dependent, including inflammation, oxidative stress, altered protein processing, and decreased mitochondrial function, but also with multiple processes not previously linked to functional brain aging. These novel processes included downregulated early response signaling, biosynthesis and activity-regulated synaptogenesis, and upregulated myelin turnover, cholesterol synthesis, lipid and monoamine metabolism, iron utilization, structural reorganization, and intracellular Ca2+ release pathways. Multiple transcriptional regulators and cytokines also were identified. Although most gene expression changes began by mid-life, cognition was not clearly impaired until late life. Collectively, these results suggest a new integrative model of brain aging in which genomic alterations in early adulthood initiate interacting cascades of decreased signaling and synaptic plasticity in neurons, extracellular changes, and increased myelin turnover-fueled inflammation in glia that cumulatively induce aging-related cognitive impairment.

Aging↗
PubMed2006

A dose-response model for the conventional phototherapy of the newborn.

Jaundice of the newborn is a common problem as a consequence of the rapid increment of blood bilirubin in the first days of live. In most cases, it is considered a physiological transient situation, but unmanaged hyperbilirubinemia can lead to death or serious injuries for the survivors. For decades, phototherapy has been used as the main method for prevention and treatment of hyperbilirubinaemia of the newborn. This work aims at finding a predictive model for the decrement of blood bilirubin for patients submitted to conventional phototherapy. Data from the phototherapy of 90 term newborns were collected and used in a multiple regression method. A rigorous statistical analysis was done in order to guarantee a correct and valid model. The obtained model was able to explain 78% of the variation of the dependent variable. We show that it is possible to predict the total serum bilirubin of the patient under conventional phototherapy by knowing its birth weight, bilirubin level at the beginning of treatment and the radiant energy density (dose). Besides, it is possible to infer the time necessary for a given decrement of bilirubin, under approximately constant irradiance. Statistical analysis of the obtained model shows that it is valid for several ranges of birth weight, initial bilirubin level, and radiant energy density. It is expected that the proposed model can be useful in the clinical management of hyperbilirubinemia of the newborn.

Computer Simulation↗
PubMed1996

An investigation of systematic changes in occupational exposure.

Nonstationary behavior in occupational exposure was examined among a number of job groups from different industries. A change in the mean level of exposure between two survey periods was evaluated by applying mixed-effects models. Overall, differences between surveys were observed in slightly more than one-third of the industries analyzed and in about one-quarter of the total number of comparisons performed. Exposures in the majority of cases decreased in the later survey. Further analyses examined the impact of nonstationary exposures on the estimation of the between- and within-worker components of variance. When changes in the mean exposure level were detected, point estimates of the variance components generated under the mixed model were compared with those estimates obtained under the one-way random-effects model, which assumes that the mean exposure level remains constant over time. The results indicate that the magnitude of the bias in the variance component estimates can be substantial when the misspecified model is applied. It is concluded that, in the absence of changes known to affect exposure, data collected within a year are likely to result in relatively valid inferences about mean and variance parameters using models that assume stationarity; for periods extending beyond a year, systematic changes in exposure are more likely to occur. Thus, exposure assessment strategies should be designed so that sufficient data are collected among groups of workers to investigate systematic changes and to ensure that appropriate statistical models are applied. In this way, occupational hygienists will be able to make reliable inferences about the underlying distribution of exposures pertinent to each occupational group.

Analysis of Variance↗
PubMed2001

Unfolding of microarray data.

The use of DNA microarrays for the analysis of complex biological samples is becoming a mainstream part of biomedical research. One of the most commonly used methods compares the relative abundance of mRNA in two different samples by probing a single DNA microarray simultaneously. The simplicity of this concept sometimes masks the complexity of capturing and processing microarray data. On the basis of the analysis of many of our microarray experiments, we identified the major causes of distortion of the microarray data and the sources of noise. In this study, we provide a systematic statistical approach for extraction of true expression ratios from raw microarray data, which we describe as an unfolding process. The results of this analysis are presented in the form of a model describing the relationship between the measured fluorescent intensities and the concentrations of mRNA transcripts. We developed and tested several algorithms for inference of the model parameters for the microarray data. Special emphasis is given to the statistical robustness of these algorithms, in particular resistance to outliers. We also provide methods for measurement of noise and reproducibility of the microarray experiments.

Computational Biology↗
PubMed2000

Lines that connect: assessing the causality inference in the case of particulate pollution.

The question of when it would be appropriate to conclude that the associations between particulate pollution and various outcomes (including mortality) should be judged as causal in nature has been difficult and controversial. Although such a judgment must be subject to revision, the volume of new information and new experimental findings has been so great that such a reevaluation is required at frequent intervals. The useful summary by Gamble [PM(2. 5) and Mortality in Long-Term Prospective Cohort Studies: Cause-Effect or Statistical Associations? Environ Health Perspect 106:535-554 (1998)] of the reasons why a causal inference was, in his opinion, not justified provides a basis for reevaluation in the light of new data. Such a reexamination indicates that the associative evidence is now stronger and that the biologic basis for a number of adverse effects has now been demonstrated. All of the useful guideline criteria customarily applied to such questions seem to have been met, although there is still much to be learned about interactive effects and the possibility of statistical thresholds.

Air Pollution↗
PubMed2005

Clinical versus statistical prediction: the contribution of Paul E. Meehl.

The background of Paul E. Meehl's work on clinical versus statistical prediction is reviewed, with detailed analyses of his arguments. Meehl's four main contributions were the following: (a) he put the question, of whether clinical or statistical combinations of psychological data yielded better predictions, at center stage in applied psychology; (b) he convincingly argued, against an array of objections, that clinical versus statistical prediction was a real (not concocted) problem needing thorough study; (c) he meticulously and even-handedly dissected the logic of clinical inference from theoretical and probabilistic standpoints; and (c) he reviewed the studies available in 1954 and thereafter, which tested the validity of clinical versus statistical predictions. His early conclusion that the literature strongly favors statistical prediction has stood up extremely well, and his conceptual analyses of the prediction problem (especially his defense of applying aggregate-based probability statements to individual cases) have not been significantly improved since 1954.

Forecasting↗
PubMed1992

The effect of posture on three objective audiological measures.

This study examines the effect of posture on click evoked otoacoustic emissions, tympanic membrane displacement, and travelling wave velocity obtained using the auditory brainstem response. Statistically significant changes with posture were observed for each technique. The changes in evoked emission and tympanic membrane displacement measurements were comparable with those reported by previous experiments. Travelling wave velocity measurements were shown to be sensitive to inferred posturally-induced changes in labyrinthine fluid pressure of around 150 mm saline. There was no statistically significant correlation between posturally-induced changes measured by the three techniques. It is suggested that different mechanisms are responsible for the posturally-induced changes observed for the three techniques.

Adult↗
PubMed2005

Detecting genome wide haplotype sharing using SNP or microsatellite haplotype data.

Genome wide association studies using high throughput technology are already being conducted despite the significant hurdles that need to be overcome (Nat Rev Genet 6:95-108, 2005; Nat Rev Genet 6:109-118, 2005). Methods for detecting haplotype association signals in genome wide haplotype datasets are as yet very limited. Much methodological research has already been devoted to linkage disequilibrium (LD) fine mapping where the focus is the identification of the disease locus rather than the detection of a disease signal. Applications of these approaches to genome wide scanning are limited by the strong model assumptions of the sharing process, which lead to computational complexity. We describe a new algorithm for the initial identification of disease susceptibility loci in genome wide haplotype association studies. Excess sharing of ancestral haplotypes, which indicates the presence of a disease locus, is detected with a simple, easy to interpret, chi2 based statistic. The method allows genome wide scanning for qualitative traits within reasonable computational timeframes and can serve as a first pass analysis prior to the usage of likelihood based methods, providing candidate regions and inferred susceptibility haplotypes. Our method makes no assumptions regarding the population history or the pattern of background LD. Statistical significance is evaluated with permutation tests. The method is illustrated on simulated and real data where it is applied to simple (cystic fibrosis) and complex disease (multiple sclerosis) examples. The statistic has low type I error and greater power to map disease loci over conventional single marker tests for low to moderate levels of LD.

Algorithms↗
PubMed2001

Most powerful permutation invariant tests for relatedness hypotheses using genotypic data.

The problem of inferring kinship structure among a sample of individuals using genetic markers is considered with the objective of developing hypothesis tests for genetic relatedness with nearly optimal properties. The class of tests considered are those that are constrained to be permutation invariant, which in this context defines tests whose properties do not depend on the labeling of the individuals. This is appropriate when all individuals are to be treated identically from a statistical point of view. The approach taken is to derive tests that are probably most powerful for a permutation invariant alternative hypothesis that is, in some sense, close to a null hypothesis of mutual independence. This is analagous to the locally most powerful test commonly used in parametric inference. Although the resulting test statistic is a U-statistic, normal approximation theory is found to be inapplicable because of high skewness. As an alternative it is found that a conditional procedure based on the most powerful test statistic can calculate accurate significance levels without much loss in power. Examples are given in which this type of test proves to be more powerful than a number of alternatives considered in the literature, including Queller and Goodknight's (1989) estimate of genetic relatedness, the average number of shared alleles (Blouin, 1996), and the number of feasible sibling triples (Almudevar and Field, 1999).

Alleles↗
PubMed2004

Use of a dense single nucleotide polymorphism map for in silico mapping in the mouse.

Rapid expansion of available data, both phenotypic and genotypic, for multiple strains of mice has enabled the development of new methods to interrogate the mouse genome for functional genetic perturbations. In silico mapping provides an expedient way to associate the natural diversity of phenotypic traits with ancestrally inherited polymorphisms for the purpose of dissecting genetic traits. In mouse, the current single nucleotide polymorphism (SNP) data have lacked the density across the genome and coverage of enough strains to properly achieve this goal. To remedy this, 470,407 allele calls were produced for 10,990 evenly spaced SNP loci across 48 inbred mouse strains. Use of the SNP set with statistical models that considered unique patterns within blocks of three SNPs as an inferred haplotype could successfully map known single gene traits and a cloned quantitative trait gene. Application of this method to high-density lipoprotein and gallstone phenotypes reproduced previously characterized quantitative trait loci (QTL). The inferred haplotype data also facilitates the refinement of QTL regions such that candidate genes can be more easily identified and characterized as shown for adenylate cyclase 7.

Adenylyl Cyclases↗
PubMed1992

The statistical analysis of circadian phase and amplitude in constant-routine core-temperature data.

Accurate estimation of the phases and amplitude of the endogenous circadian pacemaker from constant-routine core-temperature series is crucial for making inferences about the properties of the human biological clock from data collected under this protocol. This paper presents a set of statistical methods based on a harmonic-regression-plus-correlated-noise model for estimating the phases and the amplitude of the endogenous circadian pacemaker from constant-routine core-temperature data. The methods include a Bayesian Monte Carlo procedure for computing the uncertainty in these circadian functions. We illustrate the techniques with a detailed study of a single subject's core-temperature series and describe their relationship to other statistical methods for circadian data analysis. In our laboratory, these methods have been successfully used to analyze more than 300 constant routines and provide a highly reliable means of extracting phase and amplitude information from core-temperature data.

Adult↗
PubMed2005

F-statistics under alternation of sexual and asexual reproduction: a model and data from schistosomes (platyhelminth parasites).

Accurate inferences on population genetics data require a sound underlying theoretical null model. Nearly nothing is known about the gene dynamics of organisms with complex life cycles precluding any biological interpretation of population genetics parameters. In this article, we used an infinite island model to derive the expectations of those parameters for the life cycle of a dioecious organism obligatorily alternating sexual and asexual reproductions as it is the case for schistosomes (plathyhelminth parasites). This model allowed us to investigate the effects of the degree of mixing among individuals coming from different subpopulations at each new generation (represented in the model by the migration rates before and after clonal reproductions) and the variance in the reproductive success of individuals during the clonal phase. We also consider the effects of different migration rates and degrees of clonal reproductive skew between male and female individuals. Results show that the variance in the reproductive success of clones is very important in shaping the distribution of the genetic variability both within and among subpopulations. Thus, higher variance in the reproductive success of clones generates heterozygous excesses within subpopulations and also increases genetic differentiation between them. Migration occurring before and after asexual reproduction has different effects on the patterns of F(IS) and F(ST). When males and females display different degrees of reproductive skew or migration rates, we observe differences in their respective population genetic structure. While results of the model apply to any organism alternating sexual and clonal reproductions (e.g. all parasitic trematodes, many plants, and all aphididae), we finally confront some of these theoretical expectations to empirical data from Schistosoma mansoni infecting Rattus rattus in Guadeloupe.

Animals↗
PubMed2007

A comparison of denominator degrees of freedom methods for multiple observer ROC analysis.

There are several methods available for analysing multireader ROC studies that generalize results to both the reader and case populations. Two of these methods--the Dorfman-Berbaum-Metz (DBM) method and the Obuchowki-Rockette (OR) method--appear to be quite different in their original formulations. However, recently it has been shown that the DBM and OR procedures yield the same test statistic when based on the same accuracy measure and covariance estimation method, but inferences can vary depending on which denominator degrees of freedom (ddf) method, DBM or OR, is used. I show in simulations that there are problems with both ddf methods: OR is ultraconservative with significance levels considerably below the nominal level, and DBM can result in extremely wide confidence intervals because the ddf can be close to zero. I propose a new ddf method that overcomes both of these problems and can be used with either the OR or DBM procedure.

Aortic Aneurysm, Thoracic↗
PubMed1983

The surgeon general's "epidemiologic criteria for causality": a criticism of Burch's critique.

In this paper, it has not been possible to critically and objectively assess each of the points made by Burch, since it would be time-consuming both for this author as well as for the reader. However, the major areas of concern expressed by Burch have been reviewed and evaluated. This has in many instances required going back to the original reports of studies to which Burch refers. In doing so, it came as a complete surprise to note that Burch has incompletely presented the findings of several studies or has omitted discussing others more fully. This is, needless to say, most disturbing. In viewing the issue of the causal interpretation of the cigarette smoking--lung cancer relationship, it would appear that Burch would not be satisfied unless there is a randomized controlled experiment in humans. However, since such an experiment seems hardly feasible, one must depend upon a synthesis of findings of epidemiologic observations, experimental work on animals and studies of chemical constituents of tobacco and cigarette smoke. However, these do not seem to satisfy Burch, who has developed a theoretical conceptual framework for the etiology of cancer and many other diseases, based upon statistical models and equations. Such an approach is extremely limited. Scientific information and inferences are in the public domain, thereby allowing criticism and evaluation. It is customary, in the experimental sciences, for a scientist who is dissatisfied with the findings of another scientist, to attempt to repeat the experiment to see if his findings are the same or different. This should also be expected in the cigarette smoking-lung cancer issue.(ABSTRACT TRUNCATED AT 250 WORDS)

Adolescent↗
PubMed1994

Comments on the statistical aspects of the NRC's report on DNA typing.

The goal of the NRC report on DNA typing was to answer a "crescendo of questions concerning DNA typing," many of them in the areas of population genetics and statistics. Unfortunately, few of these questions were answered adequately. In lieu of answering these questions, the panel proposed another conservative method of forensic inference, the "ceiling principle." Aside from its extreme conservativeness, this new method is difficult to justify because it is based on inadequate population genetics and statistical theory. Moreover, in its ultimate implementation, the panel's method will depend on a population genetics study whose rationale is questionable. In this article, we elaborate some of the general comments we made about the NRC report in a recent article [1]. Specifically we cover three topics. First we question the statistical basis for the ceiling principle, showing that the empirical results that motivated the method are likely to be misinterpreted and showing, by power calculations, that the effects of population substructure cannot be substantial. Second, we show that the study design to determine "ceiling" allele frequencies has several undesirable statistical properties. Finally, we discuss the estimation of handling errors from the statistical perspective, a subject treated inadequately by the report.

DNA Fingerprinting↗
PubMed1996

Inferring frequency dependent selection from the molecular evolution of a rapidly evolving virus: a theoretical investigation.

Hypotheses have been put forward suggesting that immune selection generates much of the intra-patient genetic diversity of rapidly evolving viruses. A Monte Carlo simulation is presented which models sequence evolution in an HIV-like virus under selection from the immune system. Measurements of evolutionary change are then made from the resulting sequences, generating predicted outcomes for each scenario. Frequency dependent immune selection is shown by two statistical measurements to have a significant effect on viral sequence evolution. The use of drawing inferences about underlying evolutionary processes from samples of viral diversity in infected individuals is discussed.

Evolution, Molecular↗
PubMed1996

Inconsistency of evolutionary tree topology reconstruction methods when substitution rates vary across characters.

A fundamental problem in reconstructing the evolutionary history of a set of species is to infer the topology of the evolutionary tree that relates those species. A statistical method for estimating such a topology from character data is called consistent if, given data from more and more characters, the method is sure to converge to the true topology. A number of popular methods are based on modeling the evolution of each character as a Markov process along the evolutionary tree. The standard models further assume that each character has in fact evolved according to the same Markov process. This homogeneity assumption is unrealistic; for example, different types of characters are known to experience substitutions at different rates. Certain distance and maximum likelihood methods for topology estimation have been shown to be consistent under the homogeneity assumption. Here we give examples showing that these methods can fail to be consistent when the homogeneity assumption is relaxed. The examples are very simple, requiring only four taxa, binary characters, and characters that evolve at two different rates.

Animals↗