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 1,153 records · Page 64Linked to original sources
PubMed2006

Population genetics and molecular epidemiology or how to "débusquer la bête".

Parasites represent a great proportion of the world's living organisms and are of overwhelming significance because of their impact on hosts (evolutionarily, medically, agronomical and economically). The knowledge of the population biology of such organisms is thus of fundamental importance to population biologists. Most parasites cannot be studied by direct methods and their biology has to be assessed via indirect means, most notably using molecular markers. In this review, we present the molecular tools, the null models employed, the statistical tools available and the kinds of inferences one can make when using molecular markers to study the ecology/epidemiology of host-parasite systems (molecular ecology/molecular epidemiology). We conclude with relevant examples, most issued from our laboratory, to illustrate the pros and cons of such methods for the study of parasites, vectors, micropathogens and their hosts and briefly discuss future needs.

Animals↗
PubMed2002

Estimated risk of West Nile virus transmission through blood transfusion during an epidemic in Queens, New York City.

BACKGROUND: Human West Nile virus (WNV) infection has been documented in the eastern United States since its discovery there in 1999. Epidemics of WNV encephalitis and meningitis raise concern that transmission of WNV may occur through voluntary blood donations. STUDY DESIGN AND METHODS: Case onset dates from the 1999 Queens, NY, epidemic of WNV encephalitis and meningitis, and historic data on viremia in humans are used to estimate the number of cases that were viremic throughout the epidemic. Estimates of the inapparent-to-apparent WNV infection ratio, the proportion of asymptomatic infections reported in a seroepidemiologic survey coincident with the epidemic, and the population size are used to infer the WNV transfusion-transmission risk. Statistical resampling methods are used. RESULTS: The maximum and mean risk of WNV transmission (/10,000) from donors in Queens were estimated as 2.7 (95% CI, 0.9-5.6) and 1.8 (95% CI, 1.4-2.2), respectively. The risk peaked in late August, with very low risk before August and after September. CONCLUSION: Although most WNV-infected individuals have subclinical infections, these data suggest a low prevalence of viremia throughout the Queens epidemic and subsequent low risk of transmission of WNV by blood transfusion.

Blood Donors↗
PubMed2001

Recombination within natural populations of pathogenic bacteria: short-term empirical estimates and long-term phylogenetic consequences.

The identification of clones within bacterial populations is often taken as evidence for a low rate of recombination, but the validity of this inference is rarely examined. We have used statistical tests of congruence between gene trees to examine the extent and significance of recombination in six bacterial pathogens. For Neisseria meningitidis, Streptococcus pneumoniae, Streptococcus pyogenes, and Staphylococcus aureus, the congruence between the maximum likelihood trees reconstructed using seven house-keeping genes was in most cases no better than that between each tree and trees of random topology. The lack of congruence between gene trees in these four species, which include both naturally transformable and nontransformable species, is in three cases supported by high ratios of recombination to point mutation during clonal diversification (estimates of this parameter were not possible for Strep. pyogenes). In contrast, gene trees constructed for Hemophilus influenzae and pathogenic isolates of Escherichia coli showed a higher degree of congruence, suggesting lower rates of recombination. The impact of recombination therefore varies between bacterial species but in many species is sufficient to obliterate the phylogenetic signal in gene trees.

Alleles↗
PubMed1997

End-Epi: an application for inferring phylogenetic and population dynamical processes from molecular sequences.

MOTIVATION: Phylogenetic trees constructed from molecular sequences contain information about the evolutionary or population dynamical processes that created them. Here we describe a computer package (End-Epi) that uses graphical methods to allow researchers to make inferences about these processes from their data. Statistical analyses can be performed to test the consistency of the data with various competing hypotheses. AVAILABILITY: End-Epi can be obtained by WWW from http://evolve.zoo.ox.ac.uk/ and by anonymous FTP from ftp://evolve.zoo.ox.ac.uk/packages/End-Epi10.hqx. This file contains the compiled application, the manual and a test tree.

Algorithms↗
PubMed2025

Sparse polygenic risk score inference with the spike-and-slab LASSO.

MOTIVATION: Large-scale biobanks, with rich phenotypic and genomic data across hundreds of thousands of samples, provide ample opportunities to elucidate the genetics of complex traits and diseases. Consequently, there is growing demand for robust and scalable methods for disease risk prediction from genotype data. Inference in this setting is challenging due to the high-dimensionality of genomic data, especially when coupled with smaller sample sizes. Popular Polygenic Risk Score (PRS) inference methods address this challenge by adopting sparse Bayesian priors or penalized regression techniques, such as the Least Absolute Shrinkage and Selection Operator (LASSO). However, the former class of methods are not as scalable and do not produce exact sparsity, while the latter tends to over-shrink large coefficients. RESULTS: In this study, we present SSLPRS, a novel PRS method based on the Spike-and-Slab LASSO (SSL) prior, which offers a theoretical bridge between the two frameworks. We extend previous work to derive a coordinate-ascent inference algorithm that operates on GWAS summary statistics, which is orders-of-magnitude more efficient than corresponding individual-level-based implementations. To illustrate the statistical properties of the proposed model, we conducted experiments involving nine simulation configurations and nine quantitative phenotypes from the UK Biobank. Our results demonstrate that SSLPRS is competitive with state-of-the-art methods in terms of prediction accuracy and exhibits superior variable selection performance, especially in sparse genetic architectures. In simulations, this translates to upwards of 50% improvement in positive predictive value. In analysis of real phenotypes, we show that selected variants are highly enriched for meaningful genomic annotations and have better replication rates in larger meta-analyses. AVAILABILITY AND IMPLEMENTATION: SSLPRS is available in the open-source package https://github.com/li-lab-mcgill/penprs.

Multifactorial Inheritance↗
PubMed2005

A stochastic differential equation model for quantifying transcriptional regulatory network in Saccharomyces cerevisiae.

MOTIVATION: The explosion of microarray studies has promised to shed light on the temporal expression patterns of thousands of genes simultaneously. However, available methods are far from adequate in efficiently extracting useful information to aid in a greater understanding of transcriptional regulatory network. Biological systems have been modeled as dynamic systems for a long history, such as genetic networks and cell regulatory network. This study evaluated if the stochastic differential equation (SDE), which is prominent for modeling dynamic diffusion process originating from the irregular Brownian motion, can be applied in modeling the transcriptional regulatory network in Saccharomyces cerevisiae. RESULTS: To model the time-continuous gene-expression datasets, a model of SDE is applied to depict irregular patterns. Our goal is to fit a generalized linear model by combining putative regulators to estimate the transcriptional pattern of a target gene. Goodness-of-fit is evaluated by log-likelihood and Akaike Information Criterion. Moreover, estimations of the contribution of regulators and inference of transcriptional pattern are implemented by statistical approaches. Our SDE model is basic but the test results agree well with the observed dynamic expression patterns. It implies that advanced SDE model might be perfectly suited to portray transcriptional regulatory networks. AVAILABILITY: The R code is available on request. CONTACT: cykao@csie.ntu.edu.tw SUPPLEMENTARY INFORMATION: http://www.csie.ntu.edu.tw/~b89x035/yeast/

Gene Expression Regulation↗
PubMed1991

Methods for inferring phylogenies from nucleic acid sequence data by using maximum likelihood and linear invariants.

Likelihood methods and methods using invariants are procedures for inferring the evolutionary relationships among species through statistical analysis of nucleic acid sequences. A likelihood-ratio test may be used to determine the feasibility of any tree for which the maximum likelihood can be computed. The method of linear invariants described by Cavender, which includes Lake's method of evolutionary parsimony as a special case, is essentially a form of the likelihood-ratio method. In the case of a small number of species (four or five), these methods may be used to find a confidence set for the correct tree. An exact version of Lake's asymptotic chi 2 test has been mentioned by Holmquist et al. Under very general assumptions, a one-sided exact test is appropriate, which greatly increases power.

Animals↗
PubMed2001

Multiple imputation for multivariate data with missing and below-threshold measurements: time-series concentrations of pollutants in the Arctic.

Many chemical and environmental data sets are complicated by the existence of fully missing values or censored values known to lie below detection thresholds. For example, week-long samples of airborne particulate matter were obtained at Alert, NWT, Canada, between 1980 and 1991, where some of the concentrations of 24 particulate constituents were coarsened in the sense of being either fully missing or below detection limits. To facilitate scientific analysis, it is appealing to create complete data by filling in missing values so that standard complete-data methods can be applied. We briefly review commonly used strategies for handling missing values and focus on the multiple-imputation approach, which generally leads to valid inferences when faced with missing data. Three statistical models are developed for multiply imputing the missing values of airborne particulate matter. We expect that these models are useful for creating multiple imputations in a variety of incomplete multivariate time series data sets.

Air Pollutants↗
PubMed2001

Structural abnormalities in frontal, temporal, and limbic regions and interconnecting white matter tracts in schizophrenic patients with prominent negative symptoms.

OBJECTIVE: Imaging studies of schizophrenia have repeatedly demonstrated global abnormalities of cerebral and ventricular volumes. However, pathological changes at more local levels of brain organization have not yet been so clearly characterized because of the few brain regions of interest heretofore included in morphometric analyses as well as heterogeneity of patient samples. METHOD: Dual echo magnetic resonance imaging (MRI) data were acquired at 1.5 T from 27 right-handed patients who met DSM-IV criteria for schizophrenia with enduring negative symptoms and from 27 healthy comparison subjects. Between-group differences in gray and white matter volume were estimated at each intracerebral voxel after registration of the images in standard space. The relationship between clinical symptom scores and brain structure was also examined within the patient group. Spatial statistics and permutation tests were used for inference. RESULTS: Significant deficits of gray matter volume in the patient group were found at three main locations: 1) the left superior temporal gyrus and insular cortex, 2) the left medial temporal lobe (including the parahippocampal gyrus and hippocampus), and 3) the anterior cingulate and medial frontal gyri. The volume of these three regions combined was 14% lower in the patients relative to the comparison subjects. White matter deficits were found in similar locations in the left temporal lobe and extended into the left frontal lobe. The patient group showed a relative excess of gray matter volume in the basal ganglia. Within the patient group, basal ganglia gray matter volume was positively correlated with positive symptom scores. CONCLUSIONS: Anatomical abnormalities in these schizophrenic patients with marked negative symptoms were most evident in left hemispheric neocortical and limbic regions and related white matter tracts. These data are compatible with models that depict schizophrenia as a supraregional disorder of multiple, distributed brain regions and the axonal connections between them.

Adult↗
PubMed1986

Prediction and clinical inference: forty years later.

The earlier controversy between clinical and statistical prediction has faded into the shadows. Few people today challenge the necessity for both approaches in seeking to develop and apply knowledge. In more contemporary terms, the issue of which prediction method should be preferred involves choosing between a quest for historical truth (i.e., correspondence demonstrated by statistical methods) and a quest for narrative truth (i.e., coherence achieved by clinical formulations).

Art↗
PubMedDate not supplied

Survey estimates of drug-use trends in urban communities: general principles and cautionary examples.

Surveys to depict substance abuse rates and monitor trends in specific areas have become increasingly important policy tools. Yet, as illustrated by two national multiwave surveys, using small sample survey data and making longitudinal comparisons is fraught with interpretative problems. In the case of the metropolitan area "oversample" of the National Household Survey on Drug Abuse, for example, interpreting apparent declines in drug use has to take account of the devastating effects of Hurricane Andrew in the Miami Metropolitan area. In the case of a 41-community survey sponsored by the Robert Wood Johnson Foundation to evaluate substance abuse prevention, the difficulty is how to interpret small differences in drug use, which seem to follow no reasonable pattern with respect to treatment or comparison sites. Inferences from such surveys are confounded with statistical anomalies and unforeseen events. They are limited by the sample size. In part, the solution to these problems is to use other survey and nonsurvey data to validate their conclusions and to note their limitations.

Confounding Factors, Epidemiologic↗
PubMed2004

Codon usage and bias in mitochondrial genomes of parasitic platyhelminthes.

Sequences of the complete protein-coding portions of the mitochondrial (mt) genome were analysed for 6 species of cestodes (including hydatid tapeworms and the pork tapeworm) and 5 species of trematodes (blood flukes and liver- and lung-flukes). A near-complete sequence was also available for an additional trematode (the blood fluke Schistosoma malayensis). All of these parasites belong to a large flatworm taxon named the Neodermata. Considerable variation was found in the base composition of the protein-coding genes among these neodermatans. This variation was reflected in statistically-significant differences in numbers of each inferred amino acid between many pairs of species. Both convergence and divergence in nucleotide, and hence amino acid, composition was noted among groups within the Neodermata. Considerable variation in skew (unequal representation of complementary bases on the same strand) was found among the species studied. A pattern is thus emerging of diversity in the mt genome in neodermatans that may cast light on evolution of mt genomes generally.

Amino Acid Sequence↗
PubMed1991

Estimation of Hardy-Weinberg and pairwise disequilibrium in the apolipoprotein AI-CIII-AIV gene cluster.

Departures from Hardy-Weinberg (HW) equilibria and pairwise disequilibria were estimated in a sample of unrelated healthy individuals typed for six RFLPs in the apo AI-CIII-AIV gene region. The sample was composed of males and females, selected for health, from two populations, those of exclusively French-Canadian (FC) and those of some non-French-Canadian (NFC) ancestry. An approach suggested by Weir and Cockerham, which includes estimates of nonrandom association (disequilibria) between three and four alleles at two loci as well as the traditional associations between two alleles, at two loci was used. The pattern of departures from HW equilibria suggested that the genetic structures of the FC and NFC are different. Departure from HW equilibrium at an RFLP locus could not be predicted from information about other loci in the same gene region. Nonrandom associations were also evident from the pairwise analyses. Two pairs of loci had significant diallelic disequilibria, while two other pairs had significant triallelic disequilibria. All of the RFLP pairs had at least one measure of disequilibrium at its maximum value determined by allele frequencies. Inferences about pairwise disequilibria depended on the statistical approach used. Sizes of the pairwise disequilibria were not correlated with the physical distance between loci. The impact of these disequilibria on RFLP-phenotype association studies is discussed.

Adult↗
PubMed1996

Mortality of lead smelter workers with the glucose-6-phosphate dehydrogenase-deficient phenotype.

The mortality experience of 1345 male workers in a lead and zinc smelting plant was followed from 1973 to 1991. Information on the erythrocyte glucose-6-phosphate dehydrogenase (G6PD) phenotype was available for 1,222 (90.9%) cohort members, which provided the opportunity to compare the mortality experience of G6PD-deficient subjects to wild-type-G6PD coworkers with similar exposure to lead. A significant decrease in mortality was observed among the total cohort as well as among the subcohort of production and maintenance workers. Most deaths (27 of 31) and all cancer deaths occurred among production and maintenance workers. Lung cancer mortality was lower than expected. Two deaths from stomach cancer were observed versus 0.6 expected. Mortality from all causes and cancer mortality were lower among production and maintenance workers with the G6PD-deficient phenotype compared to coworkers with the wild-type phenotype. Although the low statistical power of this study prevents conclusive inference, lead smelter workers with the G6PD-deficient phenotype did not suffer adverse health outcomes in terms of mortality from all causes and cancer mortality compared to coworkers with the wild-type G6PD.

Adult↗
PubMed1987

Use of multistage models to infer stage affected by carcinogenic exposure: example of lung cancer and cigarette smoking.

Statistical methods based on the Armitage-Doll mathematical model of the carcinogenic process are presented for analyzing epidemiologic case-control studies of cancer. These methods are proposed to provide inferences regarding the stage(s) in the cancer process at which the exposure of interest acts. An example of these methods is given which shows evidence that carcinogens in cigarette smoke appear to affect the transition rates for two separate stages in the development of lung cancer, and the relative magnitudes of these effects are estimated. The data for this analysis came from a European multi-center case-control study of lung cancer. The results of the analysis show that: (1) the relative risk of lung cancer among continuing smokers compared to nonsmokers of the same age decreases as the age started smoking increases, while the rate of smoking stays fixed, a result which indicates a carcinogenic effect on an early stage in the process; and (2) the relative risk among ex-smokers compared to continuing smokers having the same duration and rate of smoking decreases with time since smoking stopped, a result which indicates a carcinogenic effect on a late stage in the process. Both results are shown to be best described by the hypothesis that cigarette smoking affects two stages. The estimated relative magnitudes of cigarettes' carcinogenic effects on the two stages indicate that the largest proportion of the total lifetime lung cancer risk among continuing smokers is due to its late stage effect, and that the proportion of risk due to causes other than smoking varies from 23% among men smoking 1-10 cigarettes per day to 6% among those smoking greater than 30 cigarettes per day. These findings imply that preventive measures directed toward inducing smokers to stop would have a potentially substantial payoff in reducing future lung cancer mortality.

Age Factors↗
PubMed1992

Phylogeny of some ascaridoid nematodes, inferred from comparison of 18S and 28S rRNA sequences.

Reverse transcription of cellular RNA was used to obtain sequences from regions of 18S and 26/28S ribosomal RNA for eight species of ascaridoid nematodes. Phylogenetic relationships among these species were inferred from the aligned sequences by maximum-parsimony and maximum-likelihood methods. Seventy-nine of the 168 sites that varied were phylogenetically informative in parsimony analysis. Phylogenetic inference based on maximum-likelihood analysis of all sequence sites yielded a tree of topology similar to that of the parsimony result. Monophyletic groups that were strongly supported by bootstrap resampling of these data included species constituting the Ascaridinae, as well as those representing the Toxocarinae. Alternative topologies that included a member of the Ascaridinae with the Toxocarinae were rejected statistically on the basis of analysis of the mean and variance of parsimony step differences between trees. The conformance of these sequence data to a molecular-clock model of evolution was evaluated statistically by a maximum-likelihood approach. The inferred rate of rRNA sequence change along the branch leading to Parascaris equorum is not consistent with a clocklike model of evolution.

Animals↗
PubMed2004

Nurses as information providers: facilitating understanding and communication of statistical information.

Nurses are increasingly being called upon to be the conveyers of important statistical information to patients. This trend is particularly evident in the domains of genetics and cancer screening. These new roles, however, demand new competencies, such as the ability to solve statistical problems, and the skill to communicate the answers effectively, as effective communication is an important ingredient in shared decision making. Genetic testing, perhaps more than other medical domains, relies heavily on the use of statistics. Being able to convey statistical information effectively is vital. In this paper, we illustrate the problems health care professionals have had in tackling and communicating statistical information. We introduce the natural frequencies method of solving Bayesian inference problems and review empirical evidence that shows the superiority of this format. Being able to transform probabilities into natural frequencies facilitates correct Bayesian inferences. It is argued that the conventional approach to educating nurses in Bayesian problem solving should be reconsidered and their statistical curriculum should be supplemented with instruction in using the natural frequency format.

Bayes Theorem↗
PubMed2024

BICEP: Bayesian inference for rare genomic variant causality evaluation in pedigrees.

Next-generation sequencing is widely applied to the investigation of pedigree data for gene discovery. However, identifying plausible disease-causing variants within a robust statistical framework is challenging. Here, we introduce BICEP: a Bayesian inference tool for rare variant causality evaluation in pedigree-based cohorts. BICEP calculates the posterior odds that a genomic variant is causal for a phenotype based on the variant cosegregation as well as a priori evidence such as deleteriousness and functional consequence. BICEP can correctly identify causal variants for phenotypes with both Mendelian and complex genetic architectures, outperforming existing methodologies. Additionally, BICEP can correctly down-weight common variants that are unlikely to be involved in phenotypic liability in the context of a pedigree, even if they have reasonable cosegregation patterns. The output metrics from BICEP allow for the quantitative comparison of variant causality within and across pedigrees, which is not possible with existing approaches.

Pedigree↗