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 613 records · Page 34Linked to original sources
PubMed2003

Sequence diversity and haplotype structure in the human ABCB1 (MDR1, multidrug resistance transporter) gene.

OBJECTIVES: There is increasing evidence that polymorphism of the ABCB1 (MDR1) gene contributes to interindividual variability in bioavailability and tissue distribution of P-glycoprotein substrates. The aim of the present study was to (1) identify and describe novel variants in the ABCB1 gene, (2) understand the extent of variation in ABCB1 at the population level, (3) analyze how variation in ABCB1 is structured in haplotypes, and (4) functionally characterize the effect of the most common amino acid change in P-glycoprotein. METHODS AND RESULTS: Forty-eight variant sites, including 30 novel variants and 13 coding for amino acid changes, were identified in a collection of 247 ethnically diverse DNA samples. These variants comprised 64 statistically inferred haplotypes, 33 of which accounted for 92% of chromosomes analyzed. The two most common haplotypes, ABCB1*1 and ABCB1*13, differed at six sites (three intronic, two synonymous, and one non-synonymous) and were present in 36% of all chromosomes. Significant population substructure was detected at both the nucleotide and haplotype level. Linkage disequilibrium was significant across the entire ABCB1 gene, especially between the variant sites found in ABCB1*13, and recombination was inferred. The Ala893Ser change found in the common ABCB1*13 haplotype did not affect P-glycoprotein function. CONCLUSION: This study represents a comprehensive analysis of ABCB1 nucleotide diversity and haplotype structure in different populations and illustrates the importance of haplotype considerations in characterizing the functional consequences of ABCB1 polymorphisms.

Base Sequence↗
PubMed2001

Biostatistics and study design for evidence-based practice.

The hallmark of an evidence-based practitioner is one who reflects on their clinical decision making and uses research evidence to reduce clinical uncertainty and guide their practice. Understanding how the results of empirical research can be appropriately integrated into clinical practice requires a basic understanding of study design and statistical analysis. This article provides an overview of some of the key concepts related to study design and statistical inference that are important to accurately measure clinical outcomes and to appropriately interpret the results of studies within the context of evidence-based decision making.

Biometry↗
PubMed2006

Bias in psychopathology research.

PURPOSE OF REVIEW: Biases are frequently invoked in psychopathology research, either as core features of particular forms of psychopathology or as errors and distortions that affect psychiatric assessment, diagnosis, treatment, and research methodology. This review provides an overview of recent research on the forms of bias that are commonly examined in the field. RECENT FINDINGS: Recent research has made a number of advances in the analysis of cognitive and affective biases underpinning psychopathology: the effect of rating and other biases on psychiatric assessment and diagnosis; the role of race and gender in psychiatric practice; financial and institutional influences on psychiatric services; and several biases affecting research methodology, study design, and statistical inference. SUMMARY: Bias has several distinct meanings, and encompasses a disparate set of phenomena, so no over-arching conclusion about the place of bias in psychopathology research can be drawn. Recent work, however, makes solid progress toward a better understanding of systematic distortions and how they can be recognized and reduced.

Affect↗
PubMed2004

Bayesian analysis of experimental epidemics of foot-and-mouth disease.

We investigate the transmission dynamics of a certain type of foot-and-mouth disease (FMD) virus under experimental conditions. Previous analyses of experimental data from FMD outbreaks in non-homogeneously mixing populations of sheep have suggested a decline in viraemic level through serial passage of the virus, but these do not take into account possible variation in the length of the chain of viral transmission for each animal, which is implicit in the non-observed transmission process. We consider a susceptible-exposed-infectious-removed non-Markovian compartmental model for partially observed epidemic processes, and we employ powerful methodology (Markov chain Monte Carlo) for statistical inference, to address epidemiological issues under a Bayesian framework that accounts for all available information and associated uncertainty in a coherent approach. The analysis allows us to investigate the posterior distribution of the hidden transmission history of the epidemic, and thus to determine the effect of the length of the infection chain on the recorded viraemic levels, based on the posterior distribution of a p-value. Parameter estimates of the epidemiological characteristics of the disease are also obtained. The results reveal a possible decline in viraemia in one of the two experimental outbreaks. Our model also suggests that individual infectivity is related to the level of viraemia.

Animals↗
PubMed2004

Optimal haplotype block-free selection of tagging SNPs for genome-wide association studies.

It is widely hoped that the study of sequence variation in the human genome will provide a means of elucidating the genetic component of complex diseases and variable drug responses. A major stumbling block to the successful design and execution of genome-wide disease association studies using single-nucleotide polymorphisms (SNPs) and linkage disequilibrium is the enormous number of SNPs in the human genome. This results in unacceptably high costs for exhaustive genotyping and presents a challenging problem of statistical inference. Here, we present a new method for optimally selecting minimum informative subsets of SNPs, also known as "tagging" SNPs, that is efficient for genome-wide selection. We contrast this method to published methods including haplotype block tagging, that is, grouping SNPs into segments of low haplotype diversity and typing a subset of the SNPs that can discriminate all common haplotypes within the blocks. Because our method does not rely on a predefined haplotype block structure and makes use of the weaker correlations that occur across neighboring blocks, it can be effectively applied across chromosomal regions with both high and low local linkage disequilibrium. We show that the number of tagging SNPs selected is substantially smaller than previously reported using block-based approaches and that selecting tagging SNPs optimally can result in a two- to threefold savings over selecting random SNPs.

Algorithms↗
PubMed2005

Statistical field estimators for multiscale simulations.

We present a systematic approach for generating smooth and accurate fields from particle simulation data using the notions of statistical inference. As an extension to a parametric representation based on the maximum likelihood technique previously developed for velocity and temperature fields, a nonparametric estimator based on the principle of maximum entropy is proposed for particle density and stress fields. Both estimators are applied to represent molecular dynamics data on shear-driven flow in an enclosure which exhibits a high degree of nonlinear characteristics. We show that the present density estimator is a significant improvement over ad hoc bin averaging and is also free of systematic boundary artifacts that appear in the method of smoothing kernel estimates. Similarly, the velocity fields generated by the maximum likelihood estimator do not show any edge effects that can be erroneously interpreted as slip at the wall. For low Reynolds numbers, the velocity fields and streamlines generated by the present estimator are benchmarked against Newtonian continuum calculations. For shear velocities that are a significant fraction of the thermal speed, we observe a form of shear localization that is induced by the confining boundary.

Journal Article↗
PubMed2003

Wigner-Yanase skew information and uncertainty relations.

The Wigner-Araki-Yanase theorem puts a limitation on the measurement of observables in the presence of a conserved quantity, and the notion of Wigner-Yanase skew information quantifies the amount of information on the values of observables not commuting with the conserved quantity. We demonstrate that the statistical idea underlying the skew information is the Fisher information in the theory of statistical estimation. A quantum Cramér-Rao inequality and a new uncertainty relation in terms of the skew information are established, which shed considerable new light on the relationships between quantum measurement and statistical inference. The result is applied to estimating the evolution speed of quantum states.

Journal Article↗
PubMed2004

An algorithm for detecting homologues of known structured RNAs in genomes.

Distinct RNA structures are frequently involved in a wide-range of functions in various biological mechanisms. The three dimensional RNA structures solved by X-ray crystallography and various well-established RNA phylogenetic structures indicate that functional RNAs have characteristic RNA structural motifs represented by specific combinations of base pairings and conserved nucleotides in the loop region. Discovery of well-ordered RNA structures and their homologues in genome-wide searches will enhance our ability to detect the RNA structural motifs and help us to highlight their association with functional and regulatory RNA elements. We present here a novel computer algorithm, HomoStRscan, that takes a single RNA sequence with its secondary structure to search for homologous-RNAs in complete genomes. This novel algorithm completely differs from other currently used search algorithms of homologous structures or structural motifs. For an arbitrary segment (or window) given in the target sequence, that has similar size to the query sequence, HomoStRscan finds the most similar structure to the input query structure and computes the maximal similarity score (MSS) between the two structures. The homologousRNA structures are then statistically inferred from the MSS distribution computed in the target genome. The method provides a flexible, robust and fine search tool for any homologous structural RNAs.

Algorithms↗
PubMedDate not supplied

Significance of gene ranking for classification of microarray samples.

Many methods for classification and gene selection with microarray data have been developed. These methods usually give a ranking of genes. Evaluating the statistical significance of the gene ranking is important for understanding the results and for further biological investigations, but this question has not been well addressed for machine learning methods in existing works. Here, we address this problem by formulating it in the framework of hypothesis testing and propose a solution based on resampling. The proposed r-test methods convert gene ranking results into position p-values to evaluate the significance of genes. The methods are tested on three real microarray data sets and three simulation data sets with support vector machines as the method of classification and gene selection. The obtained position p-values help to determine the number of genes to be selected and enable scientists to analyze selection results by sophisticated multivariate methods under the same statistical inference paradigm as for simple hypothesis testing methods.

Algorithms↗
PubMed2005

A flexible coefficient smooth transition time series model.

In this paper, we consider a flexible smooth transition autoregressive (STAR) model with multiple regimes and multiple transition variables. This formulation can be interpreted as a time varying linear model where the coefficients are the outputs of a single hidden layer feedforward neural network. This proposal has the major advantage of nesting several nonlinear models, such as, the self-exciting threshold autoregressive (SETAR), the autoregressive neural network (AR-NN), and the logistic STAR models. Furthermore, if the neural network is interpreted as a nonparametric universal approximation to any Borel measurable function, our formulation is directly comparable to the functional coefficient autoregressive (FAR) and the single-index coefficient regression models. A model building procedure is developed based on statistical inference arguments. A Monte Carlo experiment showed that the procedure works in small samples, and its performance improves, as it should, in medium size samples. Several real examples are also addressed.

Algorithms↗
PubMed2000

Masking unmasked in the proportional hazards model.

Influence measures based on the pairwise deletion approach and the differentiation approach are developed for unmasking observations masked by other observations in the proportional hazards model. These influential observations might have substantial impact on statistical inference and might provide important information for model adequacy. One numerical example based on real data is presented and discussed.

Biometry↗
PubMed2001

Social causes of correlational selection and the resolution of a heritable throat color polymorphism in a lizard.

When selection acts on social or behavioral traits, the fitness of an individual depends on the phenotypes of its competitors. Here, we describe methods and statistical inference for measuring natural selection in small social groups. We measured selection on throat color alleles that arises from microgeographic variation in allele frequency at natal sites of side-blotched lizards (Uta stansburiana). Previous game-theoretic analysis indicates that two color morphs of female side-blotched lizards are engaged in an offspring quantity-quality game that promotes a density- and frequency-dependent cycle. Orange-throated females are r-strategists. They lay large clutches of small progeny, which have poor survival at high density, but good survival at low density. In contrast, yellow-throated females are K-strategists. They lay small clutches of large progeny, which have good survival at high density. We tested three predictions of the female game: (1) orange progeny should have a fitness advantage at low density; (2) correlational selection acts to couple color alleles and progeny size; and (3) this correlational selection arises from frequency-dependent selection in which large hatchling size confers an advantage, but only when yellow alleles are rare. We also confirmed the heritability of color, and therefore its genetic basis, by producing progeny from controlled matings. A parsimonious cause of the high heritability is that three alleles (o, b, y) segregate as one genetic factor. We review the physiology of color formation to explain the possible genetic architecture of the throat color trait. Heritability of color was nearly additive in our breeding study, allowing us to compute a genotypic value for each individual and thus predict the frequency of progeny alleles released on 116 plots. Rather than study the fitness of individual progeny, we studied how the fitness of their color alleles varied with allele frequency on plots. We confirmed prediction 1: When orange alleles are present in female progeny, they have higher fitness at low density when compared to other alleles. Even though the difference in egg size of the female morphs was small (0.02 g), it led to knife-edged survival effects for their progeny depending on local social context. Selection on hatchling survival was not only dependent on color alleles, but on a fitness interaction between color alleles and hatchling size, which confirmed prediction 2. Sire effects, which are not confounded by maternal phenotype, allowed us to resolve the frequency dependence of correlational selection on egg size and color alleles and thereby confirmed prediction 3. Selection favored large size when yellow sire alleles were rare, but small size when they were common. Correlational selection promotes the formation of a self-reinforcing genetic correlation between the morphs and life-history variation, which causes selection in the next density and frequency cycle to be exacerbated. We discuss general conditions for the evolution of self-reinforcing genetic correlations that arise from social selection associated with frequency-dependent sexual and natural selection.

Alleles↗
PubMed2005

Haplotypes in the tumour necrosis factor region and myeloma.

This study described the haplotypic structure across a region of chromosome 6 including the tumour necrosis factor (TNF) gene, and investigated its influence on the aetiology of myeloma. A total of 181 myeloma cases from the Medical Research Council Myeloma VII trial and 233 controls from the Leukaemia Research Fund Case Control Study of Adult Acute Leukaemia were included in the analysis. Genotyping by induced heteroduplex generator analysis was carried out for single nucleotide polymorphisms (SNP) located at positions -1031, -863, -857, -308 and -238 of the 5' promoter region of TNF-alpha gene, and 252 in the LT-alpha gene; and five microsatellites, TNFa, b, c, d and e. Haplotypes were inferred statistically using the phase algorithm. A limited diversity of haplotypes was observed, with the majority of variation described by 12 frequent haplotypes. Detailed characterization of the haplotype did not provide greater determination of disease risk beyond that described by the TNF-alpha-308 SNP. Some evidence was provided for a decreased risk of myeloma associated with the TNF-alpha-308 variant allele A, odds ratio, 0.57; 95% confidence interval, 0.38-0.86. The results of this study did not support our starting hypothesis; that high producer haplotypes at the TNF locus are associated with an increased risk of developing myeloma.

Adult↗
PubMed2004

Patterns of co-occurrence of three single nucleotide polymorphisms of the 5,10-methylenetetrahydrofolate reductase gene in kidney transplant recipients.

BACKGROUND: Recently, a new mutation of the 5,10-methylenetetrahydrofolate reductase (MTHFR) encoding gene was first described (1793G > A). Only few reports have studied the prevalence of this polymorphism, especially in combination with other MTHFR mutations (677C > T, 1298A > C). METHODS: We cross-sectionally identified the novel MTHFR 1793G > A polymorphism in 730 kidney transplant recipients. MTHFR 677C > T and 1298A > C were also assessed and the frequency of each was described individually as well as in cross-tabulation with the other MTHFR genotypes. The expected number of patients for each MTHFR genotype combination was calculated and contrasted with the observed numbers. Fisher's exact test was used for statistical inference. RESULTS: The allelic frequency of MTHFR 1793G > A was 0.052. Seventy-two patients (9.9%) were heterozygous and two patients (0.3%) were homozygous. From the cross-tabulations, we identified 53 patients (expected: 33.6) with the MTHFR 1298AC/1793GA genotype and 17 patients (expected: 6.7) with the MTHFR 1298CC/1793GA genotype. Furthermore, we found two patients with double homozygosity for MTHFR 1793G > A and MTHFR 1298A > C (MTHFR 1793AA/1298CC genotype). The frequencies of these genotype combinations were substantially larger than could be expected (P < 0.001). CONCLUSIONS: These findings suggest a selection or survival advantage for individuals with combined MTHFR 1793G > A and MTHFR 1298A > C genotypes, possibly owing to a mutually stabilizing effect on MTHFR enzyme activity.

5,10-Methylenetetrahydrofolate Reductase (FADH2)↗
PubMed2005

A 24-year follow-up of root filled teeth and periapical health amongst middle aged and elderly women in Göteborg, Sweden.

AIM: To describe the endodontic status amongst middle-aged and elderly women longitudinally and cross-sectionally over 24 years. METHODOLOGY: A random sample of 1462 women 38, 46, 50, 54 and 60 years old, living in Göteborg, Sweden, were sampled in 1968 for medical and dental examinations with a participation rate of 90.1%. The same women were re-examined in 1980 and 1992 together with new 38- and 50-year-old women. The dental examination consisted of questionnaires, clinical and panoramic radiological survey (OPG). The number of teeth, number of root filled teeth (RF) and number of teeth with periapical radiolucencies (PA) were registered. The RF and PA ratios were calculated. Cross-sectional data were analysed by means of anova and longitudinal data by a general linear model for repeated measures. Sample prevalences were compared and statistical inferences were made with the chi-squared test. In all analysis, the confidence interval (CI) regarded mean difference between groups (95% CI). RESULTS: The RF and PA ratio decreased over time as well as the frequency of edentulous subjects. Cross-sectional analysis revealed a minor increase in frequency of RF and PA and loss of teeth with age. Longitudinally, loss of teeth was evident in all cohorts. In addition, there was a trend of lower number of teeth with PA, and the RF ratio increased with age. CONCLUSIONS: The prevalence of periapical disease did not increase with age, probably as a result of root canal treatment and extractions. Data showed that the prevalence of RF teeth and teeth with PA decreased for comparable age cohorts during the 24-year follow-up.

Adult↗
PubMed2006

Does specialty board certification influence clinical outcomes?

BACKGROUND: The public seems to crave a simplistic index of 'quality', analogous to 'The Good Housekeeping Seal of Approval', for the complex endeavour of clinical medicine. The American Board of Medical Specialties (ABMS) and its member boards have purported to fill the vacuum in an effort that bears many of the earmarks of a public relations publicity campaign. The author examined the validity of the evidence touted in support of that effort. METHODS: By applying Hill's causal epidemiologic criteria and logical and statistical inference, the author evaluated: (i) published data sources consisting of the most comprehensive collection of studies yet gathered that purports to provide evidence of the relevance of board certification to clinical outcomes, a collection presented by Sharp et al. apparently with the advice and consent of ABMS, that they posited as containing 'relevant findings', to what purpose they left unspecified; and (ii) the review article of Sharp et al. RESULTS: The data that Sharp et al. presented provided no credible link between specialty board certification and outcomes or 'quality' of clinical care. Sharp et al. ignored the evidence of absent evidence they found and proposed enthusiastic but unjustified conclusions in support of specialty board certification as an index of clinical 'expertise'. CONCLUSIONS: No evidence supports the touted clinical benefit of specialty board certification. Specialists in clinical medicine and surgery are unamenable to simplistic evaluation by examination, yet specialty board certification remains an ersatz standard of doctors' clinical quality in the absence of supporting evidence.

Certification↗
PubMed1995

Issues in biomedical statistics: comparing means under normal distribution theory.

The test used most commonly in biomedical research to compare means when measurements have been made on a continuous scale is Student's t-test, followed closely by various forms of analysis of variance. These tests require that defined populations have been randomly sampled, but there are other assumptions about populations and samples that must be satisfied. These include: (i) normality of the population distributions; (ii) equal variance in those normal populations; and (iii) statistical independence of the samples. This review offers advice to investigators on how to recognize breaches of the assumptions of normality and equality of variance, and how to deal with them by modifying the usual t-test or by transforming the experimental data. The sample-size also has an important bearing on statistical inferences: (i) if it is too small, the risk of Type II error is inflated; and (ii) inequality of sample size exaggerates the effects of inequality of variance. The assumption of independence is breached if repeated measurements are made serially rather than in random order, but adjustments to analysis of variance can be made to correct for the inflated risk of Type I error. The review also considers the problem of making multiple comparisons of means, and recommends solutions.

Analysis of Variance↗
PubMed2005

Ethical and epistemological problems when applying evidence-based medicine to pain management.

Epistemology, or the theory of knowledge, is a branch in philosophy concerned with the definitions of knowledge and evidence. Although evidence-based medicine (EBM) has a strong ethical imperative behind it, rooted in the concern to do no harm, to do one's best for one's patients, and by doing so--eliminating waste, it still harbors within it serious epistemological limits. These include methodological and ethical limits to perform randomized controlled trials, the idea of "hierarchy of evidence" which may provide conclusions well short of medical knowledge, and the unique use of a single particular theory of statistical inference which is far from consensual. In this article, we review these difficulties and suggest that EBM is at best a methodological solution to some clinical phenomena, but remains blind to mechanisms of explanation and causation needed, in order to advance our knowledge. Further research in the theory of evidence and inference, causation and correlation, clinical judgment and collective knowledge, the structure of medical theory, and the nature of clinical effectiveness are needed.

Journal Article↗