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 1,621 records · Page 90Linked to original sources
PubMed2004

Evidence that microRNA precursors, unlike other non-coding RNAs, have lower folding free energies than random sequences.

MOTIVATION: Most non-coding RNAs are characterized by a specific secondary and tertiary structure that determines their function. Here, we investigate the folding energy of the secondary structure of non-coding RNA sequences, such as microRNA precursors, transfer RNAs and ribosomal RNAs in several eukaryotic taxa. Statistical biases are assessed by a randomization test, in which the predicted minimum free energy of folding is compared with values obtained for structures inferred from randomly shuffling the original sequences. RESULTS: In contrast with transfer RNAs and ribosomal RNAs, the majority of the microRNA sequences clearly exhibit a folding free energy that is considerably lower than that for shuffled sequences, indicating a high tendency in the sequence towards a stable secondary structure. A possible usage of this statistical test in the framework of the detection of genuine miRNA sequences is discussed.

Animals↗
PubMed2003

Age-conditional probabilities of developing cancer.

We propose an estimator of the probability of developing a disease in a given age range, conditional on never having developed the disease prior to the beginning of the age range. Our estimator improves the one described by Wun, Merrill and Feuer ( Lifetime Data Analysis 1998; 4, 169-186) that is currently used by the U.S. National Cancer Institute for the SEER Cancer Statistics Review. Both estimators use cross-sectional disease rates and provide an interpretation of these rates in terms of the age-conditional probability of developing disease in a hypothetical cohort. The difficulty of this problem is that rates are not available per person-years alive and disease free, but only per person-years alive. Wun et al. used ad hoc methods to handle this problem which did not properly account for competing risks, did not provide a measure of variability, and only allowed age ranges using prespecified 5-year age intervals. Here we solve the problem under a unified competing risks framework, which allows the calculation of the age-conditional probabilities for any age range. We generalize gamma confidence intervals to apply to our new statistic. Although our new method provides estimates which are numerically similar to that of Wun et al., this paper provides a comprehensive theoretical basis for estimation and inference about the age-conditional probability of developing a disease.

Age of Onset↗
PubMed2006

Review of microarray experimental design strategies for genetical genomics studies.

Genetical genomics approaches provide a powerful tool for studying the genetic mechanisms governing variation in complex traits. By combining information on phenotypic traits, pedigree structure, molecular markers, and gene expression, such studies can be used for estimating heritability of mRNA transcript abundances, for mapping expression quantitative trait loci (eQTL), and for inferring regulatory gene networks. Microarray experiments, however, can be extremely costly and time consuming, which may limit sample sizes and statistical power. Thus it is crucial to optimize experimental designs by carefully choosing the subjects to be assayed, within a selective profiling approach, and by cautiously controlling systematic factors affecting the system. Also, a rigorous strategy should be used for allocating mRNA samples across assay batches, slides, and dye labeling, so that effects of interest are not confounded with nuisance factors. In this presentation, we review some selective profiling strategies for genetical genomics studies, including the selection of individuals for increased genetic dissimilarity and for a higher number of recombination events. Efficient designs for studying epistasis are also discussed, as well as experiments for inferring heritability of transcriptional levels. It is shown that solving an optimal design problem generally requires a numerical implementation and that the optimality criteria should be intimately related to the goals of the experiment, such as the estimation of additive, dominance, and interacting effects, localizing putative eQTL, or inferring genetic and environmental variance components associated with transcriptional abundances.

Animals↗
PubMed1997

On measures of agreement calculated from contingency tables with categories defined by the empirical quantiles of the marginal distributions.

Epidemiologists sometimes collect bivariate continuous data on a number of subjects, compute the empirical (sample) quantiles of the marginal data, and then use these values to partition the original data into two-way contingency tables. Tables created in this manner have row and column categories defined by the random empirical marginal quantiles rather than by preset cutpoints, so these tables have fixed marginal totals. Hence, instead of the conventional multinomial distribution, these tables have the empirical bivariate quantile-partitioned (EBQP) distribution. In this paper, the authors demonstrate how to use empirical methods appropriate for EBQP tables to make inferences and construct confidence intervals for three commonly used measures of agreement: kappa, weighted kappa, and another class of measures derived from conditional proportions in the extreme rows of the table. They also show that if one incorrectly applies conventional methods appropriate for multinomial tables to statistics calculated from EBQP tables, one can obtain substantially misleading results. In addition, the authors present alternative parametric methods for estimating these measures of agreement and illustrate corresponding methods of inference and confidence interval construction. Finally, they show that these empirical (EBQP) methods can have low efficiency compared with parametric methods for some of these measures of agreement.

Epidemiology↗
PubMed1999

Recovery of mutations of different sizes from a population sample of DNA sequences under variable mutation rates across sites.

Mutations may be classified according to their positions of occurrence in the genealogy of the sampled DNA sequences from a population. A mutation is said to be of size i if it has i descendants in the sample. Such classifications for mutations may yield detailed insights into the evolutionary history and properties of the population. Statistical methods based on such classification have been developed and shown to be efficient and powerful. However, the utility of these statistical methods critically depends on reliable and robust recovery of mutations of different sizes. We investigated the distributional changes of mutations of different sizes due to genealogy reconstruction using the unweighted pair-group method with arithmetic mean (UPGMA) and the performance of maximum-parsimony method in inferring mutations of different sizes on a given topology. Genealogy reconstruction by UPGMA was found to change the distribution of mutations of different sizes on constructed topologies. Multiple hits at some nucleotide sites made it difficult to infer mutations of different sizes with the maximum-parsimony method, even when the true topology was designated. These results suggest that while the newly developed statistical methods employing information on mutations of different sites are powerful, they also impose significant new challenges for developing methods to accurately recover mutations of different sizes from population DNA sequence data.

Algorithms↗
PubMed2000

Genome-wide analysis of single-nucleotide polymorphisms in human expressed sequences.

Single-nucleotide polymorphisms (SNPs) have been explored as a high-resolution marker set for accelerating the mapping of disease genes. Here we report 48,196 candidate SNPs detected by statistical analysis of human expressed sequence tags (ESTs), associated primarily with coding regions of genes. We used Bayesian inference to weigh evidence for true polymorphism versus sequencing error, misalignment or ambiguity, misclustering or chimaeric EST sequences, assessing data such as raw chromatogram height, sharpness, overlap and spacing, sequencing error rates, context-sensitivity and cDNA library origin. Three separate validations-comparison with 54 genes screened for SNPs independently, verification of HLA-A polymorphisms and restriction fragment length polymorphism (RFLP) testing-verified 70%, 89% and 71% of our predicted SNPs, respectively. Our method detects tenfold more true HLA-A SNPs than previous analyses of the EST data. We found SNPs in a large fraction of known disease genes, including some disease-causing mutations (for example, the HbS sickle-cell mutation). Our comprehensive analysis of human coding region polymorphism provides a public resource for mapping of disease genes (available at http://www.bioinformatics.ucla.edu/snp).

Base Sequence↗
PubMed2006

Loss of the flagellum happened only once in the fungal lineage: phylogenetic structure of kingdom Fungi inferred from RNA polymerase II subunit genes.

BACKGROUND: At present, there is not a widely accepted consensus view regarding the phylogenetic structure of kingdom Fungi although two major phyla, Ascomycota and Basidiomycota, are clearly delineated. Regarding the lower fungi, Zygomycota and Chytridiomycota, a variety of proposals have been advanced. Microsporidia may or may not be fungi; the Glomales (vesicular-arbuscular mycorrhizal fungi) may or may not constitute a fifth fungal phylum, and the loss of the flagellum may have occurred either once or multiple times during fungal evolution. All of these issues are capable of being resolved by a molecular phylogenetic analysis which achieves strong statistical support for major branches. To date, no fungal phylogeny based upon molecular characters has satisfied this criterion. RESULTS: Using the translated amino acid sequences of the RPB1 and RPB2 genes, we have inferred a fungal phylogeny that consists largely of well-supported monophyletic phyla. Our major results, each with significant statistical support, are: (1) Microsporidia are sister to kingdom Fungi and are not members of Zygomycota; that is, Microsporidia and fungi originated from a common ancestor. (2) Chytridiomycota, the only fungal phylum having a developmental stage with a flagellum, is paraphyletic and is the basal lineage. (3) Zygomycota is monophyletic based upon sampling of Trichomycetes, Zygomycetes, and Glomales. (4) Zygomycota, Basidiomycota, and Ascomycota form a monophyletic group separate from Chytridiomycota. (5) Basidiomycota and Ascomycota are monophyletic sister groups. CONCLUSION: In general, this paper highlights the evolutionary position and significance of the lower fungi (Zygomycota and Chytridiomycota). Our results suggest that loss of the flagellum happened only once during early stages of fungal evolution; consequently, the majority of fungi, unlike plants and animals, are nonflagellated. The phylogeny we infer from gene sequences is the first one that is congruent with the widely accepted morphology-based classification of Fungi. We find that, contrary to what has been published elsewhere, the four morphologically defined phyla (Ascomycota, Basidiomycota, Zygomycota and Chytridiomycota) do not overlap with one another. Microsporidia are not included within kingdom Fungi; rather they are a sister-group to the Fungi. Our study demonstrates the applicability of protein sequences from large, slowly-evolving genes to the derivation of well-resolved and highly supported phylogenies across long evolutionary distances.

Amino Acid Sequence↗
PubMed1992

Inference in linkage analysis of multifactorial traits using recombinant inbred strains of mice.

Recombinant inbred strains have been shown to be important tools for segregation and linkage analysis of multifactorial traits. Tests of association have been used as robust methods of linkage detection, however, guidelines for forming inferences from significance levels have not been generally available. In this paper, lessons learned from a Bayesian statistical approach to linkage analysis of Mendelian traits have been applied to studies of multifactorial traits. Criteria for detection of linkage based on Bonferroni's correction for multiple testing are also discussed.

Animals↗
PubMed2005

Is premating isolation in Drosophila overestimated due to uncontrolled factors?

Sexual isolation in Drosophila is typically measured by multiple-choice mating tests. While many environmental variables during such tests are controlled by the researcher, there are some factors that are usually uncontrolled. We demonstrate, using Drosophila melanogaster and D. pseudoobscura flies, that the temperature of rearing, pre-adult density, and level of consanguinity, can all produce differences in mating propensity between genetically equivalent flies. These differences in mating propensity, in turn, can give rise to statistically significant results in multiple-choice mating tests, leading to positive isolation values and the artifactual inference of sexual isolation between populations. This fact agrees with a nonrandom excess of significant positive tests found in a review of the literature of Drosophila intraspecific mating choice. An overestimate of true cases of sexual isolation in Drosophila in the literature can, therefore, not be ruled out.

Adaptation, Physiological↗
PubMed1982

Do clinical levels of general anaesthetics affect lipid bilayers? Evidence from Raman scattering.

We have used Raman spectroscopy to investigate the effects of the general anaesthetics halothane and chloroform on lipid bilayer order. Clinical concentrations of these anaesthetics had no significant effect on the hydrocarbon chain conformation in multilamellar vesicles of dimyristoylphosphatidylcholine/cholesterol. This result was obtained with a technique sufficiently precise to monitor changes in the acyl chain trans-gauche population ratio associated with a 1-2 K alteration in temperature. Very high levels of anaesthetics caused a marked disordering of the hydrocarbon chains. The danger of inferring an effect at clinical concentrations from data obtained at much higher levels is illustrated by a statistical analysis of our dose-response curves.

Cholesterol↗
PubMed1993

A computer package for the multivariate nonparametric rank test in completely randomized experimental designs.

When research data are measured on at least an ordinal scale and the assumptions required in the theory underlying parametric statistical methods are in question, nonparameteric procedures based on the ranks provide a sound approach to statistical analysis. Biomedical investigations, especially clinical trials, typically involve multivariate response and therefore multivariate statistical methods are called for in the interpretation of results. We discuss applications of the nonparametric multivariate rank test for completely randomized designs. Large sample theory can be used to support these statistical methods for assessing group differences in location. In small samples, randomization tests provide a basis for inferences. The execution of the procedure is facilitated by a computer program developed by the authors.

Algorithms↗
PubMed1991

Quantitative prediction of human cancer risk from rodent carcinogenic potencies: a closer look at the epidemiological evidence for some chemicals not definitively carcinogenic in humans.

The existence of rodent carcinogens for which at least one epidemiological study found no evidence of human carcinogenicity has been claimed to provide evidence of the poor predictivity of rodent bioassays (F. K. Ennever, T. J. Noonan, and H. S. Rosenkranz (1987). Mutagenesis 2, 73-78). We have performed quantitative comparisons of the rodent and human carcinogenic potencies for these same chemicals. Starting with the rodent TD50 at the most sensitive site, we derived a predicted human incidence for the degree of exposure and duration of follow-up corresponding to the most comprehensive epidemiological study available, and then we compared the predicted incidence with the observed incidence. If a chemical produced no statistically significant increase in cancer at any site in the exposed population, consistency with rodent results is inferred if the minimum rodent TD50 is sufficiently high that no attributable cases would have been expected under the actual conditions of human exposure and follow-up. For 18 of the 22 chemicals examined, the human evidence is consistent with the predictions based on the rodent bioassay results. For two chemicals, dichlorobenzidine and ethylene thiourea, there is not enough epidemiological information to make a useful comparison with rodent bioassay data. For the two remaining chemicals, actinomycin D and vinylidene chloride, the human evidence is inconsistent with the predictions. But the conditions of the rodent bioassay of actinomycin D were inappropriate for the comparison, and for vinylidene chloride the human exposure dose and duration were uncertain; either chemical might yet demonstrate consistency with the rodent results in future epidemiological studies.

Algorithms↗
PubMed2005

Hidden Markov event sequence models: toward unsupervised functional MRI brain mapping.

RATIONALE AND OBJECTIVES: Most methods used in functional MRI (fMRI) brain mapping require restrictive assumptions about the shape and timing of the fMRI signal in activated voxels. Consequently, fMRI data may be partially and misleadingly characterized, leading to suboptimal or invalid inference. To limit these assumptions and to capture the broad range of possible activation patterns, a novel statistical fMRI brain mapping method is proposed. It relies on hidden semi-Markov event sequence models (HSMESMs), a special class of hidden Markov models (HMMs) dedicated to the modeling and analysis of event-based random processes. MATERIALS AND METHODS: Activation detection is formulated in terms of time coupling between (1) the observed sequence of hemodynamic response onset (HRO) events detected in the voxel's fMRI signal and (2) the "hidden" sequence of task-induced neural activation onset (NAO) events underlying the HROs. Both event sequences are modeled within a single HSMESM. The resulting brain activation model is trained to automatically detect neural activity embedded in the input fMRI data set under analysis. The data sets considered in this article are threefold: synthetic epoch-related, real epoch-related (auditory lexical processing task), and real event-related (oddball detection task) fMRI data sets. RESULTS: Synthetic data: Activation detection results demonstrate the superiority of the HSMESM mapping method with respect to a standard implementation of the statistical parametric mapping (SPM) approach. They are also very close, sometimes equivalent, to those obtained with an "ideal" implementation of SPM in which the activation patterns synthesized are reused for analysis. The HSMESM method appears clearly insensitive to timing variations of the hemodynamic response and exhibits low sensitivity to fluctuations of its shape (unsustained activation during task). Real epoch-related data: HSMESM activation detection results compete with those obtained with SPM, without requiring any prior definition of the expected activation patterns thanks to the unsupervised character of the HSMESM mapping approach. Along with activation maps, the method offers a wide range of additional fMRI analysis functionalities, including activation lag mapping, activation mode visualization, and hemodynamic response function analysis. Real event-related data: Activation detection results confirm and validate the overall strategy that consists in focusing the analysis on the transients, time-localized events that are the HROs. CONCLUSION: All the experiments performed on synthetic and real fMRI data demonstrate the relevance of HSMESMs in fMRI brain mapping. In particular, the statistical character of these models, along with their learning and generalizing abilities are of particular interest when dealing with strong variabilities of the active fMRI signal across time, space, experiments, and subjects.

Adolescent↗
PubMed2003

Diagnosis and exploration of massively univariate neuroimaging models.

The goal of this work is to establish the validity of neuroimaging models and inferences through diagnosis and exploratory data analysis. While model diagnosis and exploration are integral parts of any statistical modeling enterprise, these aspects have been mostly neglected in functional neuroimaging. We present methods that make diagnosis and exploration of neuroimaging data feasible. We use three- and one-dimensional summaries that characterize the model fit and the four-dimensional residuals. The statistical tools are diagnostic summary statistics with tractable null distributions and the dynamic graphical tools which allow the exploration of multiple summaries in both spatial and temporal/interscan aspects, with the ability to quickly jump to spatiotemporal detail. We apply our methods to a fMRI data set, demonstrating their ability to localize subtle artifacts and to discover systematic experimental variation not captured by the model.

Algorithms↗
PubMed1984

Methodological considerations in the use of attribute variables in neuropsychological research.

This paper examines the conceptual and statistical difficulties created when neuropsychological research uses attribute variables in traditional orthogonal experimental designs. It is argued that attribute variables, as a result of their statistical and theoretical nonindependence, break the underlying assumptions of these traditional designs, and may lead to incorrect inferences being drawn. These difficulties are illustrated in a consideration of the typical use of analysis of variance designs, matched groups designs, and the analysis of covariance. Finally, a plea is made for the explicit consideration of the assumptions underlying the design models used in neuropsychological research, and a suggestion is made regarding the more appropriate use of correlational techniques in neuropsychology.

Adolescent↗
PubMed1969

Cellular differentiation of the immune system of mice. IV. Lack of class differentiation in thymic antigen-reactive cells.

Thymocytes and marrow cells of unprimed donor mice were mixed in vitro and transplanted into X-irradiated syngeneic mice. 18 hr later, sheep erythrocytes were injected to induce immune responses. Splenic plaque-forming cells (PFC) secreting IgM (direct PFC) or IgG (indirect PFC) hemolytic antibody were enumerated at the time of peak responses. By transplanting graded and limiting numbers of thymocytes with 4 x 10(7) marrow cells, inocula were found which contained one or a few thymic antigen-reactive cells (ARC) reaching the recipient spleens, interacting with marrow cells, and inducing PFC formation. The frequency values of ARC inferred from direct and indirect plaque assays were very similar, 1 in approximately 10(7) thymocytes. Furthermore, statistical analysis indicated that the formation of direct PFC was not independent of the formation of indirect PFC. This was interpreted to mean that ARC were not specialized themselves and did not determine the molecular class of antibody to be secreted after interaction with marrow cells. Spleens of thymus-marrow grafted mice containing one or two ARC and non-limiting numbers of marrow precursors of PFC (P-PFC), had direct and indirect PFC clustered in several focal areas. Assuming that each focal area represented the progeny of one P-PFC that had interacted with ARC, these results confirmed the statistical evidence for lack of class differentiation in thymic ARC, and also indicated that each ARC or its progeny cells interacted with more than one P-PFC of either class.

Animals↗