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.

SourceResearch connectionFrom yearThrough year

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

At least 1,297 records · Page 72Linked to original sources

PubMed2003

Lung cancer mortality among nuclear workers of the Mayak facilities in the former Soviet Union. An updated analysis considering smoking as the main confounding factor.

A new analysis of lung cancer mortality in a cohort of male Mayak workers who started their employment in the plutonium and reprocessing plants between 1948 and 1958 has been carried out in terms of a relative risk model. The follow-up has been extended until 1999, moreover a new dosimetry system (DOSES2000) has been established. Particular emphasis has been given to a discrimination of the effects of external gamma-exposure and internal alpha-exposure due to incorporated plutonium. This study has also utilized and incorporated the information from a cohort of Mayak reactor workers, who were exposed only externally to gamma-rays. The influence of smoking as the main confounding factor for lung cancer has been studied. The baseline lung cancer mortality rate was not taken from national statistics but was derived from the cohort itself. The estimated excess relative risk for the plutonium alpha-rays was 0.23/Sv (95%CI: 0.16-0.31). The resulting risk coefficient for external gamma-ray exposure was very low with a statistically insignificant estimate of 0.058/Sv (95%CI: -0.072-0.20). The inferred relative risk for smokers was 16.5 (95%CI: 12.6-20.5).

Cohort Studies↗

PubMed2006

Inferring population parameters from single-feature polymorphism data.

This article is concerned with a statistical modeling procedure to call single-feature polymorphisms from microarray experiments. We use this new type of polymorphism data to estimate the mutation and recombination parameters in a population. The mutation parameter can be estimated via the number of single-feature polymorphisms called in the sample. For the recombination parameter, a two-feature sampling distribution is derived in a way analogous to that for the two-locus sampling distribution with SNP data. The approximate-likelihood approach using the two-feature sampling distribution is examined and found to work well. A coalescent simulation study is used to investigate the accuracy and robustness of our method. Our approach allows the utilization of single-feature polymorphism data for inference in population genetics.

Arabidopsis↗

PubMed1998

Segregation analysis of plasminogen activator inhibitor-1 and fibrinogen levels in the NHLBI family heart study.

Elevated plasminogen activator inhibitor-1 (PAI-1) and fibrinogen concentrations are risk factors for coronary heart disease. We investigated environmental, familial, and genetic influences on PAI-1 antigen and fibrinogen concentrations in 2029 adults from 512 randomly ascertained families in 4 US communities. We used maximum-likelihood segregation analysis to fit several genetic and nongenetic modes of inheritance to the data to determine whether mendelian inheritance of a major gene could best explain the familial distributions of these 2 hemostatic factors. Age- and gender-adjusted familial correlations for PAI-1 antigen level averaged 0.16 in first-degree relatives (95% CI=0.11 to 0.21); the spouse correlation was positive but not statistically significant (r=0.10, 95% CI=-0.02 to 0.23). Complex segregation analysis indicated a major gene associated with higher PAI-1 concentrations in 65% of individuals from these families. Demographic, anthropometric, lifestyle, and metabolic characteristics together explained 37% to 47% of the variation in PAI-1 antigen levels, and the inferred major gene explained an additional 17% of the variance. Positive and statistically significant age- and gender-adjusted familial correlations in first-degree relatives indicated a possible heritable component influencing plasma fibrinogen concentration (r=0. 17, 95% CI=0.13 to 0.22); however, segregation analysis did not provide statistical evidence of a major gene controlling fibrinogen level. These family data suggest that there are modest familial and genetic effects on the concentration of PAI-1.

Adult↗

PubMed2005

Grammatical inference in bioinformatics.

Bioinformatics is an active research area aimed at developing intelligent systems for analyses of molecular biology. Many methods based on formal language theory, statistical theory, and learning theory have been developed for modeling and analyzing biological sequences such as DNA, RNA, and proteins. Especially, grammatical inference methods are expected to find some grammatical structures hidden in biological sequences. In this article, we give an overview of a series of our grammatical approaches to biological sequence analyses and related researches and focus on learning stochastic grammars from biological sequences and predicting their functions based on learned stochastic grammars.

Algorithms↗

PubMed2005

Asequential Monte Carlo quantum mechanics study of the hydrogen-bond interaction and the solvatochromic shift of the n-pi* transition of acrolein in water.

The sequential Monte Carlo (MC) quantum mechanics (QM) methodology, using time-dependent density-functional theory (TD-DFT), is used to study the solvatochromic shift of the n-pi* transition of trans-acrolein in water. Using structures obtained from the isothermal-isobaric Metropolis MC simulation TD-DFT calculations, within the B3LYP functional, are performed for the absorption spectrum of acrolein in water. In the average acrolein makes one hydrogen bond with water and the hydrogen-bond shell is responsible for 30% of the total solvatochromic shift, considerably less than the shift obtained for the minimum-energy configurations. MC configurations are sampled after analysis of the statistical correlation and 100 configurations are extracted for subsequent QM calculations. All-electron TD-DFT B3LYP calculations of the absorption transition including acrolein and all explicit solvent molecules within the first hydration shell, 26 water molecules, give a solvatochromic shift of 0.18 +/- 0.11 eV. Using simple point charges to represent the solvent the shifts are calculated for the first, second, and third solvation shells. The results converge for the calculated shift of 0.20 +/- 0.10 eV in very good agreement with the experimentally inferred result of 0.20 +/- 0.05 eV. All average results presented are statistically converged.

Acrolein↗

PubMed1990

Sampling strategies for distances between DNA sequences.

An international effort is now underway to obtain the DNA sequence for the entire human genome (Watson and Jordan, 1989, Genomics 5, 654-656; Barnhart, 1989, Genomics 5, 657-660). This Human Genome Initiative will generate sequence data from several species other than humans, and will result in several copies per species of at least some regions of the genome. Although the project has generated much interest, it is but one aspect of the widespread effort to generate DNA sequence data. Published sequences are collected in common databases, and release 63 of GenBank in March 1990 contained 40,127,752 bases from 33,337 reported sequences (News from GenBank 3; Mountain View, California: Intelligenetics, Inc., 1990). Large though this database is, it is only about 1% of the number of bases in the human genome. Interpretations of data of such magnitude are going to require the collaborative efforts of biometricians and molecular biologists, and an aim of this paper is to show that there is also a role for readers of this journal in the design of surveys of DNA sequences. Discussion here will center on the use of sequence data in evolutionary studies, where some region of DNA is sequenced in several different species. The object is to infer the evolutionary history of that particular region, or of the species themselves. Statistical issues in the very important studies on sequences to locate and characterize regions responsible for human diseases will not be addressed here. We will discuss appropriate ways of measuring distances between DNA sequences and of predicting the sampling properties of the distances. There are procedures for inferring evolutionary histories for a set of elements that depend on a matrix of distances between each pair of elements, and the precision of resulting trees must be influenced by the precision of the distances. We will show that account needs to be taken of two sampling processes--the sampling of sequences by the investigator ("statistical sampling"), and the sampling of genetic material involved in the formation of offspring from a parental population ("genetic sampling").

Analysis of Variance↗

PubMed2000

Applications of likelihood asymptotics for nonlinear regression in herbicide bioassays.

Dose-response models are intensively used in herbicide bioassays. Despite recent advancements in the development of new herbicides, statistical analyses are commonly based on asymptotic approximations that are sometimes poor. This paper presents the use of recent results in higher order asymptotics for likelihood-based inference in nonlinear regression. The methods presented provide accurate approximation for the distribution of test statistics and for prediction limits. Analyses of the fit and measures of detection limits of the bioassays are considered, and the potential of the methods is illustrated by examples with real data.

Biological Assay↗

PubMed1987

Epidemiologic programs for computers and calculators. Inferences on odds ratios, relative risks, and risk differences based on standard regression programs.

Statistical analyses of the joint effects of several factors (covariates) on the risk of disease, death, or other dichotomous outcomes, are frequently based on a model that relates the effect of the covariates to some function of the probability of the outcome. The odds ratio, relative risk, and the difference in risks are among the simplest candidates for the outcome function. Each can be specified as a special case of the generalized linear model, but their use has been limited to researchers with access to specialized computer programs that are not yet generally available in standard computer packages. The purpose of this communication is to describe how to implement the maximum likelihood estimation procedures and hypothesis testing associated with the generalized linear model using any computer program that can perform weighted least squares analyses. The procedure is applied specifically to models for relative risks, risk differences, and odds ratios. The techniques are illustrated with SAS and SPSSx programs for data sets previously presented.

Computers↗

PubMed1996

Bayesian inference for hierarchical mixtures-of-experts with applications to regression and classification.

This paper studies the problems of inference and prediction in a class of models known as hierarchical mixtures-of-experts (HME). The statistical model underlying an HME is a mixture model in which both the mixture coefficients and the mixture components are generalized linear models. Bayesian inference regarding an HME's parameters is presented in the contexts of regression and classification using Markov chain Monte Carlo methods. A benefit of this Bayesian approach is the ability to obtain a sample from the posterior distribution of any functional of the parameters of the given model. In this way, more information is obtained than provided by a point estimate. The methods are illustrated on a nonlinear regression problem and on a breast cancer classification problem. The results indicate that the HME showed good prediction performance, and also gave the additional benefit of providing for the opportunity to assess the degree of certainty of the model in its predictions.

Algorithms↗

PubMed1999

Fuzzy logic alternative for analysis in the biomedical sciences.

Fuzzy logic brings new possibilities into control, modeling, data analysis, diagnostics, decision making, and other working fields in biomedical sciences. This paper presents how fuzzy logic can be used as an alternative or supplement to statistics in biomedical analysis. It shows an adaptive neuro-fuzzy inference computing in comparison with linear and curvilinear regression. The main goal of this presentation is to involve fuzzy logic in biomedical research. Thus, we carried out a mathematical treatment of the clinical sample, semen of infertile man, with the independent variable Concentration of spermatozoa and the dependent variable Number of spermatozoa by 230 observations.

Biometry↗

PubMed1981

Suitability of control materials. General principles and methods of investigation.

We propose methods for characterizing the behavior of quality-control specimens. Candidate quality-control specimens and authentic patients' specimens were analyzed by various methods. Patients' specimens were chosen to be fully representative of those encountered, including subsets from persons who were healthy, had defined disease states, were in therapy, or whose specimens were lipemic, icteric, etc. The analytical methods chosen include those most commonly used as well as reference analytical methods. Procedures for characterizing the behavior of patients' specimens and candidate quality-control specimens are proposed and their applicability is demonstrated. The linear ratio method is a univariate graphical approach in which differences in accuracy among methods for any specimen or group of specimens are each displayed on a linear scale. Correspondence analysis is a descriptive multivariate statistical technique that allows both the specimens and the analytical methods to be characterized. The statistical techniques, in our application, allow the behavior of quality-control specimens to be assessed with respect to authentic patients' specimens without influencing the assessment process. Correspondence analysis provides a graphic representation by projecting both the specimens and the analytical methods on factorial planes. The appropriateness of te behavior of a quality-control specimen may be inferred from its position relative to those of authentic patients' specimens. These statistical techniques also provide some information regarding the specificity of analytical methods.

Blood Chemical Analysis↗

PubMed1994

A test of the model-free formulas. Effects of anisotropic rotational diffusion and dimerization.

The effects of anisotropy of rotational diffusion and extent of dimerization on the performance of the simple and extended model-free formulas are investigated. Numerically exact 15N NMR R1, R2, and NOE data are simulated for cylindrically symmetric species and also for mixtures of spherical monomers and dimers with the same internal dynamics. The relevant internuclear vectors are assumed to move in isotropic deflection potentials fixed at different orientations in the molecule and to exhibit a single relaxation time in their internal correlation functions. The simple model-free formula is fitted to these simulated data in order to obtain the best-fit order parameter and internal relaxation time for each nucleus. Fitting is accomplished by the standard data-analysis protocol, in which a single common global correlation time is adjusted, and also by an alternative protocol, in which the global correlation time is adjusted separately for each nucleus. The extended model-free formula is likewise fitted to these same data. With noise-free data, the simple model-free formula and standard protocol yield remarkably good best-fit internal motion parameters up to moderate anisotropies (r = D parallel/D perpendicular = 2.0), but some or many of the NMR relaxation data are not fitted well even for quite modest anisotropies (r = 1.3). The extended model-free formula yields an improved fit to the NMR data, but predicts substantial amplitudes of nonexistent slow internal motions (tau approximately greater than 0.2 ns) for many of the nuclei for all r > or = 1.3. The simple model-free formula with the alternate protocol yields even better internal motion parameters than the standard protocol and also an excellent fit to the NMR relaxation data. The best-fit global correlation time for each nucleus corresponds very closely to the theoretical correlation time defined herein. Knowledge of these times would allow one not only to estimate the anisotropy of diffusion but also in favorable cases to infer the existence of slow internal motions. Inclusion of typical statistical errors in R1, R2, and NOE, or modest exchange contributions to R2, seriously degrades the performance of the simple model-free formula with either protocol, especially in regard to the internal relaxation times, which can exhibit very large deviations from their input value even for spherical diffusors. When the fraction of monomers existing as dimers lies in the range 0.1 < or = fd < or = 0.8, none of the three model-free approaches tested yields reliable internal motion parameters.

Algorithms↗

PubMed2026

An avuncular relationship generating a parent-offspring signal in forensic familial DNA searching: a case report.

In 2019, a series of vehicle burglaries occurred near the Dead Sea, Israel. DNA profiles obtained from six crime scenes were concordant, but no direct match was found in the national forensic DNA database. A CODIS familial search identified a male candidate as the highest-ranked potential relative. Pairwise kinship analysis based on 15 shared autosomal STR loci yielded the highest likelihood ratio under the parent-offspring (PO) hypothesis (LR = 530,300). However, Y-STR analysis performed in parallel with the familial search excluded a shared paternal lineage. Full mitochondrial genome sequencing subsequently demonstrated an identical haplotype, supporting a shared maternal lineage. Investigative inquiries identified a maternal uncle of the candidate whose reference STR profile fully matched the evidentiary profile.Population-based simulations of 100,000 second-degree relative pairs and 100,000 unrelated pairs showed that 2.05% of simulated second-degree pairs produced LRs equal to or greater than the observed second-degree LR (CODIS HS LR = 5,538), demonstrating that the observed similarity, although within the upper tail, remained within the expected second-degree distribution. In a retrospective expanded-marker analysis, increasing the shared autosomal STR loci from 15 to 20 excluded the PO hypothesis (LR = 0), while close-relationship hypotheses remained supported.This case illustrates how stochastic allele sharing across a limited number of autosomal STR loci can produce overlap between relationship categories and how additional markers can substantially alter relationship inference. Integrating sufficiently informative autosomal markers, lineage-specific markers, statistical evaluation, and investigative information is therefore important when interpreting familial DNA search results.

Autosomal STRs↗

PubMed2005

Bottom-up and top-down dynamics in visual cortex.

A key emergent property of the primary visual cortex (V1) is the orientation selectivity of its neurons. Recent experiments demonstrate remarkable bottom-up and top-down plasticity in orientation networks of the adult cortex. The basis for such dynamics is the mechanism by which orientation tuning is created and maintained, by integration of thalamocortical and intracortical inputs. Intracellular measurements of excitatory and inhibitory synaptic conductances reveal that excitation and inhibition balance each other at all locations in the cortex. This balance is particularly critical at pinwheel centers of the orientation map, where neurons receive intracortical input from a wide diversity of local orientations. The orientation tuning of neurons in adult V1 changes systematically after short-term exposure to one stimulus orientation. Such reversible physiological shifts in tuning parallel the orientation tilt aftereffect observed psychophysically. Neurons at or near pinwheel centers show pronounced changes in orientation preference after adaptation with an oriented stimulus, while neurons in iso-orientation domains show minimal changes. Neurons in V1 of alert, behaving monkeys also exhibit short-term orientation plasticity after very brief adaptation with an oriented stimulus, on the time scale of visual fixation. Adaptation with stimuli that are orthogonal to a neuron's preferred orientation does not alter the preferred orientation but sharpens orientation tuning. Thus, successive fixation on dissimilar image patches, as happens during natural vision, combined with mechanisms of rapid cortical plasticity, actually improves orientation discrimination. Finally, natural vision involves judgements about where to look next, based on an internal model of the visual world. Experiments in behaving monkeys in which information about future stimulus locations can be acquired in one set of trials but not in another demonstrate that V1 neurons signal the acquisition of internal representations. Such Bayesian updating of responses based on statistical learning is fundamental for higher level vision, for deriving inferences about the structure of the visual world, and for the regulation of eye movements.

Adaptation, Psychological↗

PubMed2004

Coordinate-based versus structural approaches to brain image analysis.

A basic issue in neurosciences is to look for possible relationships between brain architecture and cognitive models. The lack of architectural information in magnetic resonance images, however, has led the neuroimaging community to develop brain mapping strategies based on various coordinate systems without accurate architectural content. Therefore, the relationships between architectural and functional brain organizations are difficult to study when analyzing neuroimaging experiments. This paper advocates that the design of new brain image analysis methods inspired by the structural strategies often used in computer vision may provide better ways to address these relationships. The key point underlying this new framework is the conversion of the raw images into structural representations before analysis. These representations are made up of data-driven elementary features like activated clusters, cortical folds or fiber bundles. Two classes of methods are introduced. Inference of structural models via matching across a set of individuals is described first. This inference problem is illustrated by the group analysis of functional statistical parametric maps (SPMs). Then, the matching of new individual data with a priori known structural models is described, using the recognition of the cortical sulci as a prototypical example.

Brain↗

PubMed2002

Molecular phylogeny of symbiotic dinoflagellates inferred from partial chloroplast large subunit (23S)-rDNA sequences.

Symbiotic associations between invertebrates and dinoflagellates of the genus Symbiodinium are a common occurrence in marine environments. However, despite our extensive knowledge concerning the physiological contributions of these algae to their symbiotic partners, our understanding of zooxanthella phylogenetics is still in its early stages. In the past 10 years, studies of Symbiodinium phylogenetics have relied solely on nuclear ribosomal (rDNA) genes. To date, organellar DNA sequences have not been employed to infer phylogenies for this genus of symbiotic dinoflagellates. We address this by presenting the first Symbiodinium phylogeny based on chloroplast (cp) large subunit (23S)-rDNA sequences. Cp23S-rDNA Domain V sequences were determined for 35 dinoflagellate cultures isolated from a range of invertebrate host species and geographical locations. Symbiodinium phylogenies inferred from cp23S-rDNA produced topologies that were not statistically different from those generated from nuclear rDNA, providing the first independent evidence supporting the published major clades of Symbiodinium. In addition, comparisons of sequence dissimilarity indicated that cp23S-rDNA Domain V evolves 9-30 times faster than the V1-V4 regions of nuclear small subunit (n18S)-rDNA, 1-7 times as fast as the D1-D3 regions of nuclear large subunit (n28S)-rDNA, and 0.27-2.25 times that of the internal transcribed spacer (ITS)-rDNA region. Our data suggested that cp23S-rDNA Domain V will prove to be a useful molecule for exploring Symbiodinium phylogenetics.

Animals↗

PubMed2006

Relationship between Escherichia coli strains causing urinary tract infection in women and the dominant faecal flora of the same hosts.

To clarify whether prevalence or special pathogenicity is more important in determining urinary tract infection (UTI) causation, we compared the biotype, phylogenetic group, and virulence genes of Escherichia coli urine strains from 11 women with acute lower UTI with those of the host's dominant intestinal E. coli strain(s). Twenty-one unique E. coli clones were identified. For three women, the single faecal clone identified was also the host's urine clone, whereas for eight women faecal samples yielded 1 or 2 distinct non-urine clones (total, n = 10), either with (n = 3) or without (n = 5) the concurrent urine clone. The eight urine clones from the latter eight women exhibited significantly greater inferred virulence, according to virulence gene content and phylogenetic background, than did the hosts' 10 corresponding 'faecal only' clones. In contrast, the three urine clones that were detected as the host's sole faecal clone exhibited significantly lower inferred virulence than the other eight urine clones, and were statistically indistinguishable from the 10 'faecal only' clones. In conclusion, special pathogenicity is an important determinant of UTI pathogenesis in women, although prevalence may occasionally allow less virulent strains to cause UTI.

Adult↗

PubMed2006

Time as a guide to cause.

How do people learn causal structure? In 2 studies, the authors investigated the interplay between temporal-order, intervention, and covariational cues. In Study 1, temporal order overrode covariation information, leading to spurious causal inferences when the temporal cues were misleading. In Study 2, both temporal order and intervention contributed to accurate causal inference well beyond that achievable through covariational data alone. Together, the studies show that people use both temporal-order and interventional cues to infer causal structure and that these cues dominate the available statistical information. A hypothesis-driven account of learning is endorsed, whereby people use cues such as temporal order to generate initial models and then test these models against the incoming covariational data.

Computers↗