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 1,531 records · Page 85Linked to original sources
PubMed1989

[Analytical epidemiology of urolithiasis].

In this paper, urolithiasis is reviewed from the standpoint of analytical epidemiology, which examines a statistical association between a given disease and a hypothesized factor with an aim of inferring its causality. Factors incriminated epidemiologically for stone formation include age, sex, occupation, social class (level of affluence), season of the year and climate, dietary and fluid intake and genetic prodisposition. Since some of these factors are interlinked, they are broadly classified into five categories and epidemiologically looked over here. Genetic predisposition is essentially endorsed by the more frequent episodes of stone formation in the family members of stone formers, as compared to non-stone formers. Nevertheless, some environmental factors (likely to be dietary habits) shared by family members are believed to be relatively more important than genetic predisposition. A hot, sunny climate may influence stone formation through inducing dehydration with increased perspiration and increased solute concentration with decreased urine volume, coupled with inadequate liquid intake, and possibly through the greater exposure to ultraviolet radiation which eventually results in an increased vitamin D production, conceivably correlated with seasonal variation in calcium and oxalate excretion to the urine. Urinary tract infections are importantly involved in the formation of magnesium ammonium phosphate stones in particular. The association with regional water hardness is still in controversy. Excessive intake of coffee, tea and alcoholic beverages seemingly increase the risk of renal calculi, though not consistently confirmed. Many dietary elements have been suggested by numerous clinical and experimental investigations, but a few elements are substantiated by analytical epidemiological investigations. An increased ingestion of animal protein and sugar and a decreased ingestion of dietary fiber and green-yellow vegetables are linked with the higher probability of stone formation in the industrialized countries. No trace elements in foodstuffs and liquids have been epidemiologically associated. The dietary guidelines for avoiding stone formation and/or recurrence are summarized in this paper, including other daily-life recommendations.

Diet↗
PubMed1987

Parental and sib likelihoods in genealogy reconstruction.

Estimation of genealogical relationships from genetic data provides an approach to answering many questions of population biology. In this estimation problem, previous work has shown that bilateral relatives such as full sibs may be more likely parents than the true parent individuals. This paper investigates the source of this paradox, and the circumstances under which it may arise. Alternative approaches to inferring parentage are proposed; these involve analysis of the distributions of log-likelihood statistics and of the bivariate distribution of sib and parent log-likelihoods. A Bayesian approach may also be superposed on the likelihood analysis, enabling any prior knowledge of the population to be incorporated.

Alleles↗
PubMed1996

Paternity exclusion by DNA markers: effects of paternal mutations.

In parentage testing when one parent is excluded, the distribution of the number of loci showing exclusion due to mutations of the transmitting alleles is derived, and it is contrasted with the expected distribution when the exclusion is caused by nonpaternity. This theory is applied to allele frequency data on short tandem repeat loci scored by PCR analysis, and VNTR data scored by Southern blot RFLP analysis that are commonly used in paternity analysis. For such hypervariable loci, wrongly accused males should generally be excluded based two or more loci, while a true father is unlikely to be excluded based on multiple loci due to mutations of paternal alleles. Thus, when these DNA markers are used for parentage analysis, the decision to infer non-paternity based on exclusions at two or more loci has a statistical support. Our approach places a reduced weight on the combined exclusion probability. Even with this reduced power of exclusion, the probability of exclusion based on combined tests on STR and VNTR loci is sufficiently large to resolve most paternity dispute cases in general populations.

Adult↗
PubMed1997

Investigation of the mechanism of action of 2% fusidic acid lotion in the treatment of acne vulgaris.

We describe the results of a single-centre, double-blind, vehicle-controlled, parallel group study on the quantitative effects of 2% fusidic acid lotion (Fucidin lotion) in facial acne vulgaris. The trial was completed by 52 patients aged 15-25 years with mild to moderate acne who had been randomized to either Fucidin Lotion (n = 25) or its base (n = 27). Primary outcome measures included colony counts of Propionibacterium acnes and micrococcaceae and measurements of skin surface lipid free fatty acids and sebum excretion rate. Clinical assessment was based on the acne grade, count of inflamed and non-inflamed lesions and evidence of a primary irritant dermatitis. There was a variable but gradual reduction in lesion counts with the maximum improvement at 12 weeks for inflamed lesions, where the reduction was 19.9% for fusidic acid and 24.7% for the placebo. The non-inflamed lesions decreased by 10.8% in the fusidic acid group and increased by 15.9% in the placebo group; this difference was not statistically significant. Although the fusidic acid reduced the micrococcaceae count by 1 log cycle, inferring adequate compliance, there was no reduction in the counts of P. acnes, surface free fatty acids or sebum excretion rate. This study has failed to explain the mechanism of action of topical fusidic acid.

Acne Vulgaris↗
PubMed1989

Sample sizes for constructing confidence intervals and testing hypotheses.

Although estimation and confidence intervals have become popular alternatives to hypothesis testing and p-values, statisticians usually determine sample sizes for randomized clinical trials by controlling the power of a statistical test at an appropriate alternative, even those statisticians who recommend the use of confidence intervals for inference. There is merit in achieving consistency in the techniques for data analysis and sample size determination. To that end, this paper compares sample size determination with use of the length of the confidence interval with that obtained by control of power.

Angina Pectoris↗
PubMed1993

Statistical test of the shortening of latent periods in experimental radiation carcinogenesis under competing risks.

The mean life span of animals killed by a specific type of tumor is influenced by competing risks. The parametric inference method of Noda et al. was applied to a set of mouse experimental data in order to correct for the appearance of observed life span distribution under competing risks and to test statistical significances of difference between corrected mean life spans. Data were from an experiment on tumors induced in mice by X-rays: whole body irradiated with 600 R; head with 800 R; trunk or lower body with 800 R. The statistically significant changes were found: Whole body irradiation shortened the mean latent period of malignant lymphomas whereas the head irradiation shortened the latent periods of none of tumors. Trunk irradiation shortened mean latent periods of lung tumors. Lower body irradiation showed a tendency to shorten the mean latent periods of mammary tumors. Results that differed from the above were obtained when there was no correction for competing risks.

Animals↗
PubMed1994

Statistical methods in neuroimaging with particular application to emission tomography.

We review statistical methods being applied in four key areas connected with PET and SPECT neuroimaging: (i) image reconstruction (briefly); (ii) tracer-kinetic, or compartmental, modelling; (iii) inference from region-of-interest data; (iv) inference at the pixel or voxel level. Under the last heading, we pay particular attention to the analysis of data from serial scans. We conclude by identifying some topics for future statistical research.

Algorithms↗
PubMed2004

Hunting drug targets by systems-level modeling of gene expression profiles.

Structural learning of Bayesian networks applied to sets of genome-wide expression patterns has been recently discovered as a potentially useful tool for the systems-level statistical description of gene interactions. We train and analyze Bayesian networks with the goal of inferring biological aspects of gene function. Our two-component approach focuses on supporting the drug discovery process by identifying genes with central roles for the network operation, which could act as drug targets. The first component, referred to as scale-free analysis, uses topological measures of the network-related to a high-traffic load of genes-as estimators for their functional importance. The second component, referred to as generative inverse modeling, is a method of estimating the effect of a simulated drug treatment or mutation on the global state of the network, as measured in the expression profile. We show for a dataset from acute lymphoblastic leukemia patients that both approaches are suitable for finding genes with central cellular functions. In addition, generative inverse modeling correctly identifies a known oncogene in a purely data-driven way.

Algorithms↗
PubMed1992

Genetic and environmental determinants of type II diabetes in Mexico City and San Antonio.

To study genetic and environmental determinants of non-insulin-dependent (type II) diabetes, we compared a random sample of 35- to 64-yr-old Mexican-American men and women living in several low-income barrio neighborhoods of San Antonio to similarly aged Mexicans living in a low-income colonia of Mexico City (Colonia Liberales). A total of 1138 Mexican Americans, representing 64.3% of the original sample, and 646 Mexicans, representing 69.2% of the original sample, participated in the survey. Diabetes was diagnosed using World Health Organization criteria. Genetic susceptibility to type II diabetes was inferred from the percentage of Native American genetic admixture as estimated from skin reflectance measurements. The prevalence of diabetes was 36% higher among San Antonio Mexican Americans than among Mexicans in Mexico City; this difference was highly statistically significant (age- and sex-adjusted prevalence ratio 1.36, P = 0.006). This excess was observed despite the fact that genetic susceptibility, as inferred from the admixture estimates, was similar in the two cities. On the other hand, Mexicans were somewhat leaner as measured by body mass index and skin folds. Mexican women consumed fewer total calories than Mexican-American women, but there was no difference in the caloric intake of men. Mexico City residents ate less fat (18-19% of total calories vs. 31-32% in San Antonio, P less than 0.001), more carbohydrate (64-65 vs. 49%, P less than 0.001), and performed more physical activity than San Antonio Mexican Americans. Mexicans appeared to consume more refined sugar than Mexican Americans.(ABSTRACT TRUNCATED AT 250 WORDS)

Adult↗
PubMed2000

Management of data used in clinical trials which is unevenly distributed at baseline.

In this study, 63 healthy adult males were selected for participation in a clinical trial. After initial screening to determine their suitability for participation in the trial, an appointment was scheduled for a professional prophylaxis to derive baseline data and to instruct volunteers in the use of a standard oral hygiene regimen for the trial. Volunteers were then randomly assigned to test and control groups. Follow-up appointments were scheduled two and four weeks thereafter for collection of data. The presence of dental plaque and calculus was assessed at each appointment. Data was to be analysed by using a Student's 't'-test for paired data, but significant differences in the plaque scores were found between the test and control groups at baseline. As a result, the data could not be analysed in this way to obtain a meaningful result. An initial scatter plot of the data revealed six subjects whose plaque scores varied considerably from the group. The aim of this analysis was to evaluate how two different approaches to statistical analysis of data in which significant differences between test and control groups at baseline might affect the inferences drawn from the data. Reasons for significant differences in baseline data in randomly selected groups of volunteers were considered, as well as methods of avoiding this situation. Suggestions on the management of situations in which databases significantly differ include the elimination of 'outliers' and the use of techniques like the Standard Normal Deviate (SND). The data for this study were analysed using these techniques. Although no statistical differences were identified between the two methods of analysis, numerical differences were evident which altered with the type of analysis used. It was concluded that techniques for transformation of the data, like those used in this study, made no difference to the results of subsequent statistical analysis by comparison with the original data set. The influence of sample selection and analysis of data on the results of clinical trials are discussed. The difficulties in interpretation of the results of statistical analyses were highlighted. The influence of imbalances in the data set on the interpretation of the results of statistical analysis was shown to be minimal in this clinical trial.

Adult↗
PubMed2004

Statistical parametric mapping for event-related potentials: I. Generic considerations.

In this paper, we frame the strategy and motivations behind developments in statistical parametric mapping (SPM) for the analysis of electroencephalogram (EEG) data. This work deals specifically with SPM procedures for the analysis of event-related potentials (ERP). We place these developments in the larger context of integrating electrophysiological and hemodynamic measurements of evoked brain responses through the fusion of EEG and fMRI data. In this paper, we consider some fundamental issues when selecting an appropriate statistical model that enables diverse questions to be asked of the data and at the same time retains maximum sensitivity. The three key issues addressed in this paper are as follows: (i) should multivariate or mass univariate analyses be adopted, (ii) should time be treated as an experimental factor or as a dimension of the measured response variable, and (iii) how to form appropriate explanatory variables in a hierarchical observation model. We review the relative merits of the different options and explain the rationale for our choices. In brief, we motivate a mass univariate approach in terms of sensitivity to region-specific responses. This involves modeling responses at each voxel or space bin separately. In contradistinction, we treat time as an experimental factor to enable inferences about temporally distributed responses that encompass multiple time bins. In a companion paper, we develop statistical models of ERPs in the time domain that follow from the heuristics established here and illustrate the approach using simulated and real data.

Analysis of Variance↗
PubMed1993

Bayesian analysis of mixtures applied to post-synaptic potential fluctuations.

Bayesian inference techniques have been applied to the analysis of fluctuation of post-synaptic potentials in the hippocampus. The underlying statistical model assumes that the varying synaptic signals are characterized by mixtures of (unknown) numbers of individual gaussian, or normal, component distributions. Each solution consists of a group of individual components with unique mean values and relative probabilities of occurrence and a predictive probability density. The advantages of bayesian inference techniques over the alternative method of maximum likelihood estimation (MLE) of the parameters of an unknown mixture distribution include the following: (1) prior information may be incorporated in the estimation of model parameters; (2) conditional probability estimates of the number of individual components in the mixture are calculated; (3) flexibility exists in the extent to which the estimated noise standard deviation indicates the width of each component; (4) posterior distributions for component means are calculated, including measures of uncertainty about the means; and (5) probability density functions of the component distributions and the overall mixture distribution are estimated in relation to the raw grouped data, together with measures of uncertainty about these estimates. This expository report describes this novel approach to the unconstrained identification of components within a mixture, and provides demonstration of the usefulness of the technique in the context of both simulations and the analysis of distributions of synaptic potential signals.

Action Potentials↗
PubMed2003

Inference of viral evolutionary rates from molecular sequences.

The processes of mutation and nucleotide substitution contribute to the observed variability in virulence, transmission and persistence of viral pathogens. Since most viruses evolve many times faster than their human hosts, we are in the unusual position of being able to measure these processes directly by comparing viral genes that have been isolated and sequenced at different points in time. The analysis of such data requires the use of specific statistical methods that take into account the shared ancestry of the sequences and the randomness inherent in the process of nucleotide substitution. In this paper we describe the various statistical methods for estimating evolutionary rates, which can be classified into three general approaches: linear regression, maximum likelihood, and Bayesian inference. We discuss the advantages and shortcomings of each approach and illustrate their use through the analysis of two example viruses; human immunodeficiency virus type 1 and dengue virus serotype 4. Reliable estimates of viral substitution rates have many important applications in population genetics and phylogenetics, including dating evolutionary events and divergence times, estimating demographic parameters such as population size and generation time, and investigating the effect of natural selection on molecular evolution.

Base Sequence↗
PubMed2003

Statistical and visual morph movie analysis of crystallographic mutant selection bias in protein mutation resource data.

The relationship between protein mutations and conformational change can potentially decipher the language relating sequence to structure. Elsewhere, we presented the Protein Mutant Resource (PMR), an online tool that systematically identified related mutants in the Protein DataBank (PDB), inferred mutant Gene Ontology classifications using data-mining, and allowed intuitive exploration of relationships between mutant structures. Here, we perform a comprehensive statistical analysis of PMR mutants. Although the PMR contains spectacular conformational changes, generally there is a counter-intuitive inverse relationship between conformational change and the number of mutations. That is, PDB mutations contrast naturally evolved mutations. We compare the frequencies of mutations in the PMR/PDB datasets against the PAM250 natural mutation frequencies to confirm this. We make available morph movies from PMR structure pairs, allowing visual analysis of conformational change and the ability to distinguish visually between conformational change due to motions (e.g., ligand binding)and mutations. The PMR is at http://pmr.sdsc.edu.

Bias↗
PubMedDate not supplied

A forecasting approach to accelerate drug development.

The clinical phase of drug development should be concluded sooner and at a lower cost if primarily only the pivotal and supportive studies were to be conducted. Such improved efficiency requires development of a decision support system that delivers five new capabilities: (i) it enables one to predict a result of a clinical study and to identify those studies that are expected to have an acceptable probability of success; (ii) it will allow one to optimally utilize available pharmacokinetic and pharmacodynamic (PK/PD) data and improve its predictive capability as more data become available; (iii) it will enable one to project useful population results, not just mean results; (iv) predictions will be accompanied by a measure of reliability; and (v) expected initial clinical results will be predictable from animal and related drug class data. With such a tool population targets could be specified very early in the drug development programme, challenged, and then rationally revised at each step during the development process. This report describes progress in developing and testing a clinical trials Forecaster, a prototype for such a system. The Forecaster generates estimates of the joint density for a population of combined PK/PD parameters. That population then serves as a surrogate for the population of individuals. When the resulting joint density is sampled, the obtained sets of parameters may be used to generate data that is statistically indistinguishable from the original experimental data. Such simulated data can be used to validate assumptions, and make inferences on specified population targets that are accompanied by a measure of prediction reliability. We demonstrate use of the forecaster by employing N = 22 PK/PD parameter sets for an orally administered analgesic.

Bias↗