Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “hypothesis testing”

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 433 records · Page 24Linked to original sources
PubMed1993

Norwegian case-control study testing the hypothesis that seafood increases the risk of thyroid cancer.

The hypothesis that consumption of seafood increases the risk of thyroid cancer has been tested by means of a matched case-control study. Linking the file of the National Health Screening Service (NHSS) containing dietary information about 60,000 Norwegians with the 1955-89 thyroid-cancer file of the Cancer Registry, by means of the 11-digit person-number, resulted in 92 cases--each of whom was matched with five controls with regard to age, gender, and place of residence. Forty-eight cases had answered questions on diet before diagnosis; 44 did so after diagnosis. Exposure data on seafood and seafood-related vitamins were recovered from the NHSS files for all 552 subjects. Odds ratios (OR) were computed by means of conditional logistic regression analysis. Univariate analysis of the 48 sets in which the case had answered the dietary questionnaire prior to the thyroid cancer diagnosis, as well as of all 92 sets, indicate that regular users of cod-liver oil, fish liver, or fish sandwich-spread run a higher risk of thyroid cancer than irregular and nonusers, and people eating more fish dinners per week also run a higher risk of thyroid cancer. Stepwise regression analysis corroborates the study hypothesis by showing that these two seafood variables increase the risk of thyroid cancer significantly. On the other hand, the results of a simultaneous regression analysis of these two seafood variables and a dietary vitamin-D index-variable tend to reduce the tenability of the above-mentioned conclusion since none of the OR estimates (all greater than one) reached significance in this part of the statistical analysis.

Adult↗
PubMed2006

A renewed approach to the nonparametric analysis of replicated microarray experiments.

DNA-microarrays find broad employment in biochemical research. This technology allows the monitoring of the expression levels of thousands of genes at the same time. Often, the goal of a microarray study is to find differentially expressed genes in two different types of tissue, for example normal and cancerous. Multiple hypothesis testing is a useful statistical tool for such studies. One approach using multiple hypothesis testing is nonparametric analysis for replicated microarray experiments. In this paper we present an improved version of this method. We also show how p-values are calculated for all significant genes detected with this testing procedure. All algorithms were implemented in an R-package, and instructions on it's use are included. The package can be downloaded at http://www.statistik.unidortmund.de/de/content/einrichtungen/lehrstuehle/personen/jung.html

Algorithms↗
PubMed2000

Meningococcemia as a model for testing the hypothesis of antisepsis therapies.

OBJECTIVE: To critically review the advantages and disadvantages of pediatric meningococcemia as a model for testing antisepsis therapies. DATA SOURCES: Research and review articles on the pathogenesis and treatment of human meningococcemia, as well as editorial commentaries discussing the failure of clinical trials for adult sepsis or Systemic Inflammatory Response Syndrome. Data from these sources are presented in the context of the author's experience as principal investigator in a large, randomized trial on children with invasive meningococcal disease. STUDY SELECTION AND DATA EXTRACTION: Studies were selected to include aspects of epidemiology, pathophysiology, outcome prediction, and therapeutic trials. DATA SYNTHESIS: Compared with an adult sepsis population, meningococcemia is a single disease, diagnosed clinically with high reliability. Patients are previously healthy, without underlying medical or surgical conditions. In contrast to sepsis trials, nearly all patients with meningococcal disease receive effective antibiotics. Finally, meningococcemia most closely resembles animal models of endotoxin infusion, in which most antisepsis therapies have been highly effective. However, the meningococcal model carries major disadvantages, among them that meningococcemia is rare and rapidly progressive and patients are widely dispersed geographically. In addition, a wide range of experimental therapies is routinely provided in an attempt to preserve life or limbs. CONCLUSIONS: Meningococcemia is an ideal model of a rapidly progressive bacterial infection associated with marked endotoxemia. Problems with the model can be overcome by extensive pretrial logistic planning, as well as close coordination and cooperation with national regulatory agencies.

Adult↗
PubMed1975

Immunogenetic aspects of nasopharyngeal carcinoma (NPC) III. HL-a type as a genetic marker of NPC predisposition to test the hypothesis that Epstein-Barr virus is an etiological factor in NPC.

HL-A typing of 144 NPC patients and 236 controls revealed an increased frequency of 1st locus HL-42 (relative risk = 2.24) and an increased frequency of unidentified antigens at the 2nd locus (relative risk = 2.60) in the NPC patients. HL-A2 and the 2nd locus "blank" appeared to act together (HL-A2 blank haplotype) in determining NPC risk in highest-risk Cantonese, whereas in relatively lower-risk non-Cantonese Chinese (Hokkiens, Teochews) they appeared to act independently. Only the "blank" had an increased frequency in Malay NPC patients. Thus there was an indication that the strength of the HL-A association with NPC reflected the 30-50-fold difference in incidence between highest-risk Cantonese and lowest-risk Indians. In Singapore, HL-A segregation patterns in families of nine Chinese NPC patients confirmed that the "blank" was a genetic phenomenon. A new 2nd locus antigen (Singapore-2) has recently been detected. Singapore-2 occurs more frequently in NPC patients and appears to be associated with a high risk for NPC. Since HL-A2 and Singapore-2 are not the risk factors, it is likely that the HL-A association with NPC reflects the existence of disease-susceptibility (DS) genes in linkage disequilibrium with alleles of the HL-A loci. It is proposed that NPC-DS genes may determine differences in immune responsiveness to environmental agents, and thereby determine differences in NPC incidence. If the known altered immune responsiveness of NPC patients to EBV reflects the function of DS genes linked to the high NPC risk HL-A type, then the hypothesis that Epstein-Barr virus has an etiological role in NPC can be tested by several types of prospective studies.

Carcinoma↗
PubMed1989

Sample size determination for confidence intervals on the population mean and on the difference between two population means.

Sample size determination is usually based on the premise that a hypothesis test is to be used. A confidence interval can sometimes serve better than a hypothesis test. In this paper a method is presented for sample size determination based on the premise that a confidence interval for a simple mean, or for the difference between two means, with normally distributed data is to be used. For this purpose, a concept of power relevant to confidence intervals is given. Some useful tables giving required sample size using this method are also presented.

Biometry↗
PubMed1999

[Application of intraclass correlation coefficient to reliability assessment].

To evaluate the reliability of questionnaire and expound the simple method of calculating and testing the intraclass correlation coefficient (ICC), the authors gave an example of how to simply calculate and conduct the hypothesis testing of ICC by using the analysis table of variance. The results demonstrated a high test-retest reliability of the illustrative questionnaire. By using ANOVA table, the calculation and hypothesis testing of the ICC is easy to do. The method can be used in the analysis of quantitative data, and categorical data as well.

Aged↗
PubMed2005

Hierarchical inverse Gaussian models and multiple testing: application to gene expression data.

Detecting differentially expressed genes in microarray experiments is a topic that has been well studied in the literature. Many hypothesis testing methods have been proposed that rely on strong distributional assumptions for the gene intensities. However, the shape of microarray data may vary substantially from one experiment to another, and model assumptions may be seriously violated in many cases. The literature on microarray data is mainly based on two distributions: the log-normal and the gamma distributions, that often appear to be effective when used in a Bayesian hierarchical framework. However, if a model that fits the data well in a global manner seems attractive, two points should be regarded with attention: the ability of the model to fit the tail of the observed distribution, and its robustness to a wrong specification of the model, in terms of error rates for the hypothesis tests. In order to focus on these aspects, we propose to use Bayesian models involving the inverse Gaussian distribution to describe gene expression data. We show that these models can be good competitors to the traditional Bayesian or random effect gamma or log-normal models in some situations. A multiple testing procedure is then proposed, based on an asymptotic property of the posterior probability of the one-sided alternative hypothesis. We show that the asymptotic property is well approximated for inverse Gaussian models, even when the number of observations available for each test is very small.

Journal Article↗
PubMed2004

Model selection in ecology and evolution.

Recently, researchers in several areas of ecology and evolution have begun to change the way in which they analyze data and make biological inferences. Rather than the traditional null hypothesis testing approach, they have adopted an approach called model selection, in which several competing hypotheses are simultaneously confronted with data. Model selection can be used to identify a single best model, thus lending support to one particular hypothesis, or it can be used to make inferences based on weighted support from a complete set of competing models. Model selection is widely accepted and well developed in certain fields, most notably in molecular systematics and mark-recapture analysis. However, it is now gaining support in several other areas, from molecular evolution to landscape ecology. Here, we outline the steps of model selection and highlight several ways that it is now being implemented. By adopting this approach, researchers in ecology and evolution will find a valuable alternative to traditional null hypothesis testing, especially when more than one hypothesis is plausible.

Journal Article↗
PubMed1985

An analysis of alcoholics' perception of hostility before and after treatment.

Volunteer alcoholics being treated in a chemical dependency unit (CDU) were administered the Paired Hands Test-Adult to assess their perceptions of others before and after three weeks of treatment. This test assessed the perception of others along a friendliness-hostility dimension. Test data were compared to a non-alcoholic control group who were not receiving any form of therapeutic services. The main hypothesis tested was that alcoholics experience more hostility than non-alcoholics and project this hostility through perceptual defenses. A secondary hypothesis tested was that traditional short-term therapy reduces the alcoholic's perception of hostility. Neither hypothesis was supported.

Adult↗
PubMed1993

A test of hypothesis on familial correlations.

When familial data are analysed, the model usually employed assumes independence of family observations and constancy of interclass and intraclass correlations. A statistic for testing the validity of the assumptions of family independence and constant interclass and intraclass correlations is developed. The test statistic is for constant family size; it has an asymptotic chi-square distribution. An example to illustrate the theory is given using Frets's data on head lengths. A recommendation is made on how to apply the test to the general case of varying sizes. Another recommendation is made on models to be tried once the null hypothesis is rejected.

Child↗
PubMed2000

Inferring the location and effect of tumor suppressor genes by instability-selection modeling of allelic-loss data.

Cancerous tumor growth creates cells with abnormal DNA. Allelic-loss experiments identify genomic deletions in cancer cells, but sources of variation and intrinsic dependencies complicate inference about the location and effect of suppressor genes; such genes are the target of these experiments and are thought to be involved in tumor development. We investigate properties of an instability-selection model of allelic-loss data, including likelihood-based parameter estimation and hypothesis testing. By considering a special complete-data case, we derive an approximate calibration method for hypothesis tests of sporadic deletion. Parametric bootstrap and Bayesian computations are also developed. Data from three allelic-loss studies are reanalyzed to illustrate the methods.

Adenocarcinoma↗
PubMed2005

Statistical shape analysis: clustering, learning, and testing.

Using a differential-geometric treatment of planar shapes, we present tools for: 1) hierarchical clustering of imaged objects according to the shapes of their boundaries, 2) learning of probability models for clusters of shapes, and 3) testing of newly observed shapes under competing probability models. Clustering at any level of hierarchy is performed using a mimimum variance type criterion criterion and a Markov process. Statistical means of clusters provide shapes to be clustered at the next higher level, thus building a hierarchy of shapes. Using finite-dimensional approximations of spaces tangent to the shape space at sample means, we (implicitly) impose probability models on the shape space, and results are illustrated via random sampling and classification (hypothesis testing). Together, hierarchical clustering and hypothesis testing provide an efficient framework for shape retrieval. Examples are presented using shapes and images from ETH, Surrey, and AMCOM databases.

Algorithms↗
PubMed2004

Reverse methanogenesis: testing the hypothesis with environmental genomics.

Microbial methane consumption in anoxic sediments significantly impacts the global environment by reducing the flux of greenhouse gases from ocean to atmosphere. Despite its significance, the biological mechanisms controlling anaerobic methane oxidation are not well characterized. One current model suggests that relatives of methane-producing Archaea developed the capacity to reverse methanogenesis and thereby to consume methane to produce cellular carbon and energy. We report here a test of the "reverse-methanogenesis" hypothesis by genomic analyses of methane-oxidizing Archaea from deep-sea sediments. Our results show that nearly all genes typically associated with methane production are present in one specific group of archaeal methanotrophs. These genome-based observations support previous hypotheses and provide an informed foundation for metabolic modeling of anaerobic methane oxidation.

Anaerobiosis↗
PubMed2002

Methods for the analysis of incidence rates in cluster randomized trials.

BACKGROUND: The published literature on cluster randomized trials focuses on outcomes that are either continuous or binary. In many trials, the outcome is an incidence rate, such as mortality, based on person-years data. In this paper we review methods for the analysis of such data in cluster randomized trials and present some simple approaches. METHODS: We discuss the choice of the measure of intervention effect and present methods for confidence interval estimation and hypothesis testing which are conceptually simple and easy to perform using standard statistical software. The method proposed for hypothesis testing applies a t-test to cluster observations. To control confounding, a Poisson regression model is fitted to the data incorporating all covariates except intervention status, and the analysis is carried out on the residuals from this model. The methods are presented for unpaired data, and extensions to paired or stratified clusters are outlined. RESULTS: The methods are evaluated by simulation and illustrated by application to data from a trial of the effect of insecticide-impregnated bednets on child mortality. CONCLUSIONS: The techniques provide a straightforward approach to the analysis of incidence rates in cluster randomized trials. Both the unadjusted analysis and the analysis adjusting for confounders are shown to be robust, even for very small numbers of clusters, in situations that are likely to arise in randomized trials.

Cluster Analysis↗
PubMedDate not supplied

Tools of the epidemiologist.

This review provides a summary of epidemiologic tools to facilitate understanding of the design and analysis of studies of Alzheimer disease (AD) and related disorders. Proportions, ratios, rates, prevalence, incidence, study designs, bias, confounding, effect modification, odds and risk ratios, statistical power, and confidence intervals are defined and discussed. Descriptive epidemiology is concerned with describing the distribution of disease by person, place, and time. It is useful for hypothesis generation, but not generally for hypothesis testing. Observational analytic epidemiology focuses on identifying putative causes for an illness. Although its primary mission is hypothesis testing, it can lead to new hypotheses as well. Finally, experimental analytic epidemiology or clinical trials can provide rigorous tests of presumed causal associations. The strengths and limitations of various designs as they apply to determining causal associations in studies of AD and dementia are reviewed. Over the past 60 years, the epidemiologic study of dementia has evolved from basic descriptive studies of prevalence and incidence to case-control and cohort studies and finally to the first clinical trials to prevent AD.

Alzheimer Disease↗
PubMed1979

Formal education and intellectual functioning in the immigrant Cuban elderly.

Formal educational experience during childhood and adolescence is an important modifier of intellectual functioning in North American elderly populations. The culture-independence of this relationship was examined with 31 immigrant Cuban elderly men and women who received their education in Cuba. The amount of formal education was significantly related to performance on measures of classification, combinatorial analysis (males only), hypothesis testing, and matrices. An index of fluid intelligence (matrices) also was significantly related to performance on the classification and hypothesis testing tasks. All participants conserved both liquid and mass, thus showing no regression on these two concerete operational tasks.

Aged↗
PubMed2003

Dose-based duration adjustments for the effects of inhaled trichloroethylene on rat visual function.

Risk assessments often must consider exposures that vary over time or for which the exposure duration of concern differs from the available data, and a variety of extrapolation procedures have been devised accordingly. The present experiments explore the relationship(s) between exposure concentration (C) and time (t) to investigate procedures for assessing the risks of short-term solvent exposures. The first hypothesis tested was that the product of C x t would produce a constant health effect (Haber's rule). The second hypothesis tested was that exposure conditions produce effects in proportion to the tissue concentrations created. Awake, adult, male Long-Evans (LE) rats were exposed to trichloroethylene (TCE) vapor in a head-only exposure chamber while pattern onset/offset visual evoked potentials (VEPs) were recorded. Exposure conditions were designed to provide C x t products of 0 ppm/h (0 ppm for 4 h) or 4000 ppm/h created through four exposure scenarios: 1000 ppm for 4 h; 2000 ppm for 2 h; 3000 ppm for 1.3 h; or 4000 ppm for 1h (n = 9-10/concentration). The amplitude of the VEP frequency double component (F2) was decreased significantly by exposure; this decrease was related to C but not to t or to the C x t product, indicating that Haber's rule did not hold. The mean amplitude (+/- SEM in muV) of the F2 component in the control and treatment groups measured 4.4 +/- 0.5 (0 ppm/4 h), 3.1 +/- 0.5 (1000 ppm/4 h), 3.1 +/- 0.4 (2000 ppm/2 h), 2.3 +/- 0.3 (3000 ppm/1.3 h), and 1.9 +/- 0.4 (4000 ppm/1 h). A physiologically based pharmacokinetic (PBPK) model was used to estimate the concentrations of TCE in the brain achieved during each exposure condition. The F2 amplitude of the VEP decreased monotonically as a function of the estimated peak brain concentration but was not related to the area under the curve (AUC) of the brain TCE concentration. In comparison to estimates from the PBPK model, extrapolations based on Haber's rule yielded approximately a 6-fold error in estimated exposure duration when extrapolating across only a 4-fold change in exposure concentration. These results indicate that the use of a linear form of Haber's rule will not predict accurately the risks of acute exposure to TCE, nor will an estimate of AUC of brain TCE. However, an estimate of the brain TCE concentration at the time of VEP testing predicted the effects of TCE across exposure concentrations and durations.

Administration, Inhalation↗
PubMed2004

Cumulative meta-analysis: a new tool for detection of temporal trends and publication bias in ecology.

Temporal changes in the magnitude of research findings have recently been recognized as a general phenomenon in ecology, and have been attributed to the delayed publication of non-significant results and disconfirming evidence. Here we introduce a method of cumulative meta-analysis which allows detection of both temporal trends and publication bias in the ecological literature. To illustrate the application of the method, we used two datasets from recently conducted meta-analyses of studies testing two plant defence theories. Our results revealed three phases in the evolution of the treatment effects. Early studies strongly supported the hypothesis tested, but the magnitude of the effect decreased considerably in later studies. In the latest studies, a trend towards an increase in effect size was observed. In one of the datasets, a cumulative meta-analysis revealed publication bias against studies reporting disconfirming evidence; such studies were published in journals with a lower impact factor compared to studies with results supporting the hypothesis tested. Correlation analysis revealed neither temporal trends nor evidence of publication bias in the datasets analysed. We thus suggest that cumulative meta-analysis should be used as a visual aid to detect temporal trends and publication bias in research findings in ecology in addition to the correlative approach.

Carbon↗