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 703 records · Page 39Linked to original sources
PubMed2005

Fold-change estimation of differentially expressed genes using mixture mixed-model.

Microarray experiments produce expression measurements for thousands of genes simultaneously, though usually for a small number of RNA samples. The most common problem is the identification of genes that are differentially expressed between different groups of samples or biological conditions. As the number of genes far exceeds the number of RNA samples, the inherent multiplicity poses a severe problem in both hypothesis testing and effect estimation. While much of the recent literature is focused on the hypothesis aspects, we concentrate in this paper on effect estimation as a tool for the identification of differentially expressed genes. We propose a linear mixed model where the random effects are assumed to follow a mixture distribution, and study in detail the case of three normals, corresponding to genes that are down-, up- or non regulated. Our approach leads to a new type of non-linear shrinkage estimation, where a proportion of estimates is shrunk to zero, while the rest follows standard linear shrinkage. This allows us to estimate the log fold-change of the genes involved and to identify those that are differentially expressed within the same model framework. We investigate the operating characteristics of our method using simulation and spike-in studies, and illustrate its application to real data using a breast-cancer dataset.

Journal Article↗
PubMed1993

Semi-automated cervical smear pre-screening systems: an evaluation of the Cytoscan-110.

This paper reports a test of a system for provision of machine assistance in cervical cytology screening. The hypothesis tested was that if the results of examination by a screener of a small number of high-ploidy cells on specially prepared monolayers, automatically selected and presented by the system, were combined with machine measurement of cell and cell population characteristics, it would be possible to distinguish conditions requiring further action on the part of a cytology service from those in which the patient could safely be signed out. The system appeared broadly capable of this discrimination, with a false-negative error not significantly different (for the numbers tested) on CIN1 and more severe cases to that obtaining for routine screening of the parallel PAP smears, and also to results obtained by a panel of three observers. The machine system appeared to do better than other systems in selecting borderline cases for review, but this may have been an artefact of the method of evaluation used: all results were compared with a 'reference diagnosis', which was computed using statistical techniques to integrate diagnostic information from all available sources. The false-negative error-rate of the system amounted to 5% of high-grade cases, 17% of CIN1's and 29% of borderlines, but were not substantially different from the FN rates for other reporting systems on the same material. The proportion of negative cases referred back for full cytological diagnosis was 34%. Despite this high false-positive rate, the system is potentially cost-effective in use.

Automation↗
PubMedDate not supplied

The influence of the hypertensive patient's education in compliance with their medication.

The purpose of this study was to examine the relationships between patient's education in compliance with their medical regimen and the external variables: (1) "years of schooling," (2) duration of treatment, and (3) compliance with the medical regimen. The hypothesis tested in this study was as follows: "Hypertensive individuals who are educated about the importance of their medication and about the consequences of not taking the prescribed dosage will show better compliance with their prescribed drug regimen than those who are not thus educated." The sample of the study consisted of 40 hypertensive patients. A "posttest-only" control group design was used in this study. The hypothesis of the study was tested by using the Mann-Whitney U test. For the relationship between the external variables (years of schooling, duration of treatment, and compliance with the medical regimen), the Spearman test was used. The findings of the study revealed a statistically significant difference between compliance levels in the experimental group and in the control group (U = 130, p < 0.05), a positive correlation between "years of schooling" and compliance (rs = 0.33, p = 0.04), and a negative correlation between duration of treatment and compliance (rs = -0.45, p = 0.005). The findings support the hypothesis of the study.

Aged↗
PubMed1993

[Test strategies in evaluation of quantitative psychological hypotheses: the example of total learning time in learning of texts].

In most textbooks on statistics and experimental design, the analysis of trend hypotheses is incomplete or at least not satisfactory from an hypothesis testing point of view. Quantitative psychological hypotheses usually predict that a particular trend component will be significant, while all other trends are expected to be absent. Only a conjunction of these two results, however, eventually confirms the psychological hypothesis. This fact is not addressed in popular textbooks, and so this article deals with some statistical testing strategies that can be used to examine functional psychological hypotheses via trend tests. Under some circumstances, however, the strategies discussed may fail when several psychological hypotheses are examined simultaneously. This failure can be avoided by adding a further test to the strategies which allows a comparison of predicted and actual correlations. The different strategies for testing trend hypotheses are then applied to the simultaneous examination of two simple quantitative psychological hypotheses which address the role of total presentation time and its pacing in text learning ("total-time hypothesis"). Although Bredenkamp (1975) has convincingly argued on a theoretical basis that the form most often encountered in the literature must be false, this variant has been discussed most often in various fields of psychology. Therefore, two experiments were planned and performed in which this well-known variant of the hypothesis is compared with a modification claiming a less steep linear function than the classical variant. The article shows how the necessary tests can be planned to prevent the cumulation of error probabilities from being too large. The experiments in which N = 180 and N = 216 students have to learn and recall until they have mastered a short prose passage, demonstrated convincingly that the classical form of the total-time hypothesis does not hold, whereas the modification can be regarded as confirmed.

Adult↗
PubMed1999

Statistical limitations in functional neuroimaging. II. Signal detection and statistical inference.

The field of functional neuroimaging (FNI) methodology has developed into a mature but evolving area of knowledge and its applications have been extensive. A general problem in the analysis of FNI data is finding a signal embedded in noise. This is sometimes called signal detection. Signal detection theory focuses in general on issues relating to the optimization of conditions for separating the signal from noise. When methods from probability theory and mathematical statistics are directly applied in this procedure it is also called statistical inference. In this paper we briefly discuss some aspects of signal detection theory relevant to FNI and, in addition, some common approaches to statistical inference used in FNI. Low-pass filtering in relation to functional-anatomical variability and some effects of filtering on signal detection of interest to FNI are discussed. Also, some general aspects of hypothesis testing and statistical inference are discussed. This includes the need for characterizing the signal in data when the null hypothesis is rejected, the problem of multiple comparisons that is central to FNI data analysis, omnibus tests and some issues related to statistical power in the context of FNI. In turn, random field, scale space, non-parametric and Monte Carlo approaches are reviewed, representing the most common approaches to statistical inference used in FNI. Complementary to these issues an overview and discussion of non-inferential descriptive methods, common statistical models and the problem of model selection is given in a companion paper. In general, model selection is an important prelude to subsequent statistical inference. The emphasis in both papers is on the assumptions and inherent limitations of the methods presented. Most of the methods described here generally serve their purposes well when the inherent assumptions and limitations are taken into account. Significant differences in results between different methods are most apparent in extreme parameter ranges, for example at low effective degrees of freedom or at small spatial autocorrelation. In such situations or in situations when assumptions and approximations are seriously violated it is of central importance to choose the most suitable method in order to obtain valid results.

Biometry↗
PubMed2003

Tests for individual and population bioequivalence based on generalized p-values.

The U.S. Food and Drug Administration (FDA) has proposed new regulations that address the 'prescribability' and 'switchability' of new formulations of already-approved drugs. These new criteria are known, respectively, as population and individual bioequivalence. Two methods have been proposed in the bioequivalence literature for assessing population and individual bioequivalence that calculate an upper 95 per cent confidence bound for the bioequivalence criterion in question, and then test bio-equivalence by comparing this bound to the limit established by the FDA. In this paper we propose applying the generalized test function (GTF) methodology of Tsui and Weerahandi (Journal of the American Statistical Association 1989; 602-607) to this problem to produce tests based on a generalized p-value (GPV). This methodology allows us to construct hypothesis tests in the presence of nuisance parameters. Using simulation we show that these tests perform well in comparison to the confidence interval methods and have superior power for assessing population bioequivalence.

Adrenergic Agents↗
PubMed2004

Efficient exact p-value computation for small sample, sparse, and surprising categorical data.

A major obstacle in applying various hypothesis testing procedures to datasets in bioinformatics is the computation of ensuing p-values. In this paper, we define a generic branch-and-bound approach to efficient exact p-value computation and enumerate the required conditions for successful application. Explicit procedures are developed for the entire Cressie-Read family of statistics, which includes the widely used Pearson and likelihood ratio statistics in a one-way frequency table goodness-of-fit test. This new formulation constitutes a first practical exact improvement over the exhaustive enumeration performed by existing statistical software. The general techniques we develop to exploit the convexity of many statistics are also shown to carry over to contingency table tests, suggesting that they are readily extendible to other tests and test statistics of interest. Our empirical results demonstrate a speed-up of orders of magnitude over the exhaustive computation, significantly extending the practical range for performing exact tests. We also show that the relative speed-up gain increases as the null hypothesis becomes sparser, that computation precision increases with increase in speed-up, and that computation time is very moderately affected by the magnitude of the computed p-value. These qualities make our algorithm especially appealing in the regimes of small samples, sparse null distributions, and rare events, compared to the alternative asymptotic approximations and Monte Carlo samplers. We discuss several established bioinformatics applications, where small sample size, small expected counts in one or more categories (sparseness), and very small p-values do occur. Our computational framework could be applied in these, and similar cases, to improve performance.

Computational Biology↗
PubMed1982

Genetic factors in puerperal affective psychoses.

The hypothesis that puerperal affective psychosis (PAP) is genetically related to manic-depressive disorder was tested by comparing the morbidity risks for puerperal and non-puerperal affective disorders in the relatives of 17 PAP subjects and 20 parous manic-depressives (PMD) with no history of puerperal illness. The risk for affective disorder (mania, depression or suicide) and puerperal affective disorder was the same in the two groups of relatives and the test hypothesis was accepted, although the sample size was small. The frequencies of HLA-A, B and C locus antigens, nine blood group antigens and 10 red blood cell isoenzymes were not significantly different in the PAP and PMD subjects, showing that in this series genetic markers do not distinguish puerperal from non-puerperal affective psychoses.

Adult↗
PubMed2001

Bootstrap statistics of ECASS II data: just another post hoc analysis of a negative stroke trial?

UNLABELLED: The results of the Second European-Australasian Acute Stroke Study (ECASS II) were negative with respect to the primary endpoint. This post hoc analysis of ECASS II data was designed to make the least number of a priori assumptions. This is accomplished by a bootstrap-based hypothesis test on a non-parametric test statistic. No assumptions are made on shape or variance of population distributions and the method does not suffer from the disadvantages of dichotomization. By reducing the number of a priori assumptions, the possibilities to modify the test result by adjusting the test procedure are minimized. RESULTS: If rt-PA does not improve the outcome (null hypothesis), the probability of observing a difference of modified ranking scale equal or larger than the one observed in ECASS II is 0.047. We therefore rejected the null hypothesis.

Controlled Clinical Trials as Topic↗
PubMed2002

Truncated product method for combining P-values.

We present a new procedure for combining P-values from a set of L hypothesis tests. Our procedure is to take the product of only those P-values less than some specified cut-off value and to evaluate the probability of such a product, or a smaller value, under the overall hypothesis that all L hypotheses are true. We give an explicit formulation for this P-value, and find by simulation that it can provide high power for detecting departures from the overall hypothesis. We extend the procedure to situations when tests are not independent. We present both real and simulated examples where the method is especially useful. These include exploratory analyses when L is large, such as genome-wide scans for marker-trait associations and meta-analytic applications that combine information from published studies, with potential for dealing with the "publication bias" phenomenon. Once the overall hypothesis is rejected, an adjustment procedure with strong family-wise error protection is available for smaller subsets of hypotheses, down to the individual tests.

Genetic Linkage↗
PubMed2005

Effects of intense training during and after pregnancy in top-level athletes.

This study investigates the effects of vigorous exercise during and after pregnancy in top competitive athletes. The hypothesis tested here is that training of sufficiently high volume during pregnancy can maintain initial fitness levels. A second hypothesis, that high-volume training during pregnancy in initially fit women does not pose a health risk for the mother or the fetus, was tested and found to hold in a prior report. The overall aim of the study was to define a safe training regime for the maintenance of fitness in top-level female athletes during pregnancy. Forty-one healthy athletes who had performed exercise regularly prior to conception were followed from gestational week 17 until 12 weeks postpartum while they performed standardized exercise programs. The subjects participated either in a high-volume exercise group (HEG, n=20, 8.4 h week(-1)) or in a medium-volume exercise group (MEG, n=21, 6 h week(-1)). The results show that well-trained women can benefit substantially from training at high volumes during an uncomplicated pregnancy. This can facilitate a rapid return to competitive athletics and physically active life after pregnancy. Guidelines for safe exercise by sufficiently fit women during pregnancy could be modeled on the high-volume exercise regime used here by the HEG.

Anaerobic Threshold↗
PubMed1999

A test of the hypothesis of an autopolyploid vs. allopolyploid origin for a tetraploid lineage: application to the genus barbus (Cyprinidae)

A new method is described for determination of the origin of polyploid lineages. It tests the hypothesis that a tetraploid lineage originated via autopolyploidization vs. allopolyploidization. The method is based on the hypothesis that, in the case of autopolyploidy, any genetic marker in the first tetraploid ancestor is represented by two copies (one for each homoeologous chromosome of the haploid complement), whereas in allopolyploidy some markers absent from one of the hybridizing species will display one copy at most. The model requires knowledge of the phylogeny (topology and branch lengths) of a sample of species descending from the same tetraploidization event, together with the number of homoeologous copies present in each species for a set of neutral markers. The likelihood of a given proportion of the markers being present in both homoeologous chromosome pairs of the ancestral tetraploid is expressed as a function of the deletion rate of a marker. In the case of an autopolyploid origin, this proportion equals one. A likelihood-ratio test was carried out to test this hypothesis. The method was used to examine five microsatellite loci in eight species of Barbus (sensu lato). Assuming the validity of the hypotheses on phylogenetic relationships and evolutionary rates, the test rejects the possibility that European tetraploid barbs originated through autopolyploidy. This is the first test that can reject autopolyploidy, and it would appear particularly useful for phylogenetic studies in taxa where hybridization is known and where, consequently, undetected reticulate evolution may impair phylogenetic reconstruction.

Journal Article↗
PubMed1994

Pygmy locomotion.

The hypothesis that Pygmies may differ from Caucasians in some aspects of the mechanics of locomotion was tested. A total of 13 Pygmies and 7 Caucasians were asked to walk and run on a treadmill at 4-12 km.h-1. Simultaneous metabolic measurements and three-dimensional motion analysis were performed allowing the energy expenditure and the mechanical external and internal work to be calculated. In Pygmies the metabolic energy cost was higher during walking at all speeds (P < 0.05), but tended to be lower during running (NS). The stride frequency and the internal mechanical work were higher for Pygmies at all walking (P < 0.05) and running (NS) speeds although the external mechanical work was similar. The total mechanical work for Pygmies was higher during walking (P < 0.05), but not during running and the efficiency of locomotion was similar in all subjects and speeds. The higher cost of walking in Pygmies is consistent with the allometric prediction for smaller subjects. The major determinants of the higher cost of walking was the difference in stride frequency (+9.45, SD 0.44% for Pygmies), which affected the mechanical internal work. This explains the observed higher total mechanical work of walking in Pygmies, even when the external component was the same. Most of the differences between Pygmies and Caucasians, observed during walking, tended to disappear when the speed was normalized as the Froude number. However, this was not the case for running. Thus, whereas the tested hypothesis must be rejected for walking, the data from running, do indeed suggest that Pygmies may differ in some aspects of the mechanics of locomotion.

Adult↗
PubMed2000

Beyond the significance test in administrative research and policy decisions.

PURPOSE: To describe confidence interval (CI) analysis and show how it can be used in administrative decisions. ORGANIZING CONSTRUCT: Statistical significance testing should be supplemented, if not replaced, by effect size (ES) estimation and confidence interval analysis. Hypothesis testing based on the statistical significance test is the dominant paradigm in statistics; however, this approach has inherent problems which can ultimately diminish the usefulness of research for operational decisions. After identifying major difficulties with significance testing, the authors use hypothetical examples to demonstrate how ES and CI analysis provide more informative answers to nursing administrative research questions. CONCLUSIONS: CI analysis provides the basis for both improving the interpretation of findings from individual studies and for facilitating the analysis of cumulative evidence. By clarifying the meaning of results, CI analysis can increase the relevance and usefulness of research for health care executives and practitioners.

Confidence Intervals↗
PubMed2005

Effects of compulsory treatment orders on time to hospital readmission.

To evaluate the effect of compulsory community treatment orders on subsequent time out of the hospital, the authors studied the admission dates of psychotic patients who had repeated hospitalizations in Quebec, Canada, and divided each admission according to its time in relation to the index admission, during which the judicial order was obtained. The data were stratified by type of admission (early, preindex, index, or postindex), and the hypothesis tested was that the median time to readmission would be greatest for the index admission. The hypothesis was confirmed, supporting previous findings that judicial orders that mandate severely ill psychotic patients to undergo compulsory community treatment are associated with decreased time spent in the hospital and thus increased personal freedom.

Adult↗
PubMed2004

Chronic stressors and daily hassles: unique and interactive relationships with psychological distress.

Using daily telephone interviews of a U.S. national sample of adults, aged 25-74 (N = 1,031), the present analyses draw from theories of the stress process and recent research to examine how chronic role-related stressors and daily hassles affect psychological distress. Four separate hypotheses are examined. The first explores the association between chronic stressors and daily hassles. The second tests whether daily hassles function as an intervening variable between chronic stressors and psychological distress. The third tests whether a chronic stressor moderates the relationship between daily hassles and psychological distress. The fourth hypothesis tests for cross-domain effects of chronic stressors and daily hassles. Findings indicate that chronic stressors and daily hassles are distinct types of stressors with unique contributions to psychological distress. The study provides support for chronic home stressors functioning as a moderating factor on the relationship between daily hassles and psychological distress both within and across domains.

Adult↗
PubMed2005

Sex, lies, and strategic interference: the psychology of deception between the sexes.

The desires of one sex can lead to deceptive exploitation by the other sex. Strategic Interference Theory proposes that certain "negative" emotions evolved or have been co-opted by selection, in part, to defend against deception and reduce its negative consequences. In Study 1 (N = 217) Americans reported emotional distress in response to specific forms of deception. Study 2 (N = 200) replicated the results in a German sample. Study 3 (N = 479) assessed Americans' past experiences with deception and conducted additional hypothesis tests using a procedure to control for overall sex differences in upset. Each study supported the hypothesis that emotions track sex-linked forms of strategic interference. Three clusters of sex differences proved robust across studies-emotional upset about resource deception, commitment deception, and sexual deception. We discuss implications for theories of mating and emotion and directions for research based on models of antagonistic coevolution between the sexes.

Adult↗
PubMedDate not supplied

Computerized analysis of antimicrobial drugs interactions in biological systems using an IBM-PC microcomputer.

We have developed a computer program to analyse the individual and combined effects of two treatments applied concurrently to a biological system. Analysis is done in regard to: level of significance selected for the statistical test (two-sided Student's t test); number of data available; expected combined effect resulting from addition (computed by the program); experimental hypothesis tested (synergism or antagonism). The main program gives access to eight options: input of new data; input of data from file; addition or modification to data in memory; display on monitor the results from analysis or the contents of a data file; analysis with another level of significance; printout; kinetics of interaction; end of program. The program is designed to work with an IBM-PC, Epson MX/FX 80/100 printer and Roland DXY 800 plotter. Sample runs are given.

Anti-Bacterial Agents↗