Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Statistical Power”

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 829 records · Page 46Linked to original sources
PubMed2005

Estimating dispersal from short distance spatial autocorrelation.

A series of theoretical studies has formed a strong connection between spatial statistics observed in populations and summary measures of the amount of dispersal. Synthesized, these developments allow dispersal to be indirectly estimated from standing spatial patterns of genetic variation under a range of conditions broad enough to be likely met in most populations of either plants or animals. The spatial correlations at the shortest distances are particularly robust to range of conditions and have disproportionately high statistical power. This review integrates theoretical results in a way that maximizes robustness and flexibility in the use of short distance autocorrelation to estimate Wright's neighborhood size, or the total variance in dispersal distances. Empirical guidelines are developed that are meant to be as practical and broad as possible. The guidelines focus on Moran's I-statistics for diploid genotypes converted to allele frequencies, but are also extended to or compared with several other approaches.

Animals↗
PubMed2002

p16INK4a is a prognostic marker in resected ductal pancreatic cancer: an analysis of p16INK4a, p53, MDM2, an Rb.

OBJECTIVE: To identify the prognostic relevance of the G1/S cell cycle regulator genes p16INK4a, p53, MDM2, and Rb in patients with resected ductal pancreatic cancer (PC). SUMMARY BACKGROUND DATA: The tumor suppressor genes p16INK4a, p53, and Rb are altered in PC in 27% to 95%, 40% to 70%, and 5%, respectively. The role of MDM2 is not clearly defined in PC. The prognostic value of these cell cycle regulators has not been clarified. METHODS: Sixty-two patients with PC with complete follow-up who underwent potentially curative resections were included in the study. An extreme group analysis was performed including the 20 patients with the shortest survival and the 20 patients with the longest survival. Protein expression of p16, p53, MDM2, and Rb was investigated, and mutation analysis of p16INK4a and p53 was performed. p16INK4a promoter hypermethylation was examined by methylation-specific polymerase chain reaction. RESULTS: Significantly more tumors in the shortest-surviving patients had p16INK4a alterations compared with tumors of the longest-surviving patients. In contrast, the frequency of p53 alterations was not significantly higher in the shortest-surviving versus the longest-surviving groups. Stabilization of MDM2 and loss of Rb expression were identified in a minority of tumors, independent of survival length. CONCLUSIONS: The presence of p16INK4a alterations in resected tumors of patients with PC is connected with a worse prognosis, indicating patients that might benefit from adjuvant therapy regimens. p53 alterations, MDM2 overexpression, and loss of Rb expression could not be identified as prognostic markers from this study, but a larger study with greater statistical power might show a different result with regard to p53.

Biomarkers, Tumor↗
PubMed1995

A time to pregnancy questionnaire designed for long term recall: validity in Oxford, England.

STUDY OBJECTIVE: To establish the degree of validity of data on time to pregnancy, derived retrospectively using a short questionnaire. DESIGN: Information from the questionnaire was compared with data that had been collected concurrently from the same individuals. SETTING AND PARTICIPANTS: Questionnaires were mailed to 1647 women who continue to be followed up by the Oxford Family Planning Association contraceptive study, and a further 424 were approached for personal interview. Response rates were 91% and 79% respectively. MAIN RESULTS: Matching was successful in 91% of pregnancies. Median recall time was 14 years (interquartile range, 11-16 years). At the group level, remarkably good agreement was found between the two sources of information, presented as cumulative percentage distributions of live births. The findings were at least as good with longer recall (> 14 years) as with shorter recall. Digit performance was present to a limited degree. At the individual level, some misclassification was evident, which has implications for statistical power. For detection of clinical infertility (no conception within 12 months), the sensitivity was in the range 67%-91%, and the specificity was 92%-96%. Variations with format, duration of recall, age at delivery, year of birth, parity, social class, smoking habit, last contraceptive method, and outcome (live birth or not) were generally small, and were not statistically significant. CONCLUSIONS: Time to pregnancy is a sensitive way of assessing reproductive function in either sex. Valid data at a group level can be derived retrospectively, with a long duration of recall, using a short questionnaire.

Adult↗
PubMed1988

Compliance in clinical trials: impact on design, analysis and interpretation.

A positive association between compliance and clinical outcome has been observed in several randomized, controlled, clinical trials. This association, seen in the placebo-treated group as well as the active-treatment group, clarifies the possibility that data analyses incorporating estimates of protocol adherence are potentially biased. In the presence of non-compliance, or missing data from any cause, several statistical analyses may seem plausible, with none clearly superior to the others. These may include an analysis of all patients randomized, with imputed values for missing data, and an analysis restricted to protocol-adherent patients. The recommended approach is a conservative one that examines consistency among the plausible analyses. Using compliance data in trial conduct can also introduce bias into trial results by inducing differential treatment of compliers and non-compliers. This possibility arises, for instance, when adherence is affected by the randomized treatment. Non-compliance can have a substantial impact on statistical power and sample size requirements in a clinical trial. Under certain assumptions, required sample sizes are doubled with 30% non-compliance and tripled with 40% non-compliance.

Clinical Trials as Topic↗
PubMed1995

Clinical trials: relevance of correlation between treatment modalities.

BACKGROUND: Trials that do not allow rejection of the null hypothesis of no treatment effect may have had an inappropriate design. Trials are virtually never assessed for correlation between responses to different treatment modalities. METHODS: Using a model, a simple test and several published studies we studied the influence of correlation levels on the statistical power of clinical trials. RESULTS: The level of correlation between treatment modalities is a major determinant of the power of both self-controlled and parallel group clinical trials. CONCLUSIONS: It is extremely relevant to assess correlation levels between treatment modalities of a trial a priori. With a presumably negative correlation a self-controlled design is likely to lack power. With a presumably positive correlation a parallel group design is likely to do so. Both designs are suitable for approximately zero correlations (e.g. comparison vs placebo).

Clinical Trials as Topic↗
PubMed2026

Discovering common and population-specific QTLs for leaf rust resistance in different Barley populations.

Multi-population GWAS lead to identification of common and population-specific QTLs for leaf rust resistance in barley. Genome-wide association studies (GWAS) are a powerful tool for detecting genetic markers associated with traits of interest. However, these studies are typically restricted to a single population, and transferability of identified marker effects across populations is challenged by population differences in linkage, allele frequencies, epistatic effects, and environmental context. When comparing GWAS results between populations, a lack of overlapping signals is often interpreted as a lack of common quantitative trait loci (QTLs), although such discrepancies may result from differences in statistical power to detect signals. In barley (Hordeum vulgare L.), where genetic leaf rust resistance is rapidly overcome by evolving pathogens, identification of cross-population robust and potentially transferable resistance loci is a key task. Here, we present a mixed model approach for multi-population GWAS that estimates correlated marker effects in multiple populations and use this to test for significant effects across and within populations. Applying this model to four barley breeding populations revealed both common and population-specific QTL effects for leaf rust resistance, including loci colocalizing with known Rph genes and novel regions with plausible candidate genes. Multi-population GWAS increased power, revealing signals not detected by GWAS within populations. We categorized the reported QTLs into three groups based on marker-associated allele effects: (1) consistent effect direction across populations, (2) differing effect direction across populations, and (3) present in a single population. The study highlights the transferability and limitations of leaf rust resistance QTLs across different barley populations and provides a general statistical framework to support robust marker-assisted selection across populations.

Quantitative Trait Loci↗
PubMed2001

Consistency of atypical antipsychotic superiority to placebo in recent clinical trials.

BACKGROUND: The use of control placebos in clinical trials of new antipsychotic medications is increasingly under examination. The active controlled equivalence study could offer a potential alternative design. First, however, it must be clear that any proposed standard control agent has been consistently superior to placebo in previous studies. METHODS: Through a Freedom of Information Act request, we identified nine placebo-controlled trials of risperidone, olanzapine, or quetiapine. RESULTS: Meta-analysis indicated that the pooled estimate of the true population effect size +/- SE was 0.46 +/- 0.06 for categorical response rates and >0.53 +/- 0.07 for the continuous Brief Psychiatric Rating Scale change score outcome measure. If the desired detectable effect size is set very conservatively at a 95% confidence lower bound for the estimate of true effect size, statistical power for random samples of 80 per group drawn from a population of subjects similar to that of the nine meta-analyzed studies is.67 for categorical response rates and >.82 for the continuous measure, based on one-sided alpha =.05. CONCLUSIONS: These data suggest substantial confidence that a therapeutic dose of an atypical antipsychotic will be statistically superior to placebo in an adequately sized randomized trial, when reporting a continuous measure as the principal outcome.

Antipsychotic Agents↗
PubMed2002

Corticosteroid injections for lateral epicondylitis: a systematic review.

Patients with lateral epicondylitis (tennis elbow) are frequently treated with corticosteroid injections, in order to relieve pain and diminish disability. The objective of this review was to evaluate the effectiveness of corticosteroid injections for lateral epicondylitis. Randomised controlled trials (RCTs) were identified by a highly sensitive search strategy in six databases in combination with reference tracking. Two independent reviewers selected and assessed the methodological quality of RCTs that included patients with lateral epicondylitis treated with corticosteroid injection(s), and reported at least one clinically relevant outcome measure. Standardised mean differences were computed for continuous data and relative risks (RR) for dichotomous data. A best-evidence synthesis was conducted, weighting the studies with respect to their internal validity, statistical significance, clinical relevance, and statistical power. Thirteen studies consisting of 15 comparisons were included in the review, evaluating the effects of corticosteroid injections compared to placebo injection (n=2), injection with local anaesthetic (n=5), another conservative treatment (n=5), or another corticosteroid injection (n=3). Almost all studies had poor internal validity scores. For short-term outcomes ( or=6 months), no statistically significant or clinically relevant results in favour of corticosteroid injections were found. Although the available evidence shows superior short-term effects of corticosteroid injections for lateral epicondylitis, it is not possible to draw firm conclusions on the effectiveness of injections, due to the lack of high quality studies. No beneficial effects were found for intermediate or long-term follow-up. More, better designed, conducted and reported RCTs with intermediate and long-term follow-up are needed.

Adrenal Cortex Hormones↗
PubMed1991

Analyses of multinomial mixture distributions: new tests for stochastic models of cognition and action.

Mixture distributions are formed from a weighted linear combination of 2 or more underlying basis distributions [g(x) = sigma j alpha j fj(x); sigma alpha j = 1]. They arise frequently in stochastic models of perception, cognition, and action in which a finite number of discrete internal states are entered probabilistically over a series of trials. This article reviews various distributional properties that have been examined to test for the presence of mixture distributions. A new multinomial maximum likelihood mixture (MMLM) analysis is discussed for estimating the mixing probabilities alpha j and the basis distributions fj(x) of a hypothesized mixture distribution. The analysis also generates a maximum likelihood goodness-of-fit statistic for testing various mixture hypotheses. Stochastic computer simulations characterize the statistical power of such tests under representative conditions. Two empirical studies of mental processes hypothesized to involve mixture distributions are summarized to illustrate applications of the MMLM analysis.

Arousal↗
PubMed2004

Efficient computation of significance levels for multiple associations in large studies of correlated data, including genomewide association studies.

Large exploratory studies, including candidate-gene-association testing, genomewide linkage-disequilibrium scans, and array-expression experiments, are becoming increasingly common. A serious problem for such studies is that statistical power is compromised by the need to control the false-positive rate for a large family of tests. Because multiple true associations are anticipated, methods have been proposed that combine evidence from the most significant tests, as a more powerful alternative to individually adjusted tests. The practical application of these methods is currently limited by a reliance on permutation testing to account for the correlated nature of single-nucleotide polymorphism (SNP)-association data. On a genomewide scale, this is both very time-consuming and impractical for repeated explorations with standard marker panels. Here, we alleviate these problems by fitting analytic distributions to the empirical distribution of combined evidence. We fit extreme-value distributions for fixed lengths of combined evidence and a beta distribution for the most significant length. An initial phase of permutation sampling is required to fit these distributions, but it can be completed more quickly than a simple permutation test and need be done only once for each panel of tests, after which the fitted parameters give a reusable calibration of the panel. Our approach is also a more efficient alternative to a standard permutation test. We demonstrate the accuracy of our approach and compare its efficiency with that of permutation tests on genomewide SNP data released by the International HapMap Consortium. The estimation of analytic distributions for combined evidence will allow these powerful methods to be applied more widely in large exploratory studies.

Association↗
PubMed2005

Increasing the power of functional maps of the medial temporal lobe by using large deformation diffeomorphic metric mapping.

The functional magnetic resonance imagery responses of declarative memory tasks in the medial temporal lobe (MTL) are examined by using large deformation diffeomorphic metric mapping (LDDMM) to remove anatomical variations across subjects. LDDMM is used to map the structures of the MTL in multiple subjects into extrinsic atlas coordinates; these same diffeomorphic mappings are used to transfer the corresponding functional data activation to the same extrinsic coordinates. The statistical power in the averaged LDDMM mapped signals is significantly increased over conventional Talairach-Tournoux averaging. Activation patterns are highly localized within the MTL. Whereas the present demonstration has been aimed at enhancing alignment within the MTL, this technique is general and can be applied throughout the brain.

Brain Mapping↗
PubMed2001

Alcohol consumption and overall accident mortality in 14 European countries.

AIMS: To evaluate the effects of changes in aggregate alcohol consumption on overall accident mortality in 14 western European countries after 1950, and to compare traditional beer, wine, and spirits countries with respect to the impact of alcohol. DESIGN, SETTING AND PARTICIPANTS: The countries were sorted into three groups--traditional spirits countries of northern Europe, traditional beer countries of central Europe and wine countries of southern Europe. Gender- and age-specific annual mortality rates were analysed in relation to per capita alcohol consumption, utilizing the Box-Jenkins technique for time series analysis. All series were different to remove long-term trends. The results of the analyses in individual countries were pooled within each group of countries to increase the statistical power. MEASUREMENTS: Overall accident mortality data for 5-year age groups were converted to gender and age specific mortality rates in the age groups 15-29, 30-49 and 50-69 years. Rates were age adjusted within groups. Data on per capita alcohol consumption were converted to consumption per inhabitant 15 years and older. FINDINGS: The analyses demonstrated a statistically significant and positive relationship between changes in aggregate alcohol consumption in all three groups of countries. The estimated effect parameter was larger in northern Europe than in central Europe, and smallest in southern Europe. CONCLUSION: The results are compatible with the hypothesis that accident mortality rates are influenced by per capita alcohol consumption in southern, central and northern Europe. However, alcohol appears to play a larger role in northern Europe than in southern Europe.

Accidents↗
PubMed1996

Content of brain aluminum is not elevated in Alzheimer disease.

Several studies have reported that the bulk aluminum (Al) concentration is increased in the brain in Alzheimer disease (AD), while other studies have failed to demonstrate an increase. Most of these investigations have had one or more methodological deficiencies, including lack of adequate neuropathological assessment; failure to age-match the control samples; small sample sizes, lacking statistical power; and geographical heterogeneity in the AD and control populations. The present population-based study of 92 clinically and histopathologically diagnosed AD patients and normal elderly nursing home residents was designed to avoid these potential biases. When a subsample of AD cases with the most severe brain pathology was compared with controls having no or minimal pathology, no statistically significant differences were found in the bulk aluminum concentration measured by graphite furnace atomic absorption spectrometry in frontal cortex (1.8 +/- 0.7 vs. 1.7 +/- 0.7 micrograms/g dry wt), temporal cortex (1.4 +/- 0.3 vs. 1.5 +/- 0.5 micrograms/g dry wt), liver (2.0 +/- 1.3 vs. 2.0 +/- 1.2 micrograms/g dry wt), or head of femur (2.4 +/- 1.6 vs. 2.2 +/- 1.0 micrograms/g ash wt). Within the whole series of 92 cases, there was no difference in the bulk aluminum concentration of the frontal cortex between individuals diagnosed as definite, probable, and possible cases of AD using the CERAD (Consortium to Establish a Registry for Alzheimer's Disease) criteria. The density of senile plaques and neurofibrillary tangles in frontal and temporal cortex showed no correlation with the bulk aluminum concentration. Logistic regression analyses, which controlled for age and sex, did not influence outcome for any of the comparisons. The data show conclusively that in AD, bulk aluminum concentration is not increased in two cortical brain regions that are selectively vulnerable to the neuropathological changes associated with this disorder.

Aged↗
PubMed1998

A placebo-controlled, double-blind trial of the long-term effects of albuterol administration in patients with cystic fibrosis.

This placebo-controlled study was designed to confirm a previously performed open label study that showed significant improvement in spirometry on maintenance therapy with albuterol for 1 year. In a double-blind, cross-over trial, albuterol (by metered dose inhaler) 180 microg b.i.d. or placebo were given for 6 months each. Spirometry was monitored at the start, and 3 and 6 months following initiation of each arm of the study. Peak expiratory flow rate (PEFR) was measured twice daily at home before and after study drug administration. Only patients with clinically detectable lung disease were enrolled. Twenty-one patients finished the study. All spirometric tests showed a significant improvement from start to end of the 6 month treatment with albuterol; there was no significant change on placebo. Forced vital capacity improved by 8.2% and forced expiratory volume in 1 s by 12.1% on albuterol therapy. Nevertheless, there was no significant difference between change on albuterol and change on placebo. Home measurements of PEFR showed a significant improvement of 4.7% on albuterol and a non-significant change of 2.0% on placebo from the first to the last week of treatment. None of the long-term improvements (spirometry or home PEFR) correlated with mean daily bronchodilation. For albuterol, the number of days of hospitalization was less than half that for patients on placebo (1.0/patient on albuterol versus 2.6 on placebo), but this did not reach statistical significance. These results suggest a beneficial effect from maintenance therapy with albuterol. Bronchodilation alone probably cannot explain the long-term benefits of albuterol, and other mechanisms may play a role. The lack of significant difference between change on albuterol and change on placebo is probably due to too small a number of patients in this study and lack of statistical power.

Administration, Inhalation↗
PubMed1988

Passive smoking and lung cancer: a publication bias?

To assess the likelihood of publication bias in a recent review of the effect of passive smoking on lung cancer the evidence from the reviewed papers was visualised on a "funnel" plot. In such a plot if the relative risks from various studies are plotted according to sample size they should scatter round some underlying true value, the scatter being greatest where the studies have the lowest statistical power--thus showing a "funnel" pattern. If there is publication bias and studies with non-significant results are not being published there should be a "gap" in the plot. The logarithm of the relative risks was plotted against the standard error of the logarithm of the relative risk (which was used instead of sample size as a measure of statistical uncertainty). The resulting plot was compatible with a publication bias but only in studies on men. Further studies of passive smoking and lung cancer in men seem to be warranted.

Data Interpretation, Statistical↗
PubMed1990

Adjusting for clustering in survey research.

The current widespread application of cluster sampling in survey design presents concerns to the researcher regarding the chosen unit of study. The statistical power of a study could be spuriously increased or decreased, sample size could be altered dramatically, and the uniqueness of the individual unit under study (e.g., a patient) could be lost and substituted by average values of characteristics depending on which unit of study is selected. The 1985 National Ambulatory Medical Care Survey of the U.S. National Center for Health Statistics was used to illustrate research methodologies that would deflate spuriously high results due to clustered sampling. Using the individual patient as the study unit, correction factors ranging from 1.99 to 35.40 were calculated in order to deflate exaggerated t-tests, chi-square, and F values of predictor variables. The effect of clustering was more marked on (1) continuous rather than binary outcome variables, as the former provide a richer environment to form clusters; and (2) on outcome variables relating to the practice-related or personal style of physicians. Using the physician (who represented a cluster of patients) as the unit of study, it was realized that correction factors were relevant to physician-specific predictors but not patient-specific predictors. Using design effect correction factors developed from a simple univariate analysis of variance, pharmacoepidemiologists can analyze accurately the currently available large survey databases of clustered samples.

Cluster Analysis↗
PubMed1999

Randomized trials on radioactive iodine ablation of thyroid remnants for thyroid carcinoma--a critique.

PURPOSE: The dose of radioactive iodine ((131)I) required to ablate thyroid remnants following surgery for differentiated thyroid carcinoma is controversial. Typical administered activities range from less than 30 mCi up to 100 mCi, reflecting local practice and regulations governing allowable outpatient doses. This review examines the available randomized trials designed to assess the optimal ablative dose in this setting. METHODS AND MATERIALS: The authors identified three such trials published in 1987, 1991, and 1996, and critically reviewed them from a scientific and statistical point of view. RESULTS: Two of these studies were small and lacked adequate statistical power to answer the question, and the third was very poorly conducted. CONCLUSION: In our opinion, the appropriate dose of (131)I for ablation of thyroid remnants remains undetermined.

Combined Modality Therapy↗
PubMed2001

Power Shortage: clinical trials testing the "homocysteine hypothesis" against a background of folic acid-fortified cereal grain flour.

Large randomized, controlled trials of total homocysteine-lowering therapy for the potential reduction of cardiovascular disease outcomes are ongoing in the United States and Canada. These trials are the Vitamin Intervention for Stroke Prevention (VISP) trial, the Women's Antioxidant Cardiovascular Disease Study (WACS), and the Heart Outcomes Prevention Evaluation (HOPE-2). However, the dramatic effect of policies mandating fortification of cereal grain flour products with folic acid may reduce the statistical power of these trials. All three trials assume that the active treatment groups will achieve the same mean effects of total homocysteine-lowering therapy as those reported in the absence of folic acid-fortified cereal grain flour. This paper examines this assumption using data from studies of total homocysteine-lowering therapy in U.S. and Canadian patients with cardiovascular disease who were exposed to products made with folic acid-fortified cereal grain flour. These data showed that the VISP trial, HOPE-2, and WACS will probably achieve only approximately 20% to 25% of the projected treatment effects of mean total homocysteine-lowering therapy (1.0 to 1.5 micromol/L vs. 4.0 to 6.0 micromol/L). As a result, all three trials will be substantially underpowered to test the specific hypotheses of total homocysteine-lowering therapy identified a priori. In contrast, renal transplant recipients have a persistent excess prevalence of hyperhomocysteinemia in the era of fortification but remain very responsive to supraphysiologic doses of folic acid-based supplementation (mean reduction in total homocysteine level, 5.0 to 6.0 micromol/L). Therefore, unlike other populations with normal renal function that are at high risk for cardiovascular disease but are profoundly affected by fortification efforts, renal transplant recipients continue to merit serious consideration for a controlled trial of the "homocysteine hypothesis."

Arteriosclerosis↗