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 109 records · Page 6Linked to original sources
PubMed1992

Linkage studies of schizophrenia: a stimulation study of statistical power.

In planning for a linkage study, it is important to determine the number of pedigrees needed to show linkage. Our study overcomes some of the limitations of previous power studies by simulating multigeneration pedigrees to be compatible with the demographic and genetic epidemiological features of schizophrenia; these are variable age at onset, reduced fertility, and increased mortality after onset. We evaluate the power of these pedigrees by first simulating an ascertainment rule requiring at least three ill family members per pedigree and then simulating the trait and marker genotypes according to a single gene model known to fit epidemiological family study data. Our analysis allows for incomplete and age-dependent penetrance, phenocopies, and interpedigree heterogeneity. We present the power to detect linkage at several lod score thresholds since the multiple tests and phenotypic models required for complex diseases may necessitate using a lod score significance level greater than three. The sample size needed to achieve sufficient power is feasible if 50% of the pedigrees are linked to the marker under test. It may not be feasible to detect linkage if only 25% of the pedigrees are linked, even if a very closely linked marker is used. Our results indicate that to be certain of adequate statistical power, linkage analyses of schizophrenia will require very large samples that do not have a marked degree of genetic heterogeneity.

Adult↗
PubMed1992

Analytical method comparison based upon statistical power calculations.

Testing for the equivalence of results generated by different analytical methodology is a common practice in the pharmaceutical sciences. Methodology changes are implemented for both scientific and economic reasons during a scientific study. Thus, the need to demonstrate the appropriateness of considering data generated by distinct methods as part of a single information population arises. This paper describes a rapid and simple approach to the statistical design and interpretation of method comparison experiments. The approach presented is based upon a statistical power calculation technique, a knowledge of the variability associated with the methods to be compared and the criteria for equivalence (the limits within which differences become immeasurable or, for practical purposes, insignificant). Reference tables are included which show necessary sample sizes for comparison experiments for common combinations of these three variables.

Chemistry Techniques, Analytical↗
PubMed2002

Statistical power analysis to estimate how many months of data are required to identify PACU staffing to minimize delays in admission from ORs.

When each nurse in the Phase I setting is caring for the maximum number of patients allowed by hospital staffing standards (typically 2 per ASPAN standards), patients may have to be held in the OR until a PACU nurse becomes available. Previously, the authors described a statistical method to determine the process of scheduling existing nurses without increasing staffing hours (Dexter et al. Anesth Analg. 92:947-949, 2001). The end result was to minimize the percentage of future workdays during which at least one patient would wait in his or her OR for Phase I PACU admission. In this study, the authors performed a statistical power analysis to determine how many months of PACU workload data are needed to optimize PACU staffing by using this "set covering" algorithm. One year (232 workdays) of data was available from a PACU employing up to 10 nurses working a total of 72 clinical hours a day. The data were divided into 2 subsets. Using the first subset, which varied in size between 20 and 140 days of data, the authors identified the optimal staffing solutions. These solutions were tested on the second subset of data. This process then was repeated thousands of times. There was a marked improvement in the performance of the staffing solutions at preventing "PACU hold" by increasing from 20 to 80 historical workdays of data, a slight but statistically significant improvement between 80 and 100 workdays, but no significant improvement in further increasing the number of workdays of data. PACU nurse managers should use at least 4 months of data when choosing a staffing solution to minimize the chance of patients waiting in ORs for PACU admission. Tampering with PACU staffing more often than every 4 months is unlikely to result in improvements in OR efficiency and may harm recruitment and retention of nursing staff.

Operating Rooms↗
PubMed1995

Sample size and statistical power in reproductive research.

The calculation of sample size should be an integral part of the planning stages of all research projects to avoid wasting time, money, and valuable resources. The necessary information for sample size calculations includes the alpha (type I) error level, the beta (type II) error, delta (or the difference you would like to be able to detect), and, for continuous variables, the variance. We review these terms and outline their importance in the calculation of sample size and statistical power. When necessary, the investigator should seek expertise and advice to perform these calculations.

Female↗
PubMed1994

Magnetic resonance imaging in monitoring the treatment of multiple sclerosis patients: statistical power of parallel-groups and crossover designs.

Serial brain magnetic resonance (MR) imaging detects active lesions 5-10 times more frequently than the occurrence of clinical changes in patients with early relapsing-remitting and secondary progressive multiple sclerosis (MS). Based on monthly unenhanced and gadolinium enhanced MR findings in 23 unselected and untreated patients, the power of an MS treatment trial was calculated, using MR imaging activity as the primary measure of outcome. It was shown that a 80% reduction in the number of active lesions (i.e. an efficacy of 80%) should be detected using a placebo-controlled parallel-groups design with a power of 80%, if either 2 x 20 patients are scanned monthly for 4 months, or 2 x 30 patients monthly for 2 months. Short to medium term studies of new experimental treatments in MS, using MR imaging as the primary outcome measure, provide considerable statistical power in small patient populations studied over a short period of time.

Adult↗
PubMed2006

Does bisphenol A induce superfeminization in Marisa cornuarietis? Part II: toxicity test results and requirements for statistical power analyses.

This study presents results of the effects of bisphenol A (BPA) on adult egg production, egg hatchability, egg development rates and juvenile growth rates in the freshwater gastropod, Marisa cornuarietis. We observed no adult mortality, substantial inter-snail variability in reproductive output, and no effects of BPA on reproduction during 12 weeks of exposure to 0, 0.1, 1.0, 16, 160 or 640 microg/L BPA. We observed no effects of BPA on egg hatchability or timing of egg hatching. Juveniles showed good growth in the control and all treatments, and there were no significant effects of BPA on this endpoint. Our results do not support previous claims of enhanced reproduction in Marisa cornuarietis in response to exposure to BPA. Statistical power analysis indicated high levels of inter-snail variability in the measured endpoints and highlighted the need for sufficient replication when testing treatment effects on reproduction in M. cornuarietis with adequate power.

Animals↗
PubMed1998

Individual mating success, lek stability, and the neglected limitations of statistical power.

The evolution of leks (aggregations of males displaying to females) cannot be explained solely by an increasing average gain in matings for each male as group size increases. This is because the mating skew, that is, the inequality among males in mating success, is often high and may vary with lek size. Here, we show that the common observation that matings become more evenly divided as lek size increases is also insufficient to explain by itself the benefits of aggregating. The benefits to individual males are highly sensitive to the exact relationship between mating skew and lek size, and very similar relationships can lead to opposite predictions concerning individual benefits. With data on published mating success for 18 species (71 leks), we show that different species have very similar skew versus lek size relationships. With current sample sizes, however, there is insufficient statistical power to distinguish between completely different alternatives concerning individual optima of males. Copyright 1998 The Association for the Study of Animal Behaviour

Journal Article↗
PubMedDate not supplied

Recombination, statistical power, and genetic studies of sexual isolation in Drosophila.

Genetic studies of sexual isolation in Drosophila have generally failed to fully evaluate the effects of their sample size and recombination between markers on their conclusions. In this study we evaluate recombinational distances between markers in Drosophila pseudoobscura and D. persimilis, a species pair in which numerous genetic mapping studies have been performed. We conclude that, contrary to assertions, the inversions that distinguish these two species still allow for much recombination within most of their chromosome arms in F1 hybrid females. Such recombination may have caused previous mapping studies in these species to miss (or grossly underestimate) the effects of several genomic regions. We also evaluate the effects of sample size and recombination on genetic studies of sexual isolation in other Drosophila species groups. We conclude that some of these studies may have been heavily biased toward detecting only genes of large effect. Future studies of sexual isolation should be preceded by detailed statistical power analyses that determine the effects of recombination and sample size in the species pair being studied to avoid these complications.

Animals↗
PubMed2006

Sample size and statistical power assessing the effect of interventions in the context of mixture distributions with detection limits.

Often in randomized clinical trials and observational cohort studies, a non-negative continuously distributed response variable is measured in treatment and control groups. In the presence of true zeros for the response variable, a two-part zero-inflated log-normal model (which assumes that the data has a probability mass at zero and a continuous response for values greater than zero) is usually recommended. However, in some environmental health and human immunodeficiency virus (HIV) studies, quantitative assays for metabolites of toxicants, or quantitative HIV RNA measurements are subject to left-censoring due to values falling below the limit of detection (LD). Here, a zero-inflated log-normal mixture model is often suggested since true zeros are indistinguishable from left-censored values due to the LD. When the probabilities of true zeros in the two groups are not restricted to be equal, the information contributed by values falling below LD is used only to estimate the probability of true zeros in the context of mixture distributions. We derived the required sample size to assess the effect of a treatment in the context of mixture models with equal and unequal variances based on the left-truncated log-normal distribution. Methods for calculation of statistical power are also presented. We calculate the required sample size and power for a recent study estimating the effect of oltipraz on reducing urinary levels of the hydroxylated metabolite aflatoxin M(1) (AFM(1)) in a randomized, placebo-controlled, double-blind phase IIa chemoprevention trial in Qidong, China. A Monte Carlo simulation study is conducted to investigate the performance of the proposed methods.

Aflatoxin M1↗
PubMed2003

The loss of statistical power to distinguish populations when certain samples are ambiguous.

Case-control studies are used to map loci associated with a genetic disease. The usual case-control study tests for significant differences in frequencies of alleles at marker loci. In this paper, we consider the problem of comparing two or more marker loci simultaneously and testing for significant differences in haplotype rather than allele frequencies. We consider two situations. In the first, genotypes at marker loci are resolved into haplotypes by making use of biochemical methods or by genotyping family members. In the second, genotypes at marker loci are not resolved into haplotypes, but, by assuming random mating, haplotypes can be inferred using a likelihood method such as the expectation-maximization (EM) algorithm. We assume that a causative locus has two alleles with a multiplicative effect on the penetrance of a disease, with one allele increasing the penetrance by a factor pi. We find, for small values of pi-1 and large sample sizes, asymptotic results that predict the statistical power of a test for significant differences in haplotype frequencies between cases and a random sample of the population, both when haplotypes can be resolved and when haplotypes have to be inferred. The increase in power when haplotypes can be resolved can be expressed as a ratio R, which is the increase in sample size needed to achieve the same power when haplotypes are resolved over when they are not resolved. In general, R depends on the pattern of linkage disequilibrium between the causative allele and the marker haplotypes but is independent of the frequency of the causative allele and, to a first approximation, is independent of pi. For the special situation of two di-allelic marker loci, we obtain a simple expression for R and its upper bound.

Alleles↗
PubMed2004

Estimation of thyroid radiation doses for the hanford thyroid disease study: results and implications for statistical power of the epidemiological analyses.

Residents of eastern Washington, northeastern Oregon, and western Idaho were exposed to I released into the atmosphere from operations at the Hanford Nuclear Site from 1944 through 1972, especially in the late 1940's and early 1950's. This paper describes the estimated doses to the thyroid glands of the 3,440 evaluable participants in the Hanford Thyroid Disease Study, which investigated whether thyroid morbidity was increased in people exposed to radioactive iodine from Hanford during 1944-1957. The participants were born during 1940-1946 to mothers living in Benton, Franklin, Walla Walla, Adams, Okanogan, Ferry, or Stevens Counties in Washington State. Whenever possible someone with direct knowledge of the participant's early life (preferably the participant's mother) was interviewed about the participant's individual dose-determining characteristics (residence history, sources and quantities of food, milk, and milk products consumed, production and processing techniques for home-grown food and milk products). Default information was used if no interview respondent was available. Thyroid doses were estimated using the computer program Calculation of Individual Doses from Environmental Radionuclides (CIDER) developed by the Hanford Environmental Dose Reconstruction Project. CIDER provided 100 sets of doses to represent uncertainty of the estimates. These sets were not generated independently for each participant, but reflected the effects of uncertainties in characteristics shared by participants. Estimated doses (medians of each participant's 100 realizations) ranged from 0.0029 mGy to 2823 mGy, with mean and median of 174 and 97 mGy, respectively. The distribution of estimated doses provided the Hanford Thyroid Disease Study with sufficient statistical power to test for dose-response relationships between thyroid outcomes and exposure to Hanford's I.

Adolescent↗
PubMed2004

The power of statistical tests for moderators in meta-analysis.

Calculation of the statistical power of statistical tests is important in planning and interpreting the results of research studies, including meta-analyses. It is particularly important in moderator analyses in meta-analysis, which are often used as sensitivity analyses to rule out moderator effects but also may have low statistical power. This article describes how to compute statistical power of both fixed- and mixed-effects moderator tests in meta-analysis that are analogous to the analysis of variance and multiple regression analysis for effect sizes. It also shows how to compute power of tests for goodness of fit associated with these models. Examples from a published meta-analysis demonstrate that power of moderator tests and goodness-of-fit tests is not always high.

Humans↗
PubMedDate not supplied

How to detect effects: statistical power and evidence-based practice in occupational therapy research.

The findings from 30 research investigations examining the effectiveness of occupational therapy interventions were reviewed and analyzed. The statistical conclusion validity was determined by computing post hoc power coefficients for the statistical hypothesis tests included in the examined studies. Data analysis revealed the median power values to detect small, medium, and large effect sizes were .09, .33, and .66, respectively. These results suggest a high probability of Type II errors in the sample of occupational therapy intervention research examined. In practical terms, this means the intervention produced a potentially useful treatment effect, but the effect was not detected as significant. Examples are provided that illustrate how low statistical power contributes to increases in Type II errors and inhibits the development of consensus through replication in the research literature. The presence of low-power studies with high rates of false negative findings prevents the establishment of guidelines for evidence-based practice and impedes the scientific progress of rehabilitation professions such as occupational therapy.

Evidence-Based Medicine↗
PubMed2000

A note on the statistical power in extended twin designs.

The power to detect sources of genetic and environmental variance varies with sample size, study design, effect size and the statistical significance level chosen. We explored whether the power of the classical twin study may be increased by adding non-twin siblings to the classical twin design. Sample sizes to detect genetic and shared environmental variation were compared for kinships with only twins, kinships consisting of twins and one additional sibling, and kinships with twins and two additional siblings. The effect of adding siblings to the classical twin design was considered for univariate and bivariate analyses. For the univariate case, adding one non-twin sibling resulted in a decrease in sample size needed to detect additive genetic influences in the presence of environmental influences. However, adding two additional siblings did not decrease the number of subjects as compared to the classical twin design. The sample size required to detect common environmental factors was also greatly decreased by adding one non-twin sibling. Adding two non-twin siblings resulted in a small additional decrease. In models including additive genetic, dominant genetic, and unique environmental effects, adding one sibling to a twin family decreased the required sample size to detect dominant genetic influences. Adding two siblings to a twin family resulted in only a slight additional decrease in sample size. In the bivariate case a similar pattern of results was found, in addition to the observation that the overall required sample size, as expected, was lower than in the univariate case. The decrease in sample size from bivariate testing was more pronounced in a design with one or two additional siblings, as compared to a design with twins only. It is concluded that a well considered choice of family design, i.e. including families with twins and one or two additional siblings increases the statistical power to detect sources of variance due to additive and non-additive genetic influences, and common environment.

Analysis of Variance↗
PubMed2001

Statistical power of articles published in three health psychology-related journals.

Power was calculated for 8,266 statistical tests in 187 journal articles published in the 1997 volumes of Health Psychology (HP), Addictive Behaviors (AB), and the Journal of Studies on Alcohol (JSA). Power to detect small, medium, and large effects was .34. .74. and .92 for HP; .34, .75, and .90 for AB; and .41, .81. and .92 for JSA. Mean power estimates are .36, .77, and .91, giving a good estimation for the field of health psychology. J. Cohen (1988) recommended that power to detect effects should be approximately .80. Using this criterion, the articles in these journals have adequate power to detect medium and large effects. Intervention studies have much less power to detect effects than nonintervention studies do. Results are encouraging for this field, although studies examining small effects are still very much underpowered. This issue is important, because most intervention effects in health psychology are small.

Behavioral Medicine↗
PubMed2006

Statistical power of association using the extreme discordant phenotype design.

BACKGROUND: Selective genotyping has been proven to be an effective design for mapping quantitative trait loci (QTL), either by linkage or by allelic association, wherein the individual trait values can be used as the indices for phenotype selection. It has also been proposed that association studies of dichotomous traits can benefit from such design. When there is no quantitative measurement for phenotype available, cases and/or controls having extreme discordant phenotypes (EDP) can still be selected, based on their exposure status to a drug toxicity or environmental risk factor. The advantage of EDP design is intuitive and it has been successfully used in a number of studies. METHODS: In this report, we developed a statistical method to calculate the power of EDP methodology, using a mixture model of genotype-specific distributions of a single biallelic susceptibility locus. We also compared the power of three statistical tests commonly used in association studies - including the chi test of allelic frequencies, the chi test of genotype frequencies, and the Armitage trend test. The power of two different EDP designs was evaluated under a range of scenarios. RESULTS AND CONCLUSION: Our results indicate that the chi test of genotype frequency is a robust, though less powerful, test for single-locus association, and that EDP methodology is a powerful design for genetic association studies - especially those of common diseases caused by quantifiable drug toxicity or environmental risk factors.

Alleles↗
PubMed1989

Statistical power.

Explore the source record for details and available documents.

Data Interpretation, Statistical↗