PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Statistical power analysis”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 recordsLinked to original sources
PubMedDate not supplied

Statistical power analysis in pediatric nursing research.

Pediatric nurse researchers take a serious risk when they design an intervention study with insufficient power. In an underpowered study, the researcher may be testing a genuinely effective treatment but fail to recognize its efficacy. In the first part of this article, the concept of power analysis and how to perform a statistical power analysis are addressed. The second half of this article includes a review of published nursing research studies for the past 5 years in three nursing research journals. Specific examples of pediatric nursing research are highlighted. This review revealed a neglect of power analysis. Nurse researchers need to pay greater attention to statistical power analysis. It is an essential procedure for researchers to use before conducting a study.

Bias↗
PubMed2003

RETR_PWR: an SAS macro for retrospective statistical power analysis.

In contrast to prospective power analysis, retrospective power analysis provides an estimate of the statistical power of a hypothesis test after an investigation has been conducted rather than before. In this article, three approaches to obtaining point estimates of power and an interval estimation algorithm are delineated. Previous research on the bias and sampling error of these estimates is briefly reviewed. Finally, an SAS macro that calculates the point and interval estimates is described. The macro was developed to estimate the power of an F test (obtained from analysis of variance, multiple regression analysis, or any of several multivariate analyses), but it may be easily adapted for use with other statistics, such as chi-square tests or t tests.

Algorithms↗
PubMed2002

Statistical power analysis to estimate how many months of data are required to identify operating room staffing solutions to reduce labor costs and increase productivity.

UNLABELLED: We performed a statistical power analysis to determine how many historical data are needed for optimal operating room (OR) management decision making. The work applies to hospitals that provide service for all of its surgeons' elective cases on whatever workday the surgeons and patients choose. The hospital and anesthesia group adjust OR staffing and patient scheduling to care for the patients while minimizing OR staffing costs and maximizing labor productivity. Two years of data were obtained from a seven-OR surgical suite. The data were repeatedly split into training and testing datasets. The optimal staffing solution was calculated for each training dataset to maximize the efficiency of OR time usage and was then applied to the corresponding testing dataset. Training datasets ranged in size from 30 to 270 consecutive workdays. With 30 workdays of data, the statistical method identified staffing solutions that had an average of 35% decreased costs and 27% increased productivity as compared to the existing staffing plan. There was no significant improvement in performance with more than 210 workdays (10 mo) of data. With 30 workdays of OR or anesthesia group data, the optimization method can significantly reduce staffing costs and increase productivity compared with existing staffing. When applied routinely for adjusting staffing (e.g., on a quarterly basis), 9 to 12 mo of data should be used. IMPLICATIONS: With 30 workdays of operating room or anesthesia group data, the optimization method can propose staffing solutions that significantly decrease costs and increase productivity compared with existing staffing solutions. We recommend that, when the statistical method is applied routinely for adjusting staffing (e.g., on a quarterly basis), 9 to 12 mo of data be used.

Efficiency↗
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↗
PubMedDate not supplied

Statistical power analysis for hemodynamic cardiovascular safety pharmacology studies in beagle dogs.

INTRODUCTION: We studied the statistical power of a replicated Latin square design where eight animals each receive a vehicle control and three dose levels of a drug on four separate dosing days. Cardiovascular parameters evaluated in the study were systolic arterial pressure, diastolic arterial pressure, left ventricular heart rate, and dP/dt(max). METHODS: Observations were simulated based on historical data and drug response profiles from cardiovascular safety pharmacology studies conducted at Lilly Research Laboratories. Statistical analysis for treatment effects was performed using a linear mixed model. Monotonicity of dose response was examined using sequential linear trend tests based on ordinal spacing of dose levels. RESULTS: The replicated Latin square design for cardiovascular safety pharmacology studies is shown to have at least an 80% power of detecting changes from control of at least a 10% increment in systolic and diastolic pressure and a 15% increment in heart rate and dP/dt(max). The power is not sensitive to the shape of dose response profile over time. DISCUSSION: Several unique features of our statistical power evaluation include the comparison of different covariance structures and drug response profiles. The procedure can also be applied to future power evaluations of other cardiovascular parameters, such as the QT interval, and the loss of statistical power due to missing observations.

Animals↗
PubMed1998

Statistical power analysis for PET studies in humans.

UNLABELLED: Although simple techniques have been established to determine statistical power when comparing, for example, the means of two groups of sampled data, the analysis is more complicated when establishing a trend in the data, such as with a linear regression. We present an approach to calculate the sample size necessary to reject the hypothesis that there is no trend in the data (slope is not different from zero) at a given level of statistical significance, given the intra- and inter-subject variability of the measurement. METHODS: We have derived analytically the distribution of the t statistic, for a given non-zero slope, and integrated this distribution to determine in what fraction of trials a real trend in the population would be missed. We illustrate our approach by re-examining the issue of an age-related impairment in presynaptic dopamine metabolism as measured by PET. RESULTS: We showed that the sample size necessary to determine whether 6-18F-fluoro-L-dopa retention decreases with age depends critically on both the variability of the quantitative method used and on the magnitude of the expected change. CONCLUSION: The method we have illustrated is a simple statistical test that allows investigators to be certain that an experimental design has a sufficient sample size to demonstrate the effect under study.

Age Factors↗
PubMed1996

Human performance and physiology: a statistical power analysis of ELF electromagnetic field research.

Research examining the effects of electromagnetic fields (EMFs) on human performance and physiology has produced inconsistent results; this might be attributable to low statistical power. Statistical power refers to the probability of obtaining a statistically significant result, given the fact that a real effect exists. The results of a survey of published investigations of the effects of EMFs on human performance and physiology show that statistical power levels are very low, ranging from a mean of .08 for small effect sizes to .46 for large effect sizes. Implications of these findings for the interpretation of results are discussed along with suggestions for increasing statistical power.

Behavior↗
PubMed2002

A comprehensive, statistically powered analysis of GAD2 in type 1 diabetes.

GAD2 maps to chromosome 10p11.23 and encodes the 65-kDa isoform of GAD65, a major autoantigen in type 1 diabetes. The genetic variation that influences expression of preproinsulin mRNA, encoding another major autoantigen in type 1 diabetes, has already been shown to be genetically associated with disease. Previous reports that have assessed the association of GAD2 with type 1 diabetes have not used a dense map of markers surrounding the gene and have relied on very small clinical sample sizes. Consequently, no definite conclusions can be drawn from their negative results. We have therefore systematically searched all exons, the 3' untranslated region (UTR), the 5' UTR, and the 5' upstream region of GAD2, for polymorphisms in 32 white European individuals. We have genotyped these polymorphisms in a maximum of 472 U.K. type 1 diabetic affected sib pair families exhibiting linkage to type 1 diabetes on chromosome 10p and have tested both single variants and haplotypes in the GAD2 region for association with disease. We subsequently followed up our results by genotyping a subset of these single-nucleotide polymorphisms in a maximum of 873 Finnish families with at least one affected child. Our results suggest that GAD2 does not play a major role in type 1 diabetes in these two European populations.

3' Untranslated Regions↗
PubMed1990

Trending of impedance-monitored cardiac variables: method and statistical power analysis of 100 control studies in a pediatric intensive care unit.

The NCCOM3-R6 monitor continuously monitors cardiac output and five other cardiovascular variables from the thoracic electrical bioimpedance signal. We averaged data over 5-min intervals for 130 min in 100 control studies in 40 pediatric ICU patients, age 0.04 to 20.39 yr (median 1.39) and weighing 2.0 to 59.5 kg (median 8.8). For individual studies, 99% of the 5-min averages of cardiac output fell within +/- 44% of the baseline cardiac output for that study. Normal ranges were somewhat narrower for the other five variables. When we averaged data for 100 studies, 5-min interval observations for each variable did not deviate from baseline over a 2-h period (p greater than .70). With a sample size of 100 studies, we could detect a change in cardiac output of +/- 5% at the p less than .005 level with a power of 0.95. We conclude that with a sufficiently large sample size, studies employing the NCCOM3 can detect clinically significant cardiovascular changes due to pharmacologic or procedural stressors.

Cardiac Output↗
PubMed2003

How meta-analysis increases statistical power.

One of the most frequently cited reasons for conducting a meta-analysis is the increase in statistical power that it affords a reviewer. This article demonstrates that fixed-effects meta-analysis increases statistical power by reducing the standard error of the weighted average effect size (T.) and, in so doing, shrinks the confidence interval around T.. Small confidence intervals make it more likely for reviewers to detect nonzero population effects, thereby increasing statistical power. Smaller confidence intervals also represent increased precision of the estimated population effect size. Computational examples are provided for 3 effect-size indices: d (standardized mean difference), Pearson's r, and odds ratios. Random-effects meta-analyses also may show increased statistical power and a smaller standard error of the weighted average effect size. However, the authors demonstrate that increasing the number of studies in a random-effects meta-analysis does not always increase statistical power.

Humans↗
PubMed1997

Overcoming feelings of powerlessness in "aging" researchers: a primer on statistical power in analysis of variance designs.

A general rationale and specific procedures for examining the statistical power characteristics of psychology-of-aging empirical studies are provided. First, 4 basic ingredients of statistical hypothesis testing are reviewed. Then, 2 measures of effect size are introduced (standardized mean differences and the proportion of variation accounted for by the effect of interest), and methods are given for estimating these measures from already-completed studies. Power and sample size formulas, examples, and discussion are provided for common comparison-of-means designs, including independent samples I-factor and factorial analysis of variance (ANOVA) design, analysis of covariance designs, repeated measures (correlated samples) ANOVA designs, and split-plot (combined between- and within-subjects) ANOVA designs. Because of past conceptual differences, special attention is given to the power associated with statistical interactions, and cautions about applying the various procedures are indicated. Illustrative power estimations also are applied to a published study from the literature. It is argued that psychology-of-aging researchers will be both better informed consumers of what they read and more "empowered" with respect to what they research by understanding the important roles played by power and sample size in statistical hypothesis testing.

Aged↗
PubMed1988

The power of analysis: statistical perspectives. Part 1.

Failure to consider statistical power when achieving apparently "negative" results prevents accurate interpretation of the results. A nonsignificant result can be obtained when one includes an insufficient number of subjects to permit observation of a true effect (low power to detect an effect), or when one has an adequate number of subjects, but a meaningful effect does not exist (high power, no effect); one can also have a situation of lower power and no real effect. Without considering power, one is unable to distinguish a "negative" experiment from an inadequate one. This article examines 154 published nonsignificant t-test results. When power is calculated with an effect size equal to a standardized difference of unity, over 50% of the tests have inadequate power.

Clinical Trials as Topic↗
PubMed2002

The prevalence of negative studies with inadequate statistical power: an analysis of the plastic surgery literature.

Studies published in the medical literature often neglect to consider the statistical power needed to detect a meaningful difference between study groups. Small sample sizes tend to produce negative results because of low statistical power. Studies that cannot make conclusive statements about their hypotheses can waste resources, deter further research, and impede advances in clinical treatment. The current study reviewed three of the most frequently read plastic surgery journals from 1976 to 1996 to determine the prevalence of inadequately (<80 percent) powered clinical trials and experimental studies that found no difference (negative studies) in the response variable of interest between comparison groups. The statistical power of 54 negative studies using continuous response variables was calculated to detect a difference of 1 SD (+/-1 SD) in means between the comparative groups. The power of another 57 negative studies with dichotomous response (yes/no) variables was calculated to detect a relative change in proportions of 25 percent and 50 percent from the experimental to the control group. It was found that 85 percent of the studies with continuous response variables had inadequate power to detect the desired mean difference of +/-1 SD. In studies with dichotomous response variables, 98 percent had inadequate power to detect a desired 25 percent relative change in proportions, and 74 percent had inadequate power to detect a desired 50 percent relative change in proportions. These results indicate that many of the studies in the plastic surgery literature lack adequate power to detect a moderate-to-large difference between groups. The lack of power makes the interpretation of the studies with negative findings inconclusive. Proper study design dictates that investigators consider a priori the difference between groups that is of clinical interest, and the sample size per group that is needed to provide adequate statistical power to detect the desired difference.

Animals↗
PubMed1988

The power of analysis: statistical perspectives. Part 2.

A discussion of the importance of statistical power in research is presented accompanied by nomograms for determining sample size and statistical power for the Student's paired and unpaired t tests with a Type I error of 5%. A brief review of statistical inference is presented. Some findings from Part I are reviewed.

Clinical Trials as Topic↗