SEARCH · Search PubMed

Results for “Statistical power analysis”

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.

SourceResearch connectionFrom yearThrough year

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

At least 757 records · Page 42Linked to original sources

PubMed1992

The usefulness of matched pair randomization for medical practice-based research.

To be feasible, study designs for most intervention research in primary care settings must limit the number of participating physicians, without sacrificing the statistical power required to test the research hypotheses. A model was developed to examine sample size and statistical power requirements when using the physicians' practice as the unit of analysis. Randomized designs using either matched or unmatched samples of practices were compared under varying conditions. When baseline variability is small or the number of practice pairs is large, matching at best marginally increases power. However, in the typical case when baseline variability is large or the number of practice pairs is small, matching substantially increases the power to find intervention effects with a smaller sample. Thus, matching prior to randomization could improve the design of many intervention studies in primary care settings.

Humans↗

PubMed1983

Standardizing outcome data in program evaluation.

Procedures are described for standardizing outcomes in evaluations of service delivery systems. Accounting for the variability of a given device, client gains across services can be expressed in a standard metric of change. Standardized gains take on a common meaning of change regardless of the original scale and variability of the raw data. In return, a wide range of common statistical analyses can be applied with individual client gains as the units of analysis, powerfully delineating influences on outcome variability. Implications and limitations are discussed.

Community Mental Health Services↗

PubMed2002

The relative cleaning effectiveness of manual and powered toothbrushes.

Recently, a number of new low-cost powered toothbrushes have been marketed globally. Assessment of their cleaning capability in vitro is now becoming manageable with novel configurations of new brushing machines, which allow for the conventional brushing action and added device action. In this study, the in vitro stain removal efficiency of two marketed powered toothbrushes (Crest SpinBrush and Dr. Best Battery), a new prototype (Crest SpinBrush Pro) and two manual toothbrushes (Oral-B Indicator Soft and Oral-B CrossAction) was evaluated using a different brushing technique as a modification of the laboratory testing method developed by Stookey and associates at Indiana University Oral Health Research Institute. This was a randomized, parallel-group design study that examined stain removal with a novel toothbrushing configuration adapted for powered and manual toothbrushes. Stain was scored before and after brushing for two consecutive one-minute periods using digital image analysis. The mean change in L* was statistically compared among toothbrushes with analysis of covariance. The mean baseline stain scores ranged from 36.3-40.2 for the five toothbrush treatment groups. There was statistically significant evidence of imbalance with respect to baseline mean L* (p = 0.006), ranging from 36.3 for the CrossAction brush to 40.2 for the Crest SpinBrush Pro. Baseline stain imbalance was addressed with the ANCOVA statistical model which adjusts for baseline L*, effectively comparing all treatments at the same baseline stain level. Baseline L* was not statistically significant (p > 0.1) in the ANCOVA model at one or two minutes. With respect to all surfaces examined, the new prototype powered toothbrush (Crest SpinBrush Pro) delivered an adjusted (via analysis of covariance) mean L* reduction of 14.4 and 22.0 at the end of the first and second brushing periods, respectively, while the four remaining toothbrushes delivered adjusted mean L* reductions ranging from 5.6-8.6 and 9.4-13.3 at the end of the first and second brushing periods, respectively. These results represent 67-157% for the first brushing period, and 65-134% for the second brushing period greater stain removal for the new prototype powered toothbrush. Overall, the new prototype powered toothbrush had statistically significantly greater stain removal (p < 0.001) than all other toothbrushes tested. The results, using this powered toothbrush-compatible brushing machine configuration, show that the new prototype powered toothbrush (Crest SpinBrush Pro) produced statistically significantly enhanced stain removal efficiency relative to the four other toothbrushes, including Crest SpinBrush and Dr. Best powered toothbrushes. The newly configured brushing machine delivered a robust method for separating statistically significant in vitro differences for the complex cleaning action of powered toothbrushes.

Analysis of Variance↗

PubMed2002

Research publications in vascular and interventional radiology: research topics, study designs, and statistical methods.

PURPOSE: Statistical analysis is the universal language of medical research and is a vital tool for communicating the results of vascular and interventional radiology (VIR) procedures. Major articles in two radiology journals were surveyed to characterize the research topics, study designs, and statistical methods seen in recent VIR research publications. MATERIALS AND METHODS: The authors retrospectively reviewed 130 major clinical VIR articles published from July 2000 to June 2001: 72 articles (55%) from JVIR and 58 articles (45%) from RADIOLOGY: Articles were categorized by research topic and study design. Data were collected on the statistical methodology of each article. RESULTS: Research topics included vascular intervention in 65 of 130 articles (50%), nonvascular intervention in 26 (20%), vascular imaging in 23 (18%), biopsy in nine (7%), and other topics in seven (5%). Study design was descriptive in 87 studies (67%), comparative in 39 studies (30%), and involved secondary data analysis in four studies (3%). Of 126 primary clinical studies, outcome was cross-sectional (assessed at a single time point) in 40 studies (32%) and longitudinal (measured over time) in 86 studies (68%). Median sample size was 61. Basic tests of association (t-test, chi(2) test, etc.) were used in 71 articles (56%) and advanced tests of association (regression analysis) were presented in 25 (20%). Survival analysis was applied in 34 articles (27%). Decision statistics such as sensitivity/specificity were not used commonly (12%). Confidence intervals and power calculations were reported infrequently (15% and 7%, respectively). CONCLUSIONS: VIR publications focus on time-dependent outcomes after therapeutic interventions. Readers should understand basic tests of association and survival analysis--these include only 20 named statistical tests.

Periodicals as Topic↗

PubMed2001

A general and accurate approach for computing the statistical power of the transmission disequilibrium test for complex disease genes.

Transmission disequilibrium test (TDT) is a nuclear family-based analysis that can test linkage in the presence of association. It has gained extensive attention in theoretical investigation and in practical application; in both cases, the accuracy and generality of the power computation of the TDT are crucial. Despite extensive investigations, previous approaches for computing the statistical power of the TDT are neither accurate nor general. In this paper, we develop a general and highly accurate approach to analytically compute the power of the TDT. We compare the results from our approach with those from several other recent papers, all against the results obtained from computer simulations. We show that the results computed from our approach are more accurate than or at least the same as those from other approaches. More importantly, our approach can handle various situations, which include (1) families that consist of one or more children and that have any configuration of affected and nonaffected sibs; (2) families ascertained through the affection status of parent(s); (3) any mixed sample with different types of families in (1) and (2); (4) the marker locus is not a disease susceptibility locus; and (5) existence of allelic heterogeneity. We implement this approach in a user-friendly computer program: TDT Power Calculator. Its applications are demonstrated. The approach and the program developed here should be significant for theoreticians to accurately investigate the statistical power of the TDT in various situations, and for empirical geneticists to plan efficient studies using the TDT.

Adult↗

PubMed1995

Efficacy of anterior chamber paracentesis and Carbogen in treating acute nonarteritic central retinal artery occlusion.

PURPOSE: To determine whether anterior chamber paracentesis and Carbogen inhalation therapy (95% oxygen, 5% carbon dioxide) produce a significant difference in final visual acuity in eyes with acute nonarteritic central retinal artery occlusion (CRAO), compared with untreated eyes. METHODS: In this retrospective study, the records of 89 consecutive patients seen at the Retina Vascular Unit of Wills Eye Hospital with acute CRAO who received either both anterior chamber paracentesis and Carbogen therapy, or neither anterior chamber paracentesis or Carbogen therapy, were reviewed. Forty patients were treated with both therapies, whereas 49 received neither modality. Visual acuities before treatment and at subsequent follow-up visits were measured. All patients seen within 24 hours of the onset of symptoms were treated, whereas most of those seen after 24 hours were not treated. RESULTS: Stratified Wilcoxon analysis showed no statistically significant difference between the treated and untreated groups (P = 0.87) after adjusting for initial vision. A posthoc power analysis for the difference between two proportions showed that the study had adequate power (0.80) to detect a difference of the proportion of improved patients of 10% versus 25% between that treated and untreated groups. CONCLUSION: The data suggest that anterior chamber paracentesis and Carbogen therapy offer little benefit for treating acute nonarteritic CRAO.

Acute Disease↗

PubMed1998

Recommendations for statistical designs of in vivo mutagenicity tests with regard to subsequent statistical analysis.

A workshop was held on September 13 and 14, 1993, at the GSF, Neuherberg, Germany, to start a discussion of experimental design and statistical analysis issues for three in vivo mutagenicity test systems, the micronucleus test in mouse bone marrow/peripheral blood, the chromosomal aberration tests in mouse bone marrow/differentiating spermatogonia, and the mouse dominant lethal test. The discussion has now come to conclusions which we would like to make generally known. Rather than dwell upon specific statistical tests which could be used for data analysis, serious consideration was given to test design. However, the test design, its power of detecting a given increase of adverse effects and the test statistics are interrelated. Detailed analyses of historical negative control data led to important recommendations for each test system. Concerning the statistical sensitivity parameters, a type I error of 0.05 (one tailed), a type II error of 0.20 and a dose related increase of twice the background (negative control) frequencies were generally adopted. It was recommended that sufficient observations (cells, implants) be planned for each analysis unit (animal) so that at least one adverse outcome (micronucleus, aberrant cell, dead implant) would likely be observed. The treated animal was the smallest unit of analysis allowed. On the basis of these general consideration the sample size was determined for each of the three assays. A minimum of 2000 immature erythrocytes/animal should be scored for micronuclei from each of at least 4 animals in each comparison group in the micronucleus assays. A minimum of 200 cells should be scored for chromosomal aberrations from each of at least 5 animals in each comparison group in the aberration assays. In the dominant lethal test, a minimum of 400 implants (40-50 pregnant females) are required per dose group for each mating period. The analysis unit for the dominant lethal test would be the treated male unless the background frequency of dead implants (DI) is so low that multiple males would need to be integrated to meet the minimum observation of one adverse outcome (DI) per analysis unit. A three-step strategy of data analysis was proposed for the cytogenetic assays. Use of negative historical controls was allowed in certain circumstances for interpretation of results from micronucleus tests and chromosomal aberration tests.

Animals↗

PubMed2001

The Norsjö-Cooperstown healthy heart project: a case study combining data from different studies without the use of meta-analysis.

OBJECTIVES: This paper aims to develop and describe a method for combining. comparing, and maximizing the statistical power of two longitudinal studies of risk factors for cardiovascular disease that did not have identical data collection methodologies. METHODS: Subjects from a 1986 cross-sectional study (n = 180) were pair-matched with subjects of corresponding gender and age (+5 years) from a 1990 cross-sectional study. The methodology is described and results are calculated for various measures of cardiovascular risk or risk factors (e.g. cholesterol. Finnish Risk Score). RESULTS: Box's test of equality and symmetry of covariance matrices gave chi-square values of 223.8 and 710.0 for two cardiovascular risk factors (cholesterol and cardiac risk score, respectively); these values were highly significant (p=0.0001) For the North Karelia Risk Score, repeated measures ANOVA revealed a borderline significant interaction for treatment by time (p=0.054) and a significant interaction for treatment by time by country (p=0.035). These probabilities compared favorably with a randomized blocks model. CONCLUSIONS: Creation of a synthetic longitudinal control group resulted in a statistically valid ANOVA model that increased the statistical power of the study.

Adult↗

PubMed1985

Standardizing outcome data in program evaluation.

Procedures are described for standardizing outcomes in evaluations of service delivery systems. Accounting for the variability of a given device, client gains across services can be expressed in a standard metric of change. Standardized gains take on a common meaning of change regardless of the original scale and variability of the raw data. In turn, a wide range of common statistical analyses can be applied with individual client gains as the units of analysis, powerfully delineating influences on outcome variability. Implications and limitations are discussed.

Community Mental Health Services↗

PubMed1996

Exploratory data analysis: data visualization or torture?

Exploratory Data Analysis offers a set of graphical and statistical tools to find the full meaning from data sets. The user visualizes, analyzes, and transforms data distributions with these tools. Graphs reveal relationships between variables; the residuals left after fitting data show the adequacy of the model. Without this careful examination and understanding of the data, rote data analysis using standard statistical tests can give misleading results. Exploratory Data Analysis has its own set of pitfalls and must be used with confirmatory statistics and studies. Increasing power and resolution in personal computers enables modern statistical software to make these methods widely accessible. By easily moving between data and their graphic representation, analysis can be comprehensive without being tedious. Exploratory Data Analysis can add an exciting and useful tool to the epidemiologist's repertoire. This article illustrates several tools from an evolving list.

Computer Graphics↗

PubMed2026

transFusion: a novel comprehensive platform for integration analysis of single-cell and spatial transcriptomics.

MOTIVATION: Understanding spatial organization, intercellular interactions, and regulatory networks within the spatial context of tissues is crucial for uncovering complex biological processes and disease mechanisms. Spatial transcriptomics technologies have revolutionized this field by enabling the spatially resolved profiling of gene expression. 10× Visium has emerged as the predominant spatial technology, but its low resolution and the complexity of integrating multimodal datasets present significant analytical challenges, particularly for researchers with limited computational and statistical expertise. Current spatial transcriptomics analysis platforms generally fall short of effectively integrating multimodal data and maximizing the utility of spatial information-such as uncovering complex cellular spatial dependencies, multimodal gradient patterns, and spatial coexpression of ligand-receptor pairs and regulatory networks related to disease or biological states-thereby limiting their ability to provide comprehensive end-to-end analytical workflows when analyzing 10× Visium data. RESULTS: To address these limitations, we developed transFusion, a novel, advanced web-based platform specializing in the most comprehensive and effective integration analysis of scRNA-seq and 10× Visium spatial transcriptomics data. transFusion offers 12 key functions, from basic visualization to advanced analyses, including intercellular dependency analysis, ligand-receptor coexpression identification and visualization, and spatial multimodal gradient variation patterns. Two case studies were used to demonstrate transFusion's capabilities in exploring tissue architecture, intercellular communication, dependency networks, and multimodal gradient variation patterns with minimal computational skills and statistical expertise. transFusion provides a flexible and powerful framework for multimodal data integration analysis. AVAILABILITY AND IMPLEMENTATION: transFusion is freely available at https://github.com/WQLin8/transFusion.

Spatial Transcriptomics↗

PubMed2003

A cautionary note on exact unconditional inference for a difference between two independent binomial proportions.

Fisher's exact test for comparing response proportions in a randomized experiment can be overly conservative when the group sizes are small or when the response proportions are close to zero or one. This is primarily because the null distribution of the test statistic becomes too discrete, a partial consequence of the inference being conditional on the total number of responders. Accordingly, exact unconditional procedures have gained in popularity, on the premise that power will increase because the null distribution of the test statistic will presumably be less discrete. However, we caution researchers that a poor choice of test statistic for exact unconditional inference can actually result in a substantially less powerful analysis than Fisher's conditional test. To illustrate, we study a real example and provide exact test size and power results for several competing tests, for both balanced and unbalanced designs. Our results reveal that Fisher's test generally outperforms exact unconditional tests based on using as the test statistic either the observed difference in proportions, or the observed difference divided by its estimated standard error under the alternative hypothesis, the latter for unbalanced designs only. On the other hand, the exact unconditional test based on the observed difference divided by its estimated standard error under the null hypothesis (score statistic) outperforms Fisher's test, and is recommended. Boschloo's test, in which the p-value from Fisher's test is used as the test statistic in an exact unconditional test, is uniformly more powerful than Fisher's test, and is also recommended.

Humans↗

PubMed1998

Biomarkers of leukemia risk: benzene as a model.

Although relatively rare, leukemias place a considerable financial burden on society and cause psychologic trauma to many families. Leukemia is the most common cancer in children. The causes of leukemia in adults and children are largely unknown, but occupational and environmental factors are strongly suspected. Genetic predisposition may also play a major role. Our aim is to use molecular epidemiology and toxicology to find the cause of leukemia and develop biomarkers of leukemia risk. We have studied benzene as a model chemical leukemogen, and we have identified risk factors for susceptibility to benzene toxicity. Numerous studies have associated exposure to benzene with increased levels of chromosome aberrations in circulating lymphocytes of exposed workers. Increased levels of chromosome aberrations have, in turn, been correlated with a heightened risk of cancer, especially for hematologic malignancy, in two recent cohort studies in Europe. Conventional chromosome analysis is laborious, however, and requires highly trained personnel. Further, it lacks statistical power, as only a small number of cells can be examined. The recently developed fluorescence in situ hybridization (FISH) and polymerase chain reaction (PCR)-based technologies have allowed the detection of specific chromosome aberrations. These techniques are far less time consuming and are more sensitive than classical chromosomal analysis. Because leukemias commonly show a variety of specific chromosome aberrations, detection of these aberrations by FISH and PCR in peripheral blood may provide improved biomarkers of leukemia risk.

Adult↗

PubMed1989

[EEG background activity in patients with dementia of the Alzheimer type--with special reference to analysis by t-statistic significance probability mapping (SPM) in Alzheimer's disease and senile dementia].

EEG power amplitude and power ratio data obtained from 15 (3 men and 12 women) patients with Alzheimer's disease (AD) and 8 (2 men and 6 women) with senile dementia of Alzheimer type (SDAT) were compared with similar data from 40 age- and sex-matched normal controls. Compared with the healthy controls, both patient groups demonstrated increased EEG background slowing, and it indicated more slower in AD than in SDAT. Moreover, both groups showed characteristic findings respectively on EEG topography and t-statistic significance probability mapping (SPM). The differences between AD and their controls indicated high slowing with reductions in alpha 2, beta 1 and beta 2 activity. The SPMs of power ratio in theta and alpha 2 bands showed most prominent significance in the right posterior-temporal region and delta and beta bands did in the frontal region. Severe AD indicated only frontal delta slowing compared to mild AD. The differences between SDAT and their controls indicated only mild slowing in delta and theta bands. The SPM of power amplitude showed occipital slowing, whereas the SPM of power ratio showed the slowing in the frontal region. Judging from both topographic findings, these were considered to denote diffuse slow tendency. In summary, these results presumed that in AD, cortical damages followed by EEG slowing with reductions of alpha 2 and beta bands originated rapidly and thereafter developed subcortical (non-specific area in thalamus) changes with frontal delta activity on SPM. On the other hand, in SDAT, diffuse cortico-subcortical damages with diffuse slowing on EEG topography were caused gradually.

Adult↗

PubMed2005

Increasing the degrees of freedom in future group randomized trials: the df* approach.

This article builds on the previous article by Blitstein et al. (2005), which showed how external estimates of intraclass correlation can be used to improve the precision for the analysis of an existing group randomized trial. The authors extend that work to sample size estimation and power analysis for future group-randomized trials. Often this approach will allow a smaller study than would otherwise be possible without sacrificing statistical power. Such studies are needed, for example, as pilot studies to help plan for a full-scale efficacy trial, as replication studies, or in situations in which resource constraints prohibit a larger trial. The authors discuss the circumstances under which this strategy will be most helpful and the risks associated with conducting smaller studies.

Humans↗

PubMed2000

First measured plasma concentration value as C(max); impact on the C(max) confidence interval in bioequivalence studies.

In bioequivalence studies, the first blood or plasma sample taken after dosing sometimes yields a higher assayed drug concentration than any samples drawn thereafter. This circumstance ('first C(max)' or 'FCM'), is usually considered undesirable, since a 'true C(max)' requires that the sampled concentrations immediately preceding and immediately after the 'true C(max)' concentration should be lower than the 'true C(max)' concentration. Therefore, a question arises whether the presence of FCM in a bioequivalence study affects the power and accuracy of the computed statistical confidence interval (CI) for C(max). This study examines what effect, if any, the inclusion or exclusion of FCM data has on the statistical power and accuracy of the 90% CI computed for C(max) in the analysis of results for in vivo bioequivalence studies. Actual experimental study data as well as data from simulated studies were evaluated. In the simulated studies, up to half of the study subjects exhibited FCM, and various levels of intrasubject variability were incorporated into the absorption rate constant. The two one-sided tests procedure was used to assess equivalence of C(max) for the test versus reference products when either a complete set of C(max) data was analysed (designated 'CC(max)'), which included subjects with FCM profiles; or a truncated set of data was analysed (designated 'TC(max)'), that excluded all subjects with FCM. The results showed that the CC(max) metric had greater statistical power and comparable or greater statistical accuracy compared to TC(max) for both bioequivalent and non-bioequivalent drug product formulations. Even when up to 50% of the study subjects had FCM, the power and accuracy of the 90% CI for rate of absorption (i.e. C(max)) was not significantly affected. Consequently, this study shows that, in the analysis of data from conventional in vivo bioequivalence studies, the inclusion of 50% of the subjects exhibiting FCM does not greatly impact the statistical results obtained for C(max). Published in 2000 by John Wiley & Sons, Ltd.

Absorption↗

PubMed2003

Radiation dose is reduced with a single-pass whole-body multi-detector row CT trauma protocol compared with a conventional segmented method: initial experience.

Radiation dose data were collected from a calibrated multi-detector row computed tomographic (CT) scanner during trauma CT. One protocol (used with 10 case subjects) involved a single-pass continuous whole-body acquisition from cranial vertex to symphysis pubis, while the other, conventional protocol (used with 10 control subjects) involved scouting and scanning body segments (head, cervical spine, chest, abdomen, and pelvis) individually. Technical factors were kept constant within each body segment for the single-pass and the segmented protocols. Statistics included univariate analysis, two-tailed t testing to evaluate statistical significance of the summary statistic, and power and subject population contingency tables. The mean dose length product (DLP) with the single-pass protocol was 17% lower than the sum of the DLPs of each of the individual body segment scans (P <.001). Analysis of power and subject population by using a difference in mean of 500 mGy. cm and an alpha of.05 revealed a (1-beta) of higher than 0.90 for a sample of 10 patients. Thus, a whole-body single-pass trauma protocol, compared with a typical segmented acquisition protocol matched for imaging technique, resulted in reduced total radiation dose. The reduction in radiation dose is thought to represent a reduction in redundant imaging at overlap zones between body segments scanned in the segmental protocol but not in the continuous acquisition.

Humans↗

PubMed2003

Within-sample variation of fecal glucocorticoid measurements.

Fecal glucocorticoid metabolite analysis is a useful tool for monitoring adrenocortical activity in captive and free-ranging wildlife. Glucocorticoid metabolites may not be evenly distributed within fecal samples and this variability could affect the interpretation of glucocorticoid metabolite measurements. Furthermore, the precision (i.e., repeatability of measurements) of fecal glucocorticoid measurements from well-mixed samples is unknown. We collected fresh white-tailed deer (Odocoileus virginianus) feces at various times pre- and post-adrenocorticotropin injection to provide samples with low (<75 ng/g), medium (75-90 ng/g), and high (>90 ng/g) glucocorticoid concentrations in case variability differs in samples of dissimilar hormone metabolite concentrations. We compared two sampling methods (selection of three pellet groups [one from each end of the fecal mass and one from the center] versus sampling three small portions of the thoroughly mixed fecal mass) to estimate within-sample variation of glucocorticoid metabolites. Glucocorticoid metabolite measures from pellet groups were higher than fecal glucocorticoid measures from mixed samples in the low (F=3.10; df = 1,56; P=0.08) and medium concentration (F=7.28; df = 1,50; P=0.01) groups. Fecal glucocorticoid metabolite estimates from mixed samples were less variable than glucocorticoid metabolite measures using pellet groups from the same fecal mass, although these differences were not statistically significant (low group: F=0.59; df = 1,38; P=0.45; medium group: F=0.13; df = 1,34; P=0.72; high group: F=2.30; df = 1,28; P=0.14). The mean coefficient of variation was <10% across all treatment groups and sampling methods. However, a power analysis indicated the mixed sub-sample technique requires fewer samples to detect statistically significant differences than pellet groups. Our results suggest that glucocorticoid metabolites may not be evenly distributed in white-tailed deer feces. Consequently, using only a few pellets from a fecal mass may bias assay interpretation. We suggest researchers homogenize the entire fecal mass before removing a sub-sample of fecal material for analysis. Also, other sources of variation must be considered when interpreting results of fecal glucocorticoid studies.

Animals↗