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 559 records · Page 31Linked to original sources
PubMed1994

Cerebral pressure-flow relationship during cardiopulmonary bypass in the dog at normothermia and moderate hypothermia.

We studied cerebral autoregulation by analyzing cerebral pressure-flow curves during cardiopulmonary bypass (CPB) with alpha-stat (alpha-stat) acid-base management at 28 (n = 9) and 37 degrees C (n = 9) in two groups of dogs. Cerebral blood flow (CBF) and cerebral metabolic rate for oxygen (CMRO2) were determined multiple times in each animal over an extensive range of cerebral perfusion pressure (CPP). The CPP was altered by changing perfusion flow rate. The dependence of CBF on CPP during normothermic and moderate hypothermic CPB was assessed using a block design analysis of covariance with CPP as the covariate. We anticipated maximal statistical power with this analysis to define if cerebral autoregulation was intact. This method of statistical analysis was compared with the conventional interpretation by linear regression analysis. Animals were administered sodium thiopental until an isoelectric electroencephalogram was obtained to assure stable depth of anesthesia independently of temperature effects. The animals were randomly assigned to either temperature group. The CBF was determined by injection of radioactive microspheres at each of five target CPPs randomly allocated (50, 60, 70, 80, and 90 mm Hg). The brain oxygen content difference was defined as arterial minus superior sagittal sinus (SSS) oxygen content. No difference in CPP, hemoglobin, arterial carbon dioxide tension, or pH was seen between groups at any time period. In both groups, total CBF (tCBF) increased significantly with increasing CPP (p = 0.012 and 0.017 for normothermic and hypothermic CPB, respectively; CPP as covariate). The between-group difference in slopes (CPP x temperature effect) approached statistical significance (p = 0.059).(ABSTRACT TRUNCATED AT 250 WORDS)

Analysis of Variance↗
PubMed2006

A case-crossover study of fine particulate matter air pollution and onset of congestive heart failure symptom exacerbation leading to hospitalization.

Persons with congestive heart failure may be susceptible to ambient air pollution. The authors evaluated the association between exposure to particulate matter with an aerodynamic diameter of <2.5 microm (PM2.5) and onset of symptom exacerbation leading to hospital admission in Baltimore, Maryland. They used a case-crossover design for 135 case events occurring among 125 persons with prevalent congestive heart failure who were admitted to a single hospital through the emergency department during 2002. The case period was assigned using three index times: 8-hour and 24-hour periods of symptom onset and date of hospital admission. Controlling for weather, the authors detected a modest relative increase in risk for cases defined by 8-hour symptom onset for an interquartile-range increase in PM2.5 at a 2-day lag (odds ratio=1.09, 95% confidence interval: 0.91, 1.30). A corresponding increase in risk was not observed when admission date was used to define the case period. A series of simulations based on study data indicated that the study had adequate statistical power to detect odds ratios of 1.2 or higher. Although overall findings were not statistically significant, the identification of case events defined by an 8-hour onset period may be more relevant than either a 24-hour onset period or the admission date for estimating harmful effects of air pollutant exposure on cardiovascular health.

Aged↗
PubMed2003

Emerging standards in statistical practice: implications for clinical trials in rehabilitation medicine.

This article discusses selected issues in statistical practice that occur during the conduct of clinical trials in medical rehabilitation: (1) supplementing null hypothesis statistical testing and P values, (2) determining sample size and statistical power, (3) handling missing data, and (4) dealing with multiplicity (i.e., multiple endpoints, multiple statistical comparisons, and repeated measurements). Suggested strategies to address these issues are offered in light of the International Conference on Harmonisation guideline "Statistical Principles for Clinical Trials."

Clinical Trials as Topic↗
PubMed1998

Large datasets: common uses and caveats.

BACKGROUND: Increasingly, large collections of pre-existing data are being used to analyze the occurrence, burden, and health care resources directed to the management of various skin diseases. OBJECTIVE: This article discusses a number of different types of large datasets along with their common uses. Various concerns about the use of this information are also discussed. CONCLUSION: Although large datasets provide significant statistical power with readily available data, there are significant concerns, particularly regarding data quality and statistical analysis. Readers need to be aware of how an investigator has addressed these issues. Furthermore, the profession needs to be cognizant of very legitimate public concerns regarding confidentiality of personal information.

Databases, Factual↗
PubMed2005

Spatio-temporal analysis of auditory cortex activation as detected with silent event related fMRI.

Functional magnetic resonance imaging (fMRI) allows neuroscientists to assess brain function by evaluating haemodynamic activity (blood flow) when a stimulus is present or absent. In clinical practice, the hearing levels of individuals are determined using an audiometer that allows presentation of a pure-tone of specific intensity and frequency. Functional images of the auditory nervous system have been obtained using stimuli such as pure-tone, speech, noise, etc. However, the observed activation evoked by the stimulus is confounded with the neuronal response evoked by scanner noise generated during imaging. Hence, researchers have been developing fMRI techniques to overcome the inadvertent effect of scanner noise on fMRI studies of the auditory cortex. Silent event related fMRI is a recently reported fMRI technique diminishing the confounding effects of background scanner noise. A drawback of sfMRI is that it requires long acquisition times (30-40 min) to achieve statistically significant activation. An additional complication associated with all fMRI data is that measurements obtained at consecutive times tend to exhibit substantial temporal correlation. Such correlation structure complicates the identification of brain locations (voxels) demonstrating statistically significant activation. We propose an approach for detecting activation with high statistical power and low false-positive rate. To accomplish these goals of high power and low type I error rate in sfMRI with shorter acquisition times, we describe a statistical model that accounts for the spatial and temporal correlation structure of the haemodynamic response. Temporal dependence within each voxel's measurements is modelled, and a regional measurement-error-free kriging predictor is used to combine information from neighbouring voxels when assessing voxel activation. Instead of simply applying a post hoc smoothing to thevoxelwise test statistics (e.g. t statistics), we attempt to make optimal use of information in the locality of each voxel when estimating the voxel's mean, variance, and temporal dependence parameters. The primary advantage to this spatial modelling approach is that the degree to which voxel parameters are smoothed is driven by the data. Thus, we are not subjectively smoothing noisy data, but objectively estimating the noise-free version of the spatial processes associated with the response. The resulting voxel activation maps exhibit substantially more spatial continuity than other currently used approaches, while exhibiting desirable inferential properties including a lower false-positive rate and high power for detection of activated regions. Minimal computational resources are necessary to carry out the approach, which yielded voxel activation maps for our experiment in only minutes.

Auditory Cortex↗
PubMed1986

Evaluation of possibilities for mass screening for colorectal cancer with Hemoccult fecal blood test.

Data from a health survey including the Hemoccult fecal blood test, together with official cause-specific death rates, were used to assess the magnitude of a controlled trial that would be required to prove a 25 percent reduction of the mortality from colorectal cancer associated with screening. All men in three age groups in the city of Malmö, Sweden, were invited, but 46 percent did not participate in, the Hemoccult screening. One carcinoma and 89 adenomas were detected in 56 of the 2422 who did. With the risk function used in our calculation and a compliance rate of 60 percent, a study population among 45- to 69-year-olds of 605,000 is required to prove an expected 25 percent reduction of the mortality with 90 percent power. Considering the size of such a trial, we question whether a controlled trial is feasible. With known risk functions for death from all causes and death from colorectal cancer, the study population was calculated using variable statistical power, participation rate, and risk reduction. Statistical methods and computer programs are given. In addition, alternative study models to assess the benefits associated with screening are discussed.

Adenoma↗
PubMed2005

The reading, writing, and arithmetic of the medical literature, part 2: critical evaluation of statistical reporting.

OBJECTIVE: To offer suggestions to help improve clinicians' understanding of the statistical analyses in the literature and their use of these methods in their own medical writings. DATA SOURCES: Literature searches began at the National Library of Medicine's online database and were traced to primary sources. STUDY SELECTION: All referenced information in this article was cited from primary sources. RESULTS: Physicians should be able to determine the variables studied and how they were measured, the comparisons that were made, the difference (with 95% confidence interval) between the groups, the exact P value for the difference, the statistical test used in the analysis, whether the data conformed to the assumptions of the test, whether the study had adequate statistical power, and the clinical importance of the difference. CONCLUSION: Clinicians should know how to interpret statistical results so that they can use medical science to its full extent in treating patients.

Biomedical Research↗
PubMed1998

Mapping genes that underlie ethnic differences in disease risk: methods for detecting linkage in admixed populations, by conditioning on parental admixture.

Genes that underlie ethnic differences in disease risk can be mapped in affected individuals of mixed descent if the ancestry of the alleles at each marker locus can be assigned to one of the two founding populations. Linkage can be detected by testing for association of the disease with the ancestry of alleles at the marker locus, by conditioning on the admixture (defined as the proportion of genes that have ancestry from the high-risk population) of both parents. With regard to exploiting the effects of admixture, this test is more flexible and powerful than the transmission-disequilibrium test. Under the assumption of a multiplicative model, the statistical power for a given sample size depends only on parental admixture and the risk ratio r between populations that is generated by the locus. The most informative families are those in which mean parental admixture is .2-.7 and in which admixture is similar in both parents. The number of markers required for a genome search depends on the number of generations since admixture and on the information content for ancestry (f) of the markers, defined as a function of allele frequencies in the two founding populations. Simulations using a hidden Markov model suggest that, when admixture has occurred 2-10 generations earlier, a multipoint analysis using 2,000 biallelic markers, with f values of 30%, can extract 70%-90% of the ancestry information for each locus. Sets of such markers could be selected from libraries of single-nucleotide polymorphisms, when these become available.

Alleles↗
PubMed1999

[Are mortality indicators acceptable indicators for the quality of health care?].

IMPORTANCE OF PUBLISHING MORTALITY RATES: Mortality rates for certain interventions or disease states have been used over the last decade as indicators of the quality of care provided by a given hospital, unit or, medical team. If published, these rates would be a useful tool for decision makers in the process of fund allocations, for public information, and for promoting improved care in hospitals or units with a low classification. METHODOLOGICAL LIMITATIONS: It is difficult to adjust an indicator of mortality to disease-related risk factors and any modification of this adjustment can have major consequences on the validity of subsequent comparisons. The differences in mortality observed between hospitals and physicians can reflect not only differences in quality of care but also differences in approaches to disease-related risk factors, therapeutic choices, or coding practices. The lack of statistical power is a major limiting factor in interpreting differences in mortality rates. To evidence a statistically significant difference in mortality between two hospitals whose rates are respectively 0.5% and 1% (for example in total hip replacement patients), it would be necessary to include 4673 patients, a number which would correspond to 20 years data for a hospital performing 230 interventions per year. Consequently, the number of interventions performed in the most active hospitals would not be sufficient to make such comparisons. LIMITATIONS AND COUNTER EFFECTS: Some studies have demonstrated that the publication of mortality rates does not have a major influence on patients' decisions nor on physicians' choice of a referral hospital. It would have no effect on improving health care quality of the institutions cited. One the contrary, certain counter effects have been observed: modification in patient recruitment, higher-risk patients being referred to hospitals with unpublished mortality rates. For many authors, procedure indicators are more pertinent than outcome indicators for detecting differences in health care quality between different care structures.

France↗
PubMed1994

Evaluation of 13 short tandem repeat loci for use in personal identification applications.

Personal identification by using DNA typing methodologies has been an issue in the popular and scientific press for several years. We present a PCR-based DNA-typing method using 13 unlinked short tandem repeat (STR) loci. Validation of the loci and methodology has been performed to meet standards set by the forensic community and the accrediting organization for parentage testing. Extensive statistical analysis has addressed the issues surrounding the presentation of "match" statistics. We have found STR loci to provide a rapid, sensitive, and reliable method of DNA typing for parentage testing, forensic identification, and medical diagnostics. Valid statistical analysis is generally simpler than similar analysis of RFLP-VNTR results and provides powerful statistical evidence of the low frequency of random multilocus genotype matching.

Alleles↗
PubMed2005

The comparative power of the discriminant methods used in toxicological pathology.

It is highly desirable to use experimental methodologies in toxicological pathology that combine statistical power, practicality, and objective reviewability to detect small differences. The different ways of gathering data at the microscope can result in clear differences in power to discriminate small, but real, differences between treated and control rodent groups with nonneoplastic lesions. Six alternative methods of gathering and analysing results are compared. They are referred to as the Measuring, Ordering, Scoring (or Grading), Pair-contrast, Outside-control, and Affected methods. Measuring and Ordering methods are uniformly more powerful than other more common and highly esteemed methods, such as Scoring/Grading. From the practical perspective, Measuring and Ordering can be applied objectively, reviewed objectively, and interpreted to standards that are widely accepted as valid throughout experimental science e.g., using confidence limits and intervals. They also are intuitively natural extensions of routine toxicological histopathological examinations. Establishing a small difference between control and treated groups is commonly a problem when reporting no-observed-effect levels. Ordering is the recommended method for assessing if a small difference between treated and control groups is within chance variation or is the result of a true treatment effect, when measurement is impractical.

Animals↗
PubMed2002

An efficient haplotyping method with DNA pools.

Determination of haplotype frequencies (the joint distribution of genetic markers) in large population samples is a powerful tool for association studies. This is due to their greater extent of polymorphism since any two bi-allelic single nucleotide polymorphisms (SNPs) generate a potential four-allele genetic marker. Therefore, a haplotype may capture a given functional polymorphism with higher statistical power than its SNP components. The statistical estimation of haplotype frequencies, usually employed in linkage disequilibrium studies, requires individual genotyping for each SNP in the haplotype, thus making it an expensive process. In this study, we describe a new method for direct measurement of haplotype frequencies in DNA pools by allele-specific, long-range haplotype amplification. The proposed method allows the efficient determination of haplotypes composed of two SNPs in close vicinity (up to 20 kb).

Gene Frequency↗
PubMed2007

Biased odds ratios from dichotomization of age.

Dichotomizing a continuous variable is known to result in the loss of information, lower statistical power, and lower reliability. In many epidemiological studies, age is a scaled (continuous) variable prior to statistical analyses; however, despite pleas from methodologists, researchers frequently dichotomize age in their data analysis without an appropriate rationale. Using simulated case-control data, we show that dichotomizing age generally will lead to a biased odds ratio (OR). When age was a confounder (potentially representing common causes of risks and outcomes), including age as a scaled variable (whether the age effect was linear or non-linear in the logit), provided satisfactory control, whereas when age was categorized, the estimated risk factor effect was biased. We also demonstrate that the further the cutpoint is from the median age, the greater the increase in the OR; thus, in cases where age dichotomization is warranted, researchers are cautioned not to allow the size of the empirical OR to influence their choice of cutpoint. Recommendations are made for analysing age in epidemiological data and interpretation of empirical findings.

Adult↗
PubMed2003

Effects of native forest regeneration practices on genetic diversity in Eucalyptus consideniana.

Impacts of forest harvesting and regeneration practices on genetic diversity in the Australian native forest species Eucalyptus consideniana Maiden (yertchuk) were examined using 29 Mendelian DNA markers (18 RFLPs and 11 microsatellites). Two replicate logging coupes were studied from each of the two most commonly employed silvicultural treatments: clear felling with aerial re-sowing and the seed tree system. For each coupe, genetic diversity measures were compared between a sample of the sapling regeneration and a corresponding control sample from bordering unharvested trees. When calculations were performed over all 29 loci, significant reductions of allelic richness (AR), effective number of alleles (AE) and/or expected heterozygosity (HE) were detected on one or both of seed tree coupes, but on neither of the clear falls. When calculations were performed over the 11 microsatellites alone, all three measures, AR, AE and HE, were significantly reduced on both of the seed replicates but on neither of the two clear falls. In contrast, when the RFLPs were examined separately, there were no significant reductions of diversity on either of the two seed tree coupes or on the two clear falls. These results suggest that genetic erosion is more likely under the seed tree system than under clear-felling with aerial re-sowing and that there is greater statistical power to detect it with microsatellites than with RFLPs. A Monte Carlo simulation to test the statistical significance of the number of apparently lost or gained alleles showed that significant losses of alleles above specified threshold frequencies occurred only in the two seed tree replicates. Three of the four control and regeneration population pairs were significantly differentiated, as indicated by exact tests or by pairwise FST estimates. Comparisons of CONTML dendrograms, constructed for the regeneration populations only versus the control populations only, indicated that genetic drift was significantly promoted under forest management. No significant decreases in observed heterozygosity, or increases in the panmictic index (f), were observed in any of the comparisons suggesting that inbreeding was not promoted by a single rotation of forest management.

Computer Simulation↗
PubMedDate not supplied

Microcomputer-based system to measure, record and process flow-volume curves, respiratory questionnaire data and environmental exposure.

A microcomputer-based system was developed to measure flow-volume curve parameters, record respiratory questionnaire data and analyse the collected data. The hardware of the system consists of two parts which operate independently and are linked together for data transfer. The first part is a microprocessor-based unit to accurately measure flow-volume curve parameters. The second part is a microcomputer unit used to receive flow-volume curve parameters from the first part, to record responses to questionnaires stored in the unit and to perform all statistical analysis. The software included a monitor program controlling system operations, a data base and a powerful statistical package. Two sets of questionnaires are stored in the system, one for adults and the other for children. The user is only required to enter to the system answers to questions displayed on the screen. Flow-volume data can be entered via the keyboard of the microcomputer unit or transmitted from the flow-volume test unit. The developed system is compact, easy to operate and moderately priced.

Adult↗
PubMed2001

The role of prospective randomized clinical trials in pediatric surgery: state of the art?

PURPOSE: This study sought to determine the role of randomized controlled trials (RCT) in the evolution of pediatric surgical practice. METHODS: The authors used a computer-assisted literature search to identify all clinical trials related to pediatric surgery published in the English-language literature from 1966 through 1999. Each article was reviewed in detail for purpose, content, conduct, and quality of the trial. The authors assessed quality with a previously validated instrument (Chalmers Qualitative Assessment). RESULTS: The authors identified 134 RCTs related to pediatric surgery over the past 33 years. This accounts for 0.17% of 80,377 articles published in the field. The areas of surgery studied were analgesia 65 (49%), antibiotics 17 (13%), extracorporeal membrane oxygenation (ECMO) 9 (7%), gastrointestinal, burns, oncology, minimally invasive surgery, vascular access, congenital anomalies, and trauma (each <5%). Only 16 (12%) trials compared 2 surgical therapies, 9 (7%) compared a medical versus a surgical therapy, and 109 (81%) compared 2 medical therapies in surgical patients. Fourteen (10%) RCTs were funded by peer-reviewed agencies. Only 17 (13%) RCTs included a biostatistician as an author or a consultant. Trial design included calculation of sample size and statistical power in 21 (16%) RCTs. Method of randomization was reported in only 51 (38%). The test statistic and observed probability value was reported in 15 (11%). CONCLUSIONS: Clinical trials are used infrequently to answer questions related to pediatric surgery. When RCTs are utilized, they often suffer from poor trial design, inadequate statistical analysis, and incomplete reporting. Pediatric surgery could benefit from increased expertise, funding, and participation in clinical trials.

California↗
PubMed1995

Interplay between design and analysis for behavioral intervention trials with community as the unit of randomization.

This paper outlines an approach for the design and analysis of randomized controlled trials investigating community-based interventions for behavioral change aimed at health promotion. The approach is illustrated using the Community Intervention Trial for Smoking Cessation (COMMIT), conducted from 1988 to 1993, involving 11 pairs of communities in North America, matched on geographic location, size, and sociodemographic factors. The situation discussed is when assignment to intervention is done at the community level; for COMMIT, the very nature of the intervention required this. The number of communities as a key determinant of the statistical power of the trial. The use of matched pairs of communities can achieve a gain in statistical efficiency. Randomization is used to obtain an unbiased assessment of the intervention effect; randomization also provides the basis for statistical analysis. Permutation tests (and corresponding test-based confidence intervals), using community as the unit of analysis, follow directly from the randomization distribution. Within this framework, individual-level covariates can be used for imputation of missing values and for adjusting analyses of intervention effect.

Health Behavior↗
PubMed1987

Effects of child restraint laws on traffic fatalities in eleven states.

Mandatory child restraint laws in 11 states were evaluated for their effect on motor vehicle fatality rates among young children. Data from 1976 through 1983 were analyzed using a monthly time-series design involving 54 months' pre-law and 12 months' post-law data. The 11 states collectively had a mean of 8.8 and a standard deviation of 3.6 fatalities per month among young children. Such small frequency counts resulted in a large proportion of the variation being random. Statistical power analyses found fatality reductions of 20% to 25% following the child restraint laws would be statistically significant. Reductions of such a magnitude were not found for young children. Based on these findings, we recommend that evaluations of highway safety policies focusing on a specific age group within a single state not be limited to analyses of traffic fatalities alone. Studies employing analyses of the larger numbers of crash-induced injuries have identified modest but important casualty reductions not found when analyzing fatalities alone.

Accidents, Traffic↗