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 757 records · Page 42Linked to original sources
PubMed1982

A multi-stage Gaussian transformation algorithm for clinical laboratory data.

We have developed a multi-stage computer algorithm to transform non-normally distributed data to a normal distribution. This transformation is of value for calculation of laboratory reference intervals and for normalization of clinical laboratory variates before applying statistical procedures in which underlying data normality is assumed. The algorithm is able to normalize most laboratory data distributions with either negative or positive coefficients of skewness or kurtosis. Stepwise, a logarithmic transform removes asymmetry (skewness), then a Z-score transform and power function transform remove residual peakedness or flatness (kurtosis). Powerful statistical tests of data normality in the procedure help the user evaluate both the necessity for and the success of the data transformation. Erroneous assessments of data normality caused by rounded laboratory test values have been minimized by introducing computer-generated random noise into the data values. Reference interval endpoints that were estimated parametrically (mean +/- 2 SD) by using successfully transformed data were found to have a smaller root-mean-squared error than those estimated by the non-parametric percentile technique.

Adult↗
PubMed2005

Perspectives on the molecular epidemiology of aerodigestive tract cancers.

Improving laboratory techniques and the greater availability of genetic data have led to a flurry of publications from molecular epidemiologic studies on aerodigestive tract cancers. Inconsistent results have been observed in studies of sequence variants, due to limitations such as small sample size, possible detection of false positives, moderate prior probabilities that each SNP confers a substantial increase in cancer risk, and publication bias. Meta- and pooled-analyses were shown to be effective in elucidating modest increases in aerodigestive tract cancer risk attributable to sequence variants. Phenotypic assays developed to quantify an individual's DNA repair capacity have been applied to epidemiological studies on aerodigestive tract cancers. Epigenetic events have also been studied in tumor progression and as susceptibility factors for aerodigestive tract cancers, in smaller scale studies. It is imperative that limitations of previous studies are addressed for future research in the molecular epidemiology of aerodigestive tract cancers. Some recommendations for future research are to: (i) incorporate multiple markers of different types (ex. genotype and phenotype data), (ii) enhance statistical power by conducting studies with larger sample size, and developing consortia to coordinate research efforts, (iii) improve marker selection via a hybrid strategy of incorporating data on evolutionary biology and physico-chemical properties of amino acids, with haplotype/tag SNP data, (iv) employ novel statistical methods such as hierarchical modeling with Bayesian adjustments, false positive reporting probability and modeling of complex pathways. Consortia have been initiated for head and neck cancer (International Head and Neck Cancer Epidemiology Consortium (INHANCE)) and lung cancer (International Lung Cancer Consortium (ILCCO)) with the aim to share comparable data, to focus on rare subgroups such as nonsmokers and to coordinate laboratory analyses. Such collaborative efforts and integration across disciplines will be essential in contributing to the elucidation of genetic susceptibility to aerodigestive tract cancers.

Carcinogens↗
PubMed1998

Multipoint genetic mapping of quantitative trait loci using a variable number of sibs per family.

We present a multipoint algorithm to map quantitative trait loci (QTLs) using families from outbred populations with a variable number of sibs. The algorithm uses information from all markers on a chromosome simultaneously to extract information of QTL segregation. A previous multipoint method (Kruglyak & Lander (1995) American Journal of Human Genetics 57, 439-454) extracts information using a hidden Markov model. However, this method is restricted to small families (< 10 sibs). We present an approximate hidden Markov model approach that can handle large sibships while retaining similar efficiency to the previous method. Computer simulations support the notion that data sampled from a small number of large families provide more power than data obtained from a large number of small families, under the constraint that the total number of individuals for the two schemes is the same. This is further reflected in simulations with variable family sizes, where variance in family size improves the statistical power of QTL detection relative to a constant size control.

Chromosome Mapping↗
PubMed2006

Chromosome substitution strains: a new way to study genetically complex traits.

Many biological traits and heritable diseases are multifactorial, involving combinations of genetic variants and environmental factors. To dissect the genetic basis for these traits and to characterize their functional consequences, mouse models are widely used, not only because of their genetic and physiological similarity to humans, but also because an extraordinary variety of genetic resources enable rigorous functional studies. Chromosome substitution strains (CSSs) are a powerful complement to existing resources for studying multigenic traits. By partitioning the genome into a panel of new inbred strains with single chromosome substitutions, one strain for each of the autosomes, the X and Y chromosome, and the mitochondria, unique experimental designs and considerable statistical power are possible. Multigenic trait genes (or quantitative trait loci [QTLs]) with weak effects are easily detected, linkage and congenic crosses can be quickly made, gene interactions are readily characterized, and discovery of QTLs is greatly accelerated. Several published studies demonstrate the considerable utility of these strains and new applications for CSSs continue to be discovered.

Animals↗
PubMed2000

Power of quantitative trait locus mapping for polygenic binary traits using generalized and regression interval mapping in multi-family half-sib designs.

A generalized interval mapping (GIM) method to map quantitative trait loci (QTL) for binary polygenic traits in a multi-family half-sib design is developed based on threshold theory and implemented using a Newton-Raphson algorithm. Statistical power and bias of QTL mapping for binary traits by GIM is compared with linear regression interval mapping (RIM) using simulation. Data on 20 paternal half-sib families were simulated with two genetic markers that bracketed an additive QTL. Data simulated and analysed were: (1) data on the underlying normally distributed liability (NDL) scale, (2) binary data created by truncating NDL data based on three thresholds yielding data sets with three different incidences, and (3) NDL data with polygenic and QTL effects reduced by a proportion equal to the ratio of the heritabilities on the binary versus NDL scale (reduced-NDL). Binary data were simulated with and without systematic environmental (herd) effects in an unbalanced design. GIM and RIM gave similar power to detect the QTL and similar estimates of QTL location, effects and variances. Presence of fixed effects caused differences in bias between RIM and GIM, where GIM showed smaller bias which was affected less by incidence. The original NDL data had higher power and lower bias in QTL parameter estimates than binary and reduced-NDL data. RIM for reduced-NDL and binary data gave similar power and estimates of QTL parameters, indicating that the impact of the binary nature of data on QTL analysis is equivalent to its impact on heritability.

Algorithms↗
PubMed1997

Linearly divergent treatment effects in clinical trials with repeated measures: efficient analysis using summary statistics.

In many randomized clinical trials with repeated measures of a response variable one anticipates a linear divergence over time in the difference between treatments. This paper explores how to make an efficient choice of analysis based on individual patient summary statistics. With the objective of estimating the mean rate of treatment divergence the simplest choice of summary statistic is the regression coefficient of response on time for each subject (SLOPE). The gains in statistical efficiency imposed by adjusting for the observed pre-treatment levels, or even better the estimated intercepts, are clarified. In the process, we develop the optimal linear summary statistic for any repeated measures design with assumed known covariance structure and shape of true mean treatment difference over time. Statistical power considerations are explored and an example from an asthma trial is used to illustrate the main points.

Analysis of Variance↗
PubMed1994

High-risk studies are influenced by indirect range restriction.

High-risk studies select subjects who are at high risk for existing or future disease. Therefore, the range of disease is restricted in high-risk studies. This paper shows that high-risk studies are vulnerable to a particular type of range restriction referred to as indirect range restriction. A simulation study is used to illustrate the effects of indirect range restriction on high-risk studies. The results suggest that indirect range restriction can have a substantial impact on the results of high-risk studies. In addition, a review of several areas of behavioral medicine research suggests that high-risk studies have produced many misleading findings. The range restriction approach can be used to estimate statistical power in high-risk studies, interpret the results of high-risk studies, and design future high-risk studies.

Coronary Disease↗
PubMed2004

Schneiderian first rank symptoms predict poor outcome within first episode manic psychosis.

BACKGROUND: The validity of a sub-classification of affective psychosis according to the mood congruence of psychotic features has been questioned in the literature. While some authors have found a correlation between such symptoms and outcome, their predictive value was rather limited in these studies. METHOD: Prospective study of 108 subjects presenting with a first DSM-III-R manic episode with psychotic features to determine the frequency of different types of psychotic symptoms and to measure the predictive utility of mood incongruent psychotic symptoms (MIPS) and first-rank Schneiderian symptoms (FRSS) during the first episode for a 12-month outcome. Outcome was measured by the level of positive, negative, depressive symptoms, and psychosocial functioning. Duration of affective and psychotic symptoms was also assessed. RESULTS: Patients presented with a wide variety of psychotic symptoms. The presence of MIPS at baseline was significantly correlated with a longer persistence of psychotic symptoms, but not with poorer outcome at 12 months. By contrast, the presence of FRSS at baseline was significantly associated with earlier onset of psychosis as well as increased severity of negative symptoms and poorer psychosocial functioning after 12 months. CONCLUSION: The presence of FRSS during a first manic episode with psychotic features identifies a sub-group of patients with more severe presentation and poorer short-term outcome. These results question the prognostic utility of MIPS. LIMITATIONS: Despite the relatively large number of subjects compared with other studies, the statistical power to detect all but large effect sizes is limited by the sample size.

Adult↗
PubMed1998

A randomized trial of three antibiotic regimens for the treatment of pyelonephritis in pregnancy.

OBJECTIVE: To compare the effectiveness of three antibiotic regimens for the treatment of acute pyelonephritis in pregnancy. METHODS: One hundred seventy-nine pregnant women earlier than 24 weeks' gestation who had acute pyelonephritis were randomized to 1) intravenous (i.v.) ampicillin and gentamicin, 2) i.v. cefazolin, or 3) intramuscular ceftriaxone. All participants then completed 10-day courses of oral cephalexin after primary treatment. A urine culture was performed on admission and 5-14 days after completion of therapy. Surveillance for persistent or recurrent infection and obstetric complications continued until delivery. On the basis of a two-sided hypothesis test and with alpha = .025, 60 subjects were needed in each group for statistical power greater than 80% to detect a difference between ceftriaxone and other antibiotics if hospital length of stay differed by 1 or more days. RESULTS: The treatment groups were similar in age, parity, temperature, gestational age, and initial white blood cell count. There were no statistically significant differences in length of hospitalization, hours until becoming afebrile, days until resolution of costovertebral angle tenderness, or infecting organism. There were no statistically significant differences in birth outcomes between the three groups. The average (standard deviation) age at delivery was 38.8 +/- 3.6 weeks. The average birth weight was 3274 +/- 523 g. Eleven (6.9%) of 159 subjects delivered prematurely. Escherichia coli was the most common uropathogen isolated (137 of 179, 76.5%). Blood cultures were positive for organisms in 15 cases (8.4%). At follow-up examination within 2 weeks of initial therapy, eight (5.0%) of 159 subjects had urine cultures positive for organisms. Ten women (6.3%) had cultures positive for organisms later in their antepartum course, and 10 other participants (6.3%) developed recurrent pyelonephritis. CONCLUSION: There are no significant differences in clinical response to antimicrobial therapy or birth outcomes among subjects treated with ampicillin and gentamicin, cefazolin, or ceftriaxone for acute pyelonephritis in pregnancy before 24 weeks' gestation.

Acute Disease↗
PubMed1994

Multisite clinical trials in alcoholism treatment research: organizational, methodological and management issues.

Multisite clinical trials have two major advantages over single-site studies: the large sample size of multisite studies allows for adequate statistical power and better representativeness of the population being studied. However, they are more complex to implement than single-site studies. This article reviews previous multisite clinical trials of alcohol abuse and alcoholism, reasons for selecting a multisite design, management of such studies, and some statistical issues.

Alcoholism↗
PubMedDate not supplied

[Statistical processing of non-response in transversal epidemiological studies].

In epidemiological surveys, non-response constitutes a great limitation due to the loss of validity and statistical power it represents, whether such a loss occurs due to partial participation (the individual fails to answer certain variables) or due to total lack of participation (the individual does not answer any variable). This paper reviews the scientific literature on the different methods to process statistic data when non-response has occurred in non-longitudinal studies, so as to counteract their effect in such studies. Most statistical methods focus on dealing with partial participation (missing data). These methods, of which there is a great variety, can be classified into two large groups: imputation and complete data. For accurate selection of the study method, it is necessary to study the data matrix beforehand, observing the missing data generation mechanism, as well as the proportion they represent of the total data.

Cross-Sectional Studies↗
PubMed2005

Does loading time affect implant survival? A meta-analysis of 1,266 implants.

BACKGROUND: Considerable controversy exists as to whether immediate or early implant loading is associated with a higher failure rate compared to conventional loading. Numerous trials conducted have yielded inconsistent results, partly due to low statistical power. Thus, we sought to determine whether combining results from all published trials would provide a better estimate of the impact of implant loading time on survival. METHODS: We carried out a meta-analysis of all previously published prospective trials comparing conventional with early or immediate implant loading. The outcome of interest was implant failure rate. The Q statistics test was used to assess the presence of heterogeneity. We identified relevant studies through a search of the MEDLINE database and the Cochrane Registry of Controlled Trials. RESULTS: We found 13 prospective trials (1,266 implants) in which early or immediate implant loading was compared to conventional loading. Overall there was no difference in implant failure rate between loading techniques (odds ratio [OR] 0.91; 95% CI: 0.41 to 2.03; P=0.41). Implant failure occurred slightly, although not statistically significant, less often with early implant loading (OR 0.52; 95% CI: 0.22 to 1.24; P=0.07). Immediate implant loading was associated with slightly, although not statistically significant, worse outcomes (OR 1.26; 95% CI: 0.38 to 4.13; P=0.35). Pooling of randomized controlled trials (RCTs) confirmed these results. CONCLUSIONS: In a meta-analysis of 13 prospective trials, early implant loading was not associated with worse outcomes compared to conventional loading. Further evaluations in adequately powered large prospective trials are needed to confirm these findings.

Controlled Clinical Trials as Topic↗
PubMed2007

Validity and power in hemodynamic response modeling: a comparison study and a new approach.

One of the advantages of event-related functional MRI (fMRI) is that it permits estimation of the shape of the hemodynamic response function (HRF) elicited by cognitive events. Although studies to date have focused almost exclusively on the magnitude of evoked HRFs across different tasks, there is growing interest in testing other statistics, such as the time-to-peak and duration of activation as well. Although there are many ways to estimate such parameters, we suggest three criteria for optimal estimation: 1) the relationship between parameter estimates and neural activity must be as transparent as possible; 2) parameter estimates should be independent of one another, so that true differences among conditions in one parameter (e.g., hemodynamic response delay) are not confused for apparent differences in other parameters (e.g., magnitude); and 3) statistical power should be maximized. In this work, we introduce a new modeling technique, based on the superposition of three inverse logit functions (IL), designed to achieve these criteria. In simulations based on real fMRI data, we compare the IL model with several other popular methods, including smooth finite impulse response (FIR) models, the canonical HRF with derivatives, nonlinear fits using a canonical HRF, and a standard canonical model. The IL model achieves the best overall balance between parameter interpretability and power. The FIR model was the next-best choice, with gains in power at some cost to parameter independence. We provide software implementing the IL model.

Brain↗
PubMed2004

Random field-union intersection tests for EEG/MEG imaging.

Electrophysiological (EEG/MEG) imaging challenges statistics by providing two views of the same spatiotemporal data: topographic and tomographic. Until now, statistical tests for these two situations have developed separately. This work introduces statistical tests for assessing simultaneously the significance of spatiotemporal event-related potential/event-related field (ERP/ERF) components and that of their sources. The test for detecting a component at a given time instant is provided by a Hotelling's T(2) statistic. This statistic is constructed in such a manner to be invariant to any choice of reference and is based upon a generalized version of the average reference transform of the data. As a consequence, the proposed test is a generalization of the well-known Global Field Power statistic. Consideration of tests at all time instants leads to a multiple comparison problem addressed by the use of Random Field Theory (RFT). The Union-Intersection (UI) principle is the basis for testing hypotheses about the topographic and tomographic distributions of such ERP/ERF components. The performance of the method is illustrated with actual EEG recordings obtained from a visual experiment of pattern reversal stimuli.

Algorithms↗
PubMed2006

The use of random controls in genetic association studies.

BACKGROUND: The optimal control sample would be ethnically-matched and at minimal risk of developing the disease. Alternatively, one could collect random individuals from the population or select individuals to reduce the number of at-risk individuals in the sample. The effect of randomly selected individuals in a control sample on the statistical power and the odds ratio estimate was investigated. METHODS: Case and control genotype distributions were simulated using standard genetic models with an additional term representing the proportion of unidentified cases in the control sample. Power and odds ratio were calculated from the genotype distributions generated under different sampling scenarios using established methods. RESULTS: Random sampling of controls resulted in a loss in power and a reduction in the odds ratio estimate to a degree that is determined by the proportion of random sampling and the prevalence of the disease. Random sampling resulted in a 19% loss in power for a disease having prevalence of 0.20, compared to a control sample that contained no at-risk individuals. Having random controls results in a decrease in the odds ratio estimate. CONCLUSIONS: Investigators planning case-control genetic association studies should be aware of the statistical costs of different ascertainment approaches.

Alleles↗
PubMed2005

Application of the propensity score in a covariate-based linkage analysis of the Collaborative Study on the Genetics of Alcoholism.

BACKGROUND: Covariate-based linkage analyses using a conditional logistic model as implemented in LODPAL can increase the power to detect linkage by minimizing disease heterogeneity. However, each additional covariate analyzed will increase the degrees of freedom for the linkage test, and therefore can also increase the type I error rate. Use of a propensity score (PS) has been shown to improve consistently the statistical power to detect linkage in simulation studies. Defined as the conditional probability of being affected given the observed covariate data, the PS collapses multiple covariates into a single variable. This study evaluates the performance of the PS to detect linkage evidence in a genome-wide linkage analysis of microsatellite marker data from the Collaborative Study on the Genetics of Alcoholism. Analytical methods included nonparametric linkage analysis without covariates, with one covariate at a time including multiple PS definitions, and with multiple covariates simultaneously that corresponded to the PS definitions. Several definitions of the PS were calculated, each with increasing number of covariates up to a maximum of five. To account for the potential inflation in the type I error rates, permutation based p-values were calculated. RESULTS: Results suggest that the use of individual covariates may not necessarily increase the power to detect linkage. However the use of a PS can lead to an increase when compared to using all covariates simultaneously. Specifically, PS3, which combines age at interview, sex, and smoking status, resulted in the greatest number of significant markers identified. All methods consistently identified several chromosomal regions as significant, including loci on chromosome 2, 6, 7, and 12. CONCLUSION: These results suggest that the use of a propensity score can increase the power to detect linkage for a complex disease such as alcoholism, especially when multiple important covariates can be used to predict risk and thereby minimize linkage heterogeneity. However, because the PS is calculated as a conditional probability of being affected, it does require the presence of observed covariate data on both affected and unaffected individuals, which may not always be available in real data sets.

Alcoholism↗
PubMed1993

Sample size calculation, power analysis and randomization: research project design in Windows.

Single estimates of sample size for a study may be easily obtained by use of a hand calculator or from published tables. In contrast, performing multiple calculations is a tedious and time-consuming task, which is greatly simplified by a computer program. The computer program presented here assists the investigator in calculating sample size estimates, determining statistical power and creating randomization tables for a study. The program is designed primarily for clinical trials and thus includes some features not found in other software packages performing similar tasks. Sample size calculation and power analysis are performed for dichotomous, continuous (parametric and non-parametric tests) and time-to-failure (exponential distribution and log-rank test) response variables, and for correlation coefficients. Sample size estimates and significance levels may be adjusted for multiple participating centers, non-compliance, interim analyses and.multiple testing. The randomization subroutine generates tables for studies with up to nine treatment arms and with any valid block size. As a Windows application, the program runs in a multitasking environment, allowing switching between programs and easy pasting of results into word-processing documents and other applications. It is very simple to use, with a completely menudriven interface and sufficient built-in help to obviate the use of a manual.

Algorithms↗
PubMedDate not supplied

Implications of overviews of randomized trials.

Many randomized trials are of insufficient sample size to detect with adequate power the small to moderate effects that are most likely to occur. As a result, a single such trial can produce a null finding that is, in fact, uninformative, but none the less is misinterpreted as demonstrating no effect. An overview considers all available trials and can increase the statistical power to detect an effect if present. Thus overviews can provide perhaps the most precise estimate of the magnitude of a treatment effect based on existing data. This may have implications for the formulation of public policy but certainly should influence the conduct and planning of randomized trials. Public policy may be influenced in circumstances where further trials are unlikely to be conducted. Overviews can also provide guidance as to whether changes in protocols of ongoing studies are recommended as a result of new evidence. Perhaps most importantly, overviews can provide information about whether additional trials are warranted, and, if so, the sample size that would be required to answer the research question definitively.

Clinical Trials as Topic↗