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 703 records · Page 39Linked to original sources
PubMed2004

Factorial designs: a graphical aid for choosing study designs accounting for interaction.

The presence of possible treatment interaction when designing a factorial study can be either greeted with dismay (for an antagonistic or negative interaction) or can be welcome (in the case of a synergistic effect). The type of potential interaction may greatly influence the choice of study design. Depending on the magnitude of an expected additive or multiplicative interaction, a three-arm study, instead of a 2 x 2 factorial, may yield greater statistical power. A graphical aid for examining the loss of power due to the presence of such interaction is developed. The technique can also be applied to designing studies where prespecified subgroup analyses are of particular interest. Tests for interaction effects between subgroups are usually underpowered, even if the subgroups have been prespecified in the protocol. The technique can be used to determine the appropriate sample sizes in the subgroups to ensure adequate power to detect potential interaction effects. The method is illustrated with respect to a published 2 x 2 factorial study. In this study, interaction reduced the power of the final analysis to detect significant main effects.

Clinical Trials as Topic↗
PubMed1997

Clinical trial designs for testing of products for dentine hypersensitivity--a review.

Dentine hypersensitivity (DH) is a perplexing clinical entity. There is no doubt that patients self-report discomfort arising from various stimuli, but the highly subjective nature of the condition makes it extremely difficult to evaluate DH objectively. This is particularly true when evaluating the efficacy of desensitizing agents in the clinical trial setting. This paper attempts to provide an overview on clinical trial management to evaluate both in-office and over-the-counter (OTC) desensitizing agents. The importance of correct clinical trial design (type, allocation, blinding) with emphasis on patient selection, sample size, statistical power, duration, choice of positive/negative controls, treatment outcomes, and data collection, will be discussed.

Clinical Trials as Topic↗
PubMed1999

A relative power table for nested matched case-control studies.

OBJECTIVE: To calculate relative powers for nested case-control studies for different values of both relative risk and numbers of controls per case, given a fixed number of cases available for analysis. METHODS: Algebraic and numerical methods. RESULTS: In nested case-control studies, statistical power is a function of relative risk, rarity of exposure, number of case-control sets, and the number of controls per case. CONCLUSION: The dictum that sufficient power will be obtained in a nested case-control study by selecting only four controls per case cannot be sustained. Appropriate numbers need to be calculated for specific studies.

Case-Control Studies↗
PubMed2005

EEG nonstationarity during intracranially recorded seizures: statistical and dynamical analysis.

OBJECTIVE: The investigation of nonstationarity in complex, multivariable signals, such as electroencephalographic (EEG) recordings, requires the application of different and novel approaches to analysis. In this study, we have divided the EEG recordings during epileptic seizures into sequential stages using spectral and statistical analysis, and have as well reconstructed discrete-time models (maps) that reflect dynamical (deterministic) properties of the EEG voltage time series. METHODS: Intracranial human EEG recordings with epileptic seizures from three different subjects with medically intractable temporal lobe epilepsy were studied. The methods of statistical (power spectra, wavelet spectra, and one-dimensional probability distribution functions) and dynamical (comparison of dynamical models) nonstationarity analysis were applied. RESULTS: Dynamical nonstationarity analysis revealed more detailed inner structure within the seizures than the statistical analysis. Three or four stages with different dynamics are typically present within seizures. The difference between interictal activity and seizure events was also more evident through dynamical analysis. CONCLUSIONS: Nonstationarity analysis can reveal temporal structure within an epileptic seizure, which could further understanding of how seizures evolve. The method could also be used for identification of seizure onset. SIGNIFICANCE: Our approach reveals new information about the temporal structure of seizures, which is inaccessible using conventional methods.

Electroencephalography↗
PubMed2003

Empirical analyses of null-hypothesis perfusion FMRI data at 1.5 and 4 T.

Functional magnetic resonance imaging (fMRI) based on arterial spin labeling (ASL) perfusion contrast is an emergent methodology for visualizing brain function both at rest and during task performance. Because of the typical pairwise subtraction approach in generating perfusion images, ASL contrast manifests different noise properties and offers potential advantages for some experimental designs as compared with blood oxygenation-level-dependent (BOLD) contrast. We studied the noise properties and statistical power of ASL contrast, with a focus on temporal autocorrelation and spatial coherence, at both 1.5- and 4.0-T field strengths. Perfusion fMRI time series were found to be roughly independent in time, and voxelwise statistical analysis assuming independence of observations yielded false-positive rates compatible with theoretical values using appropriate analysis methods. Unlike BOLD fMRI data, perfusion data were not found to have spatial coherence that varied across temporal frequency. This finding has implications for the application of spatial smoothing to perfusion data. It was also found that the spatial coherence of the ASL data is greater at high magnetic field than low field, and including the global signal as a covariate in the general linear model improves the central tendency of test statistic as well as reduces the noise level in perfusion fMRI, especially at high magnetic field.

Artifacts↗
PubMed2001

Design and power of a population pharmacokinetic study.

PURPOSE: This paper investigated the influence of critical design factors on the power of a population pharmacokinetic (PK) study for identifying subpopulations that have different drug clearance than the typical population. METHODS: A study simulation approach was used for the power estimation. The design factors included the number of subjects, sampling scheme, and compliance. RESULTS: The false positive rates of incorrectly identifying a subpopulation were estimated for several scenarios. The false positive rates of the population PK study was relatively low, except when the numbers of subjects with full profiles and the subjects with troughs were distributed between populations in an unbalanced manner. The total number of subjects did not seem to have as much influence on study power as the number of subjects in the subpopulation, as long as the total number of subjects was significantly larger than the subpopulation. The variability of sampling time played an important role in both the statistical power and the accuracy of the estimated difference in clearance. Taking three samples provided greater power and better accuracy than taking two samples per subject. Taking only trough samples provided little power and poor estimation of clearance difference. Adding subjects with full profiles to a study with only trough samples taken in other subjects did not satisfactorily improve the clearance estimation. It was critical to account for dosing record in the population PK analysis to achieve appropriate power and accuracy. If the variability in dosing time was accounted for in the analysis, it improved the accuracy of the estimated difference in clearance. Missing dose administrations reduced the study power and resulted in deviation of estimated clearance difference. CONCLUSIONS: The power of a study should be determined prospectively to ensure appropriate study design for specific study objectives.

Absorption↗
PubMed2005

Use and Impact of eHealth System by Low-income Women With Breast Cancer.

This article is the second of a two-part series reporting on a population-based study intended to use an eHealth system to examine the feasibility of reaching underserved women with breast cancer (Gustafson, McTavish et al., Reducing the digital divide for low-income women with breast cancer, 2004; Madison Center for Health Systems Research and Analysis, University of Wisconsin; Comprehensive Health Enhancement Support System [CHESS]) and determine how they use the system and what impact it had on them. Participants included women recently diagnosed with breast cancer whose income was at or below 250% of poverty level and were living in rural Wisconsin (n = 144; all Caucasian) or Detroit (n = 85; all African American). Because this was a population-based study all 229 participants received CHESS. A comparison group of patients (n = 51) with similar demographics was drawn from a separate recently completed randomized clinical trial. Use rates (e.g., frequency and length of use as well as type of use) as well as impact on several dimensions of quality of life and participation in health care are reported. Low-income subjects in this study logged on and spent more time on CHESS than more affluent women in a previous study. Urban African Americans used information and analysis services more and communication services less than rural Caucasians. When all low-income women from this study are combined and compared with a low-income control group from another study, the CHESS group was superior to that control group in 4 of 8 outcome variables at both statistically and practically significant levels (social support, negative emotions, participation in health care, and information competence). When African Americans and Caucasians are separated the control group's sample size becomes 30 and 21 thus reducing power. Statistical significance is retained, however, in all four outcomes for Caucasians and in two of four for African Americans. Practical significance is retained for all four outcomes. We conclude that an eHealth system like CHESS will be used extensively and have a positive impact on low-income women with breast cancer.

Breast Neoplasms↗
PubMed1995

Continuous response variable trial design in motor neuron disease: long term treatment with a TRH analogue (RX77368).

The continuous response variable controlled trial design is developed as a model for the efficient screening of candidate treatments in motor neuron disease. A TRH analogue (RX77368) and placebo were randomly allocated to 15 matched pairs of patients with motor neuron disease. With validated composite interval scores, this trial excluded a 50% or greater improvement with RX77368 at month 12 in scores of respiratory, lower limb, and activities of daily living function with greater than 90% power, and in bulbar function scores with 80% power. For upper limbs, 52% and 75% improvements were excluded at months 9 and 12 respectively with 80% power. Patients who died during the study had faster deterioration rates in bulbar and respiratory scores than their surviving pairs. The feasibility of screening drugs for significant biological effects with small sample sizes and good statistical power is shown. The difficulties of handling deaths and dropouts when using this design are discussed. Comparisons are made with sample sizes required using other scores and rating scales, as well as with those required in hazard and event rate studies. A simple clinical grading scale for motor neuron disease, with its corresponding composite interval scores, is described.

Adult↗
PubMed2004

Selecting tagging SNPs for association studies using power calculations from genotype data.

Recent studies have indicated that linkage disequilibrium (LD) between single nucleotide polymorphism (SNP) markers can be used to derive a reduced set of tagging SNPs (tSNPs) for genetic association studies. Previous strategies for identifying tSNPs have focused on LD measures or haplotype diversity, but the statistical power to detect disease-associated variants using tSNPs in genetic studies has not been fully characterized. We propose a new approach of selecting tSNPs based on determining the set of SNPs with the highest power to detect association. Two-locus genotype frequencies are used in the power calculations. To show utility, we applied this power method to a large number of SNPs that had been genotyped in Caucasian samples. We demonstrate that a significant reduction in genotyping efforts can be achieved although the reduction depends on genotypic relative risk, inheritance mode and the prevalence of disease in the human population. The tSNP sets identified by our method are remarkably robust to changes in the disease model when small relative risk and additive mode of inheritance are employed. We have also evaluated the ability of the method to detect unidentified SNPs. Our findings have important implications in applying tSNPs from different data sources in association studies.

Algorithms↗
PubMed2005

Maintenance of T1 response as induced during PEG-IFNalpha plus ribavirin therapy controls viral replication in genotype-1 patients with chronic hepatitis C.

OBJECTIVES: To analyze the T1/T2 cytokine profile in CD8 T cells from peripheral blood mononuclear cells from patients with genotype-1 CHC during treatment with pegylated interferon (Peg-IFN) alpha2a plus ribavirin (RBV). To correlate Th1/Th2 balance with virological response. PATIENTS AND METHODS: In this prospective longitudinal study, a total of 28 naïve genotype-1 CHC patients received Peg-IFNalpha2a (180 microg/week) plus RBV (1-1.2 g/day) for 48 weeks. All patients (mean age 45 +/- 8 years) completed treatment and follow-up: 12 (43%) achieved a sustained virological response (SVR), 13 relapsed after end of treatment (47%), and only 3 (10%) were non-responders. Sixteen healthy controls were also analyzed (mean age 39 +/- 17 years). The production of IL-4, IFNgamma, and TNFalpha by CD8 T cells was measured by intracytoplasmic detection using flow cytometry in both resting and stimulated cells with a phorbol ester. STATISTICS: Student's t test for independent values, chi2 test, and ANOVA test were used; relapsers and non-responders were joined to achieve a higher statistical power. RESULTS: At third month during treatment, phorbol ester-stimulated-IL-4 levels tend to be lower in patients who presented with SVR versus those who did not (0.97 vs 2.58; p = 0.1). No statistically significant differences were found in IFNgamma and TNFalpha levels at month 3. At EOT, the stimulated-IFNgamma production was significantly higher in patients with SVR (20 vs. 8; p < 0.05). Conversely, IL-4 production was higher in NR patients although these data did not reach statistical significance (p < 0.1). No significant differences were found in TNFalpha (14 vs. 7; p < 0.2). CONCLUSIONS: Cytokine T1 induced-response maintenance during combination treatment, measured as IFNgamma production by CD8+ T lymphocytes, is associated with SVR and suggests the replication control and later clearance of patients infected by genotype-1 HCV.

Adult↗
PubMedDate not supplied

Crossover studies with continuous variables: power analysis.

The crossover design is a sensitive means of determining the efficacy of new drugs because it eliminates between-subject variability. However, if the response in the first period carries on into the second (carryover effect) or if time factors cannot be kept constant in a lengthy crossover (time effects), its statistical power may be jeopardized. This may be equally true if a negative correlation exists between treatment responses. We recently demonstrated that the crossover design with binary variables is a powerful method even if correlation between treatment responses is negative. Power analysis of crossover trials with continuous variables has not been explicitly studied. Using the Scheffé model for the assessment of treatment effect, carryover effect, and time effect, we drew power curves of hypothesized crossover studies with different levels of correlation between drug response. We demonstrate that the sensitivity of testing is largely dependent on the levels of correlation between drug response. When positive, we have a great deal of sensitivity with which to test treatment effect and little sensitivity to test carryover or time effect. When negative, the opposite is observed. The correlation level in a crossover comparison is a major determinant of the sensitivity of testing. Treatments from one class with one mode of action frequently have a positive correlation and should be particularly considered for crossover comparisons. With treatment comparisons of totally different classes of drugs/modes of action, the opposite is true. It is hoped that this work affects the design of future crossover trials.

Algorithms↗
PubMed1983

Errors, Types I and II.

The practicing physician and the clinical investigator regularly confront therapeutic trials, diagnostic tests, and other hypothesis-testing situations. The clinical literature increasingly displays statistical notations and concepts related to decision making in medicine. For these reasons, the physician is obligated to have some familiarity with the principles behind the null hypothesis, Type I and II errors, statistical power, and related elements of hypothesis testing.

Clinical Laboratory Techniques↗
PubMed1988

Pharmacokinetic evaluation of a sustained-release formulation of trihexyphenidyl in healthy volunteers.

Twenty-four male subjects were randomized to receive two oral dosage forms of trihexyphenidyl HCl (alpha-cyclohexyl-alpha-phenyl-1-piperidinepropanol HCl). The dosage regimens were (1) a 5-mg immediate release (IR) tablet given twice daily at time zero and 12 h later, and (2) two 5-mg sustained-release (SR) capsule formulations given daily. The number of adverse experiences following the SR formulation were approximately 50% of those for the IR formulation, the peak concentration (Cmax) after the SR formulation was significantly lower (p less than 0.05) than that after the first dose of the IR formulation, and the time to reach Cmax (tmax) was significantly longer after the SR formulation (p less than 0.05). The SR formulation maintained serum concentrations above 50, 60, and 70% of Cmax values for average time periods of 11.7, 9.4, and 5.9 h, respectively, compared with values of 1.8, 1.2, and 0.9 h after the IR formulation; the differences were all significant (p less than 0.05). The mean elimination half-life (t1/2) was similar (p greater than 0.05) after the SR (10.1 h) and IR (8.7 h) formulations. The statistical power of the study was 98.1% to detect a 20% difference in the area under the curve from time zero to time infinity (AUC0----infinity) between formulations. Although the AUC0----infinity after the SR formulation was statistically smaller (p less than 0.05) than after the IR tablet, the difference was less than 20%. Therefore, the SR formulation was bioequivalent to the IR tablet formulation of trihexyphenidyl.

Adult↗
PubMed1990

Introduction to biostatistics: Part 3, Sensitivity, specificity, predictive value, and hypothesis testing.

Diagnostic tests guide physicians in assessment of clinical disease states, just as statistical tests guide scientists in the testing of scientific hypotheses. Sensitivity and specificity are properties of diagnostic tests and are not predictive of disease in individual patients. Positive and negative predictive values are predictive of disease in patients and are dependent on both the diagnostic test used and the prevalence of disease in the population studied. These concepts are best illustrated by study of a two by two table of possible outcomes of testing, which shows that diagnostic tests may lead to correct or erroneous clinical conclusions. In a similar manner, hypothesis testing may or may not yield correct conclusions. A two by two table of possible outcomes shows that two types of errors in hypothesis testing are possible. One can falsely conclude that a significant difference exists between groups (type I error). The probability of a type I error is alpha. One can falsely conclude that no difference exists between groups (type II error). The probability of a type II error is beta. The consequence and probability of these errors depend on the nature of the research study. Statistical power indicates the ability of a research study to detect a significant difference between populations, when a significant difference truly exists. Power equals 1-beta. Because hypothesis testing yields "yes" or "no" answers, confidence intervals can be calculated to complement the results of hypothesis testing. Finally, just as some abnormal laboratory values can be ignored clinically, some statistical differences may not be relevant clinically.

Biometry↗
PubMed2005

[Basic concepts in epidemiology and statistics for reading controlled clinical trials].

The authors present the basic concepts in epidemiology and statistics needed for understanding properly the design and results of controlled clinical trials. Through a set of examples, the concepts of measures of association and effect, statistical significance tests, p-value, confidence interval and statistical power are presented and common their misinterpretations are discussed.

Controlled Clinical Trials as Topic↗
PubMed1997

Testing for interaction between maternal smoking and TGFA genotype among oral cleft cases born in Maryland 1992-1996.

OBJECTIVE: Infants born in Maryland between June 1992 and June 1996 were used in a case-control study of nonsyndromic oral clefts to test for effects of maternal smoking and a polymorphic genetic marker at the transforming growth factor alpha (TGFA) locus, both of which have been reported to be risk factors for these common birth defects. DESIGN AND SETTING: Cases were infants with an oral cleft ascertained through three comprehensive treatment centers, with additional ascertainment through a registry of birth defects maintained by the Maryland Health Department. Controls were healthy infants. Medical history information on infants and mothers were collected, along with DNA samples. PATIENTS, PARTICIPANTS: Among 286 cases contacted (72% ascertainment), there were 192 nonsyndromic isolated oral clefts (106 M; 86 F) available for this case-control study. MAIN OUTCOME MEASURES: The largest group of 149 Caucasian nonsyndromic cases and 86 controls was used to test for association with maternal smoking and genotype at the Taq1 polymorphism in TGFA. RESULTS: While this modest sample had limited statistical power to detect gene-environment interaction, there was a significant marginal increase in risk of having an oral cleft if the mother smoked (odds ratio = 1.75, 95% CI = 1.01 to 3.02). We could not demonstrate statistical interaction between maternal smoking and TGFA genotype in this study, however, and the observed increase in the C2 allele among cases was not statistically significant. CONCLUSIONS: We could not confirm either the reported association between oral clefts and TGFA genotype or its interaction with maternal smoking. However, these data do show an increased risk if the mother smoked during pregnancy, and this effect was greatest among infants with a bilateral cleft and no close family history of clefts.

Alleles↗
PubMed2006

Meta-analysis supports association between serotonin transporter (5-HTT) and suicidal behavior.

Suicidal behavior, which ranks among the top 10 causes of death worldwide, is an important public-health problem and a psychiatric disorder, which has been the subject of considerable study. Studies have shown association between the serotonin transporter (5-HTT) gene and suicidal behavior, although a proportion of alternative studies have produced contrary results both in terms of positive and negative findings, possibly reflecting inadequate statistical power and the use of different populations. Using the cumulative data from recent years in both European and, more particularly, Asian populations, this updated meta-analysis seeks to examine whether the aggregate data provide evidence of statistical significance, and to clarify the contradictory findings suggested by previous studies. It covers all published studies using multiple research methods up to January 2006. Compared with a previous meta-analysis, which found no association between the 5-HTTLPR polymorphism and suicidal behavior (P=0.38), the current results (39 studies) suggest a significant association with a P-value of 0.0068 (overall odds ratio=0.88 (0.8,0.97)), and supports the involvement of the brain 5-HTT in the pathogenesis of suicidal behavior.

Depressive Disorder↗
PubMed2000

Minimum risk weights for comparing treatments in stratified binomial trials.

When comparing two treatments in a stratified trial with a binary endpoint, data are commonly analysed using a weighted averaging of the stratum-specific differences between proportions. Two popular sets of weights are the harmonic means of the stratum-specific sample sizes (SSIZE) and the reciprocals of the variances of the stratum-specific differences (INVAR). Either the SSIZE or INVAR weights are chosen and prespecified in the data analysis plan. We show that the 'wrong' choice between SSIZE and INVAR can result in a significantly inefficient analysis. To circumvent this potential problem, we propose a 'minimum risk' (MR) weighting strategy. The easy-to-compute MR weights are designed to yield more precise and less biased estimates of the overall treatment difference relative to the SSIZE and INVAR weights, respectively. We show, via a simulation study, that the proposed weights are an attractive compromise between the SSIZE and INVAR weights in terms of statistical power. Numerical examples are presented to illustrate the utility of the MR weights.

Anti-Arrhythmia Agents↗