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 721 records · Page 40Linked to original sources
PubMed1982

A comment on confusion in open-field studies: abuse of null-hypothesis significance test.

The confusion in open-field studies which has resulted from a misinterpretation of statistical results was examined. Several discrepant results obtained on the basis of significance tests have revealed that the discrepancy was not so serious as had been thought. Examples of highly reliable but substantially small experimental effects were presented to indicate the erroneous impression given. The expectation that consistent results can always be obtained from even a small sample size was criticized. In order to reduce some of this confusion, the use of strength of association (eta2) together with consideration for statistical power in the interpretation of open-field results was recommended.

Analysis of Variance↗
PubMedDate not supplied

Principles and pitfalls in the analysis of prenatal treatment effects in multiparous species.

Developmental studies often assess the effect of treatment of the pregnant mother on offspring. The use of multiparous species such as rats and mice in such studies creates a special set of design and analysis problems. These arise for two reasons. First, the availability of many offspring per litter tempts the experimenter to inflate sample size by treating scores from several pups per litter as independent observations. Second, large litter size seldom makes it practical to measure exposure effects in all offspring of an exposed dam. Such studies commonly involve two-stage sampling: Drawing a random sample of dams for treatment, then drawing a second sample of pups per dam for neurobehavioral measurements. In this article, such sampling was modeled by two different simulations. The first, a standard Monte-Carlo approach, sampled from random-normal distributions for litter mean and within-litter variability. The second simulation sampled without replacement from actual data on weight of all pups in a series of 39 nontreated rat litters. These mutually-supportive approaches demonstrate that litter effects, even over as few as three litters, are generally large and statistically meaningful. Consequently, statistical significance tests are sensitive to litter effects. Inflation of sample size by treating as few as 2 pups per litter as independent measurements can almost triple the nominal 0.05 alpha level. Furthermore, two-stage sampling increases the within-treatment error term and correspondingly reduces statistical power relative to one-stage sampling.(ABSTRACT TRUNCATED AT 250 WORDS)

Analysis of Variance↗
PubMed2001

Effects of study duration, frequency of observation, and sample size on power in studies of group differences in polynomial change.

Consider a study in which 2 groups are followed over time to assess group differences in the average rate of change, rate of acceleration, or higher degree polynomial effect. In designing such a study, one must decide on the duration of the study, frequency of observation, and number of participants. The authors consider how these choices affect statistical power and show that power depends on a standardized effect size, the sample size, and a person-specific reliability coefficient. This reliability, in turn, depends on study duration and frequency. These relations enable researchers to weigh alternative designs with respect to feasibility and power. The authors illustrate the approach using data from published studies of antisocial thinking during adolescence and vocabulary growth during infancy.

Adolescent↗
PubMed1996

Design and analysis of studies evaluating smoking cessation interventions where effects vary between practices or practitioners.

BACKGROUND: Patients grouped together in practices may share characteristics that cause them to have similar responses to an intervention. Sampling from such groups means that the power of a trial is less than when subjects are selected from the population at random. Knowledge of likely variation in outcome at the practice level is necessary to calculate the extent to which sample size would need to be inflated to maintain statistical power in the face of 'cluster effects'. OBJECTIVES: To plan sample size and precision requirements of a clinical trial, we examined reports of primary care smoking cessation trials for information on outcomes at the level of clusters, and found them unhelpful. We therefore constructed hypothetical scenarios to quantity the potential importance of this effect. METHOD: Scenarios of moderate and large inter cluster variation were compared with a sample where there was no difference in effect size at the level of practices. RESULTS: A study with 80% power to detect a difference of 20% versus 10% at a 5% significance level would need 200 patients in each arm in the absence of cluster effects. With moderate variation in outcome between clusters, over a thousand patients would be needed in the study to maintain this precision. With larger inter-cluster variation, close to 4000 subjects would be required. CONCLUSIONS: In the absence of detailed data from previous studies, hypothetical models can give insight into the statistical implications of possible cluster effects on study design and analysis. With even moderate inter-cluster variation, sample size will have to be inflated considerably to maintain the same statistical precision. Workers in this field will greatly assist those planning future research if they publish details of variation in outcome at the level of clusters.

Chi-Square Distribution↗
PubMed1993

Breast Cancer Detection Demonstration Project data can determine whether the prognosis of breast cancer is affected by the time of surgery during the menstrual cycle.

The purpose of this study was to determine the feasibility of using Breast Cancer Detection Demonstration Project (BCDDP) data to ascertain whether the prognosis of breast cancer in premenopausal women is affected when surgery is performed relative to the different phases of the menstrual cycle. In the Louisville BCDDP only 40 cases were available for study, but even with this small number, the data indicate that survivorship was superior when the surgery was performed between days 7-20 of the menstrual cycle (P < 0.06). One thousand eighty-seven premenopausal women underwent surgery for breast cancer during the first 5 years of the national BCDDP, beginning in 1972. This large number of cases, plus the long period of follow-up should provide sufficient statistical power for us to evaluate if there is any relationship between the day of the menstrual cycle, the day surgery was performed, and prognosis. This feasibility study indicates that these women should be followed up and the appropriate statistical studies should be done.

Adult↗
PubMed2004

A single institutional phase III trial of preoperative chemotherapy with hyperfractionation radiotherapy plus surgery versus surgery alone for resectable esophageal squamous cell carcinoma.

BACKGROUND: We conducted a prospective randomized controlled trial comparing surgery alone (S) with concurrent chemoradiotherapy followed by surgery (CRT-S) for resectable esophageal squamous cell carcinoma (SCC) based on our previous report. PATIENTS AND METHODS: One hundred and one patients with stage II/III esophageal SCC were randomized to receive either S (50 patients) or CRT-S (51 patients). The chemoradiotherapy (CRT) consisted of cisplatin 60 mg/m(2) intravenously (i.v.) on day 1, 5-fluorouracil (5-FU) 1000 mg/m(2) i.v. on days 2-5, cisplatin 60 mg/m(2) i.v. on day 22 combined with radiation therapy (45.6 Gy, 1.2 Gy b.i.d. on days 1-28). Surgery was performed 3-4 weeks after radiotherapy was completed. For patients with disease that was stable or responsive to CRT, three additional cycles of chemotherapy (cisplatin 60 mg/m(2) i.v. on day 1, 5-FU 1000 mg/m(2) on days 2-5 every 4 weeks) were given after surgical resection. RESULTS: The median age was 62 years. The toxicity of CRT was acceptable and did not affect the post-operative morbidity and the duration of hospital stay. Clinical response was 86% including 21% of complete response (CR) rate. Pathological CR was achieved in 43% [95% confidence interval (CI) 27-59] of the patients who underwent surgery after CRT. At a median follow-up of 25 months, median overall survival (OS) was 27.3 months in S and 28.2 months in CRT-S (P = 0.69). Event-free survival (EFS) at 2 years was 51% in S and 49% in CRT-S (P = 0.93). This trial, which was statistically powered to detect a relatively large difference in 2-year survival rate from 30% to 50% with 80% power, was discontinued at interim analysis because of the unexpectedly high drop-out rate for esophagectomy (31%) and resultant excessive locoregional failure rate in CRT-S arm (22% versus 12%, P = 0.31), though it was not statistically significant. CONCLUSION: Although preoperative CRT induced high clinical and pathological response, there was no statistically significant benefit in OS and EFS.

Adult↗
PubMed2001

Graphical representation of a generalized linear model-based statistical test estimating the fit of the single-hit Poisson model to limiting dilution assays.

Standardized statistical and graphical methods for analysis of limiting dilution assays are highly desirable to enable investigators to compare and interpret results and conclusions with greater accuracy and precision. According to these requirements, we present in this work a powerful statistical slope test that estimates the fit of the single-hit Poisson model to limiting dilution experiments. This method is readily amenable to a graphical representation. This slope test is obtained by modeling limiting dilution data according to a linear log-log regression model, which is a generalized linear model specially designed for modeling binary data. The result of the statistical slope test can then be graphed to visualize whether the data are compatible or not with the single-hit Poisson model. We demonstrate this statistical test and its graphical representation by using two examples: a real limiting dilution experiment evaluating the growth frequency of IL-2-responsive tumor-infiltrating T cells in a malignant lymph node involved by a B cell non-Hodgkin's lymphoma, and a simulation of a limiting dilution assay corresponding to a theoretical non-single-hit Poisson model, suppressor two-target Poisson model.

Allergy and Immunology↗
PubMed1992

Withdrawal censoring and the sequential logrank procedure.

The effects of withdrawal censoring on the power of the group sequential logrank procedure are examined in the context of survival studies. Special attention is given to an assumption that the withdrawal censoring mechanism is only conditionally independent of survival time. Simulation studies of two-sample, fixed duration trials, under random right censoring, staggered entry and exponential life times, reveal a general decrease in statistical power that is most pronounced when the withdrawals are unbalanced, the majority occurring in the group with the higher hazard rate. Generally, this decrease in power is not of practical concern under typical withdrawal rates except when conditional independence is present in which case large fluctuations in power and type I error rates can occur.

Clinical Trials as Topic↗
PubMedDate not supplied

Contrasts and correlations in theory assessment.

OBJECTIVE: To describe a systematic quantitative approach to assessing the predictions made by competing theories using contrasts and correlational indices of effect sizes. METHODS: We illustrate the use of the contrast F and t to compare and combine predictions when the raw data are continuous scores, and z contrasts when working with frequencies in 2 x k tables of counts. RESULTS: The traditional effect size correlation indicates the magnitude of the effect on individual scores of participants' assignment to particular conditions. The contrast correlation obtained from the contrast F or t is, in some cases, the easiest way of estimating the effect size correlation in designs using more than two groups. The alerting correlation is another way of appraising the predictive power of a contrast and can be used to compute the contrast F from published results when all we have are condition means and the omnibus F from an overall analysis of variance. Omnibus Fs, those with more than 1 df in the numerator, are rarely useful in data analytic work since they address unfocused questions, yielding only vague answers. CONCLUSIONS: Asking focused questions using contrasts increases the clarity of our questions and the clarity and statistical power of our answers.

Adolescent↗
PubMed2006

Randomised controlled trials of conventional antipsychotic versus new atypical drugs, and new atypical drugs versus clozapine, in people with schizophrenia responding poorly to, or intolerant of, current drug treatment.

OBJECTIVES: To determine the clinical and cost-effectiveness of different classes of antipsychotic drug treatment in people with schizophrenia responding inadequately to, or having unacceptable side-effects from, their current medication. DESIGN: Two pragmatic, randomised controlled trials (RCTs) were undertaken. The first RCT (band 1) compared the class of older, inexpensive conventional drugs with the class of new atypical drugs in people with schizophrenic disorders, whose current antipsychotic drug treatment was being changed either because of inadequate clinical response or owing to side-effects. The second RCT (band 2) compared the new (non-clozapine) atypical drugs with clozapine in people whose medication was being changed because of poor clinical response to two or more antipsychotic drugs. Both RCTs were four-centre trials with concealed randomisation and three follow-up assessments over 1 year, blind to treatment. SETTING: Adult mental health settings in England. PARTICIPANTS: In total, 227 participants aged 18-65 years (40% of the planned sample) were randomised to band 1 and 136 (98% of the planned sample) to band 2. INTERVENTIONS: Participants were randomised to a class of drug. The managing clinician selected the individual drug within that class, except for the clozapine arm in band 2. The new atypical drugs included risperidone, olanzapine, quetiapine and amisulpride. The conventional drugs included older drugs, including depot preparations. As in routine practice, clinicians and participants were aware of the identity of the prescribed drug, but clinicians were asked to keep their participating patient on the randomised medication for at least the first 12 weeks. If the medication needed to be changed, the clinician was asked to prescribe another drug within the same class, if possible. MAIN OUTCOME MEASURES: The primary outcome was the Quality of Life Scale (QLS). Secondary clinical outcomes included symptoms [Positive and Negative Syndrome Scale (PANSS)], side-effects and participant satisfaction. Economic outcomes were costs of health and social care and a utility measure. RESULTS: Recruitment to band 1 was less than anticipated (40%) and diminished over the trial. This appeared largely due to loss of perceived clinical equipoise (clinicians progressively becoming more convinced of the superiority of new atypicals). Good follow-up rates and a higher than expected correlation between QLS score at baseline and at follow-up meant that the sample as recruited had 75% power to detect a difference in QLS score of 5 points between the two treatment arms at 52 weeks. The recruitment to band 2 was approximately as planned. Follow-up assessments were completed at week 52 in 81% of band 1 and 87% of band 2 participants. Band 1 data showed that, on the QLS and symptom measures, those participants in the conventional arm tended towards greater improvements. This suggests that the failure to find the predicted advantage for new atypicals was not due to inadequate recruitment and statistical power in this sample. Participants reported no clear preference for either class of drug. There were no statistically significant differential outcomes for participants entering band 1 for reasons of treatment intolerance to those entering because of broadly defined treatment resistance. Net costs over the year varied widely, with a mean of 18,850 pounds sterling in the conventional drug group and 20,123 pounds sterling in the new atypical group, not a statistically significant difference. Of these costs, 2.1% and 3.8% were due to antipsychotic drug costs in the conventional and atypical group, respectively. There was a trend towards participants in the conventional drug group scoring more highly on the utility measure at 1 year. The results for band 2 showed an advantage for commencing clozapine in quality of life (QLS) at trend level (p = 0.08) and in symptoms (PANSS), which was statistically significant (p = 0.01), at 1 year. Clozapine showed approximately a 5-point advantage on PANSS total score and a trend towards having fewer total extrapyramidal side-effects. Participants reported at 12 weeks that their mental health was significantly better with clozapine than with new atypicals (p < 0.05). Net costs of care varied widely, but were higher than in band 1, with a mean of 33,800 pounds sterling in the clozapine group and 28,400 pounds sterling in the new atypical group. Of these costs, 4.0% and 3.3%, respectively, were due to antipsychotic drug costs. The increased costs in the clozapine group appeared to reflect the licensing requirement for inpatient admission for commencing the drug. There was a trend towards higher mean participant utility scores in the clozapine group. CONCLUSIONS: For band 1, there is no disadvantage in terms of quality of life and symptoms, or associated costs of care, over 1 year in commencing conventional antipsychotic drugs rather than new atypical drugs. Conventional drugs were associated with non-significantly better outcomes and lower costs. Drug costs represented a small proportion of the overall costs of care (<5%). For band 2, there is a statistically significant advantage in terms of symptoms but not quality of life over 1 year in commencing clozapine rather than new atypical drugs, but with increased associated costs of care. The results suggest that conventional antipsychotic drugs, which are substantially cheaper, still have a place in the treatment of patients unresponsive to, or intolerant of, current medication. Further analyses of this data set are planned and further research is recommended into areas such as current antipsychotic treatment guidance, valid measures of utility in serious mental illness, low-dose 'conventional' treatment in first episode schizophrenia, QLS validity and determinants of QLS score in schizophrenia, and into the possible financial and other mechanisms of rewarding clinician participation in trials.

Adolescent↗
PubMed1990

Childhood cancer and overhead powerlines: a case-control study.

A case-control study has been carried out to examine the occurrence of childhood cancer in relation to the proximity of overhead power lines to a child's home address at birth and to the calculated magnetic field at the address. The study included 374 cases diagnosed in the Yorkshire Health Region between 1970 and 1979, together with 588 matched controls. Magnetic-field strengths at the birth addresses due to the load currents of overhead power lines were calculated on the basis of line-network maps and load records. The results indicate no association between the occurrence of childhood malignancies and either the proximity or the magnetic fields of overhead lines, although the statistical power of the study was limited by the small numbers of children living close to overhead power lines.

Adolescent↗
PubMed2005

Unbiased estimation of relative reproductive success of different groups: evaluation and correction of bias caused by parentage assignment errors.

Parentage assignment is widely applied to studies on mating systems, population dynamics and natural selection. However, little is known about the consequence of assignment errors, especially when some parents are not sampled. We investigated the effects of two types of error in parentage assignment, failing to assign a true parent (type A) and assigning an untrue parent (type B), on an estimate of the relative reproductive success (RRS) of two groups of parents. Employing a mathematical approach, we found that (i) when all parents are sampled, minimizing either type A or type B error insures the minimum bias on RRS, and (ii) when a large number of parents is not sampled, type B error substantially biases the estimated RRS towards one. Interestingly, however, (iii) when all parents were sampled and both error rates were moderately high, type A error biased the estimated RRS even more than type B error. We propose new methods to obtain an unbiased estimate of RRS and the number of offspring whose parents are not sampled (zW(z)), by correcting the error effects. Applying them to genotypic data from steelhead trout (Oncorhynchus mykiss), we illustrated how to estimate and control the assignment errors. In the data, we observed up to a 30% assignment error and a strong trade-off between the two types of error, depending on the stringency of the assignment decision criterion. We show that our methods can efficiently estimate an unbiased RRS and zW(z) regardless of assignment method, and how to maximize the statistical power to detect a difference in reproductive success between groups.

Animals↗
PubMed2004

The application of jackknife-based onset detection of lateralized readiness potential in correlative approaches.

The onset of the lateralized readiness potential (LRP) represents an interesting parameter within mental chronometry. According to Miller, Patterson, and Ulrich (1998), reliability increases when LRP onsets are detected in jackknifed LRP waveforms. Until now, jackknifed LRP onsets could be analyzed in factorial designs only. The aim of the present study was to extend the application of jackknifing to correlative approaches (e.g., in personality research). Using different onset scoring techniques, in several simulations run on realistic LRP data jackknifing and single-subject procedures were compared regarding their estimates of a simulated true correlation. For all scoring techniques but regression, jackknifed coefficients were on average higher than the respective single-subject coefficients, and statistical power was higher. Overall, combining jackknifing with a 50%-relative onset criterion is recommended.

Algorithms↗
PubMed2006

Predictors of future anabolic androgenic steroid use.

PURPOSE: To prospectively study the stability of anabolic androgenic steroid (AAS) use and predictors of AAS use, and to investigate whether AAS use alters the risk of later emotional and behavioral problems. METHODS: Survey of a national sample of Norwegian high school students (age 15-19) in 1994 followed up in 1999 (N = 2924). Measures of frequent alcohol intoxication (50+ times per 12 months), cannabis use (12 months), hard drug use (12 months), being offered cannabis, eating problems, conduct problems, sexual debut before age 15, BMI, involvement in power sports, perceived physical appearance, and satisfaction with body parts were obtained. RESULTS: Life-time prevalence of AAS use were 1.9 and 0.8% in the follow-up period. Multivariate logistic regression revealed that future AAS use was predicted by young age, male gender, previous AAS use, involvement in power sports, and frequent alcohol intoxication. AAS use did not predict future emotional or behavioral problems other than reducing the risk of future frequent alcohol intoxication. CONCLUSION: Frequent alcohol intoxication and involvement in power sports appear to predict future AAS use. At the population level there was little stability in individual AAS use from adolescence to early adulthood. No detrimental effects of AAS use could be detected in this study, but low statistical power limits this conclusion.

Adolescent↗
PubMed2003

The genealogy of sequences containing multiple sites subject to strong selection in a subdivided population.

A stochastic model for the genealogy of a sample of recombining sequences containing one or more sites subject to selection in a subdivided population is described. Selection is incorporated by dividing the population into allelic classes and then conditioning on the past sizes of these classes. The past allele frequencies at the selected sites are thus treated as parameters rather than as random variables. The purpose of the model is not to investigate the dynamics of selection, but to investigate effects of linkage to the selected sites on the genealogy of the surrounding chromosomal region. This approach is useful for modeling strong selection, when it is natural to parameterize the past allele frequencies at the selected sites. Several models of strong balancing selection are used as examples, and the effects on the pattern of neutral polymorphism in the chromosomal region are discussed. We focus in particular on the statistical power to detect balancing selection when it is present.

Animals↗
PubMed2000

Genetic structure of reciprocal social behavior.

OBJECTIVE: The study examined the genetic structure of deficits in reciprocal social behavior in an epidemiologic sample of male twins. METHOD: Parents of 232 pairs of 7-15-year-old male twins completed the Social Reciprocity Scale to provide data on their children's reciprocal social behavior. Scale scores were analyzed by using structural equation modeling. RESULTS: Intraclass (twin-twin) correlations for scores on the Social Reciprocity Scale were 0.73 for monozygotic twins (N=98 pairs) and 0.37 for dizygotic twins (N=134 pairs). The best fitting model of causal influences on reciprocal social behavior incorporated additive genetic influences and unique environmental influences. CONCLUSIONS: For school-age boys in the general population, reciprocal social behavior is highly heritable, with a genetic structure similar to that reported for autism in clinical samples. Continuous measures of reciprocal social behavior may be useful for characterizing the broader autism phenotype and may enhance the statistical power of genetic studies of autism.

Adolescent↗
PubMed2004

Spatiotemporal analysis of event-related fMRI data using partial least squares.

Partial least squares (PLS) has proven to be a important multivariate analytic tool for positron emission tomographic and, more recently, event-related potential (ERP) data. The application to ERP incorporates the ability to analyze space and time together, a feature that has obvious appeal for event-related functional magnetic resonance imaging (fMRI) data. This paper presents the extension of spatiotemporal PLS (ST-PLS) to fMRI, explaining the theoretical foundation and application to an fMRI study of auditory and visual perceptual memory. Analysis of activation effects with ST-PLS was compared with conventional univariate random effects analysis, showing general consensus for both methods, but several unique observations by ST-PLS, including enhanced statistical power. The application of ST-PLS for assessment of task-dependent brain-behavior relationships is also presented. Singular features of ST-PLS include (1) no assumptions about the shape of the hemodynamic response functions (HRFs); (2) robust statistical assessment at the image level through permutation tests; (3) protection against outlier influences at the voxel level through bootstrap resampling; (4) flexible analytic configurations that allow assessment of activation difference, brain-behavior relations, and functional connectivity. These features enable ST-PLS to act as an important complement to other multivariate and univariate approaches used in neuroimaging research.

Acoustic Stimulation↗
PubMed2001

Polymorphism in codon 17 of the CTLA-4 gene (+49 A/G) is not associated with susceptibility to rheumatoid arthritis in British Caucasians.

The role of the CTLA-4 antigen in the development of autoimmune diseases is well documented, with several autoimmune disorders showing association or linkage with the CTLA-4 locus. Its role in the aetiology of rheumatoid arthritis (RA) however, remains unclear, as the functional studies of the B7-CTLA-4 pathway in mouse models of RA and genetic studies in humans have given contrasting results. We have studied the single nucleotide polymorphism at position +49 (A/G) of the CTLA-4 gene, in a cohort of 421 RA cases and 452 healthy controls from the UK. Despite the high statistical power to detect even a weak susceptibility effect, no significant association was found. We also analysed the distribution of the allele and genotype frequencies with respect to the presence of the shared epitope (a known RA susceptibility factor) and found no statistically significant differences. We conclude that, although the importance of the B7-CTLA-4 interaction in the development of RA can not be excluded, the CTLA-4 gene is unlikely to be a predisposing factor to this disease.

Abatacept↗