Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Statistical power analysis”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

At least 181 records · Page 10Linked to original sources
PubMed1996

Study design in clinical research: sample size estimation and power analysis.

The purpose of this review is to describe the statistical methods available to determine sample size and power analysis in clinical trials. The information was obtained from standard textbooks and personal experience. Equations are provided for the calculations and suggestions are made for the use of power tables. It is concluded that sample size calculations and power analysis can be performed with the information provided and that the validity of clinical investigation would be improved by greater use of such analyses.

Clinical Trials as Topic↗
PubMed2000

State parity legislation and changes in health insurance and perceived access to care among individuals with mental illness: 1996-1998*

BACKGROUND: The 1990's witnessed a new wave of state and federal legislation affecting mental health insurance in the United States. Although patient advocacy groups have hailed the passage of numerous "parity" laws that require insurance coverage for mental illnesses to equal that for physical ailments, it is unclear whether this activity represents a major improvement in insurance benefits among mentally ill or significantly increases their access to care. AIMS: This paper contrasts how insurance coverage has changed among individuals with mental health problems in states with and without parity legislation. METHODS: National survey data from 1996 to 1998, subset to a panel of 1220 individuals exceeding clinical screeners for a mental health disorder. Dependent variables are change in insurance status, insurance generosity and perception of access to care. The analysis contrasts changes in dependent variables between states with and without parity legislation (a difference-in-differences analysis). RESULTS: There are no statistical significant effects of state parity; point estimates suggest that parity mandates are associated with a slightly higher number of mentally ill reporting improved insurance generosity and access to care, but also with a higher number of mentally ill losing all insurance coverage in parity states. The estimated effects are too small to be statistically significant, although the sample size is limited and the study had only good statistical power to detect large effects. DISCUSSION: At the population level, state parity legislation appears to have not had large effects on the insurance coverage of the group that was intended as the primary beneficiary of legislation. Likely reasons include the limited scope of the actual legal requirements and large numbers of mentally ill that are not covered by health insurance subject to such legislation. The results do not exclude the possibility that some subgroups experienced substantial improvements in their insurance coverage. At the population level, large effects experienced by small subgroup are diluted by groups that experienced no similar changes. However, parity legislation was not considered a minor issue by advocates and opponents and this analysis has the statistical power to detect the sizeable differences that were argued in the policy debate. IMPLICATIONS FOR HEALTH POLICIES: While state parity legislation may have improved insurance benefits for some, it appears not to have resulted in substantial improvements for the mentally ill as a whole. The results could be very different, however, if strong federal legislation were passed that has a broader scope than state legislation. IMPLICATIONS FOR RESEARCH: The parity debate provides an important reminder of how little research is available to inform policy. This study provides a crude picture, but it is far from being a conclusive evaluation. The most urgent need is for data that continue to track changes in markets and policies.

Journal Article↗
PubMed1997

Multiple nonprimary motor areas in the human cortex.

We measured the distribution of regional cerebral blood flow with positron emission tomography while three subjects moved their hand, shoulder, or leg. The images were coregistered with each individual's anatomic magnetic resonance scans. The data were analyzed for each individual to avoid intersubject averaging and so to preserve individual gyral anatomy. Instead of inspecting all pixels, we prospectively restricted the data analysis to particular areas of interest. These were defined on basis of the anatomic and physiological literature on nonhuman primates. By examining only a subset of areas, we strengthened the power of the statistical analysis and thereby increased the confidence in reporting single subject data. On the lateral convexity, motor related activity was found for all three subjects in the primary motor cortex, lateral premotor cortex, and an opercular area within the premotor cortex. In addition, there was activation of somatosensory cortex (SI), the supplementary somatosensory area (SII) in the Sylvian fissure, and parietal association areas (Brodmann areas 5 and 40). There was also activation in the insula. We suggest that the activation in the dorsal premotor cortex may correspond with dorsal premotor area (PMd) as described in the macaque brain. We propose three hypotheses as to the probable location of vental premotor area (PMv) in the human brain. On the medial surface, motor-related activity was found for all three subjects in the leg areas of the primary motor cortex and somatosensory cortex and also activity for the hand, shoulder, and leg in the supplementary motor area (SMA) on the dorsal medial convexity and in three areas in the cingulate sulcus. We suggest that the three cingulate areas may correspond with rostral cingulate premotor area, dorsal cingulate motor area (CMAd), and ventral cingulate motor area (CMAv) as identified in the macaque brain. Somatotopic mapping was demonstrated in the primary motor and primary somatosensory cortex. In all three subjects, the arm region lay anterior to the leg region in parietal area 5. Also in all three subjects, the arm region lay anterior to the leg region in the supplementary motor cortex.

Adult↗
PubMed1988

Rehabilitation outcome following initial unilateral hemispheric stroke. Life table analysis approach.

Life table analysis is a powerful statistical tool that has become the preferred technique for studying both the natural history of and the effect of treatment on disease outcome. We have found only one report using life table analysis to study rehabilitation outcome after stroke. We assessed the recovery of both independent ambulation and overall self-care function in 95 consecutive patients with unilateral hemispheric stroke using life table analysis. Our results support the segregation of patients into the following prognostic subgroups at the time of entry into the rehabilitation program (mean +/- SD 5 +/- 3 weeks after stroke): 1) motor deficit only, 2) motor deficit plus somatic sensory deficit, and 3) motor deficit plus somatic sensory deficit plus homonymous visual deficit. The probabilities of reaching independence in ambulation, being able to walk 150 feet with assistance, reaching independence in self-care function, and reaching a point of assisted self care (Barthel Index score of greater than or equal to 60) are highly significantly different among subgroups. The interval after stroke required to reach the plateau phase of recovery is also significantly different among subgroups. We propose that life table analysis can be used 1) to define patient outcome goals, 2) to define the time required to reach such goals, 3) to identify patients with medical or behavioral comorbidity who are functioning below their expected level, and 4) to assess the effect of alternative treatment regimens on both final outcome and time to reach that outcome.

Actuarial Analysis↗
PubMed2006

Investigating the genetic determinants of cardiovascular disease using candidate genes and meta-analysis of association studies.

Coronary artery disease (CAD) has a polygenic basis, and identification of CAD susceptibility genes has the potential to aid the development of new treatments and enhance prediction of disease risk. Thus far, the strategy has firstly been to choose "candidate" genes coding for important "rate-limiting" proteins in the homeostatic systems involved in maintaining cardiovascular health; secondly to identify common variants in these candidate genes; thirdly to carry out genotyping and statistical analysis using genetic association studies; and finally to test the functional effects of the identified variants in vitro and in vivo. However, lack of reproducibility of genetic association studies has led to uncertainty about the nature and number of genes involved. In part this is because many of the studies conducted have not been adequately powered to detect small risk effects, or to permit adequate exploration of gene-gene or gene-environment interactions in a robust manner. Spurious positive and negative associations due to type I and type II statistical errors are likely to co-exist with real associations in the published literature. By utilising all available data to increase statistical power, meta-analysis of genetic association studies is increasingly being used to identify genotypic risk with a greater degree of precision. Though potentially powerful, this approach may be prone to publication bias. Therefore, very large genetic association studies will also be required to identify risk genes for CAD. This review lays out the framework for the candidate gene approach for CAD and illustrates this with published results from a UK prospective study of 3000 middle-aged men.

Cardiovascular Diseases↗
PubMed1994

Quantitative analysis of CD34+ stem cells using RT-PCR on whole cells.

We have employed RT-PCR of whole cells to develop a quantitative method for estimating the number of rare cells expressing a unique mRNA in a large, mixed population of cells. We have demonstrated that RT-PCR can be done on whole cells without the need for extraction of the RNA. This allows for a great saving of time and effort, as well as allowing quantitative analysis to be based on the total number of cells analyzed in a given aliquot and the presence or absence of the specific RT-PCR product. We have employed a limiting dilution series on whole cells, with multiple aliquots at each cell concentration to achieve more statistical power in the analysis of a rare cell type. We have used a nested amplification of the CD34 mRNA to be able to detect a single cell expressing the CD34 mRNA in a larger population of non-CD34-expressing cells. We demonstrate that by using this technique, cells from blood and bone marrow containing the CD34 mRNA can be followed quantitatively during a multistep purification involving immunoadsorption followed by fluorescence-activated cell sorting. We also demonstrate that many cells that express the CD34 protein on their surface no longer contain detectable levels of CD34 mRNA, a phenomenon that appears to be developmentally regulated.

Antigens, CD↗
PubMedDate not supplied

Intravenous cyclophosphamide therapy for systemic sclerosis. A single-center experience and review of the literature with pooled analysis of lung function test results.

OBJECTIVE: Oral cyclophosphamide (CYC) is a promising therapy for Systemic Sclerosis (SSc)-related interstitial lung disease (ILD). The use of intravenous (i.v.) pulses has been considered as an alternative route of drug administration, possibly associated with reduced toxicity. Our objectives were to re-evaluate our experience with i.v. CYC, to review the literature, and to pool our results with those available from other groups, improving the statistical power of the analysis. METHODS: 1) Retrospective analysis of our center experience on 16 patients with SSc and active alveolitis, treated with i.v. CYC 750 mg + 6-methylprednisolone 125 mg every 3 weeks. 2) Pooled analysis of papers published in peer-reviewed journals reporting detailed data on each patient treated with i.v. CYC. The end-point was modification in the results of lung function tests (LFT) after 6 months. Piecewise regression analysis was performed using a linear mixed-effects model adjusted for baseline values to evaluate the changes in LFT. RESULTS: Retrospective analysis. In the period before therapy there was a significant deterioration in FVC (in 6 months: -4.3%; p=0.0009) and DLCO (-2.1%; p=0.018). After 6 months of treatment there was a modest improvement in the FVC (+2.7% p=0.08) and DLCO (+2.2%; p=0.08). Pooled analysis. In 53 evaluable patients, the improvement in LFT reached conventional statistical significance (FVC: +2.85%; 95% confidence intervals: +0.04, +5.66%; p=0.04. DLCO: +4.4%; 95% confidence intervals: +1.2%, +7.5%; p<0.001). CONCLUSION: i.v. CYC for 6 months can achieve a small, but significant improvement of LFT in patients with SSc and active alveolitis.

Adult↗
PubMed1996

Linkage between quantitative trait loci and marker loci: resolution power of three statistical approaches in single marker analysis.

This paper presents a comparison of three methods of parameter estimation in analysis of linkage between a quantitative trait locus (QTL) and a marker locus: maximum likelihood, mean square for trait cumulative distribution function, and method of moments, employing simulated backcross data. The sensitivity of estimates to violation of assumptions of normality and equal variances were also studied. Some measures of discrepancy between the trait distributions in the QTL groups are considered to evaluate the potential dependence of the resolution capacity of the QTL substitution effect with respect to trait mean value and variance.

Algorithms↗
PubMed1995

Exposure measurement errors, risk estimate and statistical power in case-control studies using dichotomous analysis of a continuous exposure variable.

BACKGROUND: Non-differential errors in exposure measurements have been shown to lead to differential misclassification of exposure. As a consequence, the common tenet that, in absence of bias, imprecise exposure assessment can only bias the risk estimates conservatively does not necessarily hold. We investigate the effects of exposure measurement errors on the risk estimate and on statistical power. METHODS: We used a computer model that simulates a case-control study. We used both hypothetical data and data modelled on empirical measurements of environmental magnetic fields exposure. RESULTS: Measurement errors are found to have a lesser impact on risk estimates and statistical power than would have been the case had misclassification been truly non-differential. However, for a given cutpoint, a bias away from the null cannot be excluded. The predominant direction of the errors is found to have important consequences on both the study power and the risk estimates. CONCLUSION: When sufficient empirical data are available, computer modelling may give a more accurate estimate of the effects of measurement errors than algebraic corrections.

Bias↗
PubMed1997

Tobacco smoke influence on heart rate, body temperature, and locomotor activity daily rhythms as assessed by radiotelemetry in rats.

Using radiotelemetry, this study aimed to evaluate the influence of tobacco smoke on heart rate (H), body temperature (T) and locomotor activity (A) daily rhythms in rats. The tobacco smoke intoxication was produced with a smoking apparatus. H, T, and A data were captured by radiotelemetry. The study was divided into three periods: a 1-week control period (P1), a 1-week stress period (P2), in order to evaluate the stress induced by the animals' restraint in the smoking apparatus, and a 1-week daily tobacco smoke intoxication period (P3). For P1, P2, and P3, a power spectrum analysis was applied in order to determine the dominant period of rhythmicity. Then, characteristics of the rhythms were determined by cosinor analysis. Statistical comparisons were done by ANOVA. Power spectrum analysis showed that neither stress nor tobacco suppressed the daily rhythmicity. Cosinor revealed some modifications: H amplitude was decreased during P2 and P3 with a greater reduction during P3, while T and A amplitudes were decreased during P2 and P3 without difference between P2 and P3. T acrophase was delayed during P2, while A acrophase was delayed during P2 and P3 without any difference between P2 and P3. These perturbations may reflect the effects of stress and tobacco on the suprachiasmatic nucleus by a dopaminergic mechanism.

Analysis of Variance↗
PubMed2004

How many pigs? Statistical power considerations in swine nutrition experiments.

Replication refers to the assignment of more than one experimental unit to the same treatment. Each replication of a treatment is an independent observation; thus, each replication involves a different experimental unit. In swine nutrition research, the experimental unit may be an individual animal, as in sow reproduction experiments, or a group of animals, as in growing-finishing pig experiments. In either case, calculation of the number of replicates needed to give an accurate and reliable outcome is an important step in deriving an experimental protocol. Although investigators often seem to choose replication arbitrarily on the basis of cost or availability of animals, housing considerations, convenience, or tradition, the question of how many pigs (i.e., how much replication is necessary) is a statistical one that has a statistical answer. A power analysis, performed while designing an experiment, will provide an investigator with an estimate of the number of replicates needed for an experiment of known power and sensitivity. This a priori, or prospective, power analysis ensures that an investigator does not waste time and resources carrying out an experiment that has little chance of finding a significant effect, if one exists. It also makes sure resources are not wasted by including more experimental units than are necessary to detect an effect. A retrospective, or a posteriori, power analysis may also be conducted. If no significant effects are found in an experiment, an investigator can assess the observed power of the experiment, or may determine the size of treatment effect that could have been detected using the standard deviation and number of replicates in the experiment. The latter may be useful in explaining results. However, the former may be misleading because a high P-value will invariably result in a low observed power, and little new information will be gained from the post hoc power analysis. In most cases, the time for making power calculations is before, not after, an experiment is conducted.

Animal Nutritional Physiological Phenomena↗
PubMed2006

Generalized genomic distance-based regression methodology for multilocus association analysis.

Large-scale, multilocus genetic association studies require powerful and appropriate statistical-analysis tools that are designed to relate genotype and haplotype information to phenotypes of interest. Many analysis approaches consider relating allelic, haplotypic, or genotypic information to a trait through use of extensions of traditional analysis techniques, such as contingency-table analysis, regression methods, and analysis-of-variance techniques. In this work, we consider a complementary approach that involves the characterization and measurement of the similarity and dissimilarity of the allelic composition of a set of individuals' diploid genomes at multiple loci in the regions of interest. We describe a regression method that can be used to relate variation in the measure of genomic dissimilarity (or "distance") among a set of individuals to variation in their trait values. Weighting factors associated with functional or evolutionary conservation information of the loci can be used in the assessment of similarity. The proposed method is very flexible and is easily extended to complex multilocus-analysis settings involving covariates. In addition, the proposed method actually encompasses both single-locus and haplotype-phylogeny analysis methods, which are two of the most widely used approaches in genetic association analysis. We showcase the method with data described in the literature. Ultimately, our method is appropriate for high-dimensional genomic data and anticipates an era when cost-effective exhaustive DNA sequence data can be obtained for a large number of individuals, over and above genotype information focused on a few well-chosen loci.

Chitinases↗
PubMed2007

Supplementary analyses regarding Langevin, Langevin, and Curnoe's (2007) findings on fraternal birth order in homosexual men.

A recent article by Langevin, Langevin, and Curnoe (2007) reported mixed results regarding the fraternal birth order effect, that is, the repeatedly observed finding that older brothers correlate with homosexuality in later-born males. Using a fraternal birth order index computed as older brothers minus younger brothers, Langevin et al. found that the "homoerotic" probands were born later among their brothers than were the "heteroerotic" probands in their full sample (N = 1194) and in their subsample over age 19 (N = 1122), but not in their subsample over age 31 (N = 698) or in their subsample with mothers over age 46 at the proband's birth (N = 727). The present writer concluded that the results obtained with the larger samples are more reliable, based on analyses demonstrating that (1) the larger samples are unlikely to be seriously affected by incomplete sibships, and (2) the smaller samples have poor statistical power. A separate analysis, based on an approximate reconstruction of Langevin et al.'s raw data, indicated that their heteroerotic probands reported a ratio of 104 older brothers per 100 older sisters, which is close to the normative population value of 106, whereas their homoerotic probands reported a ratio of 137, indicating a statistically significant excess of older brothers. These results suggest that Langevin et al.'s data showed significant evidence of a fraternal birth order effect and that their data were consistent with previous studies of this phenomenon.

Age Factors↗
PubMed2007

Covariate heterogeneity in meta-analysis: criteria for deciding between meta-regression and individual patient data.

Meta-analyses of clinical trials are increasingly seeking to go beyond estimating the effect of a treatment and may also aim to investigate the effect of other covariates and how they alter treatment effectiveness. This requires the estimation of treatment-covariate interactions. Meta-regression can be used to estimate such interactions using published data, but it is known to lack statistical power, and is prone to bias.The use of individual patient data can improve estimation of such interactions, among other benefits, but it can be difficult and time-consuming to collect and analyse. This paper derives, under certain conditions, the power of meta-regression and IPD methods to detect treatment-covariate interactions. These power formulae are shown to depend on heterogeneity in the covariate distributions across studies. This allows the derivation of simple tests, based on heterogeneity statistics, for comparing the statistical power of the analysis methods.

Aminoimidazole Carboxamide↗
PubMed1996

Effect of early hip decompression on the frequency of avascular necrosis in children with fractures of the neck of the femur.

Twenty-eight per cent of 32 children with fractures of the neck of the femur developed avascular necrosis. It occurred in three of the four type I fractures, in five of the 11 type II fractures, in one of the 12 type III fractures and in none of the five type IV fractures. We studied the effect of early hip decompression on the frequency of avascular necrosis. It had no apparent value in type I fractures. To increase the statistical power of our analysis of displaced type II and III fractures we combined our cases with similar cases from other series. Twenty-two (41 per cent) of the 54 combined cases treated without hip decompression developed avascular necrosis while only three (8 per cent) of the 39 combined cases treated with early hip decompression developed avascular necrosis. This difference was statistically significant. This finding supports the use of early hip decompression as a means of reducing the frequency of avascular necrosis in displaced type II and III fractures. Our findings also indicate that the complications of nonunion, malunion and premature closure of the proximal femoral physis are minimized by accurate reduction of displaced fractures, routine use of internal fixation for all fractures and avoidance of permanent physeal damage by internal fixation devices.

Child↗
PubMed2000

The trimmed-haplotype test for linkage disequilibrium.

Single-marker linkage-disequilibrium (LD) methods cannot fully describe disequilibrium in an entire chromosomal region surrounding a disease allele. With the advent of myriad tightly linked microsatellite markers, we have an opportunity to extend LD analysis from single markers to multiple-marker haplotypes. Haplotype analysis has increased statistical power to disclose the presence of a disease locus in situations where it correctly reflects the historical process involved. For maximum efficiency, evidence of LD ought to come not just from a single haplotype, which may well be rare, but in addition from many similar haplotypes that could have descended from the same ancestral founder but have been trimmed in succeeding generations. We present such an analysis, called the "trimmed-haplotype method." We focus on chromosomal regions that are small enough that disequilibrium in significant portions of them may have been preserved in some pedigrees and yet that contain enough markers to minimize coincidental occurrence of the haplotype in the absence of a disease allele: perhaps regions 1-2 cM in length. In general, we could have no idea what haplotype an ancestral founder carried generations ago, nor do we usually have a precise chromosomal location for the disease-susceptibility locus. Therefore, we must search through all possible haplotypes surrounding multiple locations. Since such repeated testing obliterates the sampling distribution of the test, we employ bootstrap methods to calculate significance levels. Trimmed-haplotype analysis is performed on family data in which genotypes have been assembled into haplotypes. It can be applied either to conventional parent-affected-offspring triads or to multiplex pedigrees. We present a method for summarizing the LD evidence, in any pedigree, that can be employed in trimmed-haplotype analysis as well as in other methods.

Alleles↗
PubMed1995

Adjuvant tamoxifen therapy for early stage breast cancer and second primary malignancies. Stockholm Breast Cancer Study Group.

BACKGROUND: Tamoxifen is being increasingly used for the treatment of breast cancer and is undergoing study for the primary prevention of breast cancer. However, concerns have been raised that the drug may increase the incidence of new primary malignancies, such as endometrial, liver, and colorectal cancers. PURPOSE: Our goal was to assess the carcinogenic risks associated with long-term use of tamoxifen in women with early stage breast cancer. METHODS: The incidence of new primary cancers among 2729 women participants of the Stockholm Trial was determined at a median follow-up of 9 years. In this trial, after primary surgery, postmenopausal patients aged less than 71 years with unilateral invasive breast cancer were randomly allocated to receive either 2 years of adjuvant tamoxifen (40 mg daily) or no adjuvant endocrine therapy. Information on second cancers was obtained by retrospective linkage to the Swedish Cancer Registry. To increase statistical power, a joint analysis of the incidence of endometrial and gastrointestinal cancers was performed in the following three major studies in Scandinavia evaluating adjuvant tamoxifen therapy: the Stockholm Trial, the Danish Breast Cancer Group Trial, and the South-Swedish Trial. These studies included a total of 4914 patients with a median follow-up of 8-9 years. All P values were calculated from two-tailed tests of statistical significance. RESULTS: In the Stockholm Trial, there was a statistically significant (P = .008) reduction in the incidence of second primary cancers in the contralateral breast among the tamoxifen-treated patients. However, there was a nearly sixfold increase in endometrial cancers (P < .001) and a threefold increase in gastrointestinal cancers in the tamoxifen-treated patients. The results of the joint studies showed a statistically significant increase in endometrial cancers among the tamoxifen-treated patients (relative risk [RR] = 4.1; 95% confidence interval [CI] = 1.9-8.9). There was also an excess of gastrointestinal cancers associated with tamoxifen. Most of this excess involved colorectal cancers (RR = 1.9; 95% CI = 1.1-3.3) and stomach cancer (RR = 3.2; 95% CI = 0.9-11.7). There was no substantial increase in any other type of gastrointestinal cancer (e.g., liver cancer) among the tamoxifen-treated patients. CONCLUSION: The endometrium and gastrointestinal organs may be target sites for tamoxifen-induced carcinogenesis in humans. IMPLICATIONS: The increased incidence of colorectal and stomach cancers reported here should be regarded as tentative until supported by long-term data from a larger number of tamoxifen trials. Also, appropriate surveillance of cancer incidence is warranted for the protection of participants enrolled in current tamoxifen chemoprevention trials.

Aged↗