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 991 records · Page 55Linked to original sources
PubMed2003

Comparison of effectiveness of two urinary drainage systems in intensive care unit: a prospective, randomized clinical trial.

OBJECTIVE: In a previous nonrandomized study we observed no difference in the rate of acquisition of bacteriuria between a complex closed drainage system (CCDS) and a two-chamber drainage system (TCDS) in ICU patients. To confirm this result we performed a statistically powerful study assessing the effectiveness of the CCDS and the TCDS in ICU patients. DESIGN AND SETTING: Randomized, prospective, and controlled study in the medicosurgical intensive care unit (16 beds) in a teaching hospital. PATIENTS AND INTERVENTIONS: We assigned 311 patients requiring indwelling urinary catheter for longer than 48 h to TCDS or CCDS to compare the rate of acquisition of bacteriuria. MEASUREMENTS AND RESULTS: Patients did not receive prophylactic antibiotics during placement management or catheter withdrawal. Urine samples were obtained weekly for the duration of catheterization and within 24 h after catheter removal, and each time symptoms of urinary infection were suspected. There was no statistical difference in the rate of bacteriuria between the two groups: 8% with TCDS and 8.5% with CCDS. Rates of urinary tract infection were 12.1 episodes with TCDS and 12.8 episodes with CCDS per 1000 days of catheter. CONCLUSIONS: This randomized study on the effectiveness of TCDS and CCDS in ICU patients confirms the findings of our previous study. No differences were noted between the two systems. The higher cost of CCDS is not justified for ICU patients.

Adult↗
PubMed1994

The potential for the use of personal computers in clinical forensic medicine.

This paper describes the use of a personal computer in clinical forensic medicine. It shows how a database can be easily created, updated for each new case by unqualified personnel, and then used to provide statistical data with a minimum resource input, without the need for great computer expertise. Databases will only recognise exactly identical abbreviations. Once created they can cross-reference data and provide individually tailored statistics. Registration with the Data Protection Agency is required in the UK in order to hold personal information on file. The results of 2201 cases entered on the database of one forensic physician show high levels of drug and alcohol abuse co-existing with unemployment and homelessness. 53% of individuals brought to police stations as a place of safety (under Section 136 of the Mental Health Act 1983) were in need of admission to a psychiatric hospital. 12% of those individuals were of no fixed abode. The potential for a national database linking forensic physicians on a national basis, pooling their data thereby creating a powerful statistical tool is clear.

Journal Article↗
PubMed1996

Is the percentage of cancer in biopsy cores predictive of extracapsular disease in T1-T2 prostate carcinoma?

BACKGROUND: Information regarding the quantity of biopsy material invaded by cancer may supplement the usual criteria for the preoperative staging of patients suffering from clinically localized prostate carcinoma (T1-T2). However, conflicting conclusions have been drawn and this topic needs further investigation. METHODS: A total of 170 patients had radical prostatectomy for T1-T2 prostate carcinoma. Patients' mean age (+/- standard deviation [SD]) was 66.05 +/- 6.12 years and mean prostate specific antigen (PSA) level (+/- SD) was 22.5 +/- 21.4 ng/mL (Yang Proscheck). Of the patients, 110 underwent transrectal ultrasound-guided biopsy with removal of 6 cores, from whom we had the percentage of biopsy, material invaded by cancer, the Gleason score, and the preoperative PSA. These parameters were compared with the pathologic features of the surgical specimen (capsule penetration, surgical margins, and Gleason score) and biologic progression (defined as persistent/recurrent postoperative PSA > 0.1 ng/mL). RESULTS: The most valid threshold of biopsy material invaded by cancer for predicting surgical margins and capsule status, as well as biologic progression, was 10%. When < 10% of biopsy material was invaded by cancer, positive surgical margins (SM+) were present in 30.3%, capsular penetration (pT3, pathologic extracapsular involvement) in 27.3%, and biologic progression (P+) in 21.7%. The Gleason score did not improve this prognostic evaluation. The mean quantities of tissue invaded by cancer differed significantly between positive and negative surgical margin groups, between pT2 and pT3 groups, and between P- and P+ groups (no biologic progression/biologic progression). There was statistical significance (log rank test, P = 0.0320 in the survival without biologic postoperative progression between patients with < or = or > 10% of one core biopsy invaded by tumor. If < or = 10% of tissue in only 1 of 6 cores of a biopsy was invaded by tumor, the status was pT2, SM-, and P- in 87.5% of the patients. CONCLUSIONS: On an individual basis, the percent of tissue containing carcinoma in core biopsies was a factor that lacked the statistical power to predict the status of the capsule and surgical margins, and the biologic progression. The finding of < or = 10% of carcinoma in 1 of 6 cores of a biopsy was correlated with a good prognosis.

Adult↗
PubMed2006

Improving methods of assessing natural killer cell cytotoxicity.

Natural killer (NK) cells are a class of lymphocytes important in immune resistance to viral and other serious diseases. The cytotoxic function, or 'killing activity' of NK cells has become important in studies of the effects of stress and other psychosocial factors on physical health. Unfortunately, research on NK cell function has been plagued by discrepancies in the methods of interpreting NK cytotoxicity data. We briefly review some of the variations in measuring NK cell activity and present a new model for interpreting these results, introducing maximal target cell lysis (A) and the slope of the cytolytic curve (k) as parameters that attempt to make full use of the information and the statistical power in NK cell cytotoxicity data. Examples of these interpretation methods are presented using NK cytotoxicity data from a group of metastatic breast cancer patients. This approach will be useful in applications of NK cell measurement in psychoneuroimmunology research.

Analysis of Variance↗
PubMed1998

Impact of intravascular ultrasound guidance in stent deployment on 6-month restenosis rate: a multicenter, randomized study comparing two strategies--with and without intravascular ultrasound guidance. RESIST Study Group. REStenosis after Ivus guided STenting.

OBJECTIVES: We aimed to investigate the impact of intravascular ultrasound (IVUS)-guided stent implantation on the 6-month restenosis rate, which has not yet been fully established in randomized trials. BACKGROUND: The 6-month angiographic restenosis rate was compared in patients with symptomatic ischemic heart disease who were randomly allocated to angioplasty and stent deployment, with versus without IVUS guidance. METHODS: After successful stent implantation, patients were randomized into two groups: Group A had no further dilation, and Group B had additional balloon dilation until achievement of IVUS criterion for stent expansion. The study group consisted of 164 patients, assuming a 50% reduction of the restenosis rate in Group B (15% vs. 30%) (alpha = 10%, beta = 20%). RESULTS: We enrolled 155 patients. Overdilation was carried out in 31 (39%) of 79 Group B patients, with the IVUS criterion being achieved in 63 (80%) of 79. No significant difference was observed in the minimal luminal diameter (MLD), but the stent lumen cross-sectional area (CSA) was significantly larger in Group B (mean +/- SD) (7.16 +/- 2.48 vs. 7.95 +/- 2.21 mm2, p = 0.04). At 6 months, there was no significant difference in the restenosis rate, (28.8% [21 of 73] in Group A vs. 22.5% [16 of 71] in Group B, p = 0.25), but according to the observed difference in the restenosis rate, the power of the study was only 40%. The difference in MLD was also nonsignificant (1.60 +/- 0.65 mm in Group A vs. 1.70 +/- 0.64 mm in Group B, p = 0.20), whereas the lumen CSA was 20% larger in the IVUS-guided group (4.47 +/- 2.59 vs. 5.36 +/- 2.81 mm2, p = 0.03). Lumen CSA was the only predictor of restenosis by multivariate logistic regression analysis. CONCLUSIONS: A nonsignificant 6.3% absolute reduction in the restenosis rate and a nonsignificant difference in MLD were observed in this study. Nonetheless, we still cannot rule out a beneficial effect of IVUS guidance, although this may have gone undetected owing to a lack of statistical power. A significant increase was observed in immediate and 6-month lumen size, as detected by IVUS, indicating that ultrasound guidance in stent deployment may be beneficial.

Angioplasty, Balloon, Coronary↗
PubMed2005

Behavior and the limits of genomic plasticity: power and replicability in microarray analysis of honeybee brains.

Transcription is slow relative to many post-transcriptional processes in the brain. Using the rich system of division of labor in the honeybee (Apis mellifera), we found extreme differences in the extent to which behavioral occupations of different durations were associated with gene-expression differences in the brain. Nursing and foraging, occupations lasting > 1 week, were associated with significant expression differences for nearly one-quarter of the genes tested (1208 of 5563 cDNAs tested; P < 0.01, anova), consistent with previous results. In contrast, transitional occupations, performed for 1-2 days after nursing and before the onset of foraging, were associated with either no differences (guards vs. undertakers; 19 cDNAs, fewer than the expectation of 56 false-positives) or few differences (comb builders vs. guards and undertakers; 248 cDNAs), but extensive differences relative to both nursing and foraging (> 500 cDNAs, all contrasts). Statistical power analysis indicated that expression differences of two-, 1.5- and 1.25-fold should have been detected in 100, 92 and 37% of cases, respectively. Replication of previous results at these magnitudes was 95, 71 and 51%, with no genes showing differences in the opposite direction. These results indicate that behavioral plasticity over different time-scales may be associated with substantial differences in the extent of genomic plasticity in the brain.

Animals↗
PubMed1984

Advantages of integrated trials for performing multiple Phase II studies.

Phase II trials can be conducted in an integrated fashion that minimizes assignment of patients to potentially ineffective treatments. The technique allows definitions of response to include survival; earlier identification of more effective drugs; and completion of more Phase II studies in a given time period. It also encourages investigators to analyse results promptly. Because the analysis of each trial is independent, the statistical power of the analysis of results is retained. Identified shortcomings of the method include the need for a central mechanism to assign patients to treatment, the need for several drugs to be tested, physicians' uncertainty about which drug a particular patient will receive, and the increased time it may take to complete an individual trial.

Antineoplastic Agents↗
PubMed2002

The structure of haplotype blocks in the human genome.

Haplotype-based methods offer a powerful approach to disease gene mapping, based on the association between causal mutations and the ancestral haplotypes on which they arose. As part of The SNP Consortium Allele Frequency Projects, we characterized haplotype patterns across 51 autosomal regions (spanning 13 megabases of the human genome) in samples from Africa, Europe, and Asia. We show that the human genome can be parsed objectively into haplotype blocks: sizable regions over which there is little evidence for historical recombination and within which only a few common haplotypes are observed. The boundaries of blocks and specific haplotypes they contain are highly correlated across populations. We demonstrate that such haplotype frameworks provide substantial statistical power in association studies of common genetic variation across each region. Our results provide a foundation for the construction of a haplotype map of the human genome, facilitating comprehensive genetic association studies of human disease.

Africa↗
PubMed2003

Identification and isolation of dominant susceptibility loci for pristane-induced arthritis.

Rheumatoid arthritis is a chronic inflammatory autoimmune disorder, controlled by multiple genes as well as environmental factors. With animal models, like the pristane-induced arthritis (PIA) in rats, it is possible to reduce the environmental effects and the genetic heterogeneity to identify chromosomal regions harboring genes responsible for the arthritis development. The PIA model has proved to be useful for identifying gene regions controlling different phases of the disease based on intercrosses between the resistant E3 and the susceptible DA rat. We have now performed a high-powered backcross analysis that confirms previous intercross-based data but also identifies additional loci. Earlier identified PIA loci were reproduced with high significance; Pia1 (MHC region on chromosome 20), Pia4 (chromosome 12), and Pia7 (chromosome 4) are all major regulators of PIA severity and were also found to operate in concert. These three loci were verified in congenic strains using both disease- and arthritis-inflammatory-related subphenotypes as traits. We were also able to detect five new quantitative trait loci with dominant effects on PIA: Pia10, Pia12, Pia13, Pia14, and Pia15 on chromosomes 10, 6, 7, 8, and 18, respectively. These data highlight the usefulness of the statistical power obtained in a backcross of a complex disease like arthritis.

Animals↗
PubMed1994

Epidemiology of silicone-related disease.

The epidemiology of silicone-related disease (SRD) is complicated by the variety of disease endpoints that have been associated with silicone exposure and the atypical nature of these diseases in silicone-exposed women. Current research reviewed here suggests that SRD may constitute a new disease entity, thus complicating disease definition and rendering studies of classic disease unlikely to detect risks of silicone exposure. This report addresses the most important study design issues (disease and exposure definitions, bias, confounding, and power) in the context of studies of SRD. The variety of silicones used complicates the definition of exposure for all studies, and for some populations simply determining who was implanted will be difficult. For any of these studies, inadequate patient follow-up is likely to underestimate disease risk. Studies of SRD are also complicated by confounding. That is, whether or not a woman chooses to receive an implant is related to her age, race, and other variables also related to rheumatoid and autoimmune disease. The absence of an appropriate control group also plaques published studies of silicone-related disease. Finally, inadequate sample size, resulting in studies of low statistical power, is a critical problem for rare diseases such as SRD. These points are illustrated using two published studies and five studies in progress.

Breast Implants↗
PubMed1997

A comprehensive analysis of complex traits in problem 2A.

We used descriptive analysis to investigate the relationship between affection status and five quantitative traits (Q1-Q5) in Problem 2A and results suggested the five quantitative traits fall into two groups. The first group comprised three strongly correlated traits, Q1-Q3, which underlie affection status, and the second group comprised Q4 and Q5, which are not directly related to affection status. Segregation and linkage analyses of traits Q1-Q3 and affection status from the first replicate detected one of the major loci for Q1 (MG1) linked to marker 14 on chromosome 5 (D5G14). Because our segregation analysis failed to show evidence of a major locus effect on Q2, and we overlooked the interaction between MG3 and sex, we did not detect either MG2 or MG3. Using Haseman-Elston sib-pair analysis [Haseman and Elston, 1972], we also examined the statistical power of Q1 and type I error rate (using the environmental factor as an index), for the remaining 199 replicates in the context of a genome screen.

Chromosome Mapping↗
PubMed2006

Simplified intersubject averaging on the cortical surface using SUMA.

Task and group comparisons in functional magnetic resonance imaging (fMRI) studies are often accomplished through the creation of intersubject average activation maps. Compared with traditional volume-based intersubject averages, averages made using computational models of the cortical surface have the potential to increase statistical power because they reduce intersubject variability in cortical folding patterns. We describe a two-step method for creating intersubject surface averages. In the first step cortical surface models are created for each subject and the locations of the anterior and posterior commissures (AC and PC) are aligned. In the second step each surface is standardized to contain the same number of nodes with identical indexing. An anatomical average from 28 subjects created using the AC-PC technique showed greater sulcal and gyral definition than the corresponding volume-based average. When applied to an fMRI dataset, the AC-PC method produced greater maximum, median, and mean t-statistics in the average activation map than did the volume average and gave a better approximation to the theoretical-ideal average calculated from individual subjects. The AC-PC method produced average activation maps equivalent to those produced with surface-averaging methods that use high-dimensional morphing. In comparison with morphing methods, the AC-PC technique does not require selection of a template brain and does not introduce deformations of sulcal and gyral patterns, allowing for group analysis within the original folded topology of each individual subject. The tools for performing AC-PC surface averaging are implemented and freely available in the SUMA software package.

Brain↗
PubMed2003

Non-parametric interval mapping in half-sib designs: use of midranks to account for ties.

In QTL analysis of non-normally distributed phenotypes, non-parametric approaches have been proposed as an alternative to the use of parametric tests on mathematically transformed data. The non-parametric interval mapping test uses random ranking to deal with ties. Another approach is to assign to each tied individual the average of the tied ranks (midranks). This approach is implemented and compared to the random ranking approach in terms of statistical power and accuracy of the QTL position. Non-normal phenotypes such as bacteria counts showing high numbers of zeros are simulated (0-80% zeros). We show that, for low proportions of zeros, the power estimates are similar but, for high proportions of zeros, the midrank approach is superior to the random ranking approach. For example, with a QTL accounting for 8% of the total phenotypic variance, a gain from 8% to 11% of power can be obtained. Furthermore, the accuracy of the estimated QTL location is increased when using midranks. Therefore, if non-parametric interval mapping is chosen, the midrank approach should be preferred. This test might be especially relevant for the analysis of disease resistance phenotypes such as those observed when mapping QTLs for resistance to infectious diseases.

Chromosome Mapping↗
PubMed2000

Proper ROC analysis and joint ROC analysis of the satisfaction of search effect in chest radiology.

RATIONALE AND OBJECTIVES: The purpose of this study was to test whether the satisfaction of search (SOS) effect in chest radiology could be demonstrated with proper receiver operating characteristic (ROC) curves and with joint detection and localization ROC curves. MATERIAL AND METHODS: Data from an earlier ROC study of SOS in chest radiology were analyzed with three proper ROC models and one ROC model for joint detection and localization. Fits of the models were compared on the basis of likelihood-ratio chi-squared statistics (G2). To examine further the validity of the SOS effect in chest radiology, the authors also replicated the earlier study with a new sample of readers, analyzing the new data with the same methods. RESULTS: The proper contaminated binormal model fit the data better than the other two proper ROC models. Contaminated binormal analysis of the earlier and the replication experiment demonstrated an SOS effect: a reduction in area under the ROC curve for detection of the native abnormalities with the addition of nodules. Similarly, joint ROC analysis producing curves that appropriately cross the chance line gave similar results. CONCLUSION: Preventing inappropriate chance line crossing reduces measurement error and provides more powerful statistical tests. Results of both experiments showed that the SOS effect in chest radiology can be demonstrated with ROC methods that avoid inappropriate crossing of the chance line.

Chi-Square Distribution↗
PubMed1991

[A critical analysis of clinical trials in acute pancreatitis published between 1983 and 1989].

BACKGROUND: The aim of the study was a critical review of recent clinical trials in acute pancreatitis (AP) to draw recommendations for future studies. METHODS: The pharmacological clinical trials in AP reported in English from 1983 to 1989 were identified through a computer assisted Medline search, and a manual review of the references in the initial articles. In addition to the characteristics of the studies, the results on the clinical variables were also recorded. In case of negative results, the power of the study to detect 50% reductions in mortality and complications was also calculated. RESULTS: In the 12 identified studies 10 different drugs were used. Only 58% were double blind. The interval between the onset of symptoms and therapy was not specified in eight studies (67%) and was two days or longer in the rest. In six studies (50%), the duration of treatment was very short (less than three days). Except in two studies, mild forms of AP predominated. Some clinical efficacy of 5-FU, TRH and CaNa2-ED-TA was reported, although with small relevance. In no trial any beneficial effects on mortality or complications were found, although the statistical power was in general low, and therefore a false negative result cannot be excluded. CONCLUSIONS: The guidelines for clinical trials in AP should be unified, particularly regarding the type of study, inclusion criteria and duration of treatments. Some treatments may be too early discarded owing to false negative results due to small sample size.

Acute Disease↗
PubMed2006

Preoperative bone quality as a factor in dual-energy X-ray absorptiometry analysis comparing bone remodelling between two implant types.

Recently it was shown that the design changes from the ABG-I to ABG-II hip stem resulted in a better, although not significant, proximal bone preservation. Our hypothesis was that by matching patients for preoperative bone quality, statistical power would increase and that the trend of better proximal bone preservation in ABG-II might become significant. Twenty-four ABG-II patients were compared to two different ABG-I groups: (1) 25 patients from our earlier prospective study and (2) a group of 24 patients selected to perfectly match the ABG-II group regarding gender, age and preoperative bone quality. Postoperative changes in periprosthetic bone mineral density (BMD) were quantified at 2 years postoperatively using DEXA scanning. Bone preservation (less BMD loss) was better for the ABG-II than the ABG-I (all two groups) in the proximal zones 1 and 7. In Gruen zone 7, a statistically significant difference was found for group B (p = 0.03). By matching patients for preoperative bone quality and gender, a statistical significant difference was found in proximal bone preservation in favour of ABG-II. In future comparative bone remodelling studies using DEXA, patients should be matched for preoperative bone quality and gender.

Absorptiometry, Photon↗
PubMed2004

Quantitative assessment of changes in patients' constructs of quality of life: an application of multilevel models.

It has often been proposed that quality of life (QL) instruments should account for potentially changing conceptualisations of QL as patients adapt to disease (response-shift). Most instruments do not do this, and some that do are relatively complicated and burdensome for patients. The extent to which patients reconceptualise QL is unknown, and it is unclear whether this additional complication is necessary. This paper reviews existing methods for assessing response-shift and introduces an alternative approach using multilevel models. The method is described using data from a cancer clinical trial, and its performance is evaluated in simulations. The models reveal substantial response-shift in these cancer patients. Simulations under the null hypothesis of zero response-shift confirm that the method performs correctly in terms of its risk of type I error, and further simulations illustrate its statistical power to detect pre-defined levels of response-shift. The method is a relatively simple extension of familiar multiple regression models and yields parameters with a simple interpretation, representing the changes in importance of QL domains over time. It can be applied to existing datasets collected with other analysis strategies in mind and may have application in the investigation of response shifts and other manifestations of adaptation.

Colorectal Neoplasms↗
PubMed1998

A close look at therapeutic touch.

CONTEXT: Therapeutic Touch (TT) is a widely used nursing practice rooted in mysticism but alleged to have a scientific basis. Practitioners of TT claim to treat many medical conditions by using their hands to manipulate a "human energy field" perceptible above the patient's skin. OBJECTIVE: To investigate whether TT practitioners can actually perceive a "human energy field." DESIGN: Twenty-one practitioners with TT experience for from 1 to 27 years were tested under blinded conditions to determine whether they could correctly identify which of their hands was closest to the investigator's hand. Placement of the investigator's hand was determined by flipping a coin. Fourteen practitioners were tested 10 times each, and 7 practitioners were tested 20 times each. MAIN OUTCOME MEASURE: Practitioners of TT were asked to state whether the investigator's unseen hand hovered above their right hand or their left hand. To show the validity of TT theory, the practitioners should have been able to locate the investigator's hand 100% of the time. A score of 50% would be expected through chance alone. RESULTS: Practitioners of TT identified the correct hand in only 123 (44%) of 280 trials, which is close to what would be expected for random chance. There was no significant correlation between the practitioner's score and length of experience (r=0.23). The statistical power of this experiment was sufficient to conclude that if TT practitioners could reliably detect a human energy field, the study would have demonstrated this. CONCLUSIONS: Twenty-one experienced TT practitioners were unable to detect the investigator's "energy field." Their failure to substantiate TT's most fundamental claim is unrefuted evidence that the claims of TT are groundless and that further professional use is unjustified.

Humans↗