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 109 records · Page 6Linked to original sources
PubMed1990

Semen analysis and fertility assessment in rabbits: statistical power and design considerations for toxicology studies.

Semen analysis is commonly used in evaluating human response to reproductive toxicants. Serial semen samples can be collected from rabbits and fertility assessed by artificial insemination, hence this species is potentially well suited for male reproductive toxicity studies that might be extrapolated to humans. However, the size and cost of rabbits often restricts the number of animals used, reducing the sensitivity of such studies. Therefore, it was of interest to optimize study design for semen analysis and fertility assessment in rabbits. Semen samples were collected weekly from sexually mature New Zealand white rabbits and a range of parameters was analyzed (Semen--pH, volume, osmolality; Sperm--number and concentration, morphology, viability, percentage motility, motion characteristics; Seminal plasma--fructose, citric acid, carnitine and protein concentrations, acid phosphatase activity). Male fertility was assessed by inseminating female rabbits with the minimum number of motile sperm required for normal fertility, determined to be one million. The within- and between-buck variabilities were determined for all parameters and used to calculate the statistical power of different study designs. The variability of sperm number and concentration was decreased when measured in four ejaculates collected within a short period of time rather than in a single ejaculate; this was not true of other endpoints measured. In addition, use of preexposure observations further increased the statistical power for all of the parameters. These data can be used to determine the optimum design for studies of male reproductive toxicity using rabbits, with particular regard to cost and the number of animals used.

Acid Phosphatase↗
PubMed2000

Computer-assisted EEG monitoring during carotid endarterectomy.

The purpose of this study was to develop a reliable method of EEG analysis during carotid endarterectomy. EEGs of 104 patients under general anesthesia were processed by three different methods: a) "on-line" visual analysis during surgery, b) "off-line" visual analysis in laboratory, and c) computer analysis. To identify pathological EEGs, variability and asymmetry indexes of the 0.5-3.5 Hz and 8-15 Hz bands, absolute power and variability indexes of spectral edge frequency (SEF), and main dominant frequency were evaluated. On-line visual analysis showed clamp-related modifications in 29 EEGs (27.9%). Off-line visual analysis detected 24 pathological EEGs (23.1%): 18 with major changes and 6 with moderate changes. Computer analysis showed 21 EEGs (20.19%) with at least one altered index and 7 (6.7%) with altered variability for both SEF and 8-15 Hz power. The statistical analysis was significant for SEF variability and for 8-15 Hz power variability and asymmetry (P < 0.0001, analysis of variance test). While SEF and 8-15 Hz power variability did not appear influenced by anesthesia and single electrode artifacts, 8-15 Hz power asymmetry index was confounded by the presence of contralateral internal carotid occlusion. The data show that the use of these spectral indexes adds objective information to visual analysis, supporting and making easier intraoperative strategies. Their routine clinical use does not involve additional costs remaining technical requirements unchanged compared to traditional recording.

Aged↗
PubMed2004

Sleep in young adults with Asperger syndrome.

Asperger syndrome (AS) is a neurodevelopmental disorder belonging to autism spectrum disorders. Both children and adults with AS have subjective impairment in the initiation and continuity of sleep, and studies using objective assessment are sparse. Twenty young AS adults with frequent complaints of low sleep quality were compared to 10 age-, gender- and education-matched controls without sleep complaints using polysomnography and spectral power analysis of slow-wave sleep. AS subjects displayed a similar polysomnographic profile as compared with controls. In spectral power analysis, a statistically nonsignificant trend towards decreased relative delta power and increased theta power in slow-wave sleep was found in the AS group. It seems that nonorganic insomnia, due to anxiety inherent in AS, is responsible for the low sleep quality in these subjects.

Adult↗
PubMedDate not supplied

[Differential diagnosis of chronic obstructive lung disease, A statistical analysis of the discriminating power of various lung function tests (author's transl)].

Among 65 patients admitted to the hospital for chronic obstructive lung disease, the following pulmonary tests were systematically performed : spirometric vital capacity and total lung capacity, FEV1, functional residual capacity and total lung capacity measured by body plethysmography, airway resistance and specific conductance, CO diffusion capacity measured by single-breath test, N2 clearance by single breath oxygen dilution, and blood gases. The patients were divided into bronchitics, emphysematous and broncho-emphysematous, according to the clinical and radiological Nash's score, and to another personal score derived from the former. The simple and multiple correlations between the clinico-radiological score and the functional results are low. The clustering analysis groups the 65 patients into four clouds of points, around two principal axes : the volume axis and the overinflation axis. This study indicates that the most suggestive results for emphysema diagnosis are increased FRC and TLC and low Tlco/V'a. The clinical score is not dominant for the clustering of the patients into the dynamic clouds. Beneath the bronchitic, the broncho-emphysematous and the emphysematous groups, the clustering analysis individualizes a fourth group of cases characterized by chronic asthma, and which were not isolated by Nash's score.

Airway Resistance↗
PubMed1993

Current status of models for testing antibiotic residues.

Models for testing the effect of antibiotic residues on the human gut flora should be (i) feasible (quality of data, statistics, price, duration), (ii) sensitive (baseline resistance, background variability, response to low doses), and (iii relevant (composition and ecology of the flora, predictive value). An evaluation of existing models led to the following conclusions: 1. Flora. Relevant models must include anaerobic flora that antagonize colonization by minor bacterial populations. In vitro tests on pure strains, batch or continuous flow cultures, do not take this barrier effect into account. 2. Drug treatment. Treatment should be long enough to allow the detection of indirect selection due to a weakening of the barrier effect (i.e., greater than 15 days). For dose response analysis, trials should include at least 3 groups: a control group, an experimental group given the antibiotic at residue levels, and a positive control group given a high dose of the same drug. 3. Target strain(s). The target bacteria should be identified, resident in the gut, accurately countable, drug susceptible but with drug resistant variants, and related to a pathogen. Some gut aerobes meet these requirements: sensitive to the ecosystem balance, easy to count accurately, opportunistic pathogens, and R-plasmid carriers. Total anaerobes are not suitable. An anaerobe species may serve as a target strain if it is particularly susceptible to, or selected by, the test antibiotic. Thus, each in vivo protocol should be based on in vitro data. 4. Measure of resistance. The determination of the minimum inhibitory concentration (MIC) of selected clones from the model flora is time consuming, does not detect subdominant resistance (less than 1%); and a MIC shift is difficult to test statistically. In contrast, direct counting of bacteria on drug supplemented media allows for the rapid measure of minor resistant populations. 5. Statistics. Most published designs do not include a power calculation, nor yield enough data points for accurate statistical analysis. Sufficient statistical power is critical for studies using conventional humans and animals, because the data are highly variable and not normally distributed. 6. Human trials. The lowest level of antibiotic tested in human volunteers (2 mg oxytetracycline/day for 7 days in 6 subjects) increased the proportion of resistant fecal enterobacteria (p = 0.05). However, the large day-to-day and inter individual variation in the human flora limit the significance of this change. Confirmation of this finding would require a large number of volunteers.(ABSTRACT TRUNCATED AT 400 WORDS)

Animals↗
PubMed1995

Mammographic screening for women aged 40 to 49 years: the primary care practitioner's dilemma.

The data from population-based, randomized trials of the mammographic screening of women aged 40 to 49 years are limited by retrospective subgroup analysis, low statistical power, and the use of older mammographic techniques. Nonetheless, meta-analysis involving the most recently reported data from all similarly designed trials shows a 21% mortality reduction in women who have had mammographic screening compared with those in control groups, a statistically significant difference (upper bound of 95% Cl, 0.98). Evidence from modern mammography demonstration projects (which are limited by a lack of control groups and the unavailability of mortality results) also shows that the tumor size, axillary lymph node status, and stage of screening-detected breast cancers in women aged 40 to 49 years indicate that screening is at least as beneficial for these women as it is for those aged 50 to 64 years, for whom mammographic screening is widely accepted. Overall, the evidence suggests that screening will benefit women aged 40 to 49 years, but some argue that the level of proof provided is not rigorous enough to establish the efficacy of screening. In the United States, more than 10,000 deaths per year occur among women who develop breast cancer between the ages of 40 and 49. Thousands of lives are probably lost each year because women are not being screened. We believe that it is much more prudent to endorse mammographic screening now, risking the unlikely subsequent determination that the effort was ineffective, than to withhold screening until it is determined whether "proof" of efficacy will be obtained, risking the loss of so many lives. We urge primary care practitioners to recommend routine mammography for women aged 40 to 49 years.

Adult↗
PubMed2003

Bootstrap approach to inference and power analysis based on three test statistics for covariance structure models.

We study several aspects of bootstrap inference for covariance structure models based on three test statistics, including Type I error, power and sample-size determination. Specifically, we discuss conditions for a test statistic to achieve a more accurate level of Type I error, both in theory and in practice. Details on power analysis and sample-size determination are given. For data sets with heavy tails, we propose applying a bootstrap methodology to a transformed sample by a downweighting procedure. One of the key conditions for safe bootstrap inference is generally satisfied by the transformed sample but may not be satisfied by the original sample with heavy tails. Several data sets illustrate that, by combining downweighting and bootstrapping, a researcher may find a nearly optimal procedure for evaluating various aspects of covariance structure models. A rule for handling non-convergence problems in bootstrap replications is proposed.

Humans↗
PubMed2002

Advice on statistical analysis for Circulation Research.

Since the late 1970s when many journals published articles warning about the misuse of statistical methods in the analysis of data, researchers have become more careful about statistical analysis, but errors including low statistical power and inadequate analysis of repeated-measurement studies are still prevalent. In this review, several statistical methods are introduced that are not always familiar to basic and clinical cardiologists but may be useful for revealing the correct answer from the data. The aim of this review is not only to draw the attention of investigators to these tests but also to stress the conditions in which they are applicable. These methods are now generally available in statistical program packages. Researchers need not know how to calculate the statistics from the data but are required to select the correct method from the menu and interpret the statistical results accurately. With the choice of appropriate statistical programs, the issue is no longer how to do the test but when to do it.

Analysis of Variance↗
PubMed1989

Satisfied conclusion validity of early intervention research with handicapped children.

The statistical conclusion validity of early intervention research studies was examined by conducting a post hoc power analysis of 484 statistical tests from 49 early intervention articles. Statistical power determinations were made based on Cohen's (1977) criteria for small, medium, and large effect sizes. The analysis revealed that the median power to detect small, medium, and large effect sizes ranged from .08 to .46. Four percent of early intervention studies had adequate power (.80 or greater) to detect medium intervention effects and 18% to detect large intervention effects. The power values suggest poor statistical conclusion validity in the analyzed research and should alert investigators to the possibility of Type II experimental errors in the early intervention research literature. The argument is made that low statistical conclusion validity has practical consequences in relation to program evaluation and cost-effectiveness determinations.

Child, Preschool↗
PubMedDate not supplied

Intraocular lens power calculation for cataract surgery after photorefractive keratectomy for high myopia.

OBJECTIVE: To assess intraocular lens (IOL) power calculations in patients undergoing cataract surgery after excimer laser photorefractive keratectomy (PRK) for myopia. METHODS: Four eyes of two patients underwent phacoemulsification with IOL implantation after PRK for myopia. The estimated refractive error that would have been induced had the IOL predicted for emmetropia been implanted was calculated using SRK-II, SRK/T, Holladay, and Binkhorst formulas. Manual keratometry and videokeratography-simulated keratometry values measured before surgery were used. Keratometry values calculated by subtracting the refractive change induced by the excimer laser PRK from the manual keratometry or videokeratography-simulated keratometry values measured before PRK were also used. Both spectacle and corneal plane calculations were performed. RESULTS: Manual keratometry and videokeratography-simulated keratometry values underpredicted the IOL power. Corneal plane manual or videokeratography refraction-derived keratometry calculations were most accurate using the SRK/T formula, while spectacle plane calculations were most accurate using the SRK-II formula. In both methods the calculated refractive error was within 0.52 diopters (D) for the emmetropic lens power predicted. Statistical analysis was not performed. CONCLUSIONS: Refraction-derived keratometric values provided the most accuracy in calculating IOL powers. Our results suggest the SRK/T formula was the most accurate for corneal plane calculations, while the SRK-II formula was the most accurate for spectacle plane calculations.

Cornea↗
PubMed1995

[Studies and recommendations on the design ov ROC analyses in nuclear medicine].

ROC analysis is the method of choice for an objective assessment of diagnostic tests; however, it requires large sample sizes. We investigated the influence of study design and data analysis on sampling requirements. A sample size of 123 for the patient as well as the control group, is required to prove a difference in sensitivity of 75% vs 90% (specificity 90%, statistical power 0.8). Analysis with the binormal bivariate ROC model allows > 35% reduction in sample size. If the patient group is increased the control group can be smaller, and vice versa; here the correlated ROC model also allows substantial decreases in sample size. If both diagnostic tests are performed in the same patient and control group and evaluated with the correlated ROC model, an objective, statistically sound assessment of diagnostic performance is possible with relatively small samples.

Analysis of Variance↗
PubMed1980

A comparison of trimipramine and imipramine: a controlled study.

Trimipramine, a new tricyclic antidepressant, was compared to imipramine in 38 hospitalized depressives. Both groups improved, with no major differences seen between the drugs. Analysis of the power of the statistical analysis shows that it is very unlikely that a true difference was present and not detected. There were fewer adverse reactions to trimipramine.

Adult↗
PubMed2001

Comparing meta-analysis and ecological-longitudinal analysis in time-series studies. A case study of the effects of air pollution on mortality in three Spanish cities.

STUDY OBJECTIVE: The objective of this paper is to introduce a different approach, called the ecological-longitudinal, to carrying out pooled analysis in time series ecological studies. Because it gives a larger number of data points and, hence, increases the statistical power of the analysis, this approach, unlike conventional ones, allows the complementation of aspects such as accommodation of random effect models, of lags, of interaction between pollutants and between pollutants and meteorological variables, that are hardly implemented in conventional approaches. DESIGN: The approach is illustrated by providing quantitative estimates of the short-term effects of air pollution on mortality in three Spanish cities, Barcelona, Valencia and Vigo, for the period 1992-1994. Because the dependent variable was a count, a Poisson generalised linear model was first specified. Several modelling issues are worth mentioning. Firstly, because the relations between mortality and explanatory variables were non-linear, cubic splines were used for covariate control, leading to a generalised additive model, GAM. Secondly, the effects of the predictors on the response were allowed to occur with some lag. Thirdly, the residual autocorrelation, because of imperfect control, was controlled for by means of an autoregressive Poisson GAM. Finally, the longitudinal design demanded the consideration of the existence of individual heterogeneity, requiring the consideration of mixed models. MAIN RESULTS: The estimates of the relative risks obtained from the individual analyses varied across cities, particularly those associated with sulphur dioxide. The highest relative risks corresponded to black smoke in Valencia. These estimates were higher than those obtained from the ecological-longitudinal analysis. Relative risks estimated from this latter analysis were practically identical across cities, 1.00638 (95% confidence intervals 1.0002, 1.0011) for a black smoke increase of 10 microg/m(3) and 1.00415 (95% CI 1.0001, 1.0007) for a increase of 10 microg/m(3) of sulphur dioxide. Because the statistical power is higher than in the individual analysis more interactions were statistically significant, especially those among air pollutants and meteorological variables. CONCLUSIONS: Air pollutant levels were related to mortality in the three cities of the study, Barcelona, Valencia and Vigo. These results were consistent with similar studies in other cities, with other multicentric studies and coherent with both, previous individual, for each city, and multicentric studies for all three cities.

Air Pollutants↗
PubMed2001

Simultaneous measurement of cerebral blood flow and mRNA signals: pixel-based inter-modality correlational analysis.

The analysis of pixel-based relationships between local cerebral blood flow (LCBF) and mRNA expression can reveal important insights into brain function. Traditionally, LCBF and in situ hybridization studies for genes of interest have been analyzed in separate series. To overcome this limitation and to increase the power of statistical analysis, this study focused on developing a double-label method to measure local cerebral blood flow (LCBF) and gene expressions simultaneously by means of a dual-autoradiography procedure. A 14C-iodoantipyrine autoradiographic LCBF study was first performed. Serial brain sections (12 in this study) were obtained at multiple coronal levels and were processed in the conventional manner to yield quantitative LCBF images. Two replicate sections at each bregma level were then used for in situ hybridization. To eliminate the 14C-iodoantipyrine from these sections, a chloroform-washout procedure was first performed. The sections were then processed for in situ hybridization autoradiography for the probes of interest. This method was tested in Wistar rats subjected to 12 min of global forebrain ischemia by two-vessel occlusion plus hypotension, followed by 2 or 6 h of reperfusion (n=4-6 per group). LCBF and in situ hybridization images for heat shock protein 70 (HSP70) were generated for each rat, aligned by disparity analysis, and analyzed on a pixel-by-pixel basis. This method yielded detailed inter-modality correlation between LCBF and HSP70 mRNA expressions. The advantages of this method include reducing the number of experimental animals by one-half; and providing accurate pixel-based correlations between different modalities in the same animals, thus enabling paired statistical analyses. This method can be extended to permit correlation of LCBF with the expression of multiple genes of interest.

Algorithms↗
PubMed2005

A model of the statistical power of comparative genome sequence analysis.

Comparative genome sequence analysis is powerful, but sequencing genomes is expensive. It is desirable to be able to predict how many genomes are needed for comparative genomics, and at what evolutionary distances. Here I describe a simple mathematical model for the common problem of identifying conserved sequences. The model leads to some useful rules of thumb. For a given evolutionary distance, the number of comparative genomes needed for a constant level of statistical stringency in identifying conserved regions scales inversely with the size of the conserved feature to be detected. At short evolutionary distances, the number of comparative genomes required also scales inversely with distance. These scaling behaviors provide some intuition for future comparative genome sequencing needs, such as the proposed use of "phylogenetic shadowing" methods using closely related comparative genomes, and the feasibility of high-resolution detection of small conserved features.

Animals↗
PubMed1997

Silicon tissue assay: a measurement of capsular levels from chemotherapeutic port-a-catheter devices.

A plethora of data has been used to condemn and defend the role of silicone and its association with "adjuvant disease." In the ongoing attempt to enhance our knowledge, we have chosen to identify tissue silicon levels (n = 15) in capsules that form around chemotherapeutic port-a-catheter devices, which consist of a metal dome encapsuled by silicone. We have compared these levels with previously established silicon levels in augmented breast capsules, distant tissue sites in these same augmented women, and nonaugmented cadaveric tissues from various geographic locations in the United States. All specimens were harvested by a "no touch" technique, not formalin fixed, frozen, and shipped to an independent toxicology laboratory for analysis. Inductively coupled plasma atomic emission spectroscopy was employed to obtain the tissue silicon measurements. Results demonstrated silicon values ranging from nondetectable in 9 patients to as high as 41 micrograms/gm. These values fell in between our cadaveric (0.5 to 6.8 micrograms/gm) and augmented tissue silicon levels (18 to 8700 micrograms/gm). Although the sample size is small and the power of statistical analysis is low, there was no correlation between the patient's silicon level and age, type of cancer, type of chemotherapeutic agent, radiation therapy, or length of time the port-a-catheters were in place. Although detectable levels of silicon identified around port-a-catheter devices were higher than expected, it is impossible to make any conclusions about these levels and the role of a potential collagen-vascular disease. What we have shown, however, is that silicone breast implants may not be the only medical device that can elevate tissue silicon levels. Our data seem to suggest that there may be a progression of measurable tissue silicon levels based on the amount of environmental or device-related silicon exposure a person has had at a particular time in his or her life. It is our belief that as we identify these tissue silicon levels, they will serve as a baseline and reference for further scientific studies.

Adolescent↗
PubMed1985

Reporting methodology protocols in three acute care journals.

Our study compared the reporting of methodology protocol details in three acute care journals, Annals of Emergency Medicine, Critical Care Medicine, and Journal of Trauma. Eleven criteria previously reported for evaluation of clinical trials in the medical literature were used. These were eligibility criteria, admission before allocation, random allocation, method of randomization, patients' blindness to treatment, blind assessment of outcome, treatment complications, loss to follow-up, statistical methods, statistical analysis, and power. All prospective, interventional, controlled trials appearing in the journals from January 1980 to June 1983 were identified. A total of 45 trials was found. Each study was read independently by two reviewers to determine whether each of the 11 criteria was reported clearly, reported unclearly, or not applicable. Disagreements were resolved by a third reader (adjudicator). The results are reported as the mean proportion of items clearly reported plus or minus the standard deviation: Annals of Emergency Medicine (n = 16), 0.40 +/- 0.18; Journal of Trauma (n = 18), 0.41 +/- 0.24; Critical Care Medicine (n = 11), 0.35 +/- 0.18. A one-way analysis of variance found no statistically significant difference between journals with respect to these proportions (P = .75). The study reveals that these journals, as judged by these criteria, do not report enough methodologic information to allow assessment of bias-reducing techniques and statistical methodology.

Analysis of Variance↗