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 631 records · Page 35Linked to original sources
PubMed2006

A new method in applying power spectral statistics to examine cardio-respiratory interactions in fish.

Power spectral analysis (PSA) provides a powerful tool for determining frequency oscillations in time signals, and it is accepted that mammals can show distinct components in the heart rate (fH) spectrum that are synchronous with ventilatory frequency (fV). Using similar signal processing techniques, these fundamental components at fV are not apparent in the spectrum calculated from fish fH. Here we compare conventional PSA on the R-R interval tachogram generated from ECG traces recorded in rats and fish, with PSA on the raw ECG waveform. The rat R-R tachogram showed a defined sigmoidal component, whereas the fish R-R tachogram was a more chaotic waveform. In agreement with the literature, PSA of these respective waveforms produced a component at the same frequency as ventilation in the rat, but of lower frequency than ventilation for the fish. Applying PSA to the rat ECG produced a spectrum with a fundamental component of similar frequency to that observed in the R-R tachogram spectrum, indicating that the latter adequately contained heart rate variability (HRV) oscillations. However, PSA of the ECG in fish contrasted with that from the R-R tachogram, with components observed in the latter spectrum being absent from the former. This suggests that the frequency components determined by PSA on the fish R-R tachogram were not true components, but were aliased (or folded-back) from higher up in the spectrum. Using established aliasing equations, recalculation of these peaks showed that their true frequency was similar to that of the ventilatory frequency for individual fish. The extent of cardio-respiratory interaction, resulting in fV < f(H/2) in rats but fV > f(H/2) in fish, is suggested to be the origin of the differences observed.

Animals↗
PubMed2006

Determinants of operative mortality in valvular heart surgery.

OBJECTIVE: In some respects, outcome reporting in valvular surgery has been hampered by focusing on specific populations, reluctance to publish high-risk subgroups, and possibly skewed or inadequate samples. The goal of this study was to evaluate risk factors for operative mortality comprehensively across the entire spectrum of cardiac valvular procedures over the past decade. METHODS: All 409,904 valve procedures in the Society of Thoracic Surgeons database performed between 1994 and 2003 were assessed, and Society of Thoracic Surgeons preoperative and operative variables were related to operative mortality by using a multivariable logistic regression model. Data were greater than 95% complete, and the relative importance of relevant risk factors was determined by ranking odds ratios. The analysis had a high predictive power, with a C statistic of 0.735. RESULTS: In the model, 19 variables independently influenced operative mortality (all P < .01). The most significant was nonelective (acute) presentation (odds ratios, 2.11), followed by advanced age (odds ratios, 1.88), reoperation (odds ratios, 1.61), endocarditis (odds ratios, 1.59), and coronary disease (odds ratios, 1.58). Generally, valve replacement was associated with higher mortality than repair (odds ratios, 1.52). Overall, female gender was very important (odds ratios, 1.37), and earlier year of operation increased risk (odds ratios, 1.34), implying improving outcomes over time. Although any single comorbidity, on average, was only moderately contributory (odds ratios, 1.19), specific comorbidities, such as renal failure, or multiple comorbidities in a given patient could be very significant. Aortic root reconstruction carried the highest risk (odds ratios, 2.78), followed by tricuspid valve surgery (odds ratios, 2.26), multiple valve procedures (odds ratios, 2.06), and then isolated mitral (odds ratios, 1.47), pulmonic (odds ratios, 1.29), and aortic (reference procedure) operations. Reduced ejection fraction and severity of valve lesion were relatively less important (odds ratios, 1.34 and 0.83, respectively). CONCLUSIONS: These data illustrate the significance of acute presentation in determining operative risk, and earlier surgical intervention under elective conditions might be emphasized for all types of significant valve lesions. Because aortic root reconstruction doubles mortality compared with simple aortic valve procedures, root replacement should be reserved for specific root pathology. Finally, issues related to reoperation, endocarditis, valve repair, gender, and the various procedures deserve more detailed examination.

Aged↗
PubMed2004

The sense of belonging to a neighbourhood: can it be measured and is it related to health and well being in older women?

This study investigates the sense of belonging to a neighbourhood among 9445 women aged 73-78 years participating in the Australian Longitudinal Study on Women's Health. Thirteen items designed to measure sense of neighbourhood were included in the survey of the older women in 1999. Survey data provided a range of measures of demographic, social and health-related factors to assess scale construct validity. Factor analysis showed that seven of the items loaded on one factor that had good face validity and construct validity as a measure of the sense of neighbourhood. Two of the remaining items related to neighbourhood safety and comprised a factor. A better sense of neighbourhood was associated with better physical and mental health, lower stress, better social support and being physically active. Women who had lived longer at their present address had a better sense of belonging to their neighbourhood, as did women living in non-urban areas and who were better able to manage on their income. Feeling safe in the neighbourhood was least likely in urban areas, increased in rural townships, and was most likely in rural and remote areas. Older women living alone felt less safe, as did women who were less able to manage on their income. This study has identified two sets of items that form valid measures of aspects of the social environment of older women, namely the sense of neighbourhood and feelings of safety. These findings make a contribution to our understanding of the relationship between feelings of belonging to a neighbourhood and health in older women.

Aged↗
PubMed1994

Recipes for psychotherapy.

Stiles and Shapiro (1994) try to make a case for abandoning the model of drug research in exploring psychotherapy effectiveness--specifically, the idea that psychotherapy can be viewed in terms of effective "ingredients." Although provocative, their analysis can be challenged on methodological grounds involving failure to use multivariate analytic approaches, incomplete exploitation of advantages of growth curve analysis, and lack of attention to issues of statistical power. Acceptance of the conclusions proffered by Stiles and Shapiro would have negative effects on psychotherapy research and practice, and the case against the search for effective elements in psychotherapy process is not yet strongly made.

Humans↗
PubMed2002

Coefficient of failure: a methodology for examining longitudinal beta-cell function in Type 2 diabetes.

AIMS: We describe a new method, the determination of the coefficient of failure, which allows the assessment of beta-cell failure from any index of glycaemia. Previous methods using glycaemic thresholds and calculating time-to-failure have systematic deficiencies relating to bias, reproducibility and statistical power. Analyses using threshold methodologies and conventional survival analysis have an intrinsic disadvantage in that they use categorical data and thus make no allowance for near-failure, or progression towards failure. In contrast, the coefficient of failure includes all data in the analysis and takes into account improvement of glycaemia as well as deterioration of glycaemia. METHODS: We describe the use of a 'coefficient of failure' defined as the slope of the least-squares regression line of a glycaemic index vs. time calculated for each individual patient on constant monotherapy. We exemplify the method using HbA1c levels from data from patients on chlorpropamide (n = 64) or glibenclamide (n = 65) monotherapy in the Oxford cohort of the UKPDS. RESULTS: Chlorpropamide-treated patients showed a mean coefficient of failure of 0.34 HbA(1c)%/year (0.44%/year sd) and glibenclamide-treated patients 0.50 HbA(1c)%/year (0.50%/year sd) (P = 0.046; unpaired two-tailed t-test). Kolmogorov-Smirnov testing demonstrated that the coefficients did not differ significantly from a normal distribution (chlorpropamide P = 0.12; glibenclamide P = 0.13). CONCLUSIONS: The coefficient of failure gives an estimate of beta-cell failure using any index of glycaemia. The coefficient is not constrained by predetermined glycaemic thresholds for failure and it allows the rate of decline in beta-cell function to be determined on any therapy or combination of therapies.

Chlorpropamide↗
PubMed1997

Measures of line jaggedness and their use in foods textural evaluation.

The jaggedness of signatures, such as the force-displacement curves of brittle cereal-based foods, can be a manifestation of physical processes. Consequently, it should be regarded as an inherent property of the system rather than noise that should be discarded. Changes in the degree of jaggedness can provide useful information on the system's performance or on how it is affected by external conditions, such as exposure to moisture. Quantitative assessment of the degree of jaggedness can be done by methods that include statistical analysis, conversion of the record into a Fourier power spectrum, and determination of its apparent fractal dimension. Most can be performed with microcomputers and commercially available software. It is recommended that the jaggedness of any experimental curve or signature be determined by at least two methods or algorithms simultaneously for mutual verification. The magnitude of any single measure of jaggedness is determined by the signature's fluctuations amplitude and frequency. While the amplitude effect can be accounted for by normalization, the frequency cannot. Consequently, only curves having about the same number of points at the pertinent interval can be meaningfully compared. There is, however, a mathematical method, at this time still empirical, that allows meaningful comparison of the jaggedness of signatures obtained at different sampling rates. When several or numerous jagged signatures are recorded simultaneously, as in the case of brittle particulates compressed in bulk, the resulting combined signature is considerably smoothed. This is primarily the result of averaging caused by mutual cancellation of peaks in different directions and reducing the relative weight of any large peak. However, there are mathematical methods, some partly empirical, that enable restoration of the jaggedness of the original signatures.

Algorithms↗
PubMed1999

Allowing for missing parents in genetic studies of case-parent triads.

In earlier work, my colleagues and I described a log-linear model for genetic data from triads composed of affected probands and their parents. This model allows detection of and discrimination between effects of an inherited haplotype versus effects of the maternal haplotype, which presumably would be mediated by prenatal factors. Like the transmission disequilibrium test (TDT), the likelihood-ratio test (LRT) based on this model is not sensitive to associations that are due to genetic admixture. When used as a method for testing for linkage disequilibrium, the LRT can be regarded as an alternative to the TDT. When one or both parents are missing, the resulting incomplete triad must be discarded to ensure validity of the TDT, thereby sacrificing information. By contrast, when the problem is set in a likelihood framework, the expectation-maximization algorithm allows the incomplete triads to contribute their information to the LRT without invalidation of the analysis. Simulations demonstrate that much of the lost statistical power can be recaptured by means of this missing-data technique. In fact, power is reasonably good even when no triad is complete-for example, when a study is designed to include only mothers of cases. Information from siblings also can be incorporated to further improve the statistical power when genetic data from parents or probands are missing.

Algorithms↗
PubMed2005

mILD: a tool for constructing and analyzing matrices of pairwise phylogenetic character incongruence tests.

SUMMARY: Pairwise comparisons of disagreement in phylogenetic datasets offer a powerful tool for isolating historical incongruence for closer analysis. Statistically significant phylogenetic character incongruence may reflect important differences in evolutionary history, such as horizontal gene transfer. Such testing can also be used to specify possible combinations of datasets for further phylogenetic analysis. The process of comparing multiple datasets can be very time consuming, and it is sometimes unclear how to combine data partitions given the observed patterns of incongruence. Here we present an application that automates the process of making pairwise comparisons between large numbers of phylogenetic datasets using the Incongruence Length Difference (ILD) test. The application also implements strategies for data combination based on the patterns of incongruence observed in pairwise comparisons.

Algorithms↗
PubMed1999

Statistical limitations in functional neuroimaging. II. Signal detection and statistical inference.

The field of functional neuroimaging (FNI) methodology has developed into a mature but evolving area of knowledge and its applications have been extensive. A general problem in the analysis of FNI data is finding a signal embedded in noise. This is sometimes called signal detection. Signal detection theory focuses in general on issues relating to the optimization of conditions for separating the signal from noise. When methods from probability theory and mathematical statistics are directly applied in this procedure it is also called statistical inference. In this paper we briefly discuss some aspects of signal detection theory relevant to FNI and, in addition, some common approaches to statistical inference used in FNI. Low-pass filtering in relation to functional-anatomical variability and some effects of filtering on signal detection of interest to FNI are discussed. Also, some general aspects of hypothesis testing and statistical inference are discussed. This includes the need for characterizing the signal in data when the null hypothesis is rejected, the problem of multiple comparisons that is central to FNI data analysis, omnibus tests and some issues related to statistical power in the context of FNI. In turn, random field, scale space, non-parametric and Monte Carlo approaches are reviewed, representing the most common approaches to statistical inference used in FNI. Complementary to these issues an overview and discussion of non-inferential descriptive methods, common statistical models and the problem of model selection is given in a companion paper. In general, model selection is an important prelude to subsequent statistical inference. The emphasis in both papers is on the assumptions and inherent limitations of the methods presented. Most of the methods described here generally serve their purposes well when the inherent assumptions and limitations are taken into account. Significant differences in results between different methods are most apparent in extreme parameter ranges, for example at low effective degrees of freedom or at small spatial autocorrelation. In such situations or in situations when assumptions and approximations are seriously violated it is of central importance to choose the most suitable method in order to obtain valid results.

Biometry↗
PubMed1993

Quantitative analysis of lymphocyte CD11a using standardized flow cytometry.

CD11a is the alpha-subunit of the leucocyte adhesion and costimulation molecule LFA-1. We have refined the measurement of lymphocyte CD11a density with a FACScan using commercially available fluorescent beads for standardization and fluorescein-conjugated antibody to CD11a of known fluorescein: protein ratio. The fluorescence intensity of CD11a on peripheral blood CD4+ and CD8+ lymphocytes was measured in 60 healthy subjects. We demonstrated linear correlation between age and mean CD11a density (r = 0.47 for CD4+ cells, r = 0.71 for CD8+ cells). We established that there is a consistent logical cut off point at 4.3 x 10(3) bound antibody molecules between low-expressing and high-expressing subsets of CD8+ cells and we then investigated whether the variation in lymphocyte CD11a expression in healthy subjects was sufficiently small for the application of this method to the detection of abnormal groups or individuals. Analysis of the CD11a high subsets has high statistical power (> 99% in 60 subjects to detect a 25% difference) and good precision (< 4% differences). The advantages of the method for comparative studies of cell surface accessory molecules are discussed. We have also evaluated a frozen cell line for quality control, and demonstrated up-regulation of CD11a density on CD4+ and CD8+ cells measured in three patients with infectious mononucleosis.

Adolescent↗
PubMed2004

Nonlinear relationships and phylogenetically independent contrasts.

The method of phylogenetically independent contrasts is commonly used for exploring cross-taxon relationships between traits. Here we show that this phylogenetic comparative method (PCM) can fail to detect correlated evolution when the underlying relationship between traits is nonlinear. Simulations indicate that statistical power can be dramatically reduced when independent contrasts analysis is used on nonlinear relationships. We also reanalyze a published data set and demonstrate that ignoring nonlinearity can affect biological inferences. We suggest that researchers consider the shape of the relationship between traits when using independent contrasts analysis. Alternative PCMs may be more appropriate if data cannot be transformed to meet assumptions of linearity.

Animals↗
PubMed1991

EEG characteristics in males at risk for alcoholism.

Baseline EEG activity was recorded with eyes closed in 15 males, aged 19 to 24 at risk (HR = high risk) for the development of alcoholism and 15 matched controls (LR = low risk). Four EEG frequency bands were examined: slow alpha (7.5-10 Hz), fast alpha (10.25-12.75 Hz), slow beta (13-19.5 Hz) and fast beta (19.75-26 Hz). The HR and LR groups were compared on four measures of EEG activity for each frequency band: band power, absolute and relative area and laterality differences. Statistical analysis of the data via ANOVA revealed no significant difference between the HR and LR groups for any comparison. The results indicate that EEG measures prior to alcohol administration do not effectively discriminate between individuals at high and low risk for alcoholism.

Adult↗
PubMed1974

Microculture plaque neutralization test for California group arboviruses.

A microculture plaque neutralization test is described for California-group arboviruses that is as precise and quantitative as the standard test conducted in 60-mm petri dishes. It was shown that there was no significant between-panel or between-day variation in determinations and that a single pipette could be used for all serum-dilution levels within a titration without inoculum carry-over effect. The experimental protocol and statistical methods used produce 50% neutralization end points that meet the assumptions of parametric statistics. This permits the power and versatility of the analysis of variance to be exploited in testing for treatment effects in serological and immunological studies with viruses.

Analysis of Variance↗
PubMedDate not supplied

Power and sample size in cost-effectiveness analysis.

For resource allocation under a constrained budget, optimal decision rules for mutually exclusive programs require that the treatment with the highest incremental cost-effectiveness ratio (ICER) below a willingness-to-pay (WTP) criterion be funded. This is equivalent to determining the treatment with the smallest net health cost. The designer of a cost-effectiveness study needs to select a sample size so that the power to reject the null hypothesis, the equality of the net health costs of two treatments, is high. A recently published formula derived under normal distribution theory overstates sample-size requirements. Using net health costs, the authors present simple methods for power analysis based on conventional normal and on nonparametric statistical theory.

Bias↗
PubMed1983

Randomized clinical trials in neurosurgery.

Fifty-one randomized trials of neurosurgical topics have been identified. These have been analyzed for content, quality of reporting, and quality of statistical design and analysis. In general, there were major omissions in the reporting of critical portions of the studies, the statistical analysis was highly variable in quality, and the statistical power was low. Few, if any, major neurosurgical questions have been answered by clinical trials. This may reflect the generally low quality of these trials. To improve the quality of such trials, neurosurgeons must seek biostatistical advice in planning and conducting trials and must cooperate in multi-institutional trials to increase statistical power.

Clinical Trials as Topic↗
PubMed1989

Examination of specific nutrition/health behaviors using a social cognitive model.

Nutrition intervention programs are not always successful. In some cases, an insufficient understanding of the interrelationships among factors influencing health behaviors may be responsible for the failures. This study used social cognitive theory, a framework for studying behaviors, to structure the relationships between measurable factors important to the frequency of health-oriented food consumption. We developed a model that incorporated factors for social environment, reinforcement, commitment, behavior modeling, knowledge, and attitude relative to the frequency of consumption of four beverages (whole milk, low-fat/skin milk, regular soda, and diet soda). Four-hundred fifty-seven middle-aged adults (mean age, 47 years; 58% female) and 709 college students (mean age, 21 years; 50% female) responded to a written questionnaire designed as a self-report on frequency of consumption and measures for 10 social cognitive variables. For all four beverages, the model explained 35% or more of the variance in frequency of consumption, thus confirming its predictive power. We used the statistical approach known as path analysis to examine the relationships within the model. The analysis demonstrated that factors influencing the consumption varied between the two age groups (e.g., nutrition knowledge was related to attitude in adult soda-drinking models but not in student soda-drinking models) and between forms of the beverages (e.g., for student models, nutrition knowledge was related to taste enjoyment for low-fat/skim milk but not for whole milk).(ABSTRACT TRUNCATED AT 250 WORDS)

Adult↗
PubMed1987

[Value of quantitative EEG and EEG mapping in medicine].

Quantitative EEG consists in digitising the EEG from one or several leads and then mathematically processing the signal usually by Fourier spectral analysis. A reduction of the digital information gives characteristic parameters (frequency, amplitude or power, asymmetry, etc.), which can themselves be averaged and submitted to different statistical analysis. Quantitative EEG is particularly suitable for clinical electropharmacology for the assessment of the profiles of psychotropic drugs, for pharmacokinetic correlations of dose-effect relationships and studies of drug bioavailability. The signals obtained from schizophrenic and depressed patients have well defined quantitative EEG characteristics: dissymmetry of the amplitude and hypovariability of the EEG signals. EEg mapping is performed by computer processing of 16 simultaneous EEG lead recordings. This new form of medical imaging is fast, relatively economical and non-invasive, and it is used in psychophysiology to study cognitive tasks and the states of vigilance and sleep. It is also used to study the EEG topography of cerebrovascular accidents, brain tumours, cranial trauma, cerebral degeneration and dementia, and the EEGs of psychiatric patients on psychotropic drugs. EEG mapping represents not only a static and statistical approach by drawing the averaged maps of groups of patients but also a dynamic approach by the recording of sequential individual maps presented as an animated film. The results of this method can be correlated with other medical imaging techniques used to investigate the central nervous system.

Brain Diseases↗
PubMedDate not supplied

Psychometric assessment of the Jalowiec Coping Scale.

The Jalowiec Coping Scale consists of 40 coping behaviors culled from a comprehensive literature review, which are rated on a 1- to 5-point scale to indicate degree of use. Twenty judges classified the items to permit analysis of the coping behaviors according to a problem-oriented/affective-oriented dichotomy; 15 problem and 25 affective items resulted. Overall agreement by the judges was 85%, with greater consensus on problem items. Evaluation of stability using a two-week retest interval (N = 28) yielded significant rhos of .79 for total coping scores, .85 for problem, and .86 for affective. With a one-month interval (N = 30) coefficients were .78, .84, and .83, respectively. Alpha reliability coefficients of .86 (N = 141) and .85 (N = 150) supported instrument homogeneity. Content validity is substantiated by the systematic manner of tool development, by the large number of items used, and by the inclusion of diverse coping behaviors. Factor analysis (N = 141) was used to investigate construct validity. A two-factor solution to evaluate the validity of the dichotomous classification showed that 80% of the problem items loaded on Factor I, but only 56% of the affective items loaded on Factor II. To examine this multidimensional aspect, several other factor solutions were explored. Ultimately, the four-factor solution provided the most intelligible conceptual pattern with the least loss of information. Conceptual composition of these factors is discussed, and several tentative labels for each factor are suggested.

Adaptation, Psychological↗