Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “STATISTICS”

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 685 records · Page 38Linked to original sources
PubMed2000

[Sem: a suitable statistical software adaptated for research in oncology].

Many softwares have been adapted for medical use; they rarely enable conveniently both data management and statistics. A recent cooperative work ended up in a new software, Sem (Statistics Epidemiology Medicine), which allows data management of trials and, as well, statistical treatments on them. Very convenient, it can be used by non professional in statistics (biologists, doctors, researchers, data managers), since usually (excepted with multivariate models), the software performs by itself the most adequate test, after what complementary tests can be requested if needed. Sem data base manager (DBM) is not compatible with usual DBM: this constitutes a first protection against loss of privacy. Other shields (passwords, cryptage...) strengthen data security, all the more necessary today since Sem can be run on computers nets. Data organization enables multiplicity: forms can be duplicated by patient. Dates are treated in a special but transparent manner (sorting, date and delay calculations...). Sem communicates with common desktop softwares, often with a simple copy/paste. So, statistics can be easily performed on data stored in external calculation sheets, and slides by pasting graphs with a single mouse click (survival curves...). Already used over fifty places in different hospitals for daily work, this product, combining data management and statistics, appears to be a convenient and innovative solution.

Clinical Trials as Topic↗
PubMed2003

The Association of Academic Health Sciences Libraries Annual Statistics: a thematic history.

The Annual Statistics of Medical School Libraries in the United States and Canada (Annual Statistics) is the most recognizable achievement of the Association of Academic Health Sciences Libraries in its history to date. This article gives a thematic history of the Annual Statistics, emphasizing the leadership role of editors and Editorial Boards, the need for cooperation and membership support to produce comparable data useful for everyday management of academic medical center libraries and the use of technology as a tool for data gathering and publication. The Annual Statistics' origin is recalled, and survey features and content are related to the overall themes. The success of the Annual Statistics is evident in the leadership skills of the first editor, Richard Lyders, executive director of the Houston Academy of Medicine-Texas Medical Center Library. The history shows the development of a survey instrument that strives to produce reliable and valid data for a diverse group of libraries while reflecting the many complex changes in the library environment. The future of the Annual Statistics is assured by the anticipated changes facing academic health sciences libraries, namely the need to reflect the transition from a physical environment to an electronic operation.

Annual Reports as Topic↗
PubMed2003

A demographic statistics service for the 21st century.

This article provides a summary of a review of the uses made of population and household statistics across government in England and Wales, setting out the policy and statistical impacts of demographic change. It looks at the broad span of government uses of population and household statistics--and what these uses imply for the qualities inherent in these statistics. The article considers alternative population definitions and refers to several ongoing projects that are aiming to enhance demographic statistics in England and Wales. Following an analysis of the key issues relating to the implementation of an improved statistical service, a series of action points for ONS emerging from the review is set out.

Data Collection↗
PubMed2004

Association between industry funding and statistically significant pro-industry findings in medical and surgical randomized trials.

BACKGROUND: Conflicting reports exist in the medical literature regarding the association between industry funding and published research findings. In this study, we examine the association between industry funding and the statistical significance of results in recently published medical and surgical trials. METHODS: We examined a consecutive series of 332 randomized trials published between January 1999 and June 2001 in 8 leading surgical journals and 5 medical journals. Each eligible study was independently reviewed for methodological quality using a 21-point index with 5 domains: randomization, outcomes, eligibility criteria, interventions and statistical issues. Our primary analysis included studies that explicitly identified the primary outcome and reported it as statistically significant. For studies that did not explicitly identify a primary outcome, we defined a "positive" study as one with at least 1 statistically significant outcome measure. We used multivariable regression analysis to determine whether there was an association between reported industry funding and trial results, while controlling for study quality and sample size. RESULTS: Among the 332 randomized trials, there were 158 drug trials, 87 surgical trials and 87 trials of other therapies. In 122 (37%) of the trials, authors declared industry funding. An unadjusted analysis of this sample of trials revealed that industry funding was associated with a statistically significant result in favour of the new industry product (odds ratio [OR] 1.9, 95% confidence interval [CI] 1.3-3.5). The association remained significant after adjustment for study quality and sample size (adjusted OR 1.8, 95% CI 1.1-3.0). There was a nonsignificant difference between surgical trials (OR 8.0, 95% CI 1.1-53.2) and drug trials (OR 1.6, 95% CI 1.1-2.8), both of which were likely to have a pro-industry result (relative OR 5.0, 95% CI 0.7-37.5, p = 0.14). INTERPRETATION: Industry-funded trials are more likely to be associated with statistically significant pro-industry findings, both in medical trials and surgical interventions.

Conflict of Interest↗
PubMed2006

Adjusted Rasch person-fit statistics.

Two frequently used parametric statistics of person-fit with the dichotomous Rasch model (RM) are adjusted and compared to each other and to their original counterparts in terms of power to detect aberrant response patterns in short tests (10, 20, and 30 items). Specifically, the cube root transformation of the mean square for the unweighted person-fit statistic, t, and the standardized likelihood-based person-fit statistic Z3 were adjusted by estimating the probability for correct item response through the use of symmetric functions in the dichotomous Rasch model. The results for simulated unidimensional Rasch data indicate that t and Z3 are consistently, yet not greatly, outperformed by their adjusted counterparts, denoted t* and Z3*, respectively. The four parametric statistics, t, Z3, t*, and Z3*, were also compared to a non-parametric statistic, HT, identified in recent research as outperforming numerous parametric and non-parametric person-fit statistics. The results show that HT substantially outperforms t, Z3, t*, and Z3* in detecting aberrant response patterns for 20-item and 30-item tests, but not for very short tests of 10 items. The detection power of t, Z3, t*, and Z3*, and HT at two specific levels of Type I error, .10 and .05 (i.e., up to 10% and 5% false alarm rate, respectively), is also reported.

Humans↗
PubMed1989

Weighted Kaplan-Meier statistics: a class of distance tests for censored survival data.

A class of statistics based on the integrated weighted difference in Kaplan-Meier estimators is introduced for the two-sample censored data problem. With positive weight functions these statistics are intuitive for and sensitive against the alternative of stochastic ordering. The standard weighted log-rank statistics are not always sensitive against this alternative, particularly if the hazard functions cross. Qualitative comparisons are made between the weighted log-rank statistics and these weighted Kaplan-Meier (WKM) statistics. A statement of null asymptotic distribution theory is given and the choice of weight function is discussed in some detail. Results from small-sample simulation studies indicate that these statistics compare favorably with the log-rank procedure even under the proportional hazards alternative, and may perform better than it under the crossing hazards alternative.

Biometry↗
PubMedDate not supplied

Statistical analysis in family medicine research.

Analysis of the data is an important stage in any research project. Statistical analysis allows us to summarize data with easily understood concepts, such as rates, means, medians, or standard deviations. Statistical analysis also allows us to judge whether differences or associations identified in the sample are merely the result of the random error associated with sampling, and it often provides a measure of the strength of the associations identified. While appropriate statistical analysis is crucial to any research endeavor, the success or failure of the project is more dependent upon what has been done prior to beginning data analysis, not after. This article reviews concepts fundamental to any statistical analysis, the primary reasons to submit data to analysis, and selection of the appropriate statistical test. The discussion is brief of necessity, and readers are encouraged to consult standard statistical texts for more detailed information.

Adult↗
PubMed1977

Applications of the Mantel-Haenszel statistic to the comparison of survival distributions.

In comparing two survival distributions, a Mantel-Haenszel statistic can be computed after each death as a non-linear two-sample rank statistic. The distributions of both the maximum and terminal statistics in such a sequence are studied numerically, in the absence of censoring, and appropriate critical values are determined. The maximum statistic is applied to simultaneous inference, and both the maximum and terminal statistics are used as the basis for early stopping procedures (especially in the pseudo-sequential context). Procedures based on the two statistics are compared for power and for early decision properties such as stopping index and (for exponential distributions) stopping time.

Biometry↗
PubMedDate not supplied

The measurement of the calibers and blood-flow velocities of the arteries of the circle of Willis: a statistical investigation of 120 living subjects using transcranial color-Doppler ultrasonography.

We have examined 120 subjects (52 men, 68 women; age range: 19 to 89) with no vascular pathology. In each subject, we used transcranial color-doppler ultrasonography to measure the calibers and blood-flow velocities of the anterior, middle, and posterior cerebral arteries (ACA, MCA, and PCA, respectively). Generally, the mean measured calibers were lower than those that have been described in cadaveric studies by other investigators. The mean caliber of the MCA was found to be higher than those of the ACA or PCA; this difference was statistically significant (p < 0.05). With age, the calibers of the ACA, PCA and PCA tended to increase, but this trend was not statistically significant. We have noted a statistically significant difference between the left and right sides, the arteries of the left being larger than those of the right. However, there was no statistically significant relationship between vessel caliber and age, sex, or body weight, though the women's arteries tended to be narrower than those of the men. With respect to the maximal and mean blood-flow velocities, no statistically significant relationships with regard to side (left or right), sex, age, or body weight were demonstrable. However, the mean and maximal blood-flow velocities of the MCA were found to be statistically higher than those of the ACA or PCA (p < 0.02). This was especially true under the age of 60 (p < 0.01).

Adult↗
PubMed1993

A new statistical appraisal of baseline ECG features for localization of accessory pathways.

In order to develop a better approach to accessory pathway localization, the authors analyzed 18 separate electrocardiographic characteristics in 93 consecutive patients. All patients had successful radiofrequency catheter ablation of a single accessory pathway causing preexcitation, prolonging QRS duration to > 100 ms, with 56 pathways ablated on the right side of the heart and 37 ablated on the left side. Eight individual locations were specified at the time of ablation, five right sided and three left sided. Initially, a simple statistical approach was used, with group mean statistical comparison for both delta-wave frontal axis and QRS horizontal transition lead being compared between adjacent locations by Student's t-test. Overlap between individual values was assessed by calculating the percentage of total pathway numbers in each of the two adjacent locations being compared that lay within an arc of 2 SDs in the direction of the location being compared. The statistical significance of all 18 variables was tested using univariate analysis and oneway analysis of variance for continuous variables and the chi-square test for categorical data. Post hoc tests performed were Scheffe's test for the analysis of variance and Bonferroni's test for the chi-square test. All electrocardiographic characteristics were then reanalyzed in a stepwise linear discriminant analysis using BMDP statistical software. A jack-knifed classification was made to assess the accuracy of classification. The statistical level for a characteristic to enter the model was set at P < .05 and the statistical level for a characteristic to be removed from the model was set at P > .10. Six linear discriminant analyses were performed: (1) right side versus left side, (2) right free wall versus right septum, (3) right anterior free wall versus right posterior free wall, (4) right anterior septum versus, right midseptum versus right posterior septum, (5) left anterior pathway versus left posterior pathways, and (6) left posteroseptal versus left posterior free walls.(ABSTRACT TRUNCATED AT 250 WORDS)

Algorithms↗
PubMed1997

Statistical aspects of fish vaccination trials.

Vaccine trials are performed to measure the efficacy of vaccines or vaccination strategies. The statistical aspects pertain both to design and analysis of such trials. In experimental trials, the design should ensure that the groups to be compared are equal in all respects except for the factor to be assessed. This is achieved by proper randomisation procedures. The diagnosis of cases should as far as possible be carried out without knowledge of vaccination status (blinding). If the administration of a vaccine per se is considered to influence the outcome, a similar administration of placebo in the control group should be considered. The required sample size will depend on a specified significance level, a specified power, and on the magnitude of the effect one wants to detect. If the cumulative numbers of cases in vaccinated and unvaccinated groups are registered at the end of the observation period, the effect can be measured by the risk ratio, risk difference or the relative percent survival. If the estimation is based on a fish-time approach and the presumption of constant rate of outcome over time is fulfilled, the rate ratio or the rate difference can be estimated. If the rate is not constant, the life table would be a method of choice. In the statistical analysis of the vaccination effect it is important to consider the assumptions on which the statistical tests are based. Proper choice of the experimental and statistical units in the trials is crucial. If a trial is set up with the individual fish as the statistical unit, adjusting for dependence (cluster effect) between the units may be indicated. If possible, the vaccine effect should be given by the point estimate and the confidence intervals. The statistical aspects of fish vaccination trials are based on general principles for controlled clinical trials, but they are also influenced by characteristics connected to the fish population and the experimental conditions.

Animals↗
PubMed2000

Comparison of allele-sharing statistics for general pedigrees.

The popularity of "non-parametric" linkage analysis using moderate and large sized pedigrees has increased in the last few years. Only a few of the existing allele-sharing statistics are applicable to general pedigrees, and even fewer are in common use. Little research has been done to compare the power of these statistics. We present some preliminary investigations into the power of the most popular general-pedigree allele-sharing statistics. We show that there are indeed non-trivial differences among the statistics, and that further studies are warranted. In particular, pedigree structure and the degree of recessiveness of the trait appear to be critical factors in determining which statistics are most powerful.

Alleles↗
PubMed1995

Statistical validity for testing associations between genetic markers and quantitative traits in family data.

In genetic analysis it is often of interest to analyze associations between traits of unknown genetic etiology and genetic markers from pedigree data. Statistical methods that assume independence of pedigree members cannot be used because they disregard the statistical dependencies of members in a pedigree. For quantitative traits, a regression model proposed by George and Elston [Genet Epidemiol 4:193-201, 1987] uses an asymptotic likelihood ratio test and incorporates a correlation structure that allows for statistical dependence among the pedigree members. The statistical validity of this test is assessed for finite samples by measuring the discrepancy between the empirical and theoretical chi-square distributions. The variance of the mean of the dependent variable is determined to be related to this discrepancy and can be used to determine whether a pedigree structure is large enough for making valid statistical inferences on the basis of the asymptotic test. A multi-generational pedigree of 200 or so individuals should in many cases be sufficient for valid results when using the asymptotic likelihood ratio test for the association between markers and continuous traits.

Family↗
PubMed2006

The importance of varying the event generation process in simulation studies of statistical methods for recurrent events.

Statistical methods for the analysis of recurrent events are often evaluated in simulation studies. A factor rarely varied in such studies is the underlying event generation process. If the relative performance of statistical methods differs across generation processes, then studies based upon one process may mislead. This paper describes the simulation of recurrent events data using four models of the generation process: Poisson, mixed Poisson, autoregressive, and Weibull. For each model four commonly used statistical methods for the analysis of recurrent events (Cox's proportional hazards method, the Andersen-Gill method, negative binomial regression, the Prentice-Williams-Peterson method) were applied to 200 simulated data sets, and the mean estimates, standard errors, and confidence intervals obtained. All methods performed well for the Poisson process. Otherwise, negative binomial regression only performed well for the mixed Poisson process, as did the Andersen-Gill method with a robust estimate of the standard error. The Prentice-Williams-Peterson method performed well only for the autoregressive and Weibull processes. So the relative performance of statistical methods depended upon the model of event generation used to simulate data. In conclusion, it is important that simulation studies of statistical methods for recurrent events include simulated data sets based upon a range of models for event generation.

Computer Simulation↗
PubMed2005

Riemannian elasticity: a statistical regularization framework for non-linear registration.

In inter-subject registration, one often lacks a good model of the transformation variability to choose the optimal regularization. Some works attempt to model the variability in a statistical way, but the re-introduction in a registration algorithm is not easy. In this paper, we interpret the elastic energy as the distance of the Green-St Venant strain tensor to the identity, which reflects the deviation of the local deformation from a rigid transformation. By changing the Euclidean metric for a more suitable Riemannian one, we define a consistent statistical framework to quantify the amount of deformation. In particular, the mean and the covariance matrix of the strain tensor can be consistently and efficiently computed from a population of non-linear transformations. These statistics are then used as parameters in a Mahalanobis distance to measure the statistical deviation from the observed variability, giving a new regularization criterion that we called the statistical Riemannian elasticity. This new criterion is able to handle anisotropic deformations and is inverse-consistent. Preliminary results show that it can be quite easily implemented in a non-rigid registration algorithms.

Algorithms↗
PubMed2006

Change of diffusion anisotropy in patients with acute cerebral infarction using statistical parametric analysis.

PURPOSE: We conducted statistical parametric comparison of fractional anisotropy (FA) images and quantified FA values to determine whether significant change occurs in the ischemic region. MATERIALS AND METHODS: The subjects were 20 patients seen within 24 h after onset of ischemia. For statistical comparison of FA images, a sample FA image was coordinated by the Talairach template, and each FA map was normalized. Statistical comparison was conducted using SPM99. Regions of interest were set in the same region on apparent diffusion coefficient (ADC) and FA maps, the region being consistent with the hyperintense region on diffusion-weighted images (DWIs). The contralateral region was also measured to obtain asymmetry ratios of ADC and FA. RESULTS: Regions with areas of statistical significance on FA images were found only in the white matter of three patients, although the regions were smaller than hyperintense regions on DWIs. The mean ADC and FA ratios were 0.64 +/- 0.16 and 0.93 +/- 0.09, respectively, and the degree of FA change was less than that of the ADC change. Significant change in diffusion anisotropy was limited to the severely infarcted core of the white matter. CONCLUSION: We believe statistical comparison of FA maps to be useful for detecting different regions of diffusion anisotropy.

Acute Disease↗
PubMed2002

[Use and comprehensibility of statistical analysis in Archivos de Bronconeumología (1970-1999)].

OBJECTIVES: To describe the type of statistical analysis used most often in original research articles published in Archivos de Bronconeumología, and the evolution of statistical analysis over time in terms of complexity. To determine comprehensibility, taking bivariate analysis as the reference threshold. MATERIAL AND METHODS: All articles published in the original research section of Archivos de Bronconeumología from 1970 through 1999 were reviewed manually. For each article we recorded the category or categories of statistical analysis and its comprehensibility (with a reference threshold set at category 7). We studied the following factors: year of publication, type of analysis, comprehensibility, maximum category achieved, subject area and number of authors. RESULTS: Eight hundred sixty original articles, with a mean 5 2 authors per article were examined. The maximum category reached was a mean 4.15 4.61. The three types of analysis used most often in all articles were category 1 (descriptive only) at 49.4%, category 2 (t and z tests) at 26.4% and category 3 (bivariate tables) at 19.1%. Among the more complex analytical categories, the most often used were analysis of variance (category 8) at 9%, survival analysis (category 16) at 6.2%, and non-parametric correlations at 3.4%. Comparing results by decade, the proportion of articles with only descriptive analysis fell from 74% in the seventies to 63.9% in the eighties and to 36.1% in the nineties (90s vs. 80s, p < 0.05; 90s vs. 70s, p < 0.05; 80s vs. 70s, p < 0.05). The use of statistics from categories 3 and 6 increased (p < 0.05), and the use of the more complex categories 8, 10, 11 and 16 increased (p < 0.05). Comprehensibility decreased significantly to 68.1% in the 90s in relation to increased complexity of analysis. CONCLUSIONS: The complexity of statistical analysis in articles published in Archivos de Bronconeumología increased over time, while comprehensibility decreased.

Analysis of Variance↗
PubMed1998

[Principles of tests of hypotheses in statistics: alpha, beta and P].

Modern clinical research requires control of statistical methods. We reviewed 120 original manuscripts which were submitted to the Annales françaises d'anesthésie et de reanimation and analyzed their statistical methodology. Most of them contained errors (inappropriate numerical expression of the data, uncontrolled alpha risk, lack of power, use of inadequate statistical tests) and only 9 (7%) were considered as adequate. Therefore it is useful to come back to the methodology of hypothesis testing. An hypothesis test helps to decide between two hypothesis, the null hypothesis (H0) and the alternative hypotheses (H1) that we intend to demonstrate. The decision of the choice between H0 and H1 is associated with two probabilities: the alpha risk which is the probability to reject H0 whereas H0 is true, and the beta risk which is the probability not to reject H0 whereas H1 is true. Because the alpha risk is considered to be very important, it should be verified that the actual risk corresponds to the risk initially retained. The P value is the probability to observe a difference as great as that noted. The P value should be assessed according to its environment: the clinical relevance of a result should be assessed according to the amplitude of the difference and its confidence interval. When the null hypothesis is not rejected, the power of the test is essential. Power calculation is essential in clinical research trials. The number of patients included depends on four elements: the response to the control treatment, the expected response to the new treatment, the level of significance, and the power. The following items should be checked to choose the appropriate test: assess the kind of variable, verify the requirements for application of the test (type of the variable distribution, sample size, particular conditions such as equality of variance, dependence or independence of the variables), determine if data come from paired samples or if multiple comparisons are performed. Statistical analysis has become more easy with computers, however a precise knowledge of statistics remains essential. Advice from a statistician is often useful especially when obtained a priori and not a posteriori.

Analysis of Variance↗