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 379 records · Page 21Linked to original sources
PubMed1996

A review of the statistical analysis used in papers published in Clinical Radiology and British Journal of Radiology.

Statistical analysis such as significance testing have become essential features of published medical studies. This has resulted in an increased frequency with which statistics are used, making the interpretation of scientific publications more difficult. There is an extensive array of tests and techniques. The aim of this study is to identify which statistical tests are used in radiology publications. All major articles published in Clinical Radiology and British Journal of Radiology in one year were reviewed. The frequency of statistical methods used was as follows: no statistical method or descriptive statistics only 103 (47%), one type of statistical method 67 (31%), and two or more methods 47 (22%). Statistics dealing with basic inference, decisions, contingency tables or correlation/regression techniques were found in 124 (53%) in which a procedure had been used. Advanced statistics including receiver operating characteristics (ROC), odds ratio, regression techniques, multiway ANOVA, and nonparametric ANOVA studies accounted for only 41 (19%) in which a procedure had been used. We conclude that descriptive analysis and basic statistical techniques account for most of the statistical tests reported. Physicians should concentrate on improving their understanding of basic statistics but advice should be sought from professionals in the fields of biostatistics and epidemiology as to whether the use of more advanced techniques would be more appropriate.

Humans↗
PubMed1999

[Statistical analysis of German radiologic periodicals: developmental trends in the last 10 years].

PURPOSE: To identify which statistical tests are applied in German radiological publications, to what extent their use has changed during the last decade, and which factors might be responsible for this development. MATERIALS AND METHODS: The major articles published in "ROFO" and "DER RADIOLOGE" during 1988, 1993 and 1998 were reviewed for statistical content. The contributions were classified by principal focus and radiological subspecialty. The methods used were assigned to descriptive, basal and advanced statistics. Sample size, significance level and power were established. The use of experts' assistance was monitored. Finally, we calculated the so-called cumulative accessibility of the publications. RESULTS: 525 contributions were found to be eligible. In 1988, 87% used descriptive statistics only, 12.5% basal, and 0.5% advanced statistics. The corresponding figures in 1993 and 1998 are 62 and 49%, 32 and 41%, and 6 and 10%, respectively. Statistical techniques were most likely to be used in research on musculoskeletal imaging and articles dedicated to MRI. Six basic categories of statistical methods account for the complete statistical analysis appearing in 90% of the articles. ROC analysis is the single most common advanced technique. Authors make increasingly use of statistical experts' opinion and programs. CONCLUSIONS: During the last decade, the use of statistical methods in German radiological journals has fundamentally improved, both quantitatively and qualitatively. Presently, advanced techniques account for 20% of the pertinent statistical tests. This development seems to be promoted by the increasing availability of statistical analysis software.

Data Interpretation, Statistical↗
PubMed2006

Pharmacology and statistics: recommendations to strengthen a productive partnership.

Critical to the discovery, development and rational use of drugs and vaccines are the foundational principles and proper application of statistics. However, in too many cases, there has been misuse of statistics and/or overemphasis on statistical significance (p < 0.05), as though this criterion possessed truth-guaranteeing properties. To clarify confusion about the proper use of statistics in pharmacology, we summarize briefly the foundational principles of probability; the role of statistics in assessment of causality; the three basic uses of statistical methods, especially those employed in hypothesis testing; and current statistical issues in pharmacological research. We then review and provide examples of the meaning of statistical significance, the consequences of lack of randomization in epidemiology/observation studies, the criteria for measurement instrument validation, the problems with subgroup analyses, the need for multiple comparison statistical methods, and how to handle dropouts and missing data. Finally, based on sound experimental and statistical principles, we make a series of recommendations to both experimentalists and journal editors to improve published pharmacological experiments. These include widespread use of blinding and randomization and/or random selection of subjects in both basic and clinical pharmacology, mandatory use of rigorous evidentiary criteria in epidemiology/observation studies claiming causal associations, proper interpretation of statistical versus clinical/pharmacological significance, appropriate interpretation of meta-analyses, meaningful validation of methods, and a more rational statistical approach to subgroup analyses and genetic association studies.

Bias↗
PubMed2005

[Triple-type theory of statistics and its application in the scientific research of biomedicine].

OBJECTIVE: To point out the crux of why so many people failed to grasp statistics and to bring forth a "triple-type theory of statistics" to solve the problem in a creative way. METHODS: Based on the experience in long-time teaching and research in statistics, the "three-type theory" was raised and clarified. Examples were provided to demonstrate that the 3 types, i.e., expressive type, prototype and the standardized type are the essentials for people to apply statistics rationally both in theory and practice, and moreover, it is demonstrated by some instances that the "three types" are correlated with each other. It can help people to see the essence by interpreting and analyzing the problems of experimental designs and statistical analyses in medical research work. RESULTS: Investigations reveal that for some questions, the three types are mutually identical; for some questions, the prototype is their standardized type; however, for some others, the three types are distinct from each other. It has been shown that in some multifactor experimental researches, it leads to the nonexistence of the standardized type corresponding to the prototype at all, because some researchers have committed the mistake of "incomplete control" in setting experimental groups. This is a problem which should be solved by the concept and method of "division". CONCLUSION: Once the "triple-type" for each question is clarified, a proper experimental design and statistical method can be carried out easily. "Triple-type theory of statistics" can help people to avoid committing statistical mistakes or at least to decrease the misuse rate dramatically and improve the quality, level and speed of biomedical research during the process of applying statistics. It can also help people to improve the quality of statistical textbooks and the teaching effect of statistics and it has demonstrated how to advance biomedical statistics.

Biomedical Research↗
PubMed1995

[Current trends in the use of statistics in medicine. A study of original articles published in the Medicina Clínica (1991-1992)].

BACKGROUND: In recent years there has been a notable increase in the use of statistical techniques in biomedical journals. Furthermore, the complexity of statistical analysis has increased because of data processing. In this study statistical accessibility is quantified and the types of statistical analysis performed in all the articles published under the section of original articles in the journal Medicina Clínica from 1991 to 1992 (volumes 96 to 99). METHODS: One reviewer analyzed a total of 264 original articles. The statistical analyses were classified according to a list with 18 categories. The quantification of accessibility was obtained from the order of the 18 categories with bivariate statistics (up to simple regression), being used as the reference threshold. Intrareviewer concordance was 97%. RESULTS: Eighty-one percent of the 264 originals used categories of statistical analysis beyond that of descriptive statistics (inferential methods). The originals used bivariate tables (49.2%) and t and z tests (33.3%) most frequently. In 1992 the use of variance analysis and survival analysis increased notably (from 12.8% to 33.8% and 7.2% to 18.7%, respectively). More complex statistical techniques that models of simple regression (threshold reference) were used in 38.3% of the originals (31.2% in 1991 and 44.6% in 1992). CONCLUSIONS: The use of inferential statistics and the complexity of statistical analysis has increased suggesting a lower statistical accessibility in the originals of Medicina Clinica. The categories of variance analysis and survival analysis were those in which the greatest increase was observed in 1992 and were responsible for the increase in the complexity of 20% of the originals.

Analysis of Variance↗
PubMed2004

Statistical audit of original research articles in International Psychogeriatrics for the year 2003.

BACKGROUND: At the request of the Editor of International Psychogeriatrics, a statistical audit of all papers published in the journal during 2003 was undertaken by the statistical advisor to International Psychogeriatrics. METHOD: Only research papers using inferential statistical techniques were assessed and only the statistical elements of these papers were evaluated. The following issues were addressed: did the authors report a power calculation or address power issues? Did the authors report an appropriate effect size indicator? When multiple univariate statistical tests were used was a correction for type 1 error employed? Did authors demonstrate the adequacy of the data analyzed for the statistical tests employed? Were sufficient details reported to enable an evaluation of the statistical analyses and reported results? RESULTS: Twenty papers published during 2003 were suitable for analysis. None addressed power issues. About half reported an effect size indicator and about half adjusted the statistical analysis for the effects of multiple univariate statistical comparisons. Few demonstrated the adequacy of the data being analyzed and few provided sufficient detail to evaluate the statistical analyses and reported results. Most papers used the right statistic in the right way. CONCLUSION: The statistical quality of articles published in International Psychogeriatrics could be improved by attention to a few relatively fundamental issues.

Humans↗
PubMed1986

Comparative sensitivity of survival-adjusted chi-square and normal statistics for the mutagenesis fluctuation assay.

Three statistics for analysis of microtitre plate mutagenesis fluctuation tests were studied by simulation, and in enzyme-activated assays of dimethylnitrosamine and diethylnitramine. A survival-adjusted chi 2 statistic ('Gsq') was compared with Katz's normally distributed statistic ('Phi'), and with the survival-independent statistic ('Zsq') of Gilbert. When toxicity was either very low or high, the Phi statistic either could not be evaluated over the whole range of possible background mutant frequencies, or sometimes it indicated unusually high levels of statistical significance, even when the other tests were negative. The survival-adjusted Gsq closely followed the Zsq statistic throughout the experimentally useful range of toxicities and mutant background values, with some improvement in sensitivity. Within the range 80 +/- 10% survival approximately, Katz's statistic 'Phi' was the most sensitive. The choice of statistical test could affect the estimate of the minimal effective mutagenic concentration by a factor of 10-100. For screening unknowns, both types of test (Phi and Gsq (or Zsq] may help in detecting suspect pro-mutagens and in designing a confirmatory assay. Bacterial population statistics are needed to assess the value of statistically positive results.

Cell Survival↗
PubMed1998

Précis of statistical significance: rationale, validity, and utility.

The null-hypothesis significance-test procedure (NHSTP) is defended in the context of the theory-corroboration experiment, as well as the following contrasts: (a) substantive hypotheses versus statistical hypotheses, (b) theory corroboration versus statistical hypothesis testing, (c) theoretical inference versus statistical decision, (d) experiments versus nonexperimental studies, and (e) theory corroboration versus treatment assessment. The null hypothesis can be true because it is the hypothesis that errors are randomly distributed in data. Moreover, the null hypothesis is never used as a categorical proposition. Statistical significance means only that chance influences can be excluded as an explanation of data; it does not identify the nonchance factor responsible. The experimental conclusion is drawn with the inductive principle underlying the experimental design. A chain of deductive arguments gives rise to the theoretical conclusion via the experimental conclusion. The anomalous relationship between statistical significance and the effect size often used to criticize NHSTP is more apparent than real. The absolute size of the effect is not an index of evidential support for the substantive hypothesis. Nor is the effect size, by itself, informative as to the practical importance of the research result. Being a conditional probability, statistical power cannot be the a priori probability of statistical significance. The validity of statistical power is debatable because statistical significance is determined with a single sampling distribution of the test statistic based on H0, whereas it takes two distributions to represent statistical power or effect size. Sample size should not be determined in the mechanical manner envisaged in power analysis. It is inappropriate to criticize NHSTP for nonstatistical reasons. At the same time, neither effect size, nor confidence interval estimate, nor posterior probability can be used to exclude chance as an explanation of data. Neither can any of them fulfill the nonstatistical functions expected of them by critics.

Reproducibility of Results↗
PubMed2001

A survey of affected-sibship statistics for nonparametric linkage analysis.

We have compared the power of a large number of allele-sharing statistics for "nonparametric" linkage analysis with affected sibships. Our rationale was that there is an extensive literature comparing statistics for sibling pairs but that there has not been much guidance on how to choose statistics for studies that include sibships of various sizes. We concentrated on statistics that can be described as assigning scores to each identity-by-descent-sharing configuration that a pedigree might take on (Whittemore and Halpern 1994). We considered sibships of sizes two through five, 27 different genetic models, and varying recombination fractions between the marker and the trait locus. We tried to identify statistics whose power was robust over a wide variety of models. We found that the statistic that is probably used most often in such studies-S(all)-performs quite well, although it is not necessarily the best. We also found several other statistics (such as the R criterion, S(robdom), and the Sobel-and-Lange statistic C) that perform well in most situations, a few (such as S(-#geno) and the Feingold-and-Siegmund version of S(pairs)) that have high power only in very special situations, and a few (such as S(-#geno), the N criterion, and the Sobel-and-Lange statistic B) that seem to have low power for the majority of the trait models. For the most part, the same statistics performed well for all sibship sizes. We also used our results to give some suggestions regarding how to weight sibships of different sizes, in forming an overall statistic.

Alleles↗
PubMed2005

An entropy-based statistic for genomewide association studies.

Efficient genotyping methods and the availability of a large collection of single-nucleotide polymorphisms provide valuable tools for genetic studies of human disease. The standard chi2 statistic for case-control studies, which uses a linear function of allele frequencies, has limited power when the number of marker loci is large. We introduce a novel test statistic for genetic association studies that uses Shannon entropy and a nonlinear function of allele frequencies to amplify the differences in allele and haplotype frequencies to maintain statistical power with large numbers of marker loci. We investigate the relationship between the entropy-based test statistic and the standard chi2 statistic and show that, in most cases, the power of the entropy-based statistic is greater than that of the standard chi2 statistic. The distribution of the entropy-based statistic and the type I error rates are validated using simulation studies. Finally, we apply the new entropy-based test statistic to two real data sets, one for the COMT gene and schizophrenia and one for the MMP-2 gene and esophageal carcinoma, to evaluate the performance of the new method for genetic association studies. The results show that the entropy-based statistic obtained smaller P values than did the standard chi2 statistic.

Entropy↗
PubMedDate not supplied

[Descriptive study of statistical methods in the original article published on the cigarette smoking habit in four Spanish medical journals (1985-1996)].

BACKGROUND: Being the tobacco use a high-priority subject of investigation and having itself increased the utilization of statistical techniques in biomedical publication the used statistical techniques are described and the statistical accessibility is quantified in the original articles on tobacco use published in four Spanish medical journals. METHODS: Retrospective descriptive study of 154 original articles on the cigarette smoking habit published in 1985-1996 in the journals Atención Primaria, Medicina Clínica (Barcelona), Revista Española de Salud Pública and Revista Clínica Española. An only observer codified the statistic techniques in 14 categories in agreement with the classification processed by Carré et al (1995) from the classification settled down by Emerson and Colditz (1983). The knowledge of bivariable techniques, to simple lineal regression, was stablished as the reference for the study of statistical accessibility. RESULTS: 81.8% original articles used inferential statistics. The most frequently used categories were "Contingency tables" (37.0%), "Descriptive statistics" (18.2%) and "Life tables and analysis of survival" (9.7%). A reader familiarized with bivariable techniques has statistical access to 96.0% for the originals of Revista Española de Salud Pública, 86.2% of Atención Primaria, 66.7% of Medicina Clínia (Barcelona) and 33.3% of Revista Clínica Española. The same reader had statistical access to 100% for the originals published from 1985 to 1987 and 68.1% from 1994 to 1996. CONCLUSIONS: The use of statistical methods depends on the investigation subject and design, the journal and the year of the publication. The decrease of the statistical accessibility recommends to identify the profile of the standard reader in Spain, to adjust his knowledge to the current biomedical literature demand.

Habits↗
PubMed1987

A rationale for the teaching of statistics to surgical residents.

The two aims of this study were to investigate the use of statistics in the surgical literature and to assess the degree of statistical comprehension possessed by graduating surgical residents. Two hundred journal articles were randomly selected from the 1984 issues of four surgical journals and were reviewed for statistical content. A classification of statistical techniques was created. A reader who has knowledge of descriptive statistics only has access to 44.5% of the articles. The addition of knowledge of t tests, contingency table analysis, other nonparametric techniques, and life table analysis to a reader's repertoire increases the access rate to 80.5%. The data indicate the specific statistical techniques that would best serve the surgeon who is attempting to increase access rate to the surgical literature. Ninety-one surgical residents in their fifth postgraduate year (PGY-5) responded to a questionnaire regarding their knowledge of statistics. While 90% of the respondents thought they would benefit from a course on statistics, 92% reported that they had received less than 5 hours of instruction in statistics during their residency. Both subjective self-ratings and objective testing revealed that the residents surveyed have a suboptimal knowledge of statistics. The results suggest the need for formal instruction in statistics during surgical residency.

Attitude of Health Personnel↗
PubMedDate not supplied

Type of statistical techniques in rheumatology and internal medicine journals.

A comparison of the prevalence and type of statistical analysis used in internal medicine and rheumatology journals was done. Four representative journals of each specialty were selected and twelve original articles were randomly obtained from each journal. The papers were reviewed twice within a three month interval by the same evaluator following published definitions for classification. The rheumatology journals tended to use fewer (80 versus 115) and simpler statistical techniques (X3 = 4.28, DF = 1, p = 0.03; OR, 95% CI = 3.21, 1.05-10.85). There was a statistical difference in the utilization of statistical procedures among journals in the four categories evaluated. Seven statistical techniques were required to have access to 86% of statistical tests used in rheumatology journals (t-tests, contingency tables, descriptive statistics, non-parametric comparisons, anova, multiple regression, and Pearson's correlation). The internal medicine journals required six statistical procedures to have access to 85% of the tests (contingency tables, survival analysis, epidemiologic statistics, t-tests, non-parametric statistics, and anova). Our results could be useful to plan medical education in biostatistics emphasizing the statistical techniques most commonly used in these areas.

Internal Medicine↗
PubMed1995

An assessment of the statistical procedures used in original papers published in the SAMJ during 1992.

OBJECTIVE: To assess the statistical procedures used in original papers published in the SAMJ. DESIGN: Descriptive study based on a random sample of 100 papers from the 153 papers with methodological content that were published in the SAMJ during 1992. RESULTS: This review showed that 34% (95% CI (25%; 43%)) of papers used no statistical procedure at all or used simple descriptive statistics only. In sampling methods, there was a predominance of the use of the period sampling method as opposed to probability sampling methods. Inappropriate statistical methods were used in 15% (6%; 24%) of papers, while in 16% (9%; 23%) statistical procedures and in 13% (6%; 20%) the sampling methods used could not be identified. Inaccurate graphical methods were used in 17% (6%; 28%) of papers. Confidence intervals and power calculations are used far too infrequently, in 33% (19%; 47%) and 11% (3%; 19%) of appropriate papers respectively. If the Journal's readers are at least familiar with simple descriptive statistics, contingency table analysis, simple epidemiological statistics, t-test procedure and confidence interval calculation and interpretation, they will have a complete understanding of the statistical content of 60% of original articles published in the Journal. CONCLUSION: Guidelines for the statistical treatment of reported data and the statistical review of articles before publication will assist substantially in improving the quality of statistical analysis. More intensive use of available biostatistical and epidemiological expertise at the study design and analysis stages is needed to shift the emphasis from descriptive research to analytical investigation.

Evaluation Studies as Topic↗
PubMed2005

Interaction of luminance and higher-order statistics in texture discrimination.

Most studies of texture processing are based on textures in which individual pixel statistics are varied and spatial correlations are absent ("IID textures"), or textures in which spatial correlation structure is varied and luminance, or first-order, statistics are held constant. Here we jointly examine simple pixel statistics and fourth-order spatial correlation structure along the continuum of "even" and "odd" isodipole textures of Julesz, Gilbert and Victor [Julesz, B., Gilbert, E.N., & Victor, J.D. (1978). Biological Cybernetics, 31(3) 137-140], as well as their interactions. Absolute efficiency to detect either kind of statistical cue is low: approximately 0.05 for luminance statistics, and 0.004 for isodipole statistics. Above threshold, isodipole statistics must change by approximately four times the amount that pixel statistics must change to generate an equally salient texture. When pixel statistics and isodipole statistics are simultaneously varied, the two texture cues combine by probability summation and perceptual distances are approximately Euclidean. Superimposed on this picture are subtle foreground/background asymmetries that suggest properties of the visual mechanisms that are sensitive to these image statistics.

Adult↗
PubMed2005

A note on generalized Genome Scan Meta-Analysis statistics.

BACKGROUND: Wise et al. introduced a rank-based statistical technique for meta-analysis of genome scans, the Genome Scan Meta-Analysis (GSMA) method. Levinson et al. recently described two generalizations of the GSMA statistic: (i) a weighted version of the GSMA statistic, so that different studies could be ascribed different weights for analysis; and (ii) an order statistic approach, reflecting the fact that a GSMA statistic can be computed for each chromosomal region or bin width across the various genome scan studies. RESULTS: We provide an Edgeworth approximation to the null distribution of the weighted GSMA statistic, and, we examine the limiting distribution of the GSMA statistics under the order statistic formulation, and quantify the relevance of the pairwise correlations of the GSMA statistics across different bins on this limiting distribution. We also remark on aggregate criteria and multiple testing for determining significance of GSMA results. CONCLUSION: Theoretical considerations detailed herein can lead to clarification and simplification of testing criteria for generalizations of the GSMA statistic.

Chromosome Mapping↗
PubMed1996

[Current use of statistics in biomedical research: a comparison of general medicine journals].

BACKGROUND: The use of statistical techniques has become strongly consolidated in biomedical investigation. The present study analyzes the statistical repertoire of the original articles published in 1993 in four general medicine journals: Med Clin (Barc), Rev Clin Esp, Lancet and N Engl J Med. METHODS: A single reviewer examined 100 original articles from Med Clin (Barc), 42 from Rev Clin Esp, 105 from Lancet and 116 from N Engl J Med, studying the use of 18 categories of statistical analysis and the statistical accessibility of the reader. The criteria for assigning techniques to a specific category were those described by Emerson and Colditz. The knowledge of bivariable techniques (standard reader) was established as the reference for the study of statistical access. Statistical use consisted in the tabulation of frequencies, graphic representations and chi square tests. RESULTS: The five most used categories were: Contingency tables, t and z tests, epidemiologic statistics, survival analysis (in both English journals) and analysis of variance (in both Spanish journals). The percentage of articles without statistics or with only descriptive statistics was 16% in Med Clin (Barc), 29% in Rev Clin Esp, 18% for in Lancet and 23% in the N Engl J Med. A reader familiarized with bivariable techniques has statistical access to 58% for the originals of Med Clin (Barc), 62% of Rev Clin Esp, 35% of the Lancet and 42% of the N Engl J Med. CONCLUSIONS: In the four journals selected, the use of bivariable techniques is still frequent although the growing use of multivariant analysis is of note. The study of the current profile of the standard reader in Spain is the aim of priority.

Analysis of Variance↗
PubMed2001

Efficiency comparisons of rank and permutation tests based on summary statistics computed from repeated measures data.

A popular method of using repeated measures data to compare treatment groups in a clinical trial is to summarize each individual's outcomes with a scalar summary statistic, and then to perform a two-group comparison of the resulting statistics using a rank or permutation test. Many different types of summary statistics are used in practice, including discrete and continuous functions of the underlying repeated measures data. When the repeated measures processes of the comparison groups differ by a location shift at each time point, the asymptotic relative efficiency of (continuous) summary statistics that are linear functions of the repeated measures has been determined and used to compare tests in this class. However, little is known about the non-null behaviour of discrete summary statistics, about continuous summary statistics when the groups differ in more complex ways than location shifts or where the summary statistics are not linear functions of the repeated measures. Indeed, even simple distributional structures on the repeated measures variables can lead to complex differences between the distribution of common summary statistics of the comparison groups. The presence of left censoring of the repeated measures, which can arise when these are laboratory markers with lower limits of detection, further complicates the distribution of, and hence the ability to compare, summary statistics. This paper uses recent theoretical results for the non-null behaviour of rank and permutation tests to examine the asymptotic relative efficiencies of several popular summary statistics, both discrete and continuous, under a variety of common settings. We assume a flexible linear growth curve model to describe the repeated measures responses and focus on the types of settings that commonly arise in HIV/AIDS and other diseases.

Acquired Immunodeficiency Syndrome↗