Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Sample size estimation”

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 343 records · Page 19Linked to original sources
PubMed1998

[Stragegies for evaluation of non-randomized therapeutic comparisons exemplified by prehospital volume therapy after trauma].

Non-randomized comparisons of therapeutic approaches require extensive description of the patients. Classical subgroup analysis suffers from small sample sizes. Estimation of outcome based on known prognostic factors (e.g. scores) allow for an indirect comparison of treatment effects. Matched pair analysis generates two homogenous subgroups of patients. The propensity score approach classifies all patients according to their chance of receiving a certain therapy or not, thus giving comparable situations for stratified analysis. The preclinical fluid resuscitation for trauma patients can hardly be assessed by randomized trials. Application of the above mentioned methods shows no overall effect but polytraumatized patients seem to have a worse outcome with high volume resuscitation.

Brain Injuries↗
PubMed2004

Research in neonatology: need for introspection.

This study was conducted to evaluate the quality of neonatal research published in major Indian journals. Four indexed Indian journals were scanned for topics pertaining to neonatology and the manuscripts were evaluated for the most important morbidity studied and its relevance to the national need. The analytical studies were evaluated for their quality of research methodology. Approximately 12% studies were pertaining to neonates and only one third of them were investigative in nature. Less than 20% studies were of national interest and only 5% of the total studies were community based. Although aims of the studies were clearly defined in 81%, sample size estimation was done in only 11%, blinding in 15% and one or more category of bias was seen in 84% of the studies. We conclude that there is an urgent need for interventional and community based studies in neonatology, on issues of national interest. A need was felt for improvement in the quality of research in neonatology with special emphasis on training in clinical epidemiology.

Forecasting↗
PubMed2004

[Analysis of the quality of clinical trials about therapeutic research using the standard of evidence-based medicine].

OBJECTIVE: To investigate the quality of clinical trials of ocular therapeutic efficacy in China in order to provide the facts to support the Evidence-Based Medicine (EBM) and improve the clinical research trials. METHODS: All the articles published in Chinese Journal of Ophthalmology from 1983 to 2002 emphasizing random control trial and clinical control trial were evaluated as per EBM standard. RESULTS: The total number of articles for clinical therapeutic efficacy published in the past 20 years were 152, of which 35 articles (23.0%) were random control trials, and 8 (5.3%) articles were clinical control trials. The disparity of quality of research was found as follows. The method of random/half random was described in 10 articles (23.3%). Placebo-control and open-control were reported in 3 (3/43) and 9 articles (20.9%), respectively. Blinded, double-blinded, and single-blinded research was adopted in 7 (16.3%), 3 articles (7.0%), and 4 articles (9.3%), respectively. Ten articles (23.3%) reported strict diagnostic standard including inclusion and exclusion standards while 30 articles (69.8%) didn't use exclusion criteria. Follow-up visits from a few months to years was found in 30 out of 43 articles, of 25 articles (58.1%) provided detailed follow-up visit data; 19 articles (44.2%) didn't supply any information of the cases lost follow-up, only 7 articles (16.3%) reported the cause and process of the cases lost follow-up. Adverse events were not consistently reported in the articles. Not a single article estimated sample size when the study was designed. Most articles included small or medium size samples, while lacking of multi-center, large sample, randomized, double-blinded and placebo-controlled clinical trials. Statistical significance for either part or all data except P value was not indicated in 15 articles (34.9%). The indexes assessing the clinical significance of clinical therapeutic efficacy include relative risk reduction, absolute risk reduction, number needed to treat, however, these indexes were not used in all the articles. CONCLUSIONS: In summary, the clinical trials related to ocular therapeutic efficacy published between 1983 and 2002 were not very well designed and the accuracy and the reliability of the results were greatly affected. Therefore, it is imperative to improve the quality of the research by enhancing the design and analysis of the research in future.

Bibliometrics↗
PubMed2006

[Methodological quality assessment of clinical trials in traditional Chinese medicine: the principles of evidence-based medicine].

The quality of clinical trials in traditional Chinese medicine (TCM) was analyzed with respect to their methodology and outcome assessment according to the concepts of evidence-based medicine (EBM). It was suggested that the essential methodological principles of EBM should be applied in clinical trials of TCM, including randomization, control and blindness. The sample size estimation, optimal parameter selection for outcome assessment, compliance and intention-to-treat analysis are all important aspects of randomized controlled trials. To bring the benefits of EBM into clinical trials will improve the quality of research in TCM and also promote international co-operation and communications. It is necessary to establish an assessment system of clinical outcome for TCM on the basis of EBM in order to evaluate the efficacy and safety of TCM objectively and scientifically.

Evidence-Based Medicine↗
PubMed1995

Bypass Angioplasty Revascularization Investigation (BARI): baseline clinical and angiographic data.

This report presents baseline clinical and angiographic data from the Bypass Angioplasty Revascularization Investigation (BARI), a multicenter international trial assessing the relative efficacy of percutaneous transluminal coronary angioplasty (PTCA) versus coronary artery bypass graft surgery (CABG) in selected patients with multivessel coronary artery disease. PTCA is commonly performed in patients with multivessel coronary artery disease, yet its long-term efficacy in comparison to CABG is unknown. From August 1988 through August 1991, 1,829 qualifying patients with multivessel disease suitable for either procedure were randomized to PTCA or CABG; sample size estimates were based on anticipated 5-year mortality. Two registry populations were also defined for follow-up: (1) 2,013 patients eligible for randomization but not randomized; and (2) 422 patients considered by angiography as unsuitable for randomization. Patients randomized in BARI were at relatively high risk for subsequent cardiac events: 39% were > or = 65 years old, 55% had prior myocardial infarction, 69% presented with unstable angina or non-Q wave myocardial infarction, and 43% had 3-vessel coronary artery disease. Patients randomized to PTCA and CABG were equally matched in all the important baseline variables. The randomized and the eligible but not randomized groups were similar in most respects. However, the nonrandomized group had a higher proportion with college education; fewer with a history of myocardial infarction, heart failure, diabetes, and smoking; and a somewhat better average ejection fraction. At the 3-month follow-up, PTCA had been performed more commonly in the nonrandomized eligible patients, especially those with 2-vessel disease.(ABSTRACT TRUNCATED AT 250 WORDS)

Angioplasty, Balloon, Coronary↗
PubMed1994

Statistical aspects of the design and analysis of studies to compare haemodialysis membranes.

Some aspects of the statistical design and analysis of short-term studies of haemodialysis membranes are reviewed. The potential benefits of crossover studies comparing more than two treatments are emphasized. Designs based on Latin squares are advocated and the importance of avoiding carryover effects by ensuring adequate time between successive treatments is stressed. Studies of this type will usually record data serially within each period, so appropriate graphical techniques and the use of summary measures for the analysis of this type of data are considered. An example of the analysis of a study, using MINITAB, is included. Some issues of sample size estimation are discussed, and finally some more advanced designs and methods of analysis are briefly considered.

Humans↗
PubMed1995

Serendipitous results of a pilot study: precaution indicated.

A pilot study was conducted to estimate sample size for a clinical trial in a F area. In 1992, 98 children 14 years of age living in Fall River, MA were examined for dental caries: Fall River was fluoridated in 1973. Residence histories showed that 74% lived there from birth (B), 12% were residents from kindergarten or 1st grade (K1) and 14% moved into the community at a later time (LT). Findings on caries prevalence showed an inverse relation between DMFS and initial age of residence; mean DMFS was 3.00 for Group B, 5.33 for Group K1 and 6.93 for Group LT. A one-way ANOVA indicated significant differences among the groups (p=0.05). Because residence from birth or from early life can be considered a proxy for systemic fluoride exposure, and because controversy currently surrounds the issue of topical versus systemic benefits in explaining the mechanism of action of fluoride, the results appeared to have importance. However, internal analyses of the data comparing surface-specific (pit and fissure) results among the groups for early erupting teeth with varying systemic exposure to fluoridated water and for late erupting teeth, all with appreciable systemic exposure, showed comparable relative differences in DMFS scores. Lack of internal validity, therefore, discounted a conclusion from overall results of the role of systemic fluorides in providing decay preventive benefits. If there is any conclusion that can be drawn it is that serendipitous escapades with data from a pilot study, if not rigorously analyzed and cautiously interpreted, tend to further muddy the waters (fluoridated in this case) on controversial issues and should best be avoided.

Adolescent↗
PubMed2002

Estimating allelic richness: effects of sample size and bottlenecks.

Although differences in sampling intensity can bias comparisons of allelic richness (A) among populations, investigators often fail to correct estimates of A for differences in sample size. Methods that standardize A on the basis of the size of the smallest number of samples in a comparison are preferable to other approaches. Rarefaction and repeated random subsampling provide unbiased estimates of A with the greatest precision and thus provide greatest statistical power to detect differences in variation. Less promising approaches, in terms of bias or precision, include single random subsampling, eliminating very small samples, using sample size as a covariate or extrapolating estimates obtained from small samples to a larger number of individuals.

Alleles↗
PubMed1996

The importance of sample size for the estimation of F wave latency parameters in the peroneal nerve.

We studied the peroneal nerve F waves in 20 healthy subjects and 20 patients with neuropathy to assess the effect of sample size on the accuracy of measurements of the following F wave latency parameters: F wave minimum latency, mean latency, median latency and F chronodispersion. The values obtained from a large sample (65-110 F responses) were compared with the corresponding values from smaller samples of 10, 20 and 40 responses. The results indicated that equally accurate measurements for all parameters were provided by larger F wave samples in patients, compared with healthy subjects. Amongst the various parameters, FchR required the largest and FLmean the smallest sample, in order to achieve results of the same accuracy. A sample of 40 fulfilled the requirements for all F wave latency parameters of the peroneal nerve in almost all subjects, a finding which is in good agreement with that of a similar study for the ulnar nerve.

Adult↗
PubMed1988

Sample size.

Before undertaking a research comparison, investigators may wish to estimate the sample sizes needed to assure that the research is feasible and is worth the effort and expense. Such calculations require several decisions by the researchers: (1) the acceptable level of the type I error (P value), (2) the desired power of the test, (3) the difference between the samples that is considered to be important, and (4) the variability expected among the values to be studied. Some recipes for estimating approximate sample sizes are suggested.

Statistics as Topic↗
PubMed2003

Robustness of sample size re-estimation procedure in clinical trials (arbitrary populations).

In clinical trials, one of the main questions that is being asked is how many additional observations, if any, are needed beyond those originally planned. In a two-treatment double-blind clinical experiment, one is interested in testing the null hypothesis of equality of the means against one-sided alternative when the common variance sigma2 is unknown. We wish to determine the required total sample size when the error probabilities alpha and beta are specified at a predetermined alternative. Shih provided a two-stage procedure which is an extension of Stein's one-sample procedure, assuming normal response. He estimates sigma2 by the method of maximum likelihood via the EM algorithm and carries out a simulation study in order to evaluate the effective level of significance and the power. The author proposed a closed-form estimator for sigma2 and showed analytically that the difference between the effective and nominal levels of significance is negligible and that the power exceeds 1-beta when the initial sample size is large. Here we consider responses from arbitrary distributions in which the mean and the variance are not functionally related and show that when the initial sample size is large, the conclusions drawn previously by the author still hold. The effective coverage probability of a fixed-width interval is also evaluated. Proofs of certain assertions are deferred to the Appendix.

Clinical Trials as Topic↗
PubMed2005

Pharmacodynamic parameter estimation: population size versus number of samples.

The purpose of this study was to evaluate the effects of population size, number of samples per individual, and level of interindividual variability (IIV) on the accuracy and precision of pharmacodynamic (PD) parameter estimates. Response data were simulated from concentration input data for an inhibitory sigmoid drug efficacy (E(max)) model using Nonlinear Mixed Effect Modeling, version 5 (NONMEM). Seven designs were investigated using different concentration sampling windows ranging from 0 to 3 EC(50) (EC(50) is the drug concentration at 50% of the E(max)) units. The response data were used to estimate the PD and variability parameters in NONMEM. The accuracy and precision of parameter estimates after 100 replications were assessed using the mean and SD of percent prediction error, respectively. Four samples per individual were sufficient to provide accurate and precise estimate of almost all of the PD and variability parameters, with 100 individuals and IIV of 30%. Reduction of sample size resulted in imprecise estimates of the variability parameters; however, the PD parameter estimates were still precise. At 45% IIV, designs with 5 samples per individual behaved better than those designs with 4 samples per individual. For a moderately variable drug with a high Hill coefficient, sampling from the 0.1 to 1, 1 to 2, 2 to 2.5, and 2.5 to 3 EC(50) window is sufficient to estimate the parameters reliably in a PD study.

Humans↗
PubMed2006

Sample size determination for matched-pair equivalence trials using rate ratio.

In this article, we compare Wald-type, logarithmic transformation, and Fieller-type statistics for the classical 2-sided equivalence testing of the rate ratio under matched-pair designs with a binary end point. These statistics can be implemented through sample-based, constrained least squares estimation and constrained maximum likelihood (CML) estimation methods. Sample size formulae based on the CML estimation method are developed. We consider formulae that control a prespecified power or confidence width. Our simulation studies show that statistics based on the CML estimation method generally outperform other statistics and methods with respect to actual type I error rate and average width of confidence intervals. Also, the corresponding sample size formulae are valid asymptotically in the sense that the exact power and actual coverage probability for the estimated sample size are generally close to their prespecified values. The methods are illustrated with a real example from a clinical laboratory study.

Biometry↗