Sample Size Calculations (sample + size_calculation)

Distribution by Scientific Domains


Selected Abstracts


Using Design Effects From Previous Cluster Surveys to Guide Sample Size Calculation in Emergency Settings

DISASTERS, Issue 2 2006
Reinhard Kaiser
Abstract A good estimate of the design effect is critical for calculating the most efficient sample size for cluster surveys. We reviewed the design effects for seven nutrition and health outcomes from nine population-based cluster surveys conducted in emergency settings. Most of the design effects for outcomes in children, and one-half of the design effects for crude mortality, were below two. A reassessment of mortality data from Kosovo and Badghis, Afghanistan revealed that, given the same number of clusters, changing sample size had a relatively small impact on the precision of the estimate of mortality. We concluded that, in most surveys, assuming a design effect of 1.5 for acute malnutrition in children and two or less for crude mortality would produce a more efficient sample size. In addition, enhancing the sample size in cluster surveys without increasing the number of clusters may not result in substantial improvements in precision. [source]


Sample Size Calculations in Clinical Research, Second Edition by Shein-Chung Chow, Jun Shao, Hansheng Wang

INTERNATIONAL STATISTICAL REVIEW, Issue 2 2008
C. M. O'Brien
No abstract is available for this article. [source]


Sample size calculation in clinical research Chow S-C, Shao J, Wang H (2003) ISBN 0824709705; 368 pages; $165.00 Dekker; http://www.dekker.com/servlet/product/productid/0970-5

PHARMACEUTICAL STATISTICS: THE JOURNAL OF APPLIED STATISTICS IN THE PHARMACEUTICAL INDUSTRY, Issue 3 2004
Trevor McMullan
No abstract is available for this article. [source]


Levels of evidence available for techniques in antireflux surgery

DISEASES OF THE ESOPHAGUS, Issue 2 2007
M. Neufeld
SUMMARY., The objective of this study was to determine the levels of evidence and grades of recommendations available for techniques in antireflux surgery. Areas of technical controversy in antireflux surgery were identified and developed into eight answerable questions. The external evidence was surveyed using the databases Medline and EMBASE. Abstracts and appropriate articles were identified from January 1966 to December 2005. A set of search strategies was systematically employed to determine the levels of evidence available for each clinical question. Primary outcome measures included the determination of levels of evidence and grade of recommendation based on The Oxford Center for Evidence-Based Medicine. Secondary outcome measures included for randomized controlled trials were Jadad scores, noting the presence of a sample size calculation, and the determination of an effect estimate and the reporting of a confidence interval. Higher quality randomized controlled trials (mostly level 2b, occasional level 1b) existed to answer three questions: whether to complete a 360 or partial wrap; whether or not to divide the short gastric vessels; and whether to perform laparoscopic or open surgery. Lower quality randomized controlled trials were available to determine whether the use of mesh was helpful, whether or not to use a bougie catheter for calibration of the wrap, and whether an anterior or posterior wrap results in a superior outcome. This was deemed to be of inferior grade of recommendation due to the lack (< 2) of trials available and the sole presence of level 2b evidence. The final two questions: whether to complete fundoplication using a thoracic or abdominal approach and whether to use intraoperative manometry relied exclusively upon level 4 evidence and thus received a lower grade of recommendation. A higher Jadad score seemed to be associated with studies having a higher level of evidence available to answer the question. Sample size calculations were given to answer three questions. Effect estimate was difficult to interpret given inconsistent findings, composite outcomes and lack of reported confidence intervals. In conclusion, antireflux surgery has many randomized controlled trials available upon which to base clinical practice. Unfortunately, these are generally of poor quality. We recommend that esophageal surgeons determine consistent outcome measures and endeavor to improve the quality of randomized controlled trials they perform. [source]


Interstudy reproducibility of three-dimensional volume-selective fast spin echo magnetic resonance for quantifying carotid artery wall volume

JOURNAL OF MAGNETIC RESONANCE IMAGING, Issue 2 2005
Anitha Varghese BSc
Abstract Purpose To assess the interstudy reproducibility of a three-dimensional volume-selective, fast spin echo (FSE) magnetic resonance technique for the assessment of carotid artery wall volume, which is a marker for total carotid plaque volume. Materials and Methods Interstudy reproducibility was evaluated in 10 subjects with evidence of carotid artery atherosclerotic disease on carotid Doppler ultrasonography. Subjects were scanned twice with an interscan time of one hour to four days. The carotid artery was imaged in cross-section, and the total carotid arterial wall volume (TWV) was calculated by subtraction of the total carotid lumen volume from the total outer carotid vessel volume. Results The mean carotid TWV for the scans was 741 and 734 mm3, respectively, with no significant difference (mean difference 7 mm3; P = 0.5). The time for each study was approximately 20 minutes. The standard deviation of the differences between the measurements was 33 mm3, yielding an interstudy coefficient of variation of 4.4%. Sample size calculations showed that 16 patients would enable this difference in plaque volume over time to be detected with 80% power at a P value of 0.05. Conclusion Volumetric analysis with CMR of carotid artery plaques using a three-dimensional volume-selective FSE is efficient with good interstudy reproducibility, and is well suited for longitudinal studies of progression of carotid atheroma with reasonable sample sizes. J. Magn. Reson. Imaging 2005;21:187,191. 2005 Wiley-Liss, Inc. [source]


Exact Tests using Two Correlated Binomial Variables in Contemporary Cancer Clinical Trials

BIOMETRICAL JOURNAL, Issue 6 2009
Jihnhee Yu
Abstract New therapy strategies for the treatment of cancer are rapidly emerging because of recent technology advances in genetics and molecular biology. Although newer targeted therapies can improve survival without measurable changes in tumor size, clinical trial conduct has remained nearly unchanged. When potentially efficacious therapies are tested, current clinical trial design and analysis methods may not be suitable for detecting therapeutic effects. We propose an exact method with respect to testing cytostatic cancer treatment using correlated bivariate binomial random variables to simultaneously assess two primary outcomes. The method is easy to implement. It does not increase the sample size over that of the univariate exact test and in most cases reduces the sample size required. Sample size calculations are provided for selected designs. [source]


Blinded Sample Size Reestimation in Non-Inferiority Trials with Binary Endpoints

BIOMETRICAL JOURNAL, Issue 6 2007
Tim Friede
Abstract Sample size calculations in the planning of clinical trials depend on good estimates of the model parameters involved. When the estimates of these parameters have a high degree of uncertainty attached to them, it is advantageous to reestimate the sample size after an internal pilot study. For non-inferiority trials with binary outcome we compare the performance of Type I error rate and power between fixed-size designs and designs with sample size reestimation. The latter design shows itself to be effective in correcting sample size and power of the tests when misspecification of nuisance parameters occurs with the former design. ( 2007 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim) [source]


Feasibility of randomized controlled trials in liver surgery using surgery-related mortality or morbidity as endpoint,

BRITISH JOURNAL OF SURGERY (NOW INCLUDES EUROPEAN JOURNAL OF SURGERY), Issue 9 2009
M. A. J. van den Broek
Background: There is a shortage of randomized controlled trials (RCTs) on which to base guidelines in liver surgery. The feasibility of conducting an adequately powered RCT in liver surgery using the dichotomous endpoints surgery-related mortality or morbidity was examined. Methods: Articles published between January 2002 and November 2007 with mortality or morbidity after liver surgery as primary endpoint were retrieved. Sample size calculations for a RCT aiming to show a relative reduction of these endpoints by 33, 50 or 66 per cent were performed. Results: The mean operative mortality rate was 10 per cent and the total morbidity rate 289 per cent; mean rates of bile leakage and postresectional liver failure were 44 and 26 per cent respectively. The smallest numbers of patients needed in each arm of a RCT aiming to show a 33 per cent relative reduction were 15 614 for operative mortality, 412 for total morbidity, 3446 for bile leakage and 5924 for postresectional liver failure. Conclusion: The feasibility of conducting an adequately powered RCT in liver surgery using outcomes such as mortality or specific complications seems low. Conclusions of underpowered RCTs should be interpreted with caution. A liver surgery-specific composite endpoint may be a useful and clinically relevant solution to pursue. Copyright 2009 British Journal of Surgery Society Ltd. Published by John Wiley & Sons, Ltd. [source]


How I do it: sample size calculations

CLINICAL OTOLARYNGOLOGY, Issue 2 2008
J. O'Hara
Keypoints ,,Sample size calculations are integral to project design. ,,A description of the underlying theory behind them is set out. ,,Required are the significance level, the power, the clinical difference and the standard deviation. ,,Douglas Altman's nomogram is particularly useful for sample size calculations for comparing independent samples. [source]


Levels of evidence available for techniques in antireflux surgery

DISEASES OF THE ESOPHAGUS, Issue 2 2007
M. Neufeld
SUMMARY., The objective of this study was to determine the levels of evidence and grades of recommendations available for techniques in antireflux surgery. Areas of technical controversy in antireflux surgery were identified and developed into eight answerable questions. The external evidence was surveyed using the databases Medline and EMBASE. Abstracts and appropriate articles were identified from January 1966 to December 2005. A set of search strategies was systematically employed to determine the levels of evidence available for each clinical question. Primary outcome measures included the determination of levels of evidence and grade of recommendation based on The Oxford Center for Evidence-Based Medicine. Secondary outcome measures included for randomized controlled trials were Jadad scores, noting the presence of a sample size calculation, and the determination of an effect estimate and the reporting of a confidence interval. Higher quality randomized controlled trials (mostly level 2b, occasional level 1b) existed to answer three questions: whether to complete a 360 or partial wrap; whether or not to divide the short gastric vessels; and whether to perform laparoscopic or open surgery. Lower quality randomized controlled trials were available to determine whether the use of mesh was helpful, whether or not to use a bougie catheter for calibration of the wrap, and whether an anterior or posterior wrap results in a superior outcome. This was deemed to be of inferior grade of recommendation due to the lack (< 2) of trials available and the sole presence of level 2b evidence. The final two questions: whether to complete fundoplication using a thoracic or abdominal approach and whether to use intraoperative manometry relied exclusively upon level 4 evidence and thus received a lower grade of recommendation. A higher Jadad score seemed to be associated with studies having a higher level of evidence available to answer the question. Sample size calculations were given to answer three questions. Effect estimate was difficult to interpret given inconsistent findings, composite outcomes and lack of reported confidence intervals. In conclusion, antireflux surgery has many randomized controlled trials available upon which to base clinical practice. Unfortunately, these are generally of poor quality. We recommend that esophageal surgeons determine consistent outcome measures and endeavor to improve the quality of randomized controlled trials they perform. [source]


A systematic review and meta-analysis of randomised controlled trials evaluating interventions in adult literacy and numeracy

JOURNAL OF RESEARCH IN READING, Issue 3 2003
Carole J. Torgerson
This paper reports a systematic review of the trial literature in the field of adult literacy and numeracy. The review was undertaken to investigate the effectiveness of teaching strategies and pedagogies designed to increase adult literacy and numeracy. The objectives were to search for and locate, synthesise and quality appraise all the randomised controlled trials aiming to evaluate interventions in adult literacy and/or numeracy, published between 1980 and 2002. Fifty-nine papers were included in the descriptive map. Twelve papers were included that contained nine randomised controlled trials. All of the trials included in the review were of high quality in the sense that they had adopted an appropriate study design for assessing effectiveness. However, within that study design many of the studies had methodological problems, for example: small sample size and lack of justification of sample size calculation; unclear method of random allocation; high attrition rate and lack of ,intention to teach' analysis. There was evidence of publication bias. Pooling three studies that compared teaching against no teaching showed a strong, positive and statistically significant effect on outcome. Two other studies examined the use of computer-assisted instruction (CAI) on literacy among imprisoned adults. Pooling these two studies showed a modest but not statistically significant benefit. There is a dearth of rigorous RCTs in the field of adult literacy and numeracy. The evidence is suggestive of a benefit of adult literacy and numeracy interventions; however, because of the heterogeneity of studies, the precise role of any intervention is uncertain and this finding may be undermined by the presence of substantial publication bias. We recommend that a series of large, well-designed and well-conducted randomised trials should be undertaken in the field of adult literacy and numeracy. [source]


Sample size estimation for non-inferiority trials of time-to-event data

PHARMACEUTICAL STATISTICS: THE JOURNAL OF APPLIED STATISTICS IN THE PHARMACEUTICAL INDUSTRY, Issue 4 2008
Adam Crisp
Abstract We consider the problem of sample size calculation for non-inferiority based on the hazard ratio in time-to-event trials where overall study duration is fixed and subject enrolment is staggered with variable follow-up. An adaptation of previously developed formulae for the superiority framework is presented that specifically allows for effect reversal under the non-inferiority setting, and its consequent effect on variance. Empirical performance is assessed through a small simulation study, and an example based on an ongoing trial is presented. The formulae are straightforward to program and may prove a useful tool in planning trials of this type. Copyright 2007 John Wiley & Sons, Ltd. [source]


Quality and reporting of trial design in scientific papers in Anaesthesia over 25 years

ANAESTHESIA, Issue 1 2009
R. A. Langford
Summary We determined how the quality of trial design and its reporting in scientific papers published in Anaesthesia has changed in the last 25 years. All articles between the years 1983,87 and 2003,07 were reviewed and classified according to methodology. Reporting and trial design of all prospective, comparative clinical interventional trials were compared between the two time periods using 12 criteria. Fewer articles now originate from the United Kingdom and Ireland than 25 years ago. Although fewer human interventional trials are now published in Anaesthesia, the quality of these trials has improved in terms of study design, bias control and proper disclosure. Significant improvements were observed in all criteria of trial design except for the declaration of non-primary adverse outcomes and the minimisation of the risk of type I errors. Further improvements could still be made with respect to sample size calculation, description of the method of randomisation, and blinding. [source]


Testing Homogeneity of Two Zero-inflated Poisson Populations

BIOMETRICAL JOURNAL, Issue 1 2009
Siu Keung Tse
Abstract The problem of testing treatment difference in the occurrence of a safety parameter in a randomized parallel-group comparative clinical trial under the assumption that the number of occurrence follows a zero-inflated Poisson (ZIP) distribution is considered. Likelihood ratio tests (LRT) for homogeneity of two ZIP populations are derived under the hypotheses that (i) there is no difference in inflation parameters, (ii) there is no difference in non-zero means; and (iii) there is no difference in both inflation parameters and non-zero means. Approximate formulas for sample size calculation are also obtained for achieving a desired power for detecting a clinically meaningful difference under the corresponding alternative hypotheses. An example concerning the assessment of the gastrointestinal (GI) safety in terms of the number of erosion counts of a newly developed compound for the treatment of osteoarthritis and rheumatoid arthritis is given for illustration purpose ( 2009 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim) [source]


Pitfalls in the design and analysis of paediatric clinical trials: a case of a ,failed' multi-centre study, and potential solutions

ACTA PAEDIATRICA, Issue 2 2009
Johanna H Van Der Lee
Abstract Aim: To increase awareness of possible pitfalls in the design and analysis of a multi-centre randomized clinical trial and to give an overview of alternative study designs and their consequences for power analyses in case of limited availability of trial participants. Methods: Investigation of the assumptions in the power calculation and re-analysis of the original data of a ,failed' trial on the effect of dexamethasone on the duration of mechanical ventilation in young children with respiratory syncytial virus infection. Use of ,boundaries approach' is explored using the data from this trial. A comprehensive overview of the various modern solutions for the design of a subsequent trial in this field is given. Results: Two frequent major deficiencies of trial design and data analysis are reviewed in depth, i.e. too optimistic assumptions for the sample size calculation and failure to adjust for centre effects. Conclusion: Critical review of trial assumptions and if necessary sample size recalculation based on an internal pilot by a data monitoring committee is recommended to maximize the probability of obtaining conclusive results. [source]


Comprehensive linkage and linkage heterogeneity analysis of 4344 sibling pairs affected with hypertension from the Family Blood Pressure Program

GENETIC EPIDEMIOLOGY, Issue 3 2007
Tiffany A. Greenwood
Abstract Linkage analyses of complex, multifactorial traits and diseases, such as essential hypertension, have been difficult to interpret and reconcile. Many published studies provide evidence suggesting that different genes and genomic regions influence hypertension, but knowing which of these studies reflect true positive results is challenging. The reasons for this include the diversity of analytical methods used across these studies, the different samples and sample sizes in each study, and the complicated biological underpinnings of hypertension. We have undertaken a comprehensive linkage analysis of 371 autosomal microsatellite markers genotyped on 4,334 sibling pairs affected with hypertension from five ethnic groups sampled from 13 different field centers associated with the Family Blood Pressure Program (FBPP). We used a single analytical technique known to be robust to interpretive problems associated with a lack of completely informative markers to assess evidence for linkage to hypertension both within and across the ethnic groups and field centers. We find evidence for linkage to a number of genomic regions, with the most compelling evidence from analyses that combine data across field center and ethnic groups (e.g., chromosomes 2 and 9). We also pursued linkage analyses that accommodate locus heterogeneity, which is known to plague the identification of disease susceptibility loci in linkage studies of complex diseases. We find evidence for linkage heterogeneity on chromosomes 2 and 17. Ultimately our results suggest that evidence for linkage heterogeneity can only be detected with large sample sizes, such as the FBPP, which is consistent with theoretical sample size calculations. Genet. Epidemiol. 2007. 2007 Wiley-Liss, Inc. [source]


Optimal clinical trial design using value of information methods with imperfect implementation

HEALTH ECONOMICS, Issue 5 2010
Andrew R. Willan
Abstract Traditional sample size calculations for randomized clinical trials are based on the tests of hypotheses and depend on somewhat arbitrarily chosen factors, such as type I and II errors rates and the smallest clinically important difference. In response to this, many authors have proposed the use of methods based on the value of information as an alternative. Previous attempts have assumed perfect implementation, i.e. if current evidence favors the new intervention and no new information is sought or expected, all future patients will receive it. A framework is proposed to allow for this assumption to be relaxed. The profound effect that this can have on the optimal sample size and expected net gain is illustrated on two recent examples. In addition, a model for assessing the value of implementation strategies is proposed and illustrated. Copyright 2009 John Wiley & Sons, Ltd. [source]


Calculation of sample size for stroke trials assessing functional outcome: comparison of binary and ordinal approaches

INTERNATIONAL JOURNAL OF STROKE, Issue 2 2008
The Optimising Analysis of Stroke Trials (OAST) collaboration
Background Many acute stroke trials have given neutral results. Sub-optimal statistical analyses may be failing to detect efficacy. Methods which take account of the ordinal nature of functional outcome data are more efficient. We compare sample size calculations for dichotomous and ordinal outcomes for use in stroke trials. Methods Data from stroke trials studying the effects of interventions known to positively or negatively alter functional outcome , Rankin Scale and Barthel Index , were assessed. Sample size was calculated using comparisons of proportions, means, medians (according to Payne), and ordinal data (according to Whitehead). The sample sizes gained from each method were compared using Friedman 2 way ANOVA. Results Fifty-five comparisons (54 173 patients) of active vs. control treatment were assessed. Estimated sample sizes differed significantly depending on the method of calculation (P<00001). The ordering of the methods showed that the ordinal method of Whitehead and comparison of means produced significantly lower sample sizes than the other methods. The ordinal data method on average reduced sample size by 28% (inter-quartile range 14,53%) compared with the comparison of proportions; however, a 22% increase in sample size was seen with the ordinal method for trials assessing thrombolysis. The comparison of medians method of Payne gave the largest sample sizes. Conclusions Choosing an ordinal rather than binary method of analysis allows most trials to be, on average, smaller by approximately 28% for a given statistical power. Smaller trial sample sizes may help by reducing time to completion, complexity, and financial expense. However, ordinal methods may not be optimal for interventions which both improve functional outcome and cause hazard in a subset of patients, e.g. thrombolysis. [source]


Calculating power for the comparison of dependent , -coefficients

JOURNAL OF THE ROYAL STATISTICAL SOCIETY: SERIES C (APPLIED STATISTICS), Issue 4 2003
Hung-Mo Lin
Summary. In the psychosocial and medical sciences, some studies are designed to assess the agreement between different raters and/or different instruments. Often the same sample will be used to compare the agreement between two or more assessment methods for simplicity and to take advantage of the positive correlation of the ratings. Although sample size calculations have become an important element in the design of research projects, such methods for agreement studies are scarce. We adapt the generalized estimating equations approach for modelling dependent , -statistics to estimate the sample size that is required for dependent agreement studies. We calculate the power based on a Wald test for the equality of two dependent , -statistics. The Wald test statistic has a non-central ,2 -distribution with non-centrality parameter that can be estimated with minimal assumptions. The method proposed is useful for agreement studies with two raters and two instruments, and is easily extendable to multiple raters and multiple instruments. Furthermore, the method proposed allows for rater bias. Power calculations for binary ratings under various scenarios are presented. Analyses of two biomedical studies are used for illustration. [source]


Sample size considerations for Japanese patients in a multi-regional trial based on MHLW guidance

PHARMACEUTICAL STATISTICS: THE JOURNAL OF APPLIED STATISTICS IN THE PHARMACEUTICAL INDUSTRY, Issue 2 2010
Hui Quan
Abstract Since the publication of the International Conference on Harmonization E5 guideline, new drug approvals in Japan based on the bridging strategy have been increasing. To further streamline and expedite new drug development in Japan, the Ministry of Health, Labour and Welfare, the Japanese regulatory authority, recently issued the ,Basic Principles on Global Clinical Trials' guidance to promote Japan's participation in multi-regional trials. The guidance, in a Q&A format, provides two methods as examples for recommending the number of Japanese patients in a multi-regional trial. Method 1 in the guidance is the focus of this paper. We derive formulas for the sample size calculations for normal, binary and survival endpoints. Computations and simulation results are provided to compare different approaches. Trial examples are used to illustrate the applications of the approaches. Copyright 2009 John Wiley & Sons, Ltd. [source]


Long-interval T2-weighted subtraction magnetic resonance imaging: A powerful new outcome measure in multiple sclerosis trials

ANNALS OF NEUROLOGY, Issue 5 2010
Bastiaan Moraal MD
Objective To compare long-interval T2-weighted subtraction (T2w-Sub) imaging with monthly gadolinium-enhanced T1-weighted (Gd-T1w) imaging for (1) detection of active lesions, (2) assessment of treatment efficacy, and (3) statistical power, in a multiple sclerosis (MS), phase 2, clinical trial setting. Methods Magnetic resonance imaging (MRI) data over 9 months from 120 patients (61 treatment, 59 placebo) from the oral temsirolimus trial were used. T2w-Sub images were scored for active lesions, independent of the original reading of the monthly Gd-T1w images. Treatment efficacy was evaluated using the nonparametric Mann-Whitney U test, and parametric negative binomial (NB)-regression and power calculations were conducted. Results Datasets from 116 patients (58 treatment, 58 placebo) were evaluated. The mean number of T2w-Sub lesions in the treatment group was 3.0 (4.6) versus 5.9 (8.8) for placebo; the mean cumulative number of new Gd-T1w lesions in the treatment group was 5.5(9.1) versus 9.1(17.2) for placebo. T2w-Sub imaging showed increased power to assess treatment efficacy compared with Gd-T1w imaging, when evaluated by Mann-Whitney U test (p = 0.017 vs p = 0.177), or NB-regression without (p = 0.011 vs p = 0.092) or with baseline adjustment (p < 0.001 vs p = 0.002). Depending on the magnitude of the simulated treatment effect, sample size calculations showed reductions of 22 to 34% in the number of patients (translating into reductions of 81,83% in the number of MRI scans) needed to detect a significant treatment effect in favor of T2w-Sub imaging. Interpretation Compared with monthly Gd-T1w imaging, long-interval T2w-Sub MRI exhibited increased power to assess treatment efficacy, and could greatly increase the cost-effectiveness of phase 2 MS trials by limiting the number of patients, contrast injections, and MRI scans needed. ANN NEUROL 2010;67:667,675 [source]


Calculating Sample Size for Studies with Expected All-or-None Nonadherence and Selection Bias

BIOMETRICS, Issue 2 2009
Michelle D. Shardell
Summary We develop sample size formulas for studies aiming to test mean differences between a treatment and control group when all-or-none nonadherence (noncompliance) and selection bias are expected. Recent work by Fay, Halloran, and Follmann (2007, Biometrics63, 465,474) addressed the increased variances within groups defined by treatment assignment when nonadherence occurs, compared to the scenario of full adherence, under the assumption of no selection bias. In this article, we extend the authors' approach to allow selection bias in the form of systematic differences in means and variances among latent adherence subgroups. We illustrate the approach by performing sample size calculations to plan clinical trials with and without pilot adherence data. Sample size formulas and tests for normally distributed outcomes are also developed in a Web Appendix that account for uncertainty of estimates from external or internal pilot data. [source]


Identifying Combinations of Cancer Markers for Further Study as Triggers of Early Intervention

BIOMETRICS, Issue 4 2000
Stuart G. Baker
Summary. In many long-term clinical trials or cohort studies, investigators repeatedly collect and store tissue or serum specimens and later test specimens from cancer cases and a random sample of controls for potential markers for cancer. An important question is what combination, if any, of the molecular markers should be studied in a future trial as a trigger for early intervention. To answer this question, we summarized the performance of various combinations using Receiver Operating Characteristic (ROC) curves, which plot true versus false positive rates. To construct the ROC curves, we proposed a new class of nonparametric algorithms which extends the ROC paradigm to multiple tests. We fit various combinations of markers to a training sample and evaluated the performance in a test sample using a target region based on a utility function. We applied the methodology to the following markers for prostate cancer, the last value of total prostate-specific antigen (PSA), the last ratio of total to free PSA, the last slope of total PSA, and the last slope of the ratio. In the test sample, the ROC curve for last total PSA was slightly closer to the target region than the ROC curve for a combination of four markers. In a separate validation sample, the ROC curve for last total PSA intersected the target region in 77% of bootstrap replications, indicating some promise for further study. We also discussed sample size calculations. [source]


How I do it: sample size calculations

CLINICAL OTOLARYNGOLOGY, Issue 2 2008
J. O'Hara
Keypoints ,,Sample size calculations are integral to project design. ,,A description of the underlying theory behind them is set out. ,,Required are the significance level, the power, the clinical difference and the standard deviation. ,,Douglas Altman's nomogram is particularly useful for sample size calculations for comparing independent samples. [source]