Sample size requirements for the design of reliability study: review and new results

Shoukri, M.M.; Asyali, M.H.; Donner, A.
August 2004
Statistical Methods in Medical Research;Aug2004, Vol. 13 Issue 4, p251
Academic Journal
The reliability of continuous or binary outcome measures is usually assessed by estimation of the intraclass correlation coefficient (ICC). A crucial step for this purpose is the determination of the required sample size. In this review, we discuss the contributions made in this regard and derive the optimal allocation for the number of subjects k and the number of repeated measurements n that minimize the variance of the estimated ICC. Cost constraints are discussed for both normally and non-normally distributed responses, with emphasis on the case of dichotomous assessments. Tables showing optimal choices of k and n are given along with the guidelines for the efficient design of reliability studies.


Related Articles

  • THE EFFECTS OF SAMPLE SIZE AND CORRELATION ON THE ACCURACY OF THE EV EFFICIENCY CRITERION. Saniga, Erwin; Gressis, Nicolas; Hayya, Jack // Journal of Financial & Quantitative Analysis;Sep79, Vol. 14 Issue 3, p615 

    In this paper, we have presented the exact probabilities of correctly concluding dominance by the criterion of EV for normal populations with n = 10(10)50 and ρ = 0. We have also studied the influence of correlation on the effectiveness of the EV criterion (and indirectly on the SSD...

  • Was the study big enough? Two "cafe" rules. Glasziou, Paul; Doll, Helen // ACP Journal Club;Nov/Dec2007, Vol. 147 Issue 3, pA8 

    The authors' offer their opinion on the magnitude of clinical studies. They opine that small studies do not provide a statistically significant effect. They state that smaller studies are more susceptible to random errors, as compared to longer studies and have tighter CIs. They also discuss the...

  • A META-ANALYSIS OF THE DIFFUSION OF INNOVATIONS LITERATURE. Midgley, David F. // Advances in Consumer Research;1987, Vol. 14 Issue 1, p204 

    The 1840 published studies relating to 20 of Rogers and Shoemaker's generalisations on the diffusion of innovations are meta-analysed by way of assumptions and simple techniques addressing sampling error. It is found that most of the discrepancy between studies supporting and not supporting...

  • The Mann-Kendall Test Modified by Effective Sample Size to Detect Trend in Serially Correlated Hydrological Series. Sheng Yue; Chunyuan Wang // Water Resources Management;Jun2004, Vol. 18 Issue 3, p201 

    The non-parametric Mann-Kendall (MK) statistical test has been popularly used to assess the significance of trend in hydrological time series. The test requires sample data to be serially independent. When sample data are serially correlated, the presence of serial correlation in time series...

  • Confidence Interval Construction by Stein's Method: A Practical and Economical Approach to Sample Size Determination. Gillett, Raphael // Journal of Marketing Research (JMR);May89, Vol. 26 Issue 2, p237 

    A two-stage method of confidence interval construction developed by Stein is a practical and straightforward approach to sample size determination when one wants to estimate the mean of a normal distribution of unknown mean and variance. The technique has several advantages over the modified...

  • ESTIMATING THE CHARACTER OF UNSAMPLED SEGMENTS OF A UNIVERSE. Warner, Lucien // Journal of Marketing;Oct47, Vol. 12 Issue 2, p186 

    The article presents a surveying and sampling methodology for forecasting characteristics without extensively sampling a certain group. The statistical significance of data which is correlated to represent unsampled market segments is described. This type of estimation would be best utilized for...

  • THE INCLUSION PROBABABILITIES OF MEDIAN RANKED SET SAMPLING UNDER DIFFERENT SELECTION PROCEDURES. Ozdemir, Yaprak Arzu; Gokpinar, Fikri // Communications Series A1 Mathematics & Statistics;2010, Vol. 59 Issue 1, p9 

    In this paper, we developed generalized formulas to compute the inclusion probabilities of a median ranked set sample in a finite population setting under Level 0 and Level 2 sampling procedures given by Deshpande et al.(2006). We also compared the inclusion probabilities of these sampling...

  • Likert scales, levels of measurement and the 'laws' of statistics. Norman, Geoff // Advances in Health Sciences Education;Dec2010, Vol. 15 Issue 5, p625 

    Reviewers of research reports frequently criticize the choice of statistical methods. While some of these criticisms are well-founded, frequently the use of various parametric methods such as analysis of variance, regression, correlation are faulted because: (a) the sample size is too small, (b)...

  • A cautionary note on the appropriateness of using a linkage resource for an association study. Allen-Brady, Kristina; Farnham, James M.; Weiler, Jeff; Camp, Nicola J. // BMC Genetics;2003 Supplement 1, Vol. 4, pS89 

    Background: Utilizing a linkage resource for association analysis requires consideration both of the marker data used and correlations among relatives in pedigrees. We previously developed a method for association testing in pedigrees. We applied our method to 50 replicates of microsatellite...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics