MINIMUM SAMPLE SIZE FOR CRONBACH'S COEFFICIENT ALPHA: A MONTE-CARLO STUDY CRONBACH ALFA KATSAYISI İÇİN MİNİMUM ÖRNEKLEM GENİŞLİĞİ: MONTE-CARLO ÇALIŞMASI

The coefficient alpha is the most widely used measure of internal consistency for composite scores in the educational and psychological studies. However, due to the difficulties of data gathering in psychometric studies, the minimum sample size for the sample coefficient alpha has been frequently debated. There are various suggested minimum sample sizes for the robust estimate of the population coefficient alpha. This research indicates that the performance of an estimator of the coefficient alpha depends not only on the sample size but also on the largest eigenvalue of the sample data set. Thus, when the largest eigenvalue increases, unbiased estimation of the population coefficient alpha is possible, even though the sample size is small. The simulations in this study were based on Monte-Carlo method with bootstrap technique. OZET: Egitimsel ve psikolojik calismalarda birlesik olcmelerin guvenirliginin hesaplamasinda yaygin olarak Cronbach (1951) tarafindan gelistirilen alfa katsayisi kullanilmaktadir. Ancak bu tur calismalarda veri toplamanin zorlugu nedeniyle alfa katsayisi icin gerekli olan minimum orneklem genisligi tartisma konusudur. Evren alfa katsayisinin saglam kestirimi icin gerekli olan minimum orneklem genisligi icin farkli oneriler vardir. Bu calismanin sonuclarina gore; yansiz ve tutarli bir alfa kestirimi orneklem genisliginin buyuklugu kadar ayni zamanda olcmelerin birinci ozdegerinin buyuklugune baglidir. Buna gore, birinci ozdeger buyudukce, dusuk orneklem genisliklerinde alfa katsayisinin yansiz bir kestirimi olanaklidir. Bu calismada kullanilan simulasyonlar bootstrap teknigi ile birlikte Monte-Carlo yontemi uzerine kurulmustur. Anahtar sozcukler: Guvenirlik, orneklem genisligi, alfa katsayisi, Monte-Carlo, simulasyon

[1]  M. E. Muller,et al.  A Note on the Generation of Random Normal Deviates , 1958 .

[2]  Marilynn B. Brewer,et al.  Principles of research in social psychology , 1973 .

[3]  J. M. Cortina,et al.  What Is Coefficient Alpha? An Examination of Theory and Applications , 1993 .

[4]  H. Neudecker,et al.  On the distribution of the maximum likelihood estimator of Cronbach's alpha , 2000 .

[5]  Ke-Hai Yuan,et al.  On robusiness of the normal-theory based asymptotic distributions of three reliability coefficient estimates , 2002 .

[6]  R. Charter,et al.  Sample size requirements for precise estimates of reliability, generalizability, and validity coefficients. , 1999, Journal of clinical and experimental neuropsychology.

[7]  D. Armor.  Theta Reliability and Factor Scaling , 1973 .

[8]  D. Segall.  The reliability of linearly equated tests , 1994 .

[9]  L. Cronbach.  Coefficient alpha and the internal structure of tests , 1951 .

[10]  Yan Liu,et al.  The Impact of Outliers on Cronbach's Coefficient Alpha Estimate of Reliability: Visual Analogue Scales , 2007 .

[11]  SIMREL: Software for Coefficient Alpha and Its Confidence Intervals With Monte Carlo Studies , 2009 .

[12]  K. Yuan,et al.  A Study Of The Distribution Of Sample Coefficient Alpha With The Hopkins Symptom Checklist: Bootstrap Versus Asymptotics , 2003 .

[13]  R. Peterson.  A Meta-analysis of Cronbach's Coefficient Alpha , 1994 .

[14]  Paul Kline,et al.  A Handbook of Test Construction : Introduction to Psychometric Design , 1987 .

[15]  R. Charter,et al.  Study Samples Are Too Small to Produce Sufficiently Precise Reliability Coefficients , 2003, The Journal of general psychology.

[16]  R. MacCallum,et al.  Sample size in factor analysis. , 1999 .

[17]  T Raykov,et al.  Scale Reliability, Cronbach's Coefficient Alpha, and Violations of Essential Tau-Equivalence with Fixed Congeneric Components. , 1997, Multivariate behavioral research.