Paralel, Eşdeğer ve Konjenerik Ölçmelerde Güvenirlik Katsayılarının Karşılaştırılması

Son zamanlarda çoklu derecelenmiş testlerde kullanılan güvenirlik katsayıları üzerine ve özellikle Cronbach’ın α katsayısının yanlılığına yönelik çalışmalar yoğunluk kazanmıştır. Birleşik testlerde yer alan maddelerin paralel, eşdeğer ya da konjenerik olması durumuna göre güvenirlik katsayıları farklı sonuçlara ulaşmaktadır. İkili derecelenmiş testlerde güvenirlik katsayısı olarak, maddelerin konjenerik ölçmeler olduğu durumlarda KR20, maddelerin eşdeğer ölçmeler olduğu durumlarda ise KR21 katsayıları kullanılmaktadır. Benzer şekilde çoklu derecelenmiş testlerde maddeler konjenerik ölçme ise McDonald’ın ω, eşdeğer ölçme ise Cronbach’ın α katsayısı önerilmektedir. Bu çalışmada; ölçme yapıları ve güvenirlik için temel kavramlar ele alınmış ve değişik ölçme kümelerinde Cronbach’ın α, Armor’un θ, Heise ve Bohrnstedt’ın Ω, Revelle’nin β ve McDonald’ın ω güvenirlik katsayıları karşılaştırılmıştır.

The Comparison of Reliability Coefficients in Parallel, Tau-Equivalent, and Congeneric Measurements

The recent studies on reliability coefficients in composite tests and specially the biased of Cronbach α have become intense. If the items in composite tests have parallel measurements orcongeneric measurements, then reliability coefficients are yielded differently. In the composite tests, consist of binary items, when the items have congeneric measurements KR20 is applied, otherwise KR21 is applied as reliability coefficient. Similarly, for the polythomous items with congeneric measurements McDonald’s ω,, otherwise Cronbach’s α is suggested to be used as reliability coefficient. In this study, first basic measurement types and reliability coefficients are defined, then Cronbach’s α, Armor’s θ, Heise and Bohrnstedt’s Ω, Revelle’s β, and McDonald’s ω coefficient, in relation to different measurements are compared.

Keywords:

Reliability Coefficients, Parallel Measure, TauEquivalent Measure, Essentially Tau- Equivalent Measure Congeneric Measure,

PDF

___

Adamson, G., Shevlin, M., Lloyd, N.S.V. & Lewis, C. A. (2000). An integrated approach for assessing reliability and validity: an application of structural equation modeling to the measurements of religiosity. Personality and Individual Differences, 29, 971-979.
Alwin, D. F. (1976). Attitude scales as congeneric tests: A re-examination of an attitude-behavior model. Sociometry, 39, 377-383.
Armor, D. J. (1974). Theta reliability and factor scaling. In Costner, H. L. (ed.), Sociological Methodology. Jossey-Bass, San Francisco. 17−50.
Bacon, D. R., Sauer, P. L. & Young M. (1995). Composite Reliability in Structural Equations Modeling. Educational and Psychological Measurement, 55, 394-406.
Baykul, Y. (2000). Eğitimde ve Psikolojide Ölçme: Klasik Test Teorisi ve Uygulaması. Ankara: ÖSYM Yayınları.
Carmines, E. G., & Zeller, R. A. (1979). Reliability and validity assessment, Sage, Beverly Hills, Calif.
Christmann, A. & Aelst, S. V. (2005). Robust estimation of Cronbach’s Alpha. Journal of Multivariate Analysis. (Baskıda).
Comrey, A. L. & Lee, H. B. (1992). A first course in factor analysis. Hillsdale, NJ: Erlbaum.
Cortina, J. M. (1993). What is coefficient alpha? An examination of theory and applications. Journal of Applied Psychology, 78, 98–104.
Cronbach, L.J. (1951). Coefficient alpha and the internal structure of tests. Psychometrika,16, 297-334.
DeVellis, R. F. (2003). Scale development: Theory and application, Sage Publications, California.
Feldt, L. S. & Qualls, A. L. (1996). Bias in coefficient alpha arising from heterogeneity of test content. Applied Measurement in Education. 9(3), 277-286.
Ghiselli, E. E. (1964). Theory of Psychological Measurement. McGrawHill, New York.
Green, S. B., & Hershberger, S. L. (2000). Correlated errors in true score models and their effect on coefficient alpha. Structural Equation Modeling, 7, 251–270.
Guttman, L. (1945). A basis for analyzing test-retest reliability. Psychometrika, 10, 255-282.
Heise, D. R., & Bohrnstedt, G. W. (1970). Validity, invalidity and reliability. In Borgatta, E. F. and Bohrnstedt, G. W. (eds.), Sociological Methodology. Jossey-Bass, San Francisco. 104−129.
Jöreskog, K. G. (1971). Statistical analysis of congeneric tests. Psychometrika, 36, 109-133.
Komaroff, E. (1997). Effect of simultaneous violations of essential tau-equivalence and correlated errors on coefficient alpha. Applied Psychological Measurement, 21, 337–348.
Lord F. M. & Novick, R. (1968). Statistical theories of mental test scores. Reading MA: Addison-Wesley.
Lucke, J. F. (2005a). The $alpha$ and $omega$ of congeneric test theory: An extension of reliability and internal consistency to heterogeneous tests. Applied Psychological Measurements. 29(1), 65-81.
Lucke, J. F. (2005b). “Rassling the hog”: the influence of correlated item error on internal consistency, classical reliability, and congeneric reliability. Applied Psychological Measurements. 29(2), 106-125.
MacCallum, R. C., Widaman, K. F., Zhang, S., and Hong, S. (1999). Sample size in factor analysis. Psychological Methods 4: 84 –99.
McDonald, R. (1985). Factor analysis and related methods. Hillsdale, N J: Erlbaum.
McDonald R. P. (1999). Test theory: A unified treatment. Mahwah, NJ: LEA Publisher.
Miller, M. B. (1995). Coefficient alpha: A basic introduction from the perspectives of classical test theory and structural equation modeling. Structural Equation Modeling, 2, 255–273.
Novick, M. R. & Lewis, C. (1967). Coefficient alpha and the reliability of composite measurements. Psychometrika, 32, 1-13.
Nunnally, J. C. & Bernstein, I. H. (1994): Psychometric theory. 3rd Edition. McGraw-Hill: New York.
Osburn, H. G. (2000). Coefficient alpha and related internal consistency reliability coefficients. Psychological Methods, 5, 343–355.
Rae. G. (2006). Correcting Coefficient Alpha for Correlated Errors: Is αK a Lower Bound to Reliability? Applied Psychological Measuremet, 30(1), 56-59.
Raykov, T. (1997a). Estimation of composite reliability for congeneric measures, Applied Psychological Measurements. 21(2), 173-184.
Raykov, T. (1997b). Bias of coefficient $alpha$ for fixed congeneric measures with correlated errors. Applied Psychological Measurements. 25(1), 69-76.
Spearman, C. (1904). The proof and measurement of association between two things. American Journal of Psychology, 15, 72−101.
Traub, E. R. (1994). Reliability for the social sciences: Theory and Applications. Measurement methods for the social sciences. Sage Publications, 1994.
Yurdugül, H. (2005). Konjenerik test kuramı ve konjenerik madde analizi: Tek boyutlu çoktan seçmeli testler üzerine bir uygulama. A.Ü. Eğitim Bilimleri Fakültesi Dergisi 38(2), Baskıda.
Zinbarg, R. E., Revelle, W., Yovel, I. & Li, W. (2005). Cronbach’s $alpha$, Revelle’s, $beta$ and McDonalds $omega$: their relations with each other and two alternative conceptualizations of reliability. Psychometrika, 70(1), 1-11.
Zimmerman, D. W., B.D. & Lalonde, C. (1993). Coefficient Alpha as an estimate of test reliability under violation of two assumptions. Etucational and Psychological Measurement, 53 (1), 33-49.