Využitie a zneužitie Cronbachovej alfy pri hodnotení psychodiagnostických nástrojov

č.7(2016)

Abstrakt

Na základe výsledkov testovania prebiehajúcom v psychologickej diagnostike, vznikajú závery a rozhodnutia, ktorých validita kriticky závisí od spoľahlivosti využitých posudzovacích metód. Reliabilita nástroja je z tohto dôvodu kľúčovým pojmom pri posudzovaní akéhokoľvek psychologického atribútu. Napriek množstvu alternatív, najvýznamnejším a najpoužívanejším indikátorom kvality testového skóre ostáva sprofanovaný koeficient vnútornej konzistencie - alfa (Cronbach, 1951). Postupne identifikujeme najzávažnejšie omyly a problémy, ktoré sa pri  používaní tejto štatistiky opakovane objavujú. K jednotlivým bodom taktiež ponúkame riešenia, ktoré by mohli prispieť k zlepšeniu odhadu kvality skóre testovacích nástrojov a rozhodnutí, ktoré sa o ne opierajú.

The validity of inferences and decisions formed on the basis of testing in psychological diagnostics is critically dependent on reliability of utilized assessment tools. Therefore, whenever a psychological attribute is to be scored, reliability of the diagnostic means becomes crucial. Despite many alternatives, Cronbach’s alpha (1951), as profaned internal consistency statistic, remains the most prominent and most widely used indicator of test score quality. Because of this importance, our article is aimed to identify the most serious misconceptions and misapplications which repeatedly occur when using this statistics. For each particular point of this issue, we suggest a simple solution which may improve the estimation of the score quality of tests and therefore enhance decisions that are drawn from them.


Klíčová slova:
reliabilita; Cronbachova alfa; vnútorná konzistencia; psychomerika; reliability; Cronbach's Alpha; internal consistency; psychometrics
Reference
Cattell, R. B. (1978). The Scientific Use of Factor Analysis in Behavioral and Life Sciences. Boston, MA: Springer US.

Cortina, J. M. (1993). What is coefficient alpha: An examination of theory and applications. Journal of Applied Psychology, 78, 98-104. doi: 10.1037/0021-9010.78.1.98

Cronbach, L. J. (1951). Coefficient alpha and the internal structure of tests. Psychometrika, 12, 1-16.

Feldt, L. S., & Brennan, R. L. (1989). Reliability. In R. L. Linn (Ed.), Educational measurement (3rd ed.: pp. 105-146). New York: Macmillan.

Flora, D. B., & Curran, P. J. (2004). An empirical evaluation of alternative methods of estimation for confirmatory factor analysis with ordinal data. Psychological Methods, 9, 466-491. doi: 10.1037/1082-989X.9.4.466

Gelin, M. N., Beasley, T. M., & Zumbo, B. D. (2003). What is the impact on scale reliability and exploratory factor analysis of a Pearson correlation matrix when some respondents are not able to follow the rating scale? Paper presented at the annual meeting of the American Educational Research Association (AERA) in Chicago, Illinois.

R Core Team (2013). R: A language and environment for statistical computing. R Foundation for Statistical, Computing, Vienna, Austria. URL http://www.R-project.org/.

Revelle, W. (1979). Hierarchical clustering and the internal structure of tests. Multivariate Behavior Research, 14, 59-69. doi: 10.1207/s15327906mbr1401_4

RStudio Team (2015). RStudio: Integrated Development for R. RStudio, Inc., Boston, MA URL http://www.rstudio.com/.

Schmidt, F. L., & Hunter, J. E. (1996). Measurement error in psychological research: Lessons from 26 research scenarios. Psychological Methods, 1(2), 199-223. doi: 10.1037/1082-989X.1.2.199

Streiner, D. L. (2003). Being inconsistent about consistency: When coefficient alpha does and doesn’t matter. Journal of Personality Assessment, 80(3), 217-222. doi: 10.1207/S15327752JPA8003_01

Wilcox, R. R. (2005). Introduction to robust estimation and hypothesis testing (2nd ed.). San Diego, CA: Academic Press.

Zimmerman, D. W., Zumbo, B. D., & Lalonde, C. (1993). Coefficient alpha as an estimate of test reliability under violation of two assumptions. Educational and Psychological Measurement, 53, 33-49. doi: 10.1177/0013164493053001003

Zinbarg, R. E., Revelle, W., Yovel, I., & Wen, L. (2005). Cronbach's α, Revelle's β, and Mcdonald's ωH: Their relations with each other and two alternative conceptualizations of reliability. Psychometrika, 70(1), 1-11. doi: 10.1007/s11336-003-0974-7

Zumbo, B. D., Gadermann, A. M., & Zeisser, C.. (2007). Ordinal Versions of Coefficients Alpha and Theta For Likert Rating Scales. Journal of Modern Applied Statistical Methods, 6, 21-29.
Metriky

0


666

Views

253

původní views

36

errata views

1395

aktualizované views