Premium
AN EMPIRICAL STUDY OF THE EFFECTS OF STANDARDIZING SCORES IN THE FORMATION OF LINEAR COMPOSITES 1
Author(s) -
TERWILLIGER JAMES S.,
ANDERSON DOUGLAS H.
Publication year - 1969
Publication title -
journal of educational measurement
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.917
H-Index - 47
eISSN - 1745-3984
pISSN - 0022-0655
DOI - 10.1111/j.1745-3984.1969.tb00671.x
Subject(s) - standard deviation , raw score , component (thermodynamics) , standard error , statistics , mathematics , standard score , standardization , absolute deviation , composite number , raw data , algorithm , computer science , thermodynamics , physics , operating system
Component scores with specified means, standard deviations and intercorrelations were generated by computer. Two linear composites were calculated; one using a given set of nominal weights with the raw component scores and the second using the same nominal weights with the standard component scores. Both sets of composite scores were scaled to the same mean and standard deviation. The distribution of differences between the two scaled composite scores was examined to determine the effect of standardization. Specifically, the standard deviation of the difference scores, the largest single difference, and the number of differences greater than two were related to the number and characteristics of the original components. Implications for practice are discussed.