RELIABILITY AND VALIDITY OF THE MATH ESSENTIAL SKILL SCREENER ELEMENTARY VERSION (MESS-E)

The Math Essential Skill Screener-Elementary Version (MESS-E) is a scr eener devised to identify primary grade students at risk for math diff iculties. Item analysis, interitem consistency, test-retest reliabilit y, decision efficiency, and construct validity of the MESS-E were stud ied using four independent samples of boys and girls grades 1-3 (aged 6-8). Item analysis revealed median item difficulty of .64 and median item discrimination of .75. Interitem consistency was .92 (n = 171) an d .94 (n = 711), while 30-day test-retest reliability was .86 (n = 125 ). Exploratory factor analysis indicated a one-factor solution account ing for 37% of observed variance. LISREL 7 confirmatory factor analysi s procedures determined that the one-factor model fit the standardizat ion sample data poorly (goodness-of-fit index = .729, chi(2) to df rat io = 9.91). The MESS-E yielded concurrent validity coefficients (n = 1 71) of .74 with the Woodcock-Johnson: Tests of Achievement-Revised (WJ -R) Math Cluster, .80 with the Wide-Range Achievement Test-Revised (WR AT-R) Arithmetic subtest and .73 with the KeyMath-R Operations Area st andard scores. A diagnostic efficiency study yielded a total predictiv e value (TPV) of .93, sensitivity = .98, specificity = .88, positive p redictive power(PPP) = .89, negative predictive power(NPP) = .98, and incremental validity = 39%. The MESS-E displayed a slight tendency to overidentify children potentially at risk for math difficulties. (C) 1 998 John Wiley & Sons, Inc.