FAQ/Raykov - CBU statistics Wiki

Revision 1 as of 2011-05-05 15:00:08

Clear message
location: FAQ / Raykov

EQS code for obtaining Raykov's rho for a twenty scale item inventory

This code can also be produced using the menu bar in EQS 6.1 or above (Bentler and Wu (2002)). The file name under DATA, number of Variables, number of cases and variable labels need to be adjusted, as appropriate.

/TITLE
Model built by EQS 6 for Windows
/SPECIFICATIONS
DATA='c:\documents and settings\peterw\desktop\my documents\eqs files stai\state
a.ess';
VARIABLES=20; CASES=436; 
METHOD=ML; ANALYSIS=COVARIANCE; MATRIX=RAW; 
/LABELS
V1=S_Q_1; V2=S_Q_2; V3=S_Q_3; V4=S_Q_4; V5=S_Q_5; 
V6=S_Q_6; V7=S_Q_7; V8=S_Q_8; V9=S_Q_9; V10=S_Q_10; 
V11=S_Q_11; V12=S_Q_12; V13=S_Q_13; V14=S_Q_14; V15=S_Q_15; 
V16=S_Q_16; V17=S_Q_17; V18=S_Q_18; V19=S_Q_19; V20=S_Q_20; 
/RELIABILITY
SCALE=V1,V2,V3,V4,V5,V6,V7,V8,V9,V10,
V11,V12,V13,V14,V15,V16,V17,V18,V19,V20;
/PRINT
FIT=ALL;
TABLE=EQUATION;
/END

Like Cronbach's alpha, Raykov's rho (also known as a composite correlation), ranges between zero and one. The higher its value the more reliable the item scale. A value of rho above 0.8 indicates good internal consistency, while 0.7 represents the lower limit of adequacy (Cicchetti, 1994).

References

Bentler, P.M., & Wu, E.J.C. (2002). EQS 6 for Windows user’s guide. Encino, CA. Multivariate Software, Inc.

Cicchetti, D.V. (1994). Guidelines, criteria, and rules of thumb for evaluating normed and standardized assessment instruments in psychology. Psychological Assessment, 6, 284-290. (ON SCIENCEDIRECT FOR CBSU USERS).

Raykov T. (1997). Estimation of composite reliability for congeneric measures. Applied Psychological Measurement, 21, 173-184.