I wish to use self-monitoring scale developed by Richard D. Lennox and Raymond N. Wolfe ("Revision of self-monitoring"). It is a 2 factor structure scale with total 13 items-
(1) ability to modify self-presentation-7 items & (2) sensitivity to expressive behaviour of others-6 items .
But for a part of my study I am trying to show the impact of self-monitoring on consumption behaviour , so I feel only the first dimension (ability to modify self-representation) is useful for me . Also I have 6-7 more latent variables so the survey is already touching 90 questions so I want to minimise the items .
Can I just use the 7 items given by this scale (representing the first dimension of self-monitoring), without disturbing psychometric properties and still call the composite variable of these 7 items - "SELF MONITORING"? Is this an acceptable practice in Research ? (I will doing SEM eventually)
You can call it the "ability to modify self-representation" subscale of the "self-monitoring scale", but not "self-monitoring scale as such". As far as compromising psychometric properties of the original scale is concerned, refer to the original scale if psychometric properties of the subscales were presented as well. Often times we see in psychometric research that internal consistency reliability and construct validation processes are presented at scale level even if the scale demonstrate multidimensionality.
Hello Megha,
beyond what Viswa Chandu correctly recommended, consider two things.
1) Although there is nothing wrong with focusing on a specific latent variable/facet, reviewers will have problems with that. As Viswa said, "scales" (a terrible name) are most often sold as a monolith that one should not break apart (leading to the nonsensical calculation of an overall alpha, has Viswa complained about).
2) Whether one facet should be selected in an isolated manner depends on your overall model and whether the excluded facet has some sort of confounding effect. In your case/model, I would see the sensitivity facet as a causal antecedent of the ability facet without a direct effect on customer behavior. Hence, no confounding.
3) In contrast to using all 7 items of all the latent variables, I would concentrate (even more) on three items which exactly reflect the ability component. 7 items (NEVER) fulfil assumptions of a pure common factor model which led to the mantra "because it never fits, it is of no importance").
HTH
Holger
A possible useful approach is to use Crombach's alpah in a reliability study to see if creating a single scale merging your separate items is a suffficiently reliable one. Most psychometricians consider an alpha of .80 and up as acceptable for a scale consisting of a number of items. The reliability analysis also points out which items do not fit the scale well and should probably not be included. The end product is a reduction in items as you are using one scale for the set, and a reliable one. The analysis is included in the SPSS software suite, but I do not doubt that other packages and R have it as well.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Techniques
- Structural Equation Modeling