Hi everyone,
I'm having trouble implementing Chin et al.'s (2003) two-stage approach to test for moderation effects. Specifically, I am receiving the error, "A singular matrix occurred during the estimation of the path coefficients using the path weighting scheme. Setting another path weighting scheme could solve the problem." However, using neither the centroid nor the factor weighting scheme helps.
As background, according to Chin et al., if a moderation effect involves a formative construct, then the product indicator moderation technique cannot be used. Instead, they propose a two-stage approach:
"The first step would entail using the formative indicators in conjunction with PLS to create underlying construct scores for the predictor and moderator variables. Step two would then consist of taking those single composite scores to create a single interaction term."
To implement this, I copied the standardized latent variable scores generated by PLS. Then, for each observation, I multiplied the latent variable score of the exogenous variable (X) by the latent variable score of the moderating variable (Y). I then created a new PLS model using the data calculated with three predictors: X, Y, and X*Y. Running this model produced the error above. Any ideas?
Best,
Tony
Reference:
Chin et al. A Partial Least Squares Latent Variable Modeling Approach for Measuring Interaction Effects: Results from a Monte Carlo Simulation Study and An Electronic Mail Emotion/Adoption Study. Information Systems Research (2003) vol. 14 (2) pp. 189-217