forum.smartpls.com

Hello All, There is a bit of confusion regarding the calculation of discriminant validity of constructs. The best method was given by Fornell, Claes and David F. Larcker, (1981), "Evaluating Structural Equation Models with Unobservable Variables and Measurement Error," Journal of Marketing...

Second order constructs can be modelled using repeated indicator approach mentioned in this forum. Whether you should use it at all, depends on your theory building. The same set of statistics will be used for judging reliability and validity.

If you want to check path significances, you definitely need either bootstrap or jack knife. It is the resample size(at least 200) that matters and not raw sample size. Raw sample size should be determined using g-power software.

True Prof Bido. We check the discriminant validity in LISREL by seeing the increase in chi square value after imposing a correlation of 1 between the constructs.

By the way thanks for all your timely help. I have submitted my dissertation on supply chains.

Regards

Vivek

No no, the values of alpha are always the same. check your data.

Check out the following links for how to on gpower3

http://www.psycho.uni-duesseldorf.de/ab ... literature


http://www.psycho.uni-duesseldorf.de/ab ... -Paper.pdf

I have just submitted my PhD dissertation on the topic "An empirical study on the influence of Environmental uncertainty, supply chain practices and supply chain flexibility on competitive advantage and organisational performance" using PLS path modelling. I wish to thank all the members o...

If you want to check correlation significances between constructs, use spss and check out correlation between factor scores of the constructs.

A hypothesis is an arrow in the diagram. Check it out first.

Both are methods to find out path significances. Assume sample size is 50 In boot strap We select any one case., record it and replace it back into the data set. Then we pick another and do the same. We pick 55 cases after replacing each case. Some cases get repeated. This constitutes one resample c...

We usually do not use bootstrap results for indicators. Indicators are first purified using spss and only purified scales are tested in PLS. We usually give importance only to inner model bootstrap results while ensuring that the loadings of the indicators on constructs is more than 0.5

First develope constructs based on theory and find indicators as variables for each construct. That will indicate what values to use.

Find the RMS values for the ave scores for two constructs. If this value is greater than the construct correlations, the constructs have discriminant validity.

YOu can predict latent variable scores using indicator scores

PLS is CFA, while factor analysis usually refers to EFA. In factor analysis the end result gives the components of each factor. In PLS we assume it apriori and also check for construct validity.

Yes indicators can be repeated if the same indicator is to appear in first order and second order constructs, not otherwise.