Search found 15 matches

by bubach
Mon Mar 05, 2007 1:59 pm
Forum: Method and application
Topic: Omission Distance
Replies: 2
Views: 3116

Hello Oliver, the article from Tenenhaus et al 2005 in Computational Statistics is very helpful. On page 174f, Tenenhaus describe the Blindfolding approach. To your question: The data are divided into several groups (=omission-distance), e.g. a, b, c. First all values for a are deleted and estimated...
by bubach
Fri Mar 02, 2007 4:13 pm
Forum: Method and application
Topic: effect size negative?
Replies: 3
Views: 3471

Hello Mr Sailors,

thanks a lot for your help. So, in this case, R-Square does not depend positively on the number of paths like in multiple regression, right?

Thanks a lot,
Michael
by bubach
Fri Feb 09, 2007 12:19 pm
Forum: Method and application
Topic: Effect size: Remove path or latente variable
Replies: 1
Views: 1963

Effect size: Remove path or latente variable

Hello community,

to calculate the effect size, it is enough to remove the path from one latent variable to another or have i to remove the complete latent variable (including all paths to different constructs)?

Many thanks in advance,
Michael
by bubach
Thu Feb 08, 2007 11:17 am
Forum: Method and application
Topic: effect size negative?
Replies: 3
Views: 3471

effect size negative?

Hello Community, i need your help. I want to calculate the effect size. I have 4 Constructs (A, B, C, D) with Connection A to B, A to C, A to D and B to D and C to D. Then i calculated the R-square for the D with all paths, then i removed path A to D and calculate R-square for D again. Now i could c...
by bubach
Thu Nov 23, 2006 8:47 am
Forum: Method and application
Topic: different measures in the same formative construct
Replies: 3
Views: 3401

Thanks a lot for your answer.

I am still not sure if it is possible to use a diochtom (for Example male= 0/Female = 1) in SmartPLS.

Do you have any idea how to handle dichotom in SmartPLS?

Thanks a lot
by bubach
Wed Nov 22, 2006 3:54 pm
Forum: Method and application
Topic: comparison of the fit of two models
Replies: 4
Views: 5489

Hello Sandra,


GOF = sqrt(average(AVE)*average(Rsq))

Please note, that this GoF doesn't make sense, if you use formative consturcts.
by bubach
Mon Nov 20, 2006 8:40 am
Forum: Method and application
Topic: Second order factor
Replies: 26
Views: 24895

Additional to Sandro's question:
Does it make sense to build a second-order construct that consist of reflective first-order construct as well as formative first-order constructs?
Does anybody know some hints in the literature?

I really appreciate your help!
by bubach
Wed Nov 15, 2006 1:22 pm
Forum: Method and application
Topic: different measures in the same formative construct
Replies: 3
Views: 3401

different measures in the same formative construct

Hello all, I've got a dataset, but there is the following situation: One construct (formative) have got 4 items, but each item is measured on d different scale (e.g., one on a 7-scale, one 5-scale, on as a dichotom) Can SmartPLS handle such a situation? I'm thinking that all items are standardized b...
by bubach
Mon Oct 30, 2006 12:57 pm
Forum: Method and application
Topic: Latent variable Correlations
Replies: 1
Views: 3131

Latent variable Correlations

Hello all,

how are the "Latent variable Correlations" in SmartPLS calculated?
Are those the Pearson-Correlations?

How can i interpret "LV Index Values"?

Thanks a lot for your help!
by bubach
Mon Oct 30, 2006 12:09 pm
Forum: Method and application
Topic: Difference in results between SPSS and SmartPLS
Replies: 1
Views: 2742

Difference in results between SPSS and SmartPLS

Hello all, I calculated the cronbachs a in SPSS and SmarPLS and i found a slight difference. I guess this is caused by rounding errors. I also did a simple regression in SPSS and the same in SmartPLS. I found significant different between R-square and the path-coefficients. Could anybody explain why...
by bubach
Thu Oct 12, 2006 8:59 am
Forum: Method and application
Topic: Difference between DEV and Communality?
Replies: 7
Views: 10541

Dear Prof. de Souza Bido, Thank you so much for your explanations. They are very helpful. You wrote: The AVE will be: (0.36+0.49+0.64)/3 = 0.49666 = 40.6% (the LV explain 40.6% of the variance from all MVs). This is exactly the same formula for communality (used in Tenenhaus et al. 2005). For a late...
by bubach
Wed Oct 11, 2006 1:38 pm
Forum: SmartPLS 3 - Requested Features
Topic: Variance Infaltion Factor (VIF)
Replies: 3
Views: 5799

Variance Infaltion Factor (VIF)

Dear Dr. Ringle,

in my opinion, i would be very useful if SmartPLS would show the max. VIF for all formative constructs (e.g. in Overwiev).
What do you think about that?

Thanks,
Markus
by bubach
Wed Oct 11, 2006 11:53 am
Forum: Method and application
Topic: Difference between DEV and Communality?
Replies: 7
Views: 10541

Dear Dr. Ringle,

that means that in the reflective way AVE = Communality, right?

Thanks a lot.
by bubach
Wed Oct 11, 2006 9:23 am
Forum: Method and application
Topic: Difference between DEV and Communality?
Replies: 7
Views: 10541

Difference between DEV and Communality?

Hello Community,

does somebody knows, what's the different between DEV and Communality (both are reported in Quality-Criteria Overview)?

Thanks you for your comments.
by bubach
Tue Oct 10, 2006 6:59 am
Forum: Method and application
Topic: Bootstrapping: Sign Changes-function
Replies: 1
Views: 3765

Bootstrapping: Sign Changes-function

Hello, I have just installed the new release M3 and i found new feature in the Bootstrapping-procedure: Sign Changes: Individual Changes, Construct Level Changes and No Sign Changes Could anybody explain, what's the meaning of this function is? Maybe, somebody knows a good article about this. I real...