Search found 22 matches

by allenjia
Tue Apr 03, 2012 3:01 am
Forum: SmartPLS 2 - FAQ
Topic: lv to unstandlized
Replies: 1
Views: 2224

He said we cannot use that one. We need to calculate by ourselves.

See viewtopic.php?t=812&highlight=unstandardized++score

viewtopic.php?t=2027
by allenjia
Mon Apr 02, 2012 6:12 am
Forum: SmartPLS 2 - FAQ
Topic: Calculation about unstandardized LV score, Dr. Bido's method
Replies: 2
Views: 2372

Dear Dr. Bido, Thank you sooooooooooooo much! I think I got it. Lin 1) Run the example---PLS algorithm 2) Copy the standardized outer weights--Weights of items on relevant factors 3) Compute the standardized deviation to each indicator and copy/past to the side of the weight----use Manifest variable...
by allenjia
Thu Mar 22, 2012 6:59 am
Forum: SmartPLS 2 - FAQ
Topic: Only 9 rows of indicators imported
Replies: 4
Views: 3055

I am also cheated by what I had seen. The reality is that all data are imported. HaHa
by allenjia
Thu Mar 22, 2012 6:46 am
Forum: Method and application
Topic: The significance of indirect effect
Replies: 8
Views: 6425

Based on what I have learnt in my SEM course, we have three basic ways to do that: Sober test, bootstrap options in AMOS, Mplus. But the last one is the best one. The second one is also OK. The first one, maybe just so so.
by allenjia
Thu Mar 22, 2012 6:43 am
Forum: Method and application
Topic: Single item construct (formative vs. reflective)
Replies: 3
Views: 3382

If you use formative, it will be harder for the link between dependent and independent variable to be significant, because the single indicator will account for a big part of the variance of dependent variable. Thus, reflective
by allenjia
Thu Mar 22, 2012 6:40 am
Forum: Method and application
Topic: common method bias test
Replies: 2
Views: 2692

You can use the search function in this forum, and will find some useful directions. For example, the method in an article of MIS Q.

ASSIMILATION OF ENTERPRISE SYSTEMS: THE EFFECT
OF INSTITUTIONAL PRESSURES AND THE MEDIATING
ROLE OF TOP MANAGEMENT
by allenjia
Thu Mar 22, 2012 6:34 am
Forum: Method and application
Topic: How can I include control variables in smartpls?
Replies: 6
Views: 7806

I remembered Dr. Bido once mentioned two methods. I do it in this way: If your variable have n levels, such as high, mediem, low. You need to use n-1 dummy code variables to represent. For example, use one dummy code variable to represent gender, Male-1 for male and 0 for female. For catergorized va...
by allenjia
Tue Mar 20, 2012 3:13 am
Forum: Method and application
Topic: Mean and SD of latent variables
Replies: 5
Views: 4725

However, the problem comes. I do not know how to figure it. Maybe I understand the method in a wrong way. SD and Mean of LV are always reported in publications, but it looks like that there is not many person interested in how to do that here. Please see: http://forum.smartpls.com/viewtopic.php?t=20...
by allenjia
Mon Mar 19, 2012 1:23 am
Forum: SmartPLS 2 - FAQ
Topic: unstandardized LV score
Replies: 1
Views: 2089

unstandardized LV score

I am confused with this method. For example, we have 200 lines of original data; and run 500 sample bootstrapping. Thus we have 500 SOW/Std, and thus 500 lines of relative weight for each sample. When we get the relative weight, we can get lv score by using "w1*original value of indicator 1+……&...
by allenjia
Sun Mar 18, 2012 7:03 am
Forum: SmartPLS 2 - FAQ
Topic: Calculation about unstandardized LV score, Dr. Bido's method
Replies: 2
Views: 2372

Calculation about unstandardized LV score, Dr. Bido's method

I am confused with this method. For example, we have 200 lines of original data; and run 500 sample bootstrapping. Thus we have 500 SOW/Std, and thus 500 lines of relative weight for each sample. When we get the relative weight, we can get lv score by using "w1*original value of indicator 1+……&...
by allenjia
Sun Mar 18, 2012 4:25 am
Forum: Method and application
Topic: Mean and SD of latent variables
Replies: 5
Views: 4725

about mean and std of latent variable

We always need to report the mean/std/whether squrared root of AVE are above corrleation. Thus, I searched the forum and found the following answer by Dr. Bido. Hope it helps! viewtopic.php?t=754&highlight=standard+ ... t+variable
by allenjia
Thu Apr 21, 2011 7:17 pm
Forum: Method and application
Topic: bootstrapping - cases ans samples
Replies: 1
Views: 2159

case 158= number of observations

Sample size: big enough that t value is stable. some professors recommend 5000.
by allenjia
Thu Apr 21, 2011 7:14 pm
Forum: Method and application
Topic: (urgent) Sample Size
Replies: 17
Views: 13797

above 1000, 5000 is recommended by Dr. Chingle
by allenjia
Tue Apr 19, 2011 5:13 am
Forum: SmartPLS 2 - FAQ
Topic: sign changes after running bootstrap
Replies: 4
Views: 3025

Re: sign changes after running bootstrap

The PLS algorithm tells you the coefficient of the connection between two variables, while the bootstrap tells you whether the relevant coefficient is significant. The value on the path in outcome of the bootstrapping is t-value of this path coefficient. If it is larger than 1.7, significant at alph...
by allenjia
Sun Apr 10, 2011 7:06 pm
Forum: SmartPLS 2 - FAQ
Topic: minimum sample size
Replies: 2
Views: 2523

Re: minimum sample size

Hi,

See viewtopic.php?t=813&highlight=bootstrap

They discussed about the sample size in bootstrapping.

Best,
Lin
elahe2 wrote:Hi .
Is there a formula to compute minimum sample size in pls ?

thank you very much