Search found 990 matches

by jmbecker
Thu Jun 06, 2019 8:23 am
Forum: FAQ (Methodology)
Topic: Gender control variable: case unequal group sizes
Replies: 2
Views: 59

Re: Gender control variable: case unequal group sizes

Having a significant control you know that male and female respond differently on your DV. Statistically, there is no problem in having more male or female respondents (i.e., unequal group sizes on the control). Conceptually, however, I would find it problematic that you samples so much more of the ...
by jmbecker
Thu Jun 06, 2019 8:17 am
Forum: FAQ (Methodology)
Topic: Converting a continuous moderator to categorical
Replies: 2
Views: 47

Re: Converting a continuous moderator to categorical

There is an interesting special issue in the Journal of Consumer Psychology (https://www.sciencedirect.com/science/a ... 0815000807) that deals with this issue. It is nothing particularly specific to PLS, but more a general question when it is ok and when not.
by jmbecker
Thu Jun 06, 2019 8:14 am
Forum: FAQ (Methodology)
Topic: Getting N/A error while doing a consistent PLS Algorithm
Replies: 8
Views: 2184

Re: Getting N/A error while doing a consistent PLS Algorithm

In such a model it is more likely the case that you have a severe multicollinearity problem or some other data issues that cause the problem.
by jmbecker
Thu Jun 06, 2019 8:12 am
Forum: Application of PLS
Topic: FIMIX - Assessment of heterogenity level
Replies: 2
Views: 68

Re: FIMIX - Assessment of heterogenity level

Dear Holger, 1) In my opinion, excluding control variables in the MGA is generally a not a good idea. You want to estimate the same model as initially proposed including all controls if they are deemed important. The only exception is the grouping variable itself. If, for example, gender is a contro...
by jmbecker
Mon May 20, 2019 8:05 pm
Forum: SmartPLS Small Talk Corner
Topic: Second order construct
Replies: 5
Views: 142

Re: Second order construct

In such a case you do not want to use second-order constructs. You want to look into the moderation topic. There you create interaction effects, that sound more like what you want to study.
by jmbecker
Mon May 20, 2019 8:04 pm
Forum: FAQ (Methodology)
Topic: Interaction effect significant, both main effects not
Replies: 8
Views: 1092

Re: Interaction effect significant, both main effects not

Usually the literature suggests that when the interaction effect is not significant, you should not interpret the simple effects, but only the main effects. Likewise, if the interaction is significant you should not interpret the main effects, but only the simple effects. However, sometimes it may a...
by jmbecker
Mon May 20, 2019 3:13 pm
Forum: Application of PLS
Topic: Path coefficient over 1 in standardized data
Replies: 1
Views: 43

Re: Path coefficient over 1 in standardized data

Please use the search function. You may find for example the following discussion that may answer your question:
viewtopic.php?f=12&t=19004&p=30439
by jmbecker
Mon May 20, 2019 3:09 pm
Forum: Application of PLS
Topic: Missing values (dummy variables / categorial variables)
Replies: 2
Views: 75

Re: Missing values (dummy variables / categorial variables)

Using mean replacement does not make sense for categorical variables that are dummy coded. You may use pairwise or casewise deletion.
by jmbecker
Wed May 15, 2019 1:30 pm
Forum: FAQ (Methodology)
Topic: HTMT discriminant validity
Replies: 19
Views: 5742

Re: HTMT discriminant validity

Interpretation is that constructs are not correlated, so the cross correlations between indicators of the different constructs are small (zero).
by jmbecker
Wed May 15, 2019 1:29 pm
Forum: FAQ (Methodology)
Topic: Calculating T-Value for indirect effects: a*b/sd(ai*bi) ?
Replies: 18
Views: 8930

Re: Calculating T-Value for indirect effects: a*b/sd(ai*bi) ?

That sounds like a typical example of competetive mediation: https://www.smartpls.com/documentation/algorithms-and-techniques/mediation There could be many reasons for such an effect. Most of them a subject specific theoretical reasons. So you need to consider based on your domain knowledge whether ...
by jmbecker
Wed May 15, 2019 1:20 pm
Forum: SmartPLS Small Talk Corner
Topic: Second order construct
Replies: 5
Views: 142

Re: Second order construct

What do you mean by synergistic effects?
by jmbecker
Wed May 15, 2019 1:19 pm
Forum: Requested Features
Topic: Basic statistics for data groups
Replies: 2
Views: 100

Re: Basic statistics for data groups

Thank you for your suggestions. We will consider that for future versions.
by jmbecker
Mon Apr 29, 2019 1:44 pm
Forum: Application of PLS
Topic: Correlations & Significance + moderating effect for different scenario's
Replies: 1
Views: 58

Re: Correlations & Significance + moderating effect for different scenario's

If you have a dummy coded (0/1) variable the regression effect of this variable is usually the mean difference in the dependent variable between the two groups conditional on all other variables in the regression. For example, you have a positive 0.3 effect that mean that your DV is 0.3 larger for t...
by jmbecker
Mon Apr 29, 2019 8:30 am
Forum: Application of PLS
Topic: the moderation of the moderation
Replies: 2
Views: 615

Re: the moderation of the moderation

Yes, that is the right way of doing it in SmartPLS
by jmbecker
Mon Apr 29, 2019 8:29 am
Forum: Application of PLS
Topic: MGA for groups within a group
Replies: 1
Views: 50

Re: MGA for groups within a group

1) You may define any type of groups in the create Add Data Group dialog. You can for example specify that a variable needs to be above a certain value AND another variable needs to be equal to your country variable number. 2) PLS-MGA does not account for nested group structures. It assumes that gro...