Multigroup Analysis (PLS-MGA) using Smart-PLS

แชร์
ฝัง
  • เผยแพร่เมื่อ 2 ธ.ค. 2024

ความคิดเห็น • 47

  • @AyaKasber
    @AyaKasber 2 หลายเดือนก่อน

    Thank you for sharing this.. can you please tell me when and how do we need to comment on confidence intervals? And what if the p value for the difference is significant but the confidence interval is ranging from a negative sign to a positive sign in a symmetrical way i.e., -2.9 to 2.8

    • @researchwithfawad
      @researchwithfawad  2 หลายเดือนก่อน

      When there is a 0 in between the LL and UL, this means that the hypothesis is insignificant.

  • @mariap.4791
    @mariap.4791 3 ปีที่แล้ว +1

    Thank you so much for the explanation!

  • @TheZuhairabbas
    @TheZuhairabbas 4 ปีที่แล้ว +2

    This is very informative video

  • @jonpark3857
    @jonpark3857 ปีที่แล้ว

    Thank you very much for the video, professor! Can I use the same procedures from your video to perform a multigroup analysis for four groups? I have four groups with a 2 (short vs. long) x 2 (yes vs. no) experimental design, and I'd like to compare them: group 1 (short, yes), group 2 (short, no), group 3 (long, yes), and group 4 (long, no).
    I've read a smartPLS book that mentions the "Omnibus test of group differences (OTG) approach" for comparing more than two groups. However, your video covered a three-group comparison using multigroup analysis, which has left me slightly confused. Is it possible to perform a four-group comparison (PLS-MGA) using smartPLS 4?
    Your video has been incredibly helpful, and I would greatly appreciate your response to this question.

  • @m.sswetha3165
    @m.sswetha3165 3 ปีที่แล้ว +1

    Awesome teaching sir

  • @jasg9234
    @jasg9234 3 หลายเดือนก่อน

    Hello, would one need to do a bonferroni correction for the analysis performed in the video?

    • @researchwithfawad
      @researchwithfawad  3 หลายเดือนก่อน

      Yes, if there are multiple comparisons.

    • @jasg9234
      @jasg9234 3 หลายเดือนก่อน

      @@researchwithfawad So for one analysis with four groups that counts as multiple comparisons and the program doesn’t automatically correct for it?

  • @AdamNurkholik
    @AdamNurkholik ปีที่แล้ว

    Hi Sir, do you have tutorial PLS-MGA using R Studio? Thank you.

    • @researchwithfawad
      @researchwithfawad  ปีที่แล้ว

      Thanks for your interest. Please watch
      th-cam.com/video/QM2KCKifpwM/w-d-xo.html

  • @FatmaAhmedRagab
    @FatmaAhmedRagab 2 ปีที่แล้ว

    Sir I searched for a video in your channel for reporting multligroup analysis, but I can't find one. Could please add a video like you did in smartpls4 playlist how to report the results in the thesis. My best regards.

    • @researchwithfawad
      @researchwithfawad  2 ปีที่แล้ว +1

      I am yet to do a video on MGA using SmartPLS4

  • @Alhamzah_F_Abbas
    @Alhamzah_F_Abbas 2 ปีที่แล้ว +1

    thank you, sir, for this great video, to run PLS-MGA does it necessary to do a permutation test as well?

    • @researchwithfawad
      @researchwithfawad  2 ปีที่แล้ว +1

      For details, please refer to this paper
      Multigroup Analysis using SmartPLS: Step-by-Step Guidelines for Business
      Research

    • @Alhamzah_F_Abbas
      @Alhamzah_F_Abbas 2 ปีที่แล้ว

      @@researchwithfawad thank you very much

    • @Alhamzah_F_Abbas
      @Alhamzah_F_Abbas 2 ปีที่แล้ว

      Dear sir and brother, I already checked the paper you suggested to me, I'm relay appreciated I learned a lot. I run the MAG according to the paper steps. however, the final results show there is no significant difference between groups (gender, age) in each relationship in my model, are these results will make an issue for me in my thesis?. I will be very grateful for your reply.

    • @researchwithfawad
      @researchwithfawad  2 ปีที่แล้ว +1

      Results may be significant or insignificant. You need to check is it absolutely necessary to check for group differences. If you were expecting group differences, why were they insignificant, this shall be explained in discussion section.

    • @Alhamzah_F_Abbas
      @Alhamzah_F_Abbas 2 ปีที่แล้ว +1

      @@researchwithfawad Dear Sir, regarding MGA results, if there is no significant difference between groups, does this mean they don't have a moderation effect on the relationship between 2 variables??. I will be very grateful for your reply.

  • @iqbalkarim7107
    @iqbalkarim7107 3 ปีที่แล้ว

    I have three groups complainant, bankers and lawyers. However due to 113 sample size and as low as 11 sample for lawyer group (a specific observer).
    Once I try to run bootstrapping, it shows error minimum case should be 13. It doesn't run at 10 case.
    And for path algorithm (it doesn't show one of the group).
    So how to solve these issue?
    Thanks

    • @researchwithfawad
      @researchwithfawad  3 ปีที่แล้ว

      The groups have unequal sample size. When creating grouo did you change the minimum cases in group. With such disparity in group sizes, your results will not be adequate.

  • @basicstu3300
    @basicstu3300 9 หลายเดือนก่อน

    Hello sir I have a question, if my model have several independent variables and several mediators, can I still use pls-mga to see the difference between two groups?

  • @phoebesia9107
    @phoebesia9107 3 ปีที่แล้ว +1

    Sir, why i got significant effect on overall result but all subgroup (I've three) are not significant? Even i try to increase sample size to larger or use similar sample size of each subgroup also getting the same result.

    • @researchwithfawad
      @researchwithfawad  3 ปีที่แล้ว +1

      The sum of effect is greater than the individual effects. For instance, you are pushing a car, the car may remain still or may move a little, what if 3-4 people push it, then it will move faster.

    • @사브리나-u5u
      @사브리나-u5u 3 ปีที่แล้ว

      @@researchwithfawad How can you explain this in a mathematical formula or in PLS? I didn't get your example? I have same issue.

  • @daydreamingyou
    @daydreamingyou 2 ปีที่แล้ว

    when I tried to run MGA, I got singular matrix problem, can someone please help me.. I have 400 data, so I think it's enough and don't have to add more, I'm want to try run correlation matrix to solve the problem but idk how to do it

    • @researchwithfawad
      @researchwithfawad  2 ปีที่แล้ว

      Singular matrix issues is when you have added indicators that have similar values. If you have controls in your model, make sure you are not adding add dummy variables, instead you are leaving out a category as reference.

  • @omerashahnawaz6933
    @omerashahnawaz6933 3 ปีที่แล้ว

    Thank you Sir for making this video. Do we need to perform the test for measurement invariance before?

  • @m.sswetha3165
    @m.sswetha3165 3 ปีที่แล้ว

    Is moderation effect and Multi group Analysis gives same kind of results
    In case am using a categorical variables gender as moderator through dummy variables am doing it... When I consider the same gender as my group and get the results for both separately...does it have any difference or does it gives me the same effect

    • @researchwithfawad
      @researchwithfawad  3 ปีที่แล้ว +2

      If the categorical moderator is affecting all the relationships then use Multigroup analysis otherwise is the gender is moderating any specific relationship, use normal moderation analysis

    • @m.sswetha3165
      @m.sswetha3165 3 ปีที่แล้ว

      @@researchwithfawad okay sir thank you so much sir

    • @omerashahnawaz6933
      @omerashahnawaz6933 3 ปีที่แล้ว

      @@researchwithfawad thank you so much Sir. I had the same query

  • @muhammadnaeem7869
    @muhammadnaeem7869 4 ปีที่แล้ว

    Sir,
    how can we enter the data in spss for different countries in order to differentiate the data for these countries?
    While generating these groups why it can't be automatically generated by smartpls?

    • @researchwithfawad
      @researchwithfawad  4 ปีที่แล้ว

      AoA. You can create a variable country, in your SPSS dataset. This will work as an identifier for a particular row, and let you knowbt which country does the row belongs.
      I did not quite understand the second part of the question

  • @dr.sabahyounus60
    @dr.sabahyounus60 4 ปีที่แล้ว +1

    Hello can you help me with my model

  • @m.sswetha3165
    @m.sswetha3165 3 ปีที่แล้ว

    Respected sir
    how to report the results of PLS-MGA

    • @researchwithfawad
      @researchwithfawad  3 ปีที่แล้ว

      I can send you a paper. Email me on kh.fawad83@gmail.com

    • @m.sswetha3165
      @m.sswetha3165 3 ปีที่แล้ว

      @@researchwithfawad okay sir , I have mailed you sir

    • @사브리나-u5u
      @사브리나-u5u 3 ปีที่แล้ว

      I am intereted too. Just share the title. We can look for it. Thx