24. Non-Linear ARDL Model using Eviews || Dr. Dhaval Maheta

แชร์
ฝัง
  • เผยแพร่เมื่อ 9 พ.ย. 2024

ความคิดเห็น • 9

  • @zaferbeyiz5914
    @zaferbeyiz5914 2 หลายเดือนก่อน

    A great video and present. Thanks a lot Mr. Maheta.

  • @aminaahmedalibelal5676
    @aminaahmedalibelal5676 ปีที่แล้ว

    Great and informative videos. I would like to ask you a question, why you have choose CONSTANT in the TREND SPECIFICATION?

  • @國際企業系鄭喬文
    @國際企業系鄭喬文 2 ปีที่แล้ว +1

    Hello, Dr. Dhaval Maheta,
    First of all, thank you very much for sharing this video. I'm currently working on NARDL model as well; however, I am not quite sure about that in general, which table results should be presented in the discussion usually. (Conditional Error Correction Regression? Levels Equation ? ...etc.)

    • @DhavalSaifaleeAaryash
      @DhavalSaifaleeAaryash  2 ปีที่แล้ว +1

      We have to report
      1. Bounds Test
      2. Output at 20.3
      3. Graphs shown in last

    • @國際企業系鄭喬文
      @國際企業系鄭喬文 2 ปีที่แล้ว

      @@DhavalSaifaleeAaryash Dr. Macheta, thank you so much for the reply. I just have another question. Output at 20.3 is the result for the long-run effects, right? So, how about the short-run effects (from ECM)? We don't need to report it or it is not what we would be interested in?

  • @farhaatalhatash8793
    @farhaatalhatash8793 5 หลายเดือนก่อน

    Thank you very much.
    Is it theoritcally acceptable to apply the normal ARDL model first, and get the coefficients for all the regressors ( I have 4 in my study ), and then apply the NARDL for only one variable to test the asymmetry??

  • @jayagupta9239
    @jayagupta9239 8 หลายเดือนก่อน

    why value of beta 1 is positive for negative X

  • @abdullahnarejo1259
    @abdullahnarejo1259 ปีที่แล้ว +2

    sir, it says near singular matrix error

    • @michaelasare4987
      @michaelasare4987 3 หลายเดือนก่อน +3

      You need to check your data. A Singular Matrix Error in EViews usually occurs when you have a perfect multicollinearity in your dataset, meaning that one or more of your independent variables are perfectly correlated with each other