Chapter 14 Video 7 - Zero Inflated & Hurdle Count Regression Models in R

Поділитися
Вставка
  • Опубліковано 3 гру 2024

КОМЕНТАРІ • 7

  • @MADKan
    @MADKan 23 дні тому

    if we have panel/tscs data, and we suspect dual DGP can we still use ZIP/ZIP or we revert back to standard poisson/negative binomial?

    • @qssd
      @qssd  21 день тому +1

      The panel/TSCS data shouldn't affect whether you can use ZIP/ZINB, but I haven't explored it recently so I can't give you definitive advice on the best way to go.

  • @jessicawojcik8731
    @jessicawojcik8731 9 місяців тому

    Thank you for the very understandable video! What model should I use, if my zero inflation test tells me my model is overfitting zeros?

    • @qssd
      @qssd  9 місяців тому

      Thanks! If you are overfitting zeros using poisson regression, I would first use a negative binomial regression. If you are still overfitting zeros with NB regression, I would next use a hurdle model (probably the NB version) b/c of how it truncates the count data for only positive counts. That way you should get a better understanding of the relationship for 0 counts and positive counts.

  • @alexyankson4759
    @alexyankson4759 11 місяців тому

    What package are you using for check_zeroinflation

    • @qssd
      @qssd  11 місяців тому +1

      It's from the `performance` package