Uploaded image for project: 'Public H2O 3'
  1. Public H2O 3
  2. PUBDEV-3835

Standard Errors in GLM: calculating and showing specifically when called

    Details

    • Type: Task
    • Status: Resolved
    • Priority: Major
    • Resolution: Fixed
    • Affects Version/s: None
    • Fix Version/s: 3.10.3.3
    • Component/s: None
    • Labels:
      None
    • CustomerVisible:
      No
    • AffectedContact:
      Steve Lavdas <steve.lavdas@nielsen.com>
    • AffectedCustomers:
    • Support Assessment:
      Algorithm Extension
    • Customer Request Type:
      Support Incident

      Description

      For GLM in R, when applying a model to data, you can request standard errors of the predictions like this:

      applied <- predict.glm(myModel, myNewData, se.fit = T)
      print(applied$se.fit)
      

      Sample Code Snippet:

      counts <- c(18,17,15,20,10,20,25,13,12)
      outcome <- gl(3,1,9)
      treatment <- gl(3,3)
      print(d.AD <- data.frame(treatment, outcome, counts))
      glm.D93 <- glm(counts ~ outcome + treatment, family = poisson())
      glm.D93
      applied = predict.glm(glm.D93, NULL, se.fit = T)
      print(applied$se.fit)
      

      We should add a function in H2O to calculate standard errors and show as results.

        Attachments

          Activity

            People

            • Assignee:
              tomas Tomas Nykodym
              Reporter:
              avkash Avkash Chauhan
            • Votes:
              0 Vote for this issue
              Watchers:
              3 Start watching this issue

              Dates

              • Created:
                Updated:
                Resolved:

                Zendesk Support