Announcement

Collapse
No announcement yet.
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • R^2 for Generalized Gamma AFT regression

    Hello Stata Fam,
    I want to compare parametric survival models using r2. I have calculated r2 for Exponential, Weibull, Loglogistic and Lognormal using
    Code:
    str2d:
    but i got error message when i tried for ggamma
    Code:
    unknown distribution: ggamma
    . Is there any way I can get around this please? Also, what are other methods I can use to compare the models in order to know the best model for my data?

    Thanks

  • #2
    R2 is more a measure for linear regression. AIC and BIC are measures that apply more generally. To compute those, see help estimates stats
    ---------------------------------
    Maarten L. Buis
    University of Konstanz
    Department of history and sociology
    box 40
    78457 Konstanz
    Germany
    http://www.maartenbuis.nl
    ---------------------------------

    Comment


    • #3
      Thank you Sir Maarten Buis. Please, are there other performance measures I can use apart from AIC and BIC? I want to use more than one performance measure.

      Thanks

      Comment

      Working...
      X