BookmarkSubscribeRSS Feed
Matthewbsommer
Calcite | Level 5
I am looking to do a double hurdle model (Cragg). My first step will be a probit, my second step will be an OLS using a log normal dependent variable I have code for various tobits and heckit but cannot find proc qlim for a double hurdle as described above. Thank you for any suggestions.
4 REPLIES 4
SteveDenham
Jade | Level 19

Take a look at PROC FMM.  The Getting Started example shows how to put a mass at zero, which I assume is what the probit part does.  It then fits a Poisson to the remaining values.  A log-normal distribution could be selected instead.  I hope I have not misunderstood your question.

 

SteveDenham

SteveDenham
Jade | Level 19

A quick followup.  You will have to use the PROBMODEL statement to get the first hurdle to be a probit, rather than the default logit.

 

SteveDenham

Ksharp
Super User
Steve,
Long time no see. Where have you been ?
SteveDenham
Jade | Level 19
See my private msg for a long description.

SAS Innovate 2025: Call for Content

Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 25. Read more here about why you should contribute and what is in it for you!

Submit your idea!

What is ANOVA?

ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 4 replies
  • 950 views
  • 2 likes
  • 3 in conversation