[Limdep Nlogit List] Dependent Variable Blanks - Double Hurdle Model?

Christopher McIntosh cmcintos at d.umn.edu
Wed Sep 5 05:07:45 EST 2007

Hello All,

I have CVM survey data and have a problem. Many of the returned surveys 
list a blank for the value of the dependent variable (willingness to 
pay). Other WTP values include zero and positive numbers.

I was informed it is not correct to skip the blanks and they cannot be 
considered zeros so they should be thought of as protest bidders.

Is a double hurdle model appropriate in this case?

I greatly appreciate any modeling advice and how it might be 
implemented in LimDep.



Christopher McIntosh
Assistant Professor
Department of Economics
SBE 165, Room 171
Duluth, MN, 55812
cmcintos at d.umn.edu

More information about the Limdep mailing list