

Inequality constraints in a growth model 

Message/Author 

Jon Heron posted on Tuesday, March 09, 2010  6:02 am



Sorry, this is my second question in as many days! I'd like to fit a growth model to a repeated measure which cannot decrease  it's lifetime consumption of cigarettes. I'd like to restrict the parameters such that the trajectories are monotone increasing  I'm thinking a piecewise linear with all positive gradients. Is this possible by design, or do I just have to run the model + hope that I get what I'm after? thanks, Jon 


You may have problems with an outcome that cannot decrease. You may want to consider creating an outcome that represents the number of cigarettes smoked over a one year period. You can place constraints using MODEL CONSTRAINT. 

Jon Heron posted on Tuesday, March 09, 2010  11:20 am



Thanks Linda, I see I need to read the manual more carefully  inequalities are mentioned on P557. It seems quite common in tobacco growth modelling (a discipline I am new to) to have a measure which lacks some of the usual metric properties  e.g. a 5level ordinal variable where the first category of neversmoker can never be revisited once you've had at least one cigarette. 

Back to top 

