

Bizarre Threshold Estimates 

Message/Author 

Adam Myers posted on Saturday, May 15, 2010  11:45 pm



My threshold estimates are sometimes 15 or 15 with twotailed pvalues of 999.99. I don’t understand how to interpret thresholds. What does this mean? Also, I am getting several warning messages. Two of them suggest increasing the number of starts, but I already have increased it to 100. Another one says this: THE STANDARD ERRORS OF THE MODEL PARAMETER ESTIMATES MAY NOT BE TRUSTWORTHY FOR SOME PARAMETERS DUE TO A NONPOSITIVE DEFINITE FIRSTORDER DERIVATIVE PRODUCT MATRIX. THIS MAY BE DUE TO THE STARTING VALUES BUT MAY ALSO BE AN INDICATION OF MODEL NONIDENTIFICATION. THE CONDITION NUMBER IS 0.148D16. PROBLEM INVOLVING PARAMETER 47. Any advice with any of this issues would be much appreciated. Thanks! 


It sounds like the thresholds are being fixed to 15 and +15. This is not a problem. A threshold of 15 represents a probability of 1. A threshold of +15 represents a probability of zero. Please send the output and license number to support@statmodel.com for your other questions. 

Back to top 

