I need to get probability of car failed at inspection at various age. have run model with intercept given by spss. I was informed that we could set the intercept to zero.
What is your intention of forcing the intercept to be zero? If you are not intending to get a higher adjusted RSQ then, use standardized scores instead of raw data and the intercept will be zero for sure.
When all else fails, read the fine manual (i.e., the Command Syntax Reference Manual). Specifically, look up the ORIGIN and NOORIGIN sub-commands for the LOGISTIC REGRESSION command.
* Example with intercept included.
LOGISTIC REGRESSION
VARIABLES=PASS WITH GPA,GRE,MAT
/ORIGIN.
* Example with intercept excluded.
LOGISTIC REGRESSION
VARIABLES=PASS WITH GPA,GRE,MAT
/NOORIGIN.
The default is to include the intercept, which is what happens if neither of these sub-commands is included.
Finally, there appears to be no way to request the NOORIGIN sub-command via the GUI. This demonstrates one of the reasons why it is essential to learn to use command syntax, if you want to get the most out of SPSS. (See the link below for more on that topic!)
http://spsstools.net/en/syntax/
When running logistic regression, the constant corresponds to the mean prevalence of the studied condition after removing influence from all the other variables entered into the model. Why on earth would you need to bring it down to zero?
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS