When I include total activity time (The sum of all activity variables e.g. sedentary behaviour, light intensity, moderate intensity) SPSS removes it from the model as it is a constant. Has anyone got around this problem?
Physical Activity
Sedentary Behaviour
Accelerometry
If you mean that you are including a bunch of activity variables in your model and the sum of those same variables, you are creating a situation where there is complete linear dependence (or perfect collinearity, as the blog linked below calls it). That is, the total score is a linear combination of the components--and SPSS (or any other stats package) will have to kick one of the variables out.
Given that you have activity time broken down into different types, I suspect the solution that will work best for you is to omit the total activity time variable.
http://psychologicalstatistics.blogspot.ca/2013/11/multicollinearity-and-collinearity-in.html
Please refer to:
1. Landau, S. and Everitt, B. S.(2004). A Handbook of Statistical analyses using SPSS.
2.Howitt, D. and Cramer, D.(2008). Introduction to SPSS.
Regards,
Zuhair
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS