The SF36 is a questionnaire with 35 scoring categorical questions (2-6 categories) that are summed into 8 first order summary variables. These 8 variables are then normalised and added, after multiplying with a different constant each, together twice (with different constants) into two second order summary factors (Physical and Mental Health). These summary variables may not (orthogonal factor rotation) or may (oblique factor rotation) be correlated.
These factors explain a certain percentage of the variance of the original 35 categorical questions.
I presume there is a simple answer which I may know but I can't think of, how to calculate that variance. Is anybody able to help?
Thank you,
Christoph
That variance is mentioned at the table at the bottom of page 1518 of:
Mishra GD, Hockey R, Dobson AJ. A comparison of SF-36 summary measures of physical and mental health for women across the life course. Quality of Life Research. 2014;23(5):1515-21.
These factors explain a certain percentage of the variance of the original 35 categorical questions.
I presume there is a simple answer which I may know but I can't think of, how to calculate that variance. Is anybody able to help?
Thank you,
Christoph
That variance is mentioned at the table at the bottom of page 1518 of:
Mishra GD, Hockey R, Dobson AJ. A comparison of SF-36 summary measures of physical and mental health for women across the life course. Quality of Life Research. 2014;23(5):1515-21.