Actuarial Outpost Intuition behind Module Slide 149 of section 6
 Register Blogs Wiki FAQ Calendar Search Today's Posts Mark Forums Read
 FlashChat Actuarial Discussion Preliminary Exams CAS/SOA Exams Cyberchat Around the World Suggestions

 DW Simpson International Actuarial Jobs Canada  Asia  Australia  Bermuda  Latin America  Europe

#1
06-12-2019, 11:15 PM
 DSouth SOA Join Date: Jan 2016 College: UCLA Posts: 17
Intuition behind Module Slide 149 of section 6

I don't understand the intuition behind the last sentence which I've copied below:

Quote:
 One final issue relates to the variables SAGE, SEDUCATION, and AGEdiff. Values of zero here are not actually missing (though AGEdiff can be zero when the ages match), but are zero because there is no spouse. To see the consequences suppose our model includes a*MARSTAT + b*AGE + c*SAGE. If single, the prediction is b*AGE while if not it is a + b*AGE + c*SAGE. What this tells us is that if any of the three variables are used, we must also use MARSTAT as it allows for a constant to adjust the scale.
MARSTAT is an indicator for whether the person is married. AGE is the age of the primary person. SAGE is the age of the spouse, SEDUCATION is the spouse's education.

Thanks guys!
#2
06-12-2019, 11:50 PM
 Yossarian Member SOA Join Date: Jun 2011 Location: SoCal Posts: 39

Quote:
 Originally Posted by DSouth I don't understand the intuition behind the last sentence which I've copied below: MARSTAT is an indicator for whether the person is married. AGE is the age of the primary person. SAGE is the age of the spouse, SEDUCATION is the spouse's education. Thanks guys!
This is the only interpretation that made sense to me: "What this tells us is that if any of the three variables are used (SAGE, SEDUCATION, or AGEdiff), we must also include MARSTAT."

The intuition is that if you use any of the variables that relate to a characteristic of a spouse, you have to also include the marriage status.