eviews 7: creating age category dummies

[totallyheart]

Hi,

I'd be really grateful if someone could help me...

I need to create 7 age category dummies for my regression.

My age categories will be:
< 20 (which i will use as my reference group so dont need a dummy)
21-30
31-40
41-50
51-60
61-70
71-80
> 80

Im using eviews 7 and have tried the following to create my first category dummy:
series dum_1
smpl @ all
dum_1 = 0
smpl 21 30
dum_1 = 1

which didnt work :(

please can someone help?

thank you!

[EViews Gareth]

Do you currently have a variable that contains age information?

[EViews Glenn]

To expand on Gareth's comments, the smpl statements you employed were using the order of observations in the workfile to define the dummies not the ages.

Assuming that you have an age variable. If all you want to do is use the dummies in an equation, you can do this in two steps:

1. use the Proc/Generate by Classification series proc and the age variable with your specified limit values to create an index variable (0, 1, 2... ) with the age categories (series proc name classify).

2. use the @expand function on your newly created index variable to create dummies on the fly for use in the equation.

Check the documentation for Classification, from series for a discussion of the classification proc.

[totallyheart]

Hi

thanks for getting back to me so soon.

Im sorry to be a pain, but as im a beginner to eviews i didnt quite understand the steps to creating these dummies.

If you could go over it in layman terms it would be great! :) ...

[EViews Gareth]

Do you currently have a variable that contains age information?

[totallyheart]

yes, i do

[startz]

Try

Code: Select all

series dum_1 smpl @all dum_1 = 0 smpl if age>=21 or age<=30 dum_1 = 1

[EViews Glenn]

I assume you mean "age < 21" for your first category.

The code

Code: Select all

age.classify(method=limits) 21 31 41 51 61 71 81 @ agecat

should create your age category variable AGECAT.

Then in your regression specification, you can do

Code: Select all

equation eq1.ls y c @expand(agecat, @dropfirst)

which will create the dummies in the regression, dropping the first category.