Thread: Dummy variable question in regression

1. Dummy variable question in regression

Hello,

I'm trying to understand dummy variables in regression. I'm regressing the price of diamonds against (1) weight (2) Clarity and (3) Colour. Clarity and colour and dummy variables and I created these in Minitab. This is the equation.

Price = 1.65 Weight + 3.99 Clarity_A + 3.86 Clarity_B + 0.210 Colour_A
+ 0.157 Colour_B

Is the Price for a weight = 2, Clarity A and Colour B the following?

Price = 1.65(2) + 3.99(1) + 3.86(0) + .210(0) + .157(1)
Price = 5.797

Thank you

2. Re: Dummy variable question in regression

Yes it is correct, but only if:

- clarity and colour both have only 2 options (A and B)

What I mean is, if for instance clarity and colour be A, B and C, then you need to include a constant in your model. But given your information, it is correct.

(Ofcourse, only if all assumptions of OLS are satisfied)

3. Re: Dummy variable question in regression

Either color or clarity (or both) has to have more than two levels, else the design matrix would have linear dependence (even w/o an intercept).

 Tweet

Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts