I have the following demand equation system (expenditure ratio model):

$w_{clothes}= \beta _ {clothes} + \alpha_{clothes} * \ kids + (\gamma _{0.clothes} + \gamma _{1.clothes} * \ kids)* \ income + u_{clothes}$

$w_{food}= \beta _ {food} + \alpha_{food} * \ kids + (\gamma _{0.food} + \gamma _{1.food} * \ kids)* \ income + u_{food}$


$w_{other}= \beta _ {other} + \alpha_{other} * \ kids + (\gamma _{0.other} + \gamma _{1.other} * \ kids)* \ income + u_{other}$

where $\beta_i$ and $u_i$ denotes the constants and the residuals, kids is a dummy variable (1, if the consumer has got kids), and $w_{"product"}$ is the proportion of "product" consumption of the total expenditure.

My question is, how can I interpret the term, for example, $(\gamma _{0.clothes} + \gamma _{1.clothes} * \ kids)$? Is this a dummy variable, or interaction or other? It looks like an other regression's coefficients in this equation. I have no idea, please help.

Thank you for your time and help.


If you multiply out any one of the equations,

$$w_{clothes}= \beta _ {clothes} + \alpha_{clothes} \cdot \ kids + (\gamma _{0.clothes} + \gamma _{1.clothes} \cdot \ kids)\cdot\ income + u_{clothes}$$

$$=\beta _ {clothes} + \alpha_{clothes} \cdot \ kids + \gamma _{0.clothes}\cdot income + \gamma _{1.clothes} \cdot \ kids\cdot\ income + u_{clothes}$$

it is evident that you have "kids" and "income" as regressors, plus an interaction term

  • $\begingroup$ @ÜbelYildmar We all get to ask those. $\endgroup$ – Alecos Papadopoulos Jan 1 '16 at 21:16

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.