3
$\begingroup$

I need some help understanding the full-rank assumption. My book, Econometric Analysis by Greene, presents the following example:

Suppose that a cross-section model specifies that consumption, $C$, relates to income as follows: $$C = \beta_1 + \beta_2X_{non-labor\ income} + \beta_3X_{salary} + \beta_4X_{total\ income} + \epsilon$$ where $X_{total\ income}$is exactly equal to $X_{salary}$ plus $X_{non-labor\ income}$. Clearly, there is an exact linear dependency in the model. Now let $\beta_2' = \beta_2 + a, \beta_3' = \beta_3 + a$, and $\beta_4' = \beta_4 - a$, where a is any number. Then the exact same value appears on the right-hand side of $C$ if we substitute $\beta_2', \beta_3', \beta_4'$ for $\beta_2, \beta_3$, and $\beta_4$. Obviously, there is no way to estimate the parameters of this model.

What I do not understand of the above explanation are the second-to-last and last sentences. What do they mean? What are they trying to convey??

$\endgroup$
  • 1
    $\begingroup$ I only really got linear regression when I learned the linear algebra behind it. Basically, when the columns of your matrix X aren't independent, then the matrix $$X^{T}* X$$can't be inverted. In other words, you put that matrix formula in your calculator and you get an error--not even a bad answer, you get no answer. $\endgroup$ – Steve S Sep 30 '15 at 6:00
  • $\begingroup$ your new $\beta' s$ are only old $\beta s$ plus a constant $a$ what are that for? It is not even a random coefficient regression. $\endgroup$ – Deep North Sep 30 '15 at 6:06
  • $\begingroup$ Hey, I just tried to clean up the LaTeX a little--hopefully it will be a little clearer with the names written as subscripts... $\endgroup$ – Steve S Sep 30 '15 at 6:38
  • 1
    $\begingroup$ Important: The problem has $\beta_4 - a$! (and not $\beta_4 + a$)--does that clear things up?? $\endgroup$ – Steve S Sep 30 '15 at 6:56
  • $\begingroup$ To see what the author is getting at, try substituting in $(\beta' - a)$ for each $\beta$-value (and $\beta' + a$ for $\beta_{total\ income}$). Then, replace the term $a*X_{total\ income}$ with $a*(X_{non-labor\ income} + X_{salary})$ and notice how when you simplify the equation all the "a" terms cancel out. $\endgroup$ – Steve S Sep 30 '15 at 6:56
3
$\begingroup$

There is an error. It should be $\beta_4'=\beta_4-a$. If we substitute these new $\beta$s into the regression equation we get:

\begin{align} C &= \beta_1 + \beta_2'X_{non-labor-income}+\beta_3'X_{non-labor-income}+\beta_4'X_{total-income}+\varepsilon \\ & = \beta_1 + (\beta_2 +a)X_{non-labor-income}+(\beta_3+a)X_{salary}+(\beta_4-a)X_{total-income}+\varepsilon\\ & = \beta_1 + \beta_2X_{non-labor-income}+\beta_3X_{salary}+\beta_4X_{total- income}+\varepsilon \\ & + a(X_{non-labor-income}+X_{salary}-X_{total-income}) \end{align}

and the last term is zero. So we substituted new coefficients, but the regression did not change, which means that there are multitude of coefficient values which give the same results, whereas the main regression assumption is that the coefficients are uniquely defined.

$\endgroup$

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.