Endogeneity with an exponential regression function: Difference between revisions
Content deleted Content added
m Dating maintenance tags: {{Merge to}} |
Merged content to Instrumental variables estimation#Endogeneity with an exponential regression function, redirecting (easy-merge) Tag: New redirect |
||
| Line 1: | Line 1: | ||
#REDIRECT [[Instrumental variables estimation#Endogeneity with an exponential regression function]] |
|||
{{notability|date=January 2018}} |
|||
In statistics as applied to [[econometrics]], exponential regression models constitute a very large and popular class of [[Regression analysis|regression]] models. Standard [[econometric]] concerns such as [[Endogeneity (econometrics)|endogeneity]] or [[Omitted-variable bias|omitted variables]] can be accounted for in a more general framework. Wooldridge and Terza provide a methodology to both deal with and test for endogeneity within the exponential regression framework, which the following discussion follows closely.<ref>Wooldridge 1997; Terza 1998</ref> While the example focuses on a [[Poisson regression]] model, it is possible to generalize the test to other exponential regression models, although this may come at the cost of additional assumptions (e.g. for binary response or censored data models). |
|||
{{R from merge}} |
|||
Assume the following exponential regression model, where <math>a_i</math> is an unobserved term in the latent variable. We allow for correlation between <math>a_i</math> and <math>x_i</math> (implying <math>x_i</math> is possibly endogenous), but allow for no such correlation between <math>a_i</math> and <math>z_i</math>. |
|||
{{R to section}} |
|||
: <math>\operatorname E[y_i \nu x_i, z_i, a_i] = \exp(x_i b_0 + z_i c_0+a_i) </math> (1) |
|||
The variables <math>z_i</math> serve as [[instrumental variable]]s for the potentially endogenous <math>x_i</math>. One can assume a linear relationship between these two variables or alternatively project the endogenous variable <math>x_i</math> onto the instruments to get the following reduced form equation: |
|||
: <math>x_i=z_i\Pi+v_i</math> (2) |
|||
The usual rank condition is needed to ensure identification. The endogeneity is then modeled in the following way, where <math>\rho</math> determines the severity of endogeneity and <math>v_i</math> is assumed to be independent of <math>e_i</math>. |
|||
: <math>a_i=v_i \rho+e_i</math> (3) |
|||
Imposing these assumptions, assuming the models are correctly specified, and normalizing <math>\operatorname E[\exp(e_i)]=1,</math>, we can rewrite the conditional mean as follows: |
|||
: <math> \operatorname E[y_i v x_i, z_i , a_i] = \exp (x_i b_0 + z_i c_0 +e_i\rho)</math> (4) |
|||
If <math>e_i</math> were known at this point, it would be possible to estimate the relevant parameters by [[quasi-maximum likelihood estimation]]. Following the two step procedure strategies, Wooldridge and Terza propose estimating equation [2] by standard [[Ordinary least squares|OLS methods]]. The fitted residuals from this regression can then be plugged into the estimating equation [4] and QMLE methods will lead to consistent estimators of the parameters of interest. Significance tests on <math>\hat\rho</math> can then be used to test for endogeneity within the model. |
|||
The methodology proposed here is often used for exponential regression functions. However, the specific assumptions that need to be made can differ across models. Binary response models impose distributional assumptions on ''y''<sub>''i''</sub> and ''x''<sub>''i''</sub>, whereas this model imposed independence between <math>v_i</math> and <math>e_i</math>. |
|||
== See also == |
|||
* [[Binary response model with continuous endogenous explanatory variables]] |
|||
* [[Endogeneity in multinomial response model]] |
|||
== References == |
|||
{{Reflist}} |
|||
== Bibliography == |
|||
* Wooldridge, J. (1997): Quasi-Likelihood Methods for Count Data, Handbook of Applied Econometrics, Volume 2, ed. M. H. Pesaran and P. Schmidt, Oxford, Blackwell, pp. 352–406 |
|||
* Terza, J. V. (1998): "Estimating Count Models with Endogenous Switching: Sample Selection and Endogenous Treatment Effects." ''Journal of Econometrics'' (84), pp. 129–154 |
|||
* Wooldridge, J. (2002): "Econometric Analysis of Cross Section and Panel Data", ''MIT Press'', Cambridge, Massachusetts. |
|||
[[Category:Poisson distribution]] |
[[Category:Poisson distribution]] |
||
Revision as of 07:05, 6 July 2020
- From a merge: This is a redirect from a page that was merged into another page. This redirect was kept in order to preserve the edit history of this page after its content was merged into the content of the target page. Please do not remove the tag that generates this text (unless the need to recreate content on this page has been demonstrated) or delete this page.
- For redirects with substantive page histories that did not result from page merges use {{R with history}} instead.
- To a section: This is a redirect from a topic that does not have its own page to a section of a page on the subject. For redirects to embedded anchors on a page, use {{R to anchor}} instead.