Use the data BWGHT.raw in datasets https://faculty.utrgv.edu/diego.escobari/teaching/Datasets.html (datasets from the textbook “Introductory Econometrics” by Jeffrey Wooldridge (various editions). The files .txt have the description of the variables contained in each of the datasets. The corresponding MS Excel files are the ones that contain the datasets).
Consider the following model to estimate the effects of several variables, including cigarette smoking, on the weight of newborns:
log(bwght) = ß0 + ß1male+ ß2parity + ß3log(faminc) + ß4packs+ u
where male is a binary indicator equal to one if the child is male; parityis the birth order of this child; faminc is family income; and packsis the average number of packs of cigarettes smoked per day during pregnancy.
(i) Why might you expect packs to be endogenous?
There may be observed health factors uncorrelated with smoking behavior that affect infant birth weight.
There may be unobserved health factors correlated with smoking behavior that affect infant birth weight.
There may be observed health factors correlated with smoking behavior that affect infant birth weight.
There may be unobserved health factors uncorrelated with smoking behavior that affect infant birth weight.
(ii) Use the data in BWGHT.dta to estimate the structural equation. First, use OLS. Then, use 2SLS, where cigpriceis an instrument for packs.
(a) The difference between OLS and 2SLS in the estimated effect of packson bwghtis huge. ANSWER: _________ (TRUE or FALSE)
(b) With the OLS estimate, one more pack of cigarettes is estimated to reduce bwghtby about _______ % and _________ (IS or IS NOT) statistically significant.
(c) The 2SLS has the ____________ (SAME or OPPOSITE) sign, is ________ (HUGE or SMALL) in magnitude, and _________ (IS or IS NOT) statistically significant.
(iii) Estimate the reduced form for packs. The reduced form estimates show that cigpricedoes not significantly affect packs is _________ (TRUE or FALSE)
(iv) What do you conclude about identification of the structural equation using cigpriceas an instrument for packs?
Variable cigprice fails as an IV for packs because cigprice is partially correlated with packs.
Variable cigprice does not fail as an IV for packs because cigprice is partially correlated with packs.
Variable cigprice fails as an IV for packs because cigprice is not partially correlated with packs.
Variable cigprice does not fail as an IV for packs because cigprice is not partially correlated with packs.
