Economics Term Paper

http://onlinelibrary.wiley.com/doi/10.1002/jae.2327/abstract. For this project, I would like you to carefullyassess whether the data seems to suggest that the program helped or did not help withkeeping poor Mexican children in school longer, using the techniques that I taught inclass.

2. Wages in MalaysiaMarcia Schafgans amalyzed Malaysian wage data in an article titled ”Ethnic WageDifferences in Malaysia: Parametric and Semiparametric Estimation of the Chinese-Malay Wage Gap”. This article appeared inJournal of Applied Econometrics. At theinternet location

http://qed.econ.queensu.ca/jae/1998-v13.5/schafgans/

you will find a description a datafile and a zipped data file. This data set containswages and characteristics of 8748 people living in Malaysia of different ethnicity (Malay,Indian, and Chinese). We are interested in analyzing wage discrimination in Malaysia,and casual conversations with Malaysian grad students suggest the potential presenceof such discrimination. Examine the end of the datafile carefully - it looked to me asthough there was an obsolete number at the end of this datafile.For this project, regress the “LWAGE” variable on regressors and try to draw conclu-

sions about ethnicity based wage differences in Malaysia.

There is a substantial literature in Labor Economics about the estimation of wageequations, and for this project it should not be too difficult to write a decent overviewof the literature.

3. Do recessions exist in the data?

Do recessions exist in the data, and if they do, in what sense? Let’s translate this ques-tion to a simpler one: are we simply observing some essentially random shocks down-wards for the GDP growth rate, at which time we say “we are in a recession”; or does theGDP growth rate move to a lower plateau during a recession? Assuming that we adoptthe second interpretation, is there any empirical justification for defining a recession asnegative economic growth for two consecutive quarters? To investigate this, down-load

http://www.econ.ohio-state.edu/dejong/files/US_GDPPC.gdt.

This dataset contains US GDP per capita from the first quarter of 1947 to the third quarterof 2017 and was downloaded from the St. Louis Fed. We want to estimate the modelyt=φ1yt−1+αI(yt−1< c,yt−2< c) +εtas a starting point, forc= 0. HereI(yt−1< c,yt−2< c) is a variable that equals 1 ifyt−1< candyt−2< cand 0 otherwise. In Gretl, you add the growth rate for GDP tothe data set by clicking “log differences of selected variables”. The “recession” indicatoryou can create by going to “Add-Define new variable” and noting that something like“(X<0)” in Gretl generates a dummy variable that equals 1 if the Gretl variable Xis negative and 0 otherwise. To reference the lag of a variable in a Gretl formula,simply use “X(-1)”. For this project, look up how recessions are defined and explainhow the above model relates to the various definitions. Run a number of regressionswith the above recession indicator, see if we get significance, and explain what wecan conclude from this. The above specification can of course be extended; try variousalternative specifications anmd see what happens. In addition, you may want to changethe value ofcfrom 0 to something larger, or try include an “economic boom” indicatorvariableI(yt−1> b,yt−2> b) that equals 1 if we experienced two consecutive quartersof economic rowth above levelb(which we want to choose as something around 0.02;but feel free to vary this number or pick one yourself).