Lab: EViews Exercises

1. Consider the subsample of recent college graduates (within 10 years, assuming an individual graduates from undergrad at age 22) who live in Southern California.

a. Record the number of observations in the subsample.
b. For wages, record the mean, standard deviation, skew and kurtosis.
c. Create standardizations (z-scores) of the variables: hours. Display the resulting "histograms and statistics" (from Eviews) next to those for the unstandardized versions.

2. Construct binary (indicator) variables for people who are Caucasian and for people who have at least a bachelor's degree, and then use N-way tabulation.

a. White people (Pr[A])
b. Persons with at least a bachelor's(Pr[B])
c. Persons who are white and have at least a bachelor's (Pr[A & B])
d. Persons who are non-white and have at least a bachelor's (Pr[not A & B])
e. Persons who are white or who have at least a bachelor's (Pr[A or B])
f. The proportion of white peopleamong the persons who have at least a bachelor's (Pr[A | B])
g. The proportion of non-white people who have at least a bachelor's (Pr[not B | not A])

3. Clear your subsample. Restrict your sample to people working at least 40 hours per week (no other constraints). Construct and compare the "histogram and statistics" of wages of White people, Black people, Asian people, and American Indian/Alaskan Native people. Display the four histograms next to each other.

4. The standard distance between two data sets ?? and ?? is defined as: |x‾ - y‾| / √[(n_x - 1) s_x2 / {(n_x - 1) + (n_y - 1)} + (n_y - 1) s_y2 / {(n_x - 1) + (n_y - 1)} (Notice that the denominator is the square root of a weighted average of the two variances.) Use any combination of any variables (except wages) in the entire data set to create a subsample that is (i) most similar to you personally (or perhaps as you predict yourself to be in a couple years), but that (ii) contains at least 8 observations (i.e. n ≥ 8). (There will be many correct choices; just be specific about what your subsample is.) Do this a second time, but with a different group that also meets conditions (i) and (ii). Calculate the standard distance between these two groups, and between each of them and the BRG. (You will probably need to do this by hand; I do not know of any Eviews function that computes this distance directly, although it is embedded in more complex statistical operations.)