INFSCI 2725: Data Analytics

Assignment 2: Fundamental concepts from statistics

The assignment should be possible to do using any
statistical package or Microsoft Excel.

File retention.txt (attached) contains the data
that we looked at in class (there are 170 data points in the
file).  The first line contains the names of the eight variables
(described below).  Please, look at it carefully using a
statistical package of your choice.  Write down any interesting
observations.  Are the data normal and are the interactions linear?
As a minimum, you should:

(a) generate descriptive statistics and plot histograms for the
    following three columns: apret, tstsc, and salar.
(b) perform linear regression of apret on tstsc and salar
    separately and then of apret on both tstsc and salar.

If you find it useful, the meaning of the columns is as follows:

spend  - average spending per student (in dollars)
apret  - average retention rate (i.e., percentage of students
         making it through the studies)
top10  - percentage of incoming freshmen who were among the top
         10% students in their high schools
rejr   - school's rejection rate (percentage of applicants
          denied admission)
tstsc  - average test scores of incoming freshmen
pacc   - percent of admitted applicants who accept
         university's offer
strat  - student-teacher ratio
salar  - average faculty salary (in dollars)

Each row is for one of the 170 colleges for which the data
was measured.