Descriptions of the data files

In this file, the data files used in the additional cases are described. Included are the names of the files, a list of the variables in the file, the source of the data, and a printout of the first five observations in the file. The latter is included so that the reader can see the layout of the file, making it easier to input the data into a statistical package. We have not included a data source when the data were generally available in newspapers (e.g., stock prices). Missing values are represented by M in all data files.

The files can be accessed from the World Wide Web (WWW) using a WWW browser (e.g., Netscape) at the URL address

http://www.stern.nyu.edu/~jsimonof/Casebook

This will provide a short description of the information available. This method also provides access to an archive of new cases (in Postscript format) and updated information concerning the cases in the book.

It is possible that, for some of the cases, results using these data sets will differ slightly from those in the cases. The reason for this is that non-integer values are not necessarily provided to the full level of machine arithmetic in the data sets.


State aid to Nassau County public schools

File name


aidschl.dat

Description of data

Distribution of New York State aid to Nassau County school districts.

Variables in file

(1) School district (called DISTRICT in the case).
(2) Average state aid per student, 1994-1995 (called AID94PS in the case).
(3) Percentage change in state aid, 1988 to 1994 (called CHANGEAID in the case).
(4) Proportion of white students, 1992-1993 (called PROPWHITE in the case).
(5) Average class size, 9th grade English 1990-1991 (called SIZENG90 in 
    the case).
(6) Average class size, elementary 1990-1991.
Data source

Newsday, September 4, 1994

First five observations

Baldwin                   2171.18055 -20.87098 0.761915 19.2 22.1
Bellmore                  1813.78526 -33.18658 0.960000    M 18.6
Bellmore - Merrick        2522.39673 -20.94512 0.949851 23.1    M
Bethpage                  1454.13862 -26.71606 0.934959 18.6 20.0
Carle Place               1003.18138 -25.35590 0.884642 16.6 21.7

Salaries of major league players

File name

bsal.dat

Description of data

Salaries of major league baseball players on opening day rosters and disabled lists for the 1994 season.

Variables in file

(1) Player's name.
(2) Salary of the player (millions of dollars) (called SALARY in the case).
(3) League the player's team plays in (American or National).
Data source

The Nando X Baseball server on the World Wide Web (WWW). The URL address is http://www.nando.net/newsroom/baseball/strike/make.html.

First five observations

Cal Ripken Jr.           5665822 American
Rafael Palmeiro          5469479 American
Mike Devereaux           3375000 American
dl-Sid Fernandez         3333333 American
Brady Anderson           3083333 American

The success of teams in the National Hockey League --- 1995-1996

File name

hockey3.dat

Description of data

Success of National Hockey League Teams, 1995-1996.

Variables in file

(1) Team name.
(2) Points (called POINTS in the case).
(3) Goals scored (called GF in the case).
(4) Goals given up (called GA in the case).
(5) Predicted points using the complex model equation from the 1992--1993 data (called PREDGFGA in the case).
(6) Predicted points using the simple model equation from the 1992--1993 data (called PREDDIFF in the case).
Data source

The National Hockey League Official Guide and Record Book, 1995--1996}, Triumph Books, Chicago (1996)

First five observations

Detroit Red Wings         325  181  131   128.10   124.87
Colorado Avalanche        326  240  104   109.02   107.61
Philadelphia Flyers       282  208  103   107.71   104.03
Pittsburgh Penguins       362  284  102   104.25   105.22
New York Rangers          272  237   96   95.509   92.421

Copyright 1995, 1996, Samprit Chatterjee, Mark S. Handcock and Jeffrey S. Simonoff