charnes1981 {Benchmarking}R Documentation

Data: Charnes et al. (1981): Program follow through

Description

The data set is from an US federally sponsored program for providing remedial assistance to disadvantaged primary school students. The firms are 70 school sites, and data are from entire sites. The variables consists of results from three different kind of tests, a reading score, y1, a math score, y2, and a self–esteem score, y3, which are considered outputs in the model, and five different variables considered to be inputs, the education level of the mother, x1, the highest occupation of a family member, x2, parental visits to school, x3, time spent with children in school-related topics, x4, and the number of teachers at the site, x5.

Usage

data(charnes1981) 

Format

A data frame with 70 school sites with the following variables.

firm

school site number

x1

education level of the mother

x2

highest occupation of a family member

x3

parental visits to school

x4

time spent with children in school-related topics

x5

the number of teachers at the site

y1

reading score

y2

math score

y3

self–esteem score

pft

=1 if in program (program follow through) and =0 if not in program

name

Site name

Details

The command data(charnes1981) will create a data frame named charnes1981 with the above data.

Beside input and output varianles there is further information in the data set, that the first 50 school sites followed the program and that the last 20 are the results for sites not following the program. This is showed by the variable pft.

Note

Data as .csv are loaded by the command data using read.table(..., header=TRUE, sep=";") such that this file is a semicolon separated file and not a comma separated file.

Therefore, to read the file from a script the command must be read.csv("charnes1981.csv", sep=";") or read.csv2("charnes1981.csv").

Thus the data can be read either as charnes1981 <-
read.csv2(paste(.Library, "Benchmarking/data", "charnes1981.csv", sep ="/"))
or as data(charnes1981) if the package Benchmarking is loaded. In both cases the data will be in the data frame charnes1981.

Source

Charnes, Cooper, and Rhodes, “Evaluating Program and Managerial Efficiency: An Application of Data Envelopment Analysis to Program Follow Through”, Management Science, volume 27, number 6, June 1981, pages 668–697.

Examples

data(charnes1981)
x <- with(charnes1981, cbind(x1,x2,x3,x4,x5))
y <- with(charnes1981, cbind(y1,y2,y3))

# Farrell inpout efficiency; vrs technology
e <- dea(x,y)
# The number of times each peer is a peer
np <- get.number.peers(e) 
# Peers that are peers for more than 20 schools, and the number of
# times they are peers
np[which(np[,2]>20),]

# Plot first input against first output and emphasize the peers that
# are peers for more than 20 schools in the model with five inputs and
# three outputs
inp <- np[which(np[,2]>20),1]
dea.plot(x[,1],y[,1])
points(x[inp,1], y[inp,1], pch=16, col="red")

[Package Benchmarking version 0.29 Index]