NAME: Televisions, Physicians, and Life Expectancy

TYPE: Sample

SIZE: 40 observations, 6 variables

DESCRIPTIVE ABSTRACT:

For each of the forty largest countries in the world (according to 1990

population figures), data are given for the country's life expectancy

at birth, number of people per television set, and number of people per

physician.

SOURCE:

_The World Almanac and Book of Facts 1993_ (1993), New York: Pharos

Books.

VARIABLE DESCRIPTIONS:

Columns

1 - 15 Country

23 - 26 Life expectancy

29 - 33 People per television

36 - 40 People per physician

43 - 44 Female life expectancy

47 - 48 Male life expectancy

Values are aligned and delimited by blanks.

Missing values are denoted with *.

SPECIAL NOTES:

A country's life expectancy was calculated by averaging the life

expectancies for females and males. In most cases the almanac listed

the ratios of people per television and people per physician directly.

In the few cases for which the almanac listed the raw numbers, the

ratios were calculated from the population information. The only

missing values are people per television in Tanzania and Zaire.

STORY BEHIND THE DATA:

These data were gathered from _The World Almanac and Book of Facts

1993_ to enable students to explore properties of association,

correlation, and prediction in a context that is very easy to

understand.

Additional information about these data can be found in the "Datasets

and Stories" article "Televisions, Physicians, and Life Expectancy" in

the _Journal of Statistics Education_ (Rossman 1994).

PEDAGOGICAL NOTES:

These data provide a useful context for students to discover the

fundamental principle that correlation does not imply causation. They

also give students an opportunity to explore data transformations and

to consider whether a causal connection is necessary for one variable

to be a useful predictor of another. People per television is

negatively associated with life expectancy, and the log transformation

makes it a slightly better predictor of life expectancy than people per

physician.

SUBMITTED BY:

Allan J. Rossman

Dickinson College

Department of Mathematics and Computer Science

P.O. Box 1773

Carlisle, PA 17013