This is the pollution data so loved by writers of papers on ridge regression.
Source: McDonald, G.C. and Schwing, R.C. (1973) 'Instabilities of regression
estimates relating air pollution to mortality', Technometrics, vol.15, 463-
482.
Variables in order:
PREC   Average annual precipitation in inches
JANT   Average January temperature in degrees F
JULT   Same for July
OVR65  % of 1960 SMSA population aged 65 or older
POPN   Average household size
EDUC   Median school years completed by those over 22 (over 25 in 1960?)
HOUS   % of housing units which are sound & with all facilities
DENS   Population per sq. mile in urbanized areas, 1960
NONW   % non-white population in urbanized areas, 1960
WWDRK  % employed in white collar occupations, 1960 
POOR   % of families with income < $3000, 1960
HC     Relative hydrocarbon pollution potential
NOX    Same for nitric oxides
SO@    Same for sulphur dioxide
HUMID  Annual average % relative humidity at 1pm
MORT   Total age-adjusted mortality rate per 100,000


Data pooled from a variety of sources.


Summary of data from:

Instabilities of Regression Estimates Relating Air Pollution to
Mortality
Gary C. McDonald and Richard C. Schwing
Technometrics, Aug., 1973, Vol. 15, No. 3 (Aug., 1973), pp. 463-481

"
The total age adjusted mortality rate, our response variable in each
 regression equation, can be obtained for the years 1959-1961 for 201
 Standard Metropolitan Statistical Areas (SMSA) from Duffy and Carroll
 [4]. In Table 5 of [4], the age-adjusted death rates are given for
 the categories male white, female white, male non-white and female
 non-white. In addition, the number of deaths in each of these four
 categories is also provided. We define our total age adjusted
 mortality rate to be MR = (\sum D_i) (\sum (D_i/R_i))^{-1}, where D_i
 and R_i are the deaths and age adjusted death rates of, say, the ith
 category respectively, i = 1, 2, 3, 4. The sums are then taken over
 the four categories.

...

The pollution potential of three pollutants, namely HC, NO_x, SO2,
 have been estimated by Benedict [1]. The pollution potential is
 determined as the product of the tons emitted per day per square
 kilometer of each pollutant and a dispersion factor which accounts
 for mixing height, wind speed, number of episode days and dimension
 of each SMSA. Since each SMSA has the same dispersion factor for each
 pollutant, this quantity is "confounded" with each pollution
 potential term. Benedict's pollution potentials are available for
 sixty SMSA's, for the year 1963, which are geographically consistent
 with the available mortality data. Note, however, that the time
 period for which the pollution potentials apply (1963) is slightly
 later than the time period applicable to the mortality data.

Though the pollution variables are labeled HC,
 NO,, and S02, there are other variables, especially other pollutants,
 which are highly correlated with each of these indices. For example,
 SO2 is highly correlated with certain types of particulates and HC
 is closely tied to carbon monoxide and lead salts. Thus one cannot
 demonstrate a specific cause and effect even though the analysis
 quantifies the relationship.
"