Table 9.4 contains a subset of the pollution data analyzed by McDonald and Schwing (1973). The data are from various years in the early 1960s. They relate air pollution to mortality rates for various standard metropolitan statistical areas in the United States. The dependent variable y is the total age-adjusted mortality rate per 100,000 as computed for different metropolitan areas. The predictor variables are, in order, mean annual precipitation in inches, mean January temperature in degrees F, mean July temperature in degrees F, population per household, median school years completed by those over 25, percent of housing units that are sound and with all facilities, population per sq. mile in urbanized areas, percent non-white population in urbanized areas, relative pollution potential of sulphur dioxide, annual average of percent relative humidity at 1 pm.

Find a good predictive model for mortality.

Table 9.4: Pollution data.
x1 x2 x3 x4 x5 x6 x7 x8 x9 x10 y 36 27 71 3.34 11.4 81.5 3243 8.8 42.6 59 921.870 35 23 72 3.14 11.0 78.8 4281 3.5 50.7 57 997.875 44 29 74 3.21 9.8 81.6 4260 0.8 39.4 54 962.354 47 45 79 3.41 11.1 77.5 3125 27.1 50.2 56 982.291 43 35 77 3.44 9.6 84.6 6441 24.4 43.7 55 1071.289 53 45 80 3.45 10.2 66.8 3325 38.5 43.1 54 1030.380 43 30 74 3.23 12.1 83.9 4679 3.5 49.2 56 934.700 45 30 73 3.29 10.6 86.0 2140 5.3 40.4 56 899.529 36 24 70 3.31 10.5 83.2 6582 8.1 42.5 61 1001.902 36 27 72 3.36 10.7 79.3 4213 6.7 41.0 59 912.347 52 42 79 3.39 9.6 69.2 2302 22.2 41.3 56 1017.613 33 26 76 3.20 10.9 83.4 6122 16.3 44.9 58 1024.885 40 34 77 3.21 10.2 77.0 4101 13.0 45.7 57 970.467 35 28 71 3.29 11.1 86.3 3042 14.7 44.6 60 985.950 37 31 75 3.26 11.9 78.4 4259 13.1 49.6 58 958.839 35 46 85 3.22 11.8 79.9 1441 14.8 51.2 54 860.101 36 30 75 3.35 11.4 81.9 4029 12.4 44.0 58 936.234 15 30 73 3.15 12.2 84.2 4824 4.7 53.1 38 871.766 31 27 74 3.44 10.8 87.0 4834 15.8 43.5 59 959.221 30 24 72 3.53 10.8 79.5 3694 13.1 33.8 61 941.181 31 45 85 3.22 11.4 80.7 1844 11.5 48.1 53 891.708 31 24 72 3.37 10.9 82.8 3226 5.1 45.2 61 871.338 42 40 77 3.45 10.4 71.8 2269 22.7 41.4 53 971.122 43 27 72 3.25 11.5 87.1 2909 7.2 51.6 56 887.466 46 55 84 3.35 11.4 79.7 2647 21.0 46.9 59 952.529 39 29 75 3.23 11.4 78.6 4412 15.6 46.6 60 968.665 35 31 81 3.10 12.0 78.3 3262 12.6 48.6 55 919.729 43 32 74 3.38 9.5 79.2 3214 2.9 43.7 54 844.053 11 53 68 2.99 12.1 90.6 4700 7.8 48.9 47 861.833 30 35 71 3.37 9.9 77.4 4474 13.1 42.6 57 989.265 50 42 82 3.49 10.4 72.5 3497 36.7 43.3 59 1006.490 60 67 82 2.98 11.5 88.6 4657 13.5 47.3 60 861.439 30 20 69 3.26 11.1 85.4 2934 5.8 44.0 64 929.150 25 12 73 3.28 12.1 83.1 2095 2.0 51.9 58 857.622 45 40 80 3.32 10.1 70.3 2682 21.0 46.1 56 961.009 46 30 72 3.16 11.3 83.2 3327 8.8 45.3 58 923.234 54 54 81 3.36 9.7 72.8 3172 31.4 45.5 62 1113.156 42 33 77 3.03 10.7 83.5 7462 11.3 48.7 58 994.648 42 32 76 3.32 10.5 87.5 6092 17.5 45.3 54 1015.023 36 29 72 3.32 10.6 77.6 3437 8.1 45.5 56 991.290 37 38 67 2.99 12.0 81.5 3387 3.6 50.3 73 893.991 42 29 72 3.19 10.1 79.5 3508 2.2 38.8 56 938.500 41 33 77 3.08 9.6 79.9 4843 2.7 38.6 54 946.185 44 39 78 3.32 11.0 79.9 3768 28.6 49.5 53 1025.502 32 25 72 3.21 11.1 82.5 4355 5.0 46.4 60 874.281 Alternatively, you can obtain the complete data from the Internet statistical service STATLIB by going to http://lib.stat.cmu.edu/datasets/ and clicking on “pollution.” The data consist of 16 variables on 60 cases.