Consider the following two-stage model for Table 8.8. The first stage is a logit model with S as the response for the three-way GLS table. The second stage is a logit model with these three variables as predictors for I in the four-way table. Explain why this composite model is sensible, fit the models, and interpret results.

Table 8.8:

Transcribed Image Text:

Injury (GI, GL, GS, IL, IS, LS) (GLS, GI, IL, IS) Sample Seat Gender Location Belt Proportion Yes No No Yes Yes 993.0 721.3 988.8 781.9 845.1 387.6 1,038.1 518.2 Yes No No Female 0.12 Urban No 7,287 996 7,166.4 11,748.3 3,353.8 5,985.5 10,471.5 10,837.8 6,045.3 6,811.4 7,273.2 1,009.8 11,632.6 11,587 973 759 713.4 Yes 0.06 No 3,246 6,134 10,381 10,969 6,123 1,084 6,693 3,254.7 964.3 0.23 Rural 6,093.5 757 797.5 Yes 0.11 Male Urban No Yes No 10,358.9 834.1 812 0.07 0.03 380 10,959.2 389.8 6,150.2 1,056.8 508.4 Rural 6,697.6 Yes 513 0.07