This question is from page 732 from the textbook, Statistics for Management and Economics 11th Edition, and a separate dataset is required to solve it (CA17-02). I tried to attach the dataset to this post, but it was too big. This question is located within the multiple regression section of the book, so the answer will involve the use of multiple regression. The question CASE A17.2 is as follows:

Setting premiums for insurance is a complex task. If the premium is too high, the insurance company will lose customers; if it is too low, the company will lose money. Statistics plays a critical role in almost all aspects of the insurance business. As part of a statistical analysis, an insurance company in Florida studied the relationship between the severity of car crashes and the ages of the drivers. A random sample of crashes in 2002 in the state of Florida was drawn. For each crash, the age category of the driver was recorded as well as whether the driver was injured or killed. The data were stored as follows: Column 1: Crash number Column 2: Age category 1. 5 to 34 2. 35 to 44 3. 45 to 54 4. 55 to 64 5. 65 and over Column 3: Medical status of driver 1 = Uninjured 2 = Injured (but not killed) 3 = Killed a. Is there enough evidence to conclude that age and medical status of the driver in car crashes are related? b. Estimate with 95% confidence the proportion of all Florida drivers in crashes in 2002 who were uninjured.