Examine the United Nations data on infant mortality and other variables for 207 countries, discussed in Section 20.4.4. (a) Perform a complete-case linear least-squares regression of infant mortality...

Examine the United Nations data on infant mortality and other variables for 207 countries, discussed in Section 20.4.4.

(a) Perform a complete-case linear least-squares regression of infant mortality on GDP per capita, percentage using contraception, and female education. Does it appear reasonable to log-transform infant mortality and GDP to linearize this regression? What about contraception and education?

(b) 'Examine a scatterplot matrix (Section 3.3.1) for the variables used in the imputation example. What do you find? Then apply the multivariate Box-Cox procedure described in Section 4.6 to these variables. employed in the text? Apply the transformations and reexamine the data. Do they appear more nearly normal? Remember first to subtract 35 from female expectation of life (why?). Do the results that you obtain support the transformations