2. Using a dataset of 47 French-speaking provinces of Switzerland in the year 1888, we would like to predict fertility rates based on different socio-economic indicators: Agriculture % of males involved in agriculture as occupation Examination % draftees receiving highest mark on army examination Education % education beyond primary school Catholic % 'catholic' Infant. Mortality live births who live less than 1 year We use a procedure to select the number of predictors that should be included in our model: ## Subset selection object ## Call: regsubsets. formula(Fertility ~ ., data = swiss, nvmax = 5) # 5 Variables (and intercept) # # Forced in Forced out ## Agriculture FALSE FALSE ## Examination FALSE FALSE ## Education FALSE FALSE ## Catholic FALSE FALSE ## Infant Mortality FALSE FALSE ## 1 subsets of each size up to ## Selection Algorithm: exhaustive Agriculture Examination Education Catholic Infant Mortality ## 1 W# 2 (1 ) 1 4 1 5 0.60 SSE Adjusted RSq 2500 3500 0.45 Number of predictors Number of predictors -25 5 15 25 35 BIC Number of predictors Number of predictors2.1 {2 pt] How isthis procedure called? 2.2 {2 pts] What predictor will you use for the model with the one predictor? [Refer to the outcome above]. 2.3 {4 pts] Based on the criteria represented above, decide how many predictors should be included in your model. Make sure to specify if we are looking to maximize or minimize each criterion. 2.4 {2 pts] Write the expression of the model you chose in the previous