Consider a data set containing the weights of the body (in kg) and the weight of the brain (in g) for 40 mammals. A scatter plot of the data (with both axes on the log scale) is shown below. 100- Brain weight (in g) 1 - 10-01 18+01 18+03 Body weight (in kg) The plot suggests that there is a linear relationship between the logarithm of the brain weight and the logarithm of the body weight. A linear model was fiited using the (natural) logarithm of the brain weight as response and the (natural) logarithm of the body weight as covariate.Body weight (in kg) The plot suggests that there is a linear relationship between the logarithm of the brain weight and the logarithm of the body weight. A linear model was fiited using the (natural) logarithm of the brain weight as response and the (natural) logarithm of the body weight as covariate. Call: Im(formula = log(brain) ~ log(body), data = mammals) Residuals : Min 10 Median 30 Max -1. 62068 -0. 38400 0.02884 0.43609 2.00845 Coefficients: Estimate Std. Error t value Pr(>|t| ) (Intercept) 2.02486 0. 11412 [A] (yi - 12)? = 246.8831. i=1 [A] [B]= [C]= [D]= An arctic ground squirrel has a body weight of 0.92kg. Use the estimated regression coefficients from above to predict the brain weight of a(nvowel) arctic ground squirrel (in g). Predicted brain weight (in 9): (to 4 decimal points) Don't forget to take into account that we have log-transformed both the response and the covariate