The question need be done in Rmarkdown file, so please provide R code for necessary part. Since it contain too many data, I don't require
The question need be done in Rmarkdown file, so please provide R code for necessary part.
Since it contain too many data, I don't require the all result, just need you provide some code about what I should type in to RStudio, and general idea about the conclusion, because I have the data pack which can't be upload into this site.
T 15. Fifty states 2009. Here is a data set on various measures of the 50 United States. The Murder rate is per 100,000, HS Graduation rate is in %, Income is per capita income in dollars, Illiteracy rate is per 1000, and Life Expectancy is in years. Find a regression model for Life Expectancy with three predictor variables by trying all four of the possible models. a) Which model appears to do the best? b) Would you leave all three predictors in this model? c) Does this model mean that by changing the levels of the predictors in this equation, we could affect life ex- pectancy in that state? Explain. d) Be sure to check the conditions for multiple regres- sion. What do you conclude? Life expectancy Murder rate08 Graduation Rate Income/ cap07 State Illiteracy Alabama 74.4 7.6 62% 27557 0.15 Alaska 77.1 4.1 67 34316 0.09 Arizona 77.5 6.3 59 28088 0.13 75.2 5.7 72 25563 0.14 Arkansas California 78.2 5.8 68 35352 0.23 Colorado 78.2 3.2 68 34902 0.10 Connecticut 78.7 3.5 75 46021 0.09 5 g& & e%% Delaware 76.8 6.5 73 34533 0.11 Florida 77.5 6.4 59 32693 0.20 75.3 6.6 54 28452 0.17 Georgia Hawaii Idaho 80.0 1.9 69 33369 0.16 77.9 1.5 78 26530 0.11 Illinois 76.4 6.1 78 34290 0.13 For #15, a) Although it says to try all four models with 3 predictors, use whatever method (best subsets, forward stepwise, etc) to select a model with however many predictors you wish to include b) skip this question, but make sure you state your final model. d) make sure to include a residual plot (fitted vs predicted), a histogram of residuals and a normal probability plot. Also plot each predictor you keep versus the residuals. T 15. Fifty states 2009. Here is a data set on various measures of the 50 United States. The Murder rate is per 100,000, HS Graduation rate is in %, Income is per capita income in dollars, Illiteracy rate is per 1000, and Life Expectancy is in years. Find a regression model for Life Expectancy with three predictor variables by trying all four of the possible models. a) Which model appears to do the best? b) Would you leave all three predictors in this model? c) Does this model mean that by changing the levels of the predictors in this equation, we could affect life ex- pectancy in that state? Explain. d) Be sure to check the conditions for multiple regres- sion. What do you conclude? Life expectancy Murder rate08 Graduation Rate Income/ cap07 State Illiteracy Alabama 74.4 7.6 62% 27557 0.15 Alaska 77.1 4.1 67 34316 0.09 Arizona 77.5 6.3 59 28088 0.13 75.2 5.7 72 25563 0.14 Arkansas California 78.2 5.8 68 35352 0.23 Colorado 78.2 3.2 68 34902 0.10 Connecticut 78.7 3.5 75 46021 0.09 5 g& & e%% Delaware 76.8 6.5 73 34533 0.11 Florida 77.5 6.4 59 32693 0.20 75.3 6.6 54 28452 0.17 Georgia Hawaii Idaho 80.0 1.9 69 33369 0.16 77.9 1.5 78 26530 0.11 Illinois 76.4 6.1 78 34290 0.13 For #15, a) Although it says to try all four models with 3 predictors, use whatever method (best subsets, forward stepwise, etc) to select a model with however many predictors you wish to include b) skip this question, but make sure you state your final model. d) make sure to include a residual plot (fitted vs predicted), a histogram of residuals and a normal probability plot. Also plot each predictor you keep versus the residuals
