From Problem 2: USE RSTUDIO FOR ALL QUESTIONS AND PRESENT CODE AND RESULTS. The data set is in the link below of the problem.

the dataset "income.csv" contains with annual incomes in 2005 of the subset of National Longitudinal Survey of Youth (NLSY79) subjects who had paying jobs in 2005 and who had completed either 12 or 16 years of education by the time of their interview in 2006. All the subjects in this sample were between 41 and 49 years of age in 2006.

1 . make a side-by-side box plot of both groups (use the untransformed data, add to the pdf file). Report the Mean and Median of income for 12 years of education, and the Mean and the Median of income for 16 years of education

2. From Problem 2: Log-transform your data, make a side-by-side box plot of both groups (add graph in pdf file). Report the Mean and Median for 12 years of education, and the Mean and the Median for 16 years of education of the variable income (after transformation).

3. From Problem 2: Explain if the transformation was necessary. Support your answer using a normality test.

4. From Problem 2: find the appropriate test(s) of the difference on the amount by which the population distribution of incomes for those with 16 years of education exceeds the distribution for those with 12 years of education. Report the hypothesis you are testing (upper/lower/two tailed).

DefineGroup 1=16 years of educationandGroup 2 =12 years of education. Use the order M1- M2

From Problem 2: Report the p-value, do not use scientific notation

From Problem 2: What is your conclusion? Make sure to transform your answer to the original data ($dollars) when making this conclusion.

Instructions for your tutor:

USE RSTUDIO FOR ALL QUESTIONS AND PRESENT CODE AND RESULTS. The data set is in the link below of the problem.