Fitbit is a company that sells various activity trackers that measure physical activity. A study aims to investigate whether tracker type and gender impact the amount of physical activity (measured by the total number of steps taken per day). Assume you are the lead of a statistical analysis team that has access to data collected from randomly selected 400 Fitbit users including their:• tracker type (Versa, Charge, Inspire and Ionic – 100 people in each tracker type group),• gender (F = female, M = male), and• steps (number of steps taken per day). Copy, paste and run the R syntax below in your R console to create the dataset called fitbit. # Start of R syntax# Components of the datasettracker = c(rep("versa", 100), rep("charge", 100), rep("ionic",100), rep("inspire",100))gender = c(rep("M", 50), rep("F",50),rep("M", 50), rep("F",50),rep("M", 50), rep("F",50),rep("M", 50), rep("F",50))steps = c(runif(100, min=5000, max=8000),runif(100, min=2000, max=3500),runif(100, min=4000, max=6500),runif(100, min=7500, max=12000)) # Create the dataset called fitbitfitbit <- data. frame(tracker, gender, steps) #Check out the dataset structurestr(fitbit) # End of R syntaxDevelop and run a statistical model in R using the dataset fitbit to test the hypotheses whether tracker type (column name: tracker) and gender (column name: gender) have a statistically significant impact on the response variable (column name: steps) at the significance level 0.05. Assume there is no interaction between tracker type and gender. Which factor(s) is/are significant? What is the statistical decision? Explain your results. Now, assume there might be an interaction between tracker type and gender. Develop and run a new statistical model to include an interaction term using the dataset fitbit. Which factor(s) is/are significant? What is the statistical decision? How would you interpret the results? Which model (with or without interaction term between tracker type and gender) would you recommend using? Why? Explain your results. A junior analyst who joined your team recently is worried about whether the selected model in Question 4 is appropriate for the given data. Check the normality assumption using the appropriate visualization method in R. Does the normality assumption of the selected model hold? Explain your results.