WE1 Using RStudio

1.Import Insurance data into RStudio

2. Assess the normality of the following variables: claim amount, coverage, householdincome, and deductible (explain whether or not the variables are normally distributed, are distribution symmetricalor skewed). Explain your findings and support with descriptive (numerical and/or graphical)

3. Is there a statistical relationship between claim amount and income?Explain your findings and support with descriptive (numerical and/or graphical)

4. Is there a statistical relationship between the type of claim and marital status?

WE1 Using MS Excel

1.Open Insurance data in MS Excel

2. Assess the normality of the following variables: claim amount, coverage, householdincome, and deductible (explain whether or not the variables are normally distributed, are distribution symmetricalor skewed). Explain your findings and support with descriptive (numerical and/or graphical). Hint:

3. Is there a statistical relationship between claim amount and income?Explain your findings and support with descriptive (numerical and/or graphical)

4. Is there a statistical relationship between the type of claim and marital status?

Hints: Q2: Numerical indicators include skewness, kurtosis, and Wilks-Shapiro test. R functions can be found in the script. MS Excel users can use "skew" and "kurt" functions, while Wilks-Shapiro test is not available in MS Excel. For better results, MS Excel users should use "Descriptive Statistics" function from Data Analysis pack.

Q3 and 4: make sure to pick a correct test between correlation and chi-square. Pay attention to the variable type (e.g., continuous vs. categorical). R users do not require any data manipulations to perform these tests. MS Excel users have to create necessary contingency tables. The most efficient way of creating those tables is using a pivot table function.