1. Create a demographics table with counts and percentages for each of the following groups in a manner similar to the table below. You do not need to calculate the standard errors for age. We are using a smaller version of the same dataset, so your numbers will not perfectly match up. If you want to get fancy, try using the =text or =concatenate commands to get both the percentages and counts in the same column.

Shaw, J. W., Johnson, J. A., & Coons, S. J XXXXXXXXXXUS valuation of the EQ-5D health states: development and testing of the D1 valuation model.Medical care, XXXXXXXXXX.
2. Create a figure that displays the relationships between the included health problems and own health scale rating (often called VAS). Find a way to include the interquartile ranges in the figure.
3. Determine the number of health problems for each individual.
4. How many individuals have smoked at some point during their life. You will have to combine the data from both smoking variables to calculate this.
5. Pick any two of the health conditions and find national data on the prevalence of these conditions. Make sure to cite where you got the data from. How does our dataset compare?
6. Run a regression using VAS as the dependent variable. Include age, ever smoked, gender, education (put into thee/four groups), and income.
7. Which of these regressors appears to have the most important relationship with VAS? Provide a 3-5 sentence explanation.