Suppose you decide you want to study the relationship between activity level (your outcome of interest) and age (your explanatory variable of interest) of Toronto residents. You know that you wish to use a linear regression model to analyze your data. Consider the following questions

and give three ways to discuss:

• How should you define and collect these two variables of interest for your study? Are there benefits and drawbacks to these definitions?
• Could there be other variables you may want to also include that can help explain activity level? What might these variables be and why might they be important?
• Is it possible that a linear regression model (i.e. a straight-line relationship) might not be realistic between activity level and age?
• Do you think the results from your study could be generalized to other provinces or countries (i.e. if you collected data from that location, would you see a similar relationship)? Why or why not?

Please use three different sample