Question

imagine we wanted to look a predictors of popularity of famous sports people. We might hypothesize that the type of sport played would predict how popular the sports person was. Imagine we recruited 100 participants and asked them to rate out of 10(10 = They are the best sports person in the world, 0 = They are the worst sports person in the world) how much they liked 100 famous sports people from 10 different types of sports ( 10 sports people from each category).

Could we analyse these data using regression, and if so how?

1. no. we could not conduct a regression because our categorical predictor is made up of more than two categories.

2. no. we can only analyse this scenario using ANOVA.

3. Yes. To do this we would need to create on coding variable for the 'type of sport played' predictor variable.

4. yes To do this we would create 9 dummy variables for the type of sport played' variable.

I am guessing number 4. could you please explain if I am right or wrong? Thank you!

Answer 1

3. Yes. To do this we would need to create one coding variable for the 'type of sport played' predictor variable.

We will have one variable with the code of the sports played. 1,2,3,...,10 Not dummy variable. Dummy variables could have been added if one player plays more than one sports.

We will have the player's score given by people as one variable, sports played as another variable in code.

Code will be the independent variable and score will be dependent.