What methodology would you use if you were to conduct a research project investigating the relationship between smoking and gender in blockbuster films?
If the aim of the research is to detect whether there is any statistical association or correlation between the two variables, the correlation coefficient should be computed, using the observations of the two variables of interest: smoking (y) and gender (x) in the blockbuster enviroment.
If the aim of the research is to confirm the existence or not of a casual relationship between the variables, a regression analysis should be conducted. The y variable, which contains information of the smoking habits of the characters should be appointed as the dependent variable, while the x variable (gender) will be one of the independent or control variables. In order to prevent biases, other control variables should be introduced, such as the film genre, whether the character is the hero or villain, etc. This helps because, when computing beta coefficient for the gender variable of interest, the effect obtained will not be contaminated by other relevant factors or variables.
