Data Management and Visualization: Getting my Research Project Started

 After looking through the codebook for the NESARC study, I have decided that I am particularly interested in nicotine dependence. I will use the variables "SMOKER" (Indicating "Tobacco Use Status"), "S3AQ3B1" (Indicating "Usual Frequency when Smoked Cigarettes"), "S3AQ3C1" (Indicating "Usual quantity when Smoked Cigarettes") and "S3AQ3D1R" (Indicating "Duration (Days) of usual Cigarette Smoking") to answer the question "Have cigarette ex-smokers smoked less cigarettes on average than current cigarette smokers?" Another way of phrasing the question may be "Have ex-smokers smoked less than current ones prior to their quitting?" Notice, that there is no time period specification of the "prior to quitting" phrase. To further develop the main question, as a second topic, I give the part "smoked less cigarettes on average" 2 meanings - smoked less cigarettes as a count and smoked for a briefer duration periods than the current smokers. Although the question may seem redundant (or maybe exactly because of this), I have found no article explaining if ex-smokers did truely smoke less than current smokers before they quit. This is the main reason why I am currently unable to make any hypothesis about the posed question.