SOAN 2120 Lecture Notes - Lecture 4: Dependent And Independent Variables, Participant Observation, Fokker E.Ii
5 Dec 2016
School
Department
Course
Professor
Document Summary
Positive slope (up towards the right) implies a positive correlation. Negative slope (down to the right) implies a negative correlation. Flat slope means that there is no correlation. Scatterplots play an important role when looking at the relationships between two quantitative variables. Categorical: no rank order, non numerical. Lets us see if the relationship is linear. Gives us a preliminary view of the strength and direction of the relationship. Only when a relationship is linear does it make sense to use the correlation coefficient: the cc is a good summary measure of the direction and strength. 1 (perfect negative linear relationship) to +1 (perfect positive linear relationship: does not tell you the slope of the line (how steep) but how close the dots are to the line. Outliers: part of the data but unusual, could be a coding error, could just be a strange result.
