Lecture 4 - Jan 13th

Lecture 4 - Jan 13th - Psyc 215; Jan. 13th, 2011...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
autsmcgill.com Testing Ideas: Research Designs : Different Research Methods - social psychologists use several different methods in the research process: - descriptive methods; often the 1st step that leads to choosing what the hypothesis should be - correlational methods - experiments - goal is to describe people and their thoughts, feelings, and behaviors - observational studies - simply observing behavior - archival studies - examining existing records of past events and behaviors - surveys - involves asking people questions about their attitudes, beliefs, and behaviors - importance of random sampling in order to generalize. If we took a sample of McGill students and who they will vote for it will not generalize to the Quebec population Correlational Research - goal is to learn about the relationship between variables - how similar or distinct are two different variables? - how well does one variable predict another variable? - able to look at a phenomena in its natural environment; how 2 variables behave together; if one is going up what happens to the other? - role of the correlation coefFcient - statistical representation varying from -1 and +1; the closer to +/-1 means a stronger correlation and the stronger to 0 means more random - measure of the strength and direction of the relationship between 2 variables - concurrent vs prospective; may not always turn out the same; the more snow that has fallen, the more you shovel but in a concurrent study I do not know which one came Frst (did the amount of snow cause you to shovel or did the amount you shovel cause the fall of snow); if i did the study concurrently it would look like a positive corelation. ... if you do it prospectively I would Fnd that the more you shovel, the less snow in your drive way (negative correlation Advantages - can study the associations of naturally occurring variables that cannot be manipulated or induced - can examine phenomena difFcult or unethical to create for research purposes; are abused people satisFed in their relationship? (We can not randomly assign abuse but we can examine abusive relationships) Psyc 215; Jan. 13th, 2011
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Very Serious Disadvantage - CORRELATION IS NOT CAUSATION; can only assign cause if we manipulated variables
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 03/01/2012 for the course PSYCHOLOGY 215 taught by Professor Sullivan during the Winter '11 term at McGill.

Page1 / 5

Lecture 4 - Jan 13th - Psyc 215; Jan. 13th, 2011...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online