beware of confounding variables
Post on 23-Feb-2016
Embed Size (px)
DESCRIPTIONBeware of Confounding Variables. If I wanted to prove that smoking causes heart issues, what are some confounding variables?. The object of an experiment is to prove that A causes B. A confounding variable is anything that could cause change in B, that is not A. - PowerPoint PPT Presentation
Beware of Confounding Variables
Beware ofConfounding VariablesIf I wanted to prove that smoking causes heart issues, what are some confounding variables?The object of an experiment is to prove that A causes B.A confounding variable is anything that could cause change in B, that is not A.
Lifestyle and family history may also effect the heart. Random AssignmentOnce you have a random sample, randomly assigning them into two groups helps control for confounding variables.Experimental Group v. Control Group.Group Matching
Hawthorne EffectBut even the control group may experience changes.Just the fact that you know you are in an experiment can cause change.
Whether the lights were brighter or dimmer, production went up in the Hawthorne electric plant.Experimenter Bias
Another confounding variable.Not a conscious act.Double-Blind Procedure.
Evaluating Research: Methodological Pitfalls
Sampling bias Placebo effects Distortions in self-report data:Social desirability bias Response set
5Sampling bias when a sample is not representative of the populationpoll only men, may get a different outcome if the population is both male and female.Placebo effects when a participants expectations lead them to experience some change even though they receive empty, fake, or ineffectual treatmentcured by a sugar pill.Distortions in self-report data:Social desirability bias a tendency to give socially approved answers to questions about oneselfdid you vote?Response set a tendency to respond to questions in a particular way (agree with everything, etc.).Experimenter bias when a researchers expectations or preferences about the outcome of a study influence the results obtainedresearchers see what they want to see errors are usually in favor of the hypothesissimilarly, researchers may unintentionally influence the behavior of their subjects, possibly through body language, smiles, etc. To control for this problem, a double-blind procedure in which neither subjects nor experimenters know which subjects are in the experimental and which are in the control groups is useda non-directly involved researcher keeps track of everything.
REVIEW:WHEN THE RESEARCHERS EXPECTATIONS ABOUT THE OUTCOME OF THE STUDY INFLUENCE THE STUDY?EXPERIMENTER BIASWHEN PARTICIPANTS EXPECTATIONS LEAD THEM TO EXPERIENCE SOME CHANGE, EVEN THOUGH THEY RECEIVE A EMPTY OR FAKE TREATMENT?PLACEBO EFFECTTHE TERM FOR SAMPLING THAT IS NOT REPRESENTATIVE OF THE POPULATION?SAMPLING BIAS Correlational MethodCorrelation expresses a relationship between two variable.Does not show causation.
As more ice cream is eaten, more people are murdered. Does ice cream cause murder, or murder cause people to eat ice cream?
9Types of CorrelationPositive CorrelationThe variables go in the SAME direction.Negative CorrelationThe variables go in opposite directions.
Studying and grades hopefully has a positive correlation.Heroin use and grades probably has a negative correlation. Survey Method
Most common type of study in psychology
Cheap and fast
Need a good random sample
Low-response rateNaturalistic ObservationWatch subjects in their natural environment.Do not manipulate the environment.The good is that there is no Hawthorne effect.The bad is that we can never really show cause and effect.
Correlation CoefficientA number that measures the strength of a relationship.Range is from -1 to +1The relationship gets weaker the closer you get to zero.Which is a stronger correlation?-.13 or +.38-.72 or +.59-.91 or +.04
14Figure 2.13 Positive and negative correlation