PSYC1111 Study Guide - Final Guide: Schizophrenia, Sexual Dysfunction, Internal Validity
Validity
• The two most important forms of validity
o Internal validity (strength of the causal explanation between two variables) –
always about causation
o External Validity (population and ecological validity) – can you make this
important for general population and outside of the lab
• Threats to validity: Factors that lower validity
Threats to validity
• A threat to internal validity = Confound
o Confound = something that undermines an explanation
• A threat to external validity = Artifact
o Artifact = a by-product of a testing procedure or sample that biases all the
results
o Because of the way you are testing it
Confound
• Confound is a third variable that differs between the groups
• Confounds influence the DV and are not the variable you are
manipulating
• You may have a different confound in your experimental and
control groups
Artifact
• An artefact is present consistently in all groups and measures
• Artifacts reduce external validity
• Prevents you generalising your results
• i.e. being observed
Threats to Internal Validity
• Internal validity
• J. “. Mill’s 3 riteria to ifer ausatio
1. Covariation – There is a relationship
2. Temporal sequence – a’t ake ausal lai uless oe thig ourred first
3. Eliminate alternative explanations
▪ Third variable problem
• Confounds – Extraneous variable that systematically varies or influences both the
independent and the dependent variable
Third Variable Problem: Confound
• There is a positive correlation between coffee drinking and the likelihood of having a
heart attack
o Can we conclude that drinking coffee causes heart attacks?
o People that are smokers tend to drink more coffee
find more resources at oneclass.com
find more resources at oneclass.com
o May be increased job stress
o May have poor sleep
• Oxygen causes rust
• We breath oxygen
• Therefore, oxygen will damage our lungs
• Obviously wrong
• Third variables
o Need water
o Need iron or steel
o It is actually the interaction between irons, water and oxygen that produces
rust (iron oxide)
• The best way to account for these systematic confounds is usually to manipulate the
independent variable
• Pseudo eperiets / false eperiets ost suseptile
o Exposure to the variable of interest
o Effect of the variable of interest
o No comparison or control
o E.g. power balance wrist bands
• Importance of control groups
Control Groups
• Variable manipulation
• You want to manipulate only the variable of interest between groups/conditions
• Challenge is to keep everything else constant
Threat To Internal Validity: Confounds
• Where do they come from?
• From the experimenter
• From the participants – individual differences
• Major threats to internal validity:
o The validity of a statement about the causal relationship between variables
Confounds: From the Experimenter I
• Experimenter bias
• Maze dull and bright rats
• Told the rats were bright or dull
find more resources at oneclass.com
find more resources at oneclass.com
Document Summary
Validity: the two most important forms of validity. Confound: confound is a third variable that differs between the groups, confounds influence the dv and are not the variable you are manipulating, you may have a different confound in your experimental and control groups. Artifact: an artefact is present consistently in all groups and measures, artifacts reduce external validity, prevents you generalising your results i. e. being observed. Control groups: variable manipulation, you want to manipulate only the variable of interest between groups/conditions, challenge is to keep everything else constant. Threat to internal validity: confounds: where do they come from, from the experimenter, from the participants individual differences, major threats to internal validity, the validity of a statement about the causal relationship between variables. Confounds: from the experimenter i: experimenter bias, maze dull and bright rats, told the rats were bright or dull, the rats performed differently on the maze, no difference between the rats, experimented is influencing the outcome.