UCSB COMM 88 STUDY GUIDE 2026
ACCURATE QUESTION SET AND CORRECT
ANSWERS
◉ When and how should a correlation be computed?
Answer: To relate 2 or more continuous variables to each other
Use a statistical value "r" that gives type (+/-) and magnitude
(strength) of relationship
Cannot conclude if a variable causes the other!
◉ How is the magnitude/strength of a relationship measured?
Answer: r ranges from -1.00 to +1.00
the further from zero, the stronger the relationship
0 = no relationship
◉ What are the 3 Golden Rules to Establish Causality?
Answer: 1. Variables must be related/show an association
2. Must establish a time order
3. Must rule out other explanations/causes
,◉ What are the 2 causality problems with survey/correlation
research?
Answer: 1. Causal Direction Problem (time order)
survey data often does not tell you if X came before Y reliably
2. "Third Variable" Problem (other explanations)
taken in uncontrolled environments
◉ What is the goal and sacrifice of testing hypotheses of cause and
effect?
Answer: Goal: establish internal validity
Willing to sacrifice external validity
◉ What are the 2 key elements of a true experiment?
Answer: Manipulation of IVs
Random assignment of participants
◉ Describe the manipulation of IVs.
Answer: Divide subjects into different "conditions" groupings and
test each the same way
Examine effects on the DV
Measure will be continuous
Compare measure (mean scores) for subjects
, ◉ Describe random assignment. Why is it important?
Answer: All participants have an equal chance of ending up in either
condition
You want IV manipulation to be the only factor!! So... it makes groups
equal before manipulation --> fair comparison later
◉ manipulation/control + random assignment =
Answer: internal validity
◉ What do "p" values measure?
Answer: tests statistical significance
for ruling out chance outcomes
the smaller the "p" value, the less likely we got results by chance
◉ What are the 3 types of true experiments?
Answer: Post-Test Only
Pre-Test/Post-Test
Solomon 4-Group Design
◉ What is the post-test only control group design?
Answer: --> X1 Y (group 1)
ACCURATE QUESTION SET AND CORRECT
ANSWERS
◉ When and how should a correlation be computed?
Answer: To relate 2 or more continuous variables to each other
Use a statistical value "r" that gives type (+/-) and magnitude
(strength) of relationship
Cannot conclude if a variable causes the other!
◉ How is the magnitude/strength of a relationship measured?
Answer: r ranges from -1.00 to +1.00
the further from zero, the stronger the relationship
0 = no relationship
◉ What are the 3 Golden Rules to Establish Causality?
Answer: 1. Variables must be related/show an association
2. Must establish a time order
3. Must rule out other explanations/causes
,◉ What are the 2 causality problems with survey/correlation
research?
Answer: 1. Causal Direction Problem (time order)
survey data often does not tell you if X came before Y reliably
2. "Third Variable" Problem (other explanations)
taken in uncontrolled environments
◉ What is the goal and sacrifice of testing hypotheses of cause and
effect?
Answer: Goal: establish internal validity
Willing to sacrifice external validity
◉ What are the 2 key elements of a true experiment?
Answer: Manipulation of IVs
Random assignment of participants
◉ Describe the manipulation of IVs.
Answer: Divide subjects into different "conditions" groupings and
test each the same way
Examine effects on the DV
Measure will be continuous
Compare measure (mean scores) for subjects
, ◉ Describe random assignment. Why is it important?
Answer: All participants have an equal chance of ending up in either
condition
You want IV manipulation to be the only factor!! So... it makes groups
equal before manipulation --> fair comparison later
◉ manipulation/control + random assignment =
Answer: internal validity
◉ What do "p" values measure?
Answer: tests statistical significance
for ruling out chance outcomes
the smaller the "p" value, the less likely we got results by chance
◉ What are the 3 types of true experiments?
Answer: Post-Test Only
Pre-Test/Post-Test
Solomon 4-Group Design
◉ What is the post-test only control group design?
Answer: --> X1 Y (group 1)
