Dependent Variables
Class 09
Mid-Term
New Date: Thursday, October 22
Covers: All lectures, Class 1 (Introduction) up to and including Class 12 (Avoiding Bias)
Format: Multiple Choice and Short Answer
Duration: Entire Class
Contributes to Course Grade: 25%
Dependent Variables: Conceptual vs. Experimental
Conceptual Experimental
Hitting
Aggression
Health Status
Blood Pressure
GPA
X
X
X
X
X
How Sad Am I? A Titanic QuestionHyp: Fictional events will affect real emotions.
IV: Subjects see a tragically sad movie
DV? How sad are you?
__ Not at all __ Somewhat ___ A lot .
How much did you want to cry?
__ Not at all __ Somewhat ___ A lot
How much do you need to talk about this?
__ Not at all __ Somewhat ___ A lot
VERSUS
Observe walking speed after seeing sad movie.
Amount Kleenex bought at concession stand.
What to Consider when Selecting
Dependent Variables
What behavior best represents conceptual DV?
DV should capture richness and power of response to IV
DV should be reliable and non-obvious
DV should be as easy to use and economical as possible
Subs. should take DV seriously
DV should be ethical
Expt’l DV
Follow boring instructions
Follow embarrassing instructions
Follow instructions that hurt another against that person’s will
Yeah, but...
Lots of expts. are boring
Sometimes psych is interested in personal, hidden stuff
Holy Moly!!!
Centrality of Experimental DV to Conceptual DV
Conceptual DV
Obedience
Experiment:
Do Reminders of Discrimination Affect Support for Affirmative Action?
IV: Subjects see documentary on how women and minorities historically received unfair treatment.
What would be an appropriate DV?
Classes of DV Measures
Verbal Measures (surveys, interviews)
Behavioral
Overt behavior
Behavioroid
Physiological
Advantages of Verbal Measures(Surveys, Ratings, Vignettes)
Easy to use
Face validity: apparent direct access to thoughts, feelings
Provide multiple opportunities to respond to IV,
where as behavioral is often single-shot
Can provide for more sensitive, subtle measures.
Affirmative Action Measure
1. Do you favor Affirmative Action? ___ YES ___ NO
Problems with this measure?
Degree of favor?
Favor for all groups?
Favor all ways of implementing?
Likert Scales
What is your view on affirmative action?
Totally against
1
Mainly against
2
Some-what
against
3
Neither for nor against
4
Some-what favor
5
Mainly favor
6
Totally favor
7
Rensis Likert
Problems with this measure? Aff. Action for women? Minorities? Disable?
To what degree do you favor affirmative action for Asians?
Not at all
1
Very Little
2
Some-what
3
Very Much
4
A Great Degree
5
To what degree do you favor affirmative action for African Americans?
Not at all
1
Very Little
2
Some-what
3
Very Much
4
A Great Degree
5
To what degree do you favor affirmative action for Latinos?
Not at all
1
Very Little
2
Some-what
3
Very Much
4
A Great Degree
5
Likert Scale Considerations
1. Label each choice option, or just the extremes?
2. How many choice-options? (i.e. 3, 5, 7, 9, 131?)
3. Unipolar or bipolar?
1. Two measures problem
2. Hiding in the middle
Bi-Modal Scales
What is your view on gun control?
Totally against
-3
Mainly against
-2
Some-what
against
-1
Neither for nor against
0
Some-what favor
1
Mainly favor
2
Totally favor
3
Problems?
What does 0 mean? Undecided?Both agree and disagree?
Unequal meanings: -1 vs. -3 ≠ -1 vs +1
Affirmative Action Measure
1. Do you favor special hiring consideration for women? .55
2. Do you favor special hiring consideration for minorities? .46 3. Do you favor use of hiring quotas? .72 4. Do you favor employment of affirmative action officer? .56 5. Should affirmative action be written into the Constitution? .23 6. Are opponents of affirmative action bigots? .28 7. Would you not vote for someone opposed to affirmative action? .34
Indentify Latent Constructs as Index of Attitude
Affirmative Action Measure
1. Do you favor special hiring consideration for women? 2. Do you favor special hiring consideration for minorities? 3. Do you favor use of hiring quotas? 4. Do you favor employment of affirmative action officer? 5. Do you favor special affirmative action training for managers? 6. Do you think there should be minimal hiring standards, regardless of
background? 7. Do you think that the human resources department should provide special post-hiring services for women?
Semantic Differential (abridged)
EVALUATIVE DIMENSION
Good Bad
Beautiful Ugly
Sweet Sour
POTENCY DIMENSION
Strong Weak
Large Small
Heavy Light
ACTIVITY DIMENSION
Active Passive
Fast Slow
Hot Cold
Affirmative Action Is:
EVALUATIVE DIMENSION
Good | | | | | | | | | | | | Bad
Beautiful | | | | | | | | | | | | Ugly
Sweet | | | | | | | | | | | | Sour
POTENCY DIMENSION
Strong | | | | | | | | | | | | Weak
Large | | | | | | | | | | | | Small
Heavy | | | | | | | | | | | | Light
ACTIVITY DIMENSION
Active | | | | | | | | | | | | Passive
Fast | | | | | | | | | | | | Slow
Hot | | | | | | | | | | | | Cold
Measure Attitude Behavior
Support for Affirmative
Action Survey
Degree values Affirmative
Action
Votes for Affirmative
Action laws.
IMPLICIT MODEL OF ATTITUDE MEASURES
Problems with Verbal Measures
Response Biases:
1. Social desirability2. Sabotaging
Affected by situations and contexts Salience problem: Ss know that they are being measured.
a. High salience attn, but biasb. Low salience attn but accuracy
Reactivity problem: IV = (IV + Measure) May require atypical depth of processing/introspection May assume that people know own inner states/inner processes more than they actually do.
Cognitive Processing Model of Attitude Reporting
Behavioral Measures
1. Overt behavior 2. Behavioriod
3. Physiological
Advantages of Behavioral Measures
1. More absorbing
2. Require less inference of rel. btwn IV and behavior, b/c measure IS behavior.
3. Tell a better story
Types of Behavioral Measures
Frequency Extent/Amount Speed Intensity Duration Preference Latency Social/Physical Distance Non-verbal Cues and
Expressive Behaviors
Unobtrusive Measures
DV: Distance
DV: Non-Verbal Behavior
DV: Non-Verbal Behavior
Behavioroid Measures
Defined: Measures INTENT to commit the behavior, w/o actually measuring or inducing behavior.
Used when actual behavior is too impractical, unethical, or otherwise inappropriate.
Example of Behavioroid Measure
Freedman and Fraser "Foot in the Door" StudyJPSP, 1966
Behavioroid Measure: Willingness to have 2.5 hour intrusive survey of house conducted by 5 strangers.
a. Asked to complete short questions, and asked: 52.8%b. Asked to complete short survey, but not asked: 33.3%c. Familiarized with questions: 27.8%d. Not previously contacted: 22.2%
Physiological Measures
Defined: Bodily states that reflect psychological states
Examples: Blood pressure, heart rate, skin conductance
Advantages:
Problems:
Not under conscious control
Display mediation
Costly; Intimidating to subjects;
Typically gross, rather than subtle;
Require inference to conceptual DV
Indirect Measures
Measures that imply DV, without directly testing it.
Overt Behavior
Implied Behavior
Physical distance from disabled person
Discomfort
Re-selling price for chosen item vs. given item.
Subjective importance due to perceived control.
Degree of eye contact Affection
Concluding Points Re. DVs1. Which is the better feedback bias measure?
a. Feedback bias = anticipated feedback to minority v. White
b. Feedback bias = verbal comments to minority v. White confed.
2. Which is better measure of hostility to out-group?
a. Amount of shock delivered during “learning” task
b. Physical distance during interview
Aim for actual and behavioral, rather than anticipated and non-behavioral
Expt. DV should be close to conceptual DV.
3. Which is better measure of health after disclosure?
a. Visit MD vs. did not visit MD
b. Number of MD visitsDV should be as precise as possible
FYI: The following slides are “for your interest” only.
They will not be included in the Mid-term.
Scale Value
THURSTONE SCALE
Statement
0.0 1 Affirmative action grossly violates the Bill of Rights.
0.5 2 Affirmative action tends to create more harm than good.
1.0 3 Affirmative action distracts people from real, underlying problems of social inequity
1.5 4 Affirmative action is nice idea, but not the best solution.
2.0 5 Ed. reform will do more good than affirmative action.
2.5 6 Affirmative action can be justified in some instances.
3.0 7 Affirmative action may help remedy hiring inequity in key businesses and regions.
3.5 8 Affirmative action is the way to correct hiring inequities.
4.0 9 Affirmative action should be national policy.
4.5 10 Affirmative action is crucial for a fair and just society.
Subject A: Agrees with 2, 3, & 7 ( 1.5). Mainly anti AA, but sees it can do some good.
Subject B: Agrees with 3, 5, & 6 (1.8). Mainly pro AA, but favors other social remedies.
Ranked Order
PresentedOrder
Statement
A 2 Affirmative action is justified throughout society, due to history of discrimination.
B 3 Affirmative action is justified, but only in industries where patterns of discrimination are indicated.
C 1 Affirmative action is justified only in specific work places in which discrimination has been proven.
D 4 Affirmative action is justified in only the most extreme cases.
Guttman Scale
Guttman Scale Scoring
Score
4
3
2
1
0
X X X X
X X X X
X X X X
X X X X
X X X X
Agrees with item: Disagrees with item:
A B C D A B C D
PROBLEMS WITH GUTTMAN SCALE
1. Too labor intensive to create (90+ judges, etc.)2. Too narrow in focus; effort to precisely determine why and how much people endorse becomes overly exclusive3. Lack of sensitivity between same responses.
1. __ I believe Af. Act. is moral imperative2. __ I believe Af. Act. is needed to move society forward.3. __ I believe Af. Act. is good, but should end soon4. __ I believe Af. Act. had done good, but it's time is up.
Joe and Jody both endorse items 1-4. But for Joe, items 1 and 2 are of equal importance, for Jody 1 is of supreme importance. Guttman can't show this difference.