-
Causal VS Correlational
Causal=(one thing caused another)
- Correlational = (Just look if two things
- are related, cannot determine if one event actually triggered/caused another) –
- ex: Grades/TV
-
Describe Annectodal
One persons story/experience with the situation.
-
Illusory Correlation
- Illusory correlation: A belief where a
- relationship exists when in reality it does not.
Ex: horoscopes
-
What 3 things does the scientific attitude involve?
- Curiosity
- - passion for field.
- Sketicism
- - ask questions
- Humility
- - Study may be falsified through peer review
-
What is pseudoscience?
- Vague claims
- Preconceived ideas
- Not testable
-
What are the four general goals of science?
- Description of behavior
- Prediction of behavior
- Determine cause of behavior
- Explanation of behavior
-
What 3 things must occur to be able to determine cause (causality)?
- Temporal Precedence
- --(cause comes first, then effect)
- Covariation of the cause & effect
- in exp observe when cause is present effect occurs and when it is not present it does not occur.
Elimination of alternative explanations
-
What are basic and applied research?
Basic research = research used to gain more facts
applied research = research used to gain more facts and applying it to help someone
-
What is a major area of applied research?
Program Evaluations
Ex: DARE we found to be counter intuitive
-
What is a hypothesis?
A testable prediction often implied by a theory.
-
If our hypothesis was incorrect you state that by saying:
Our hypothesis was rejected...
-
Null Hypothesis
Want to be able to prove that two things to don't impact one another. To prove the hypothesis wrong.
-
What are the 5 main sources of ideas?
- Common Sense
- Observation of the World Around Us
- Theories
- Past Research
- Practical Problems
-
1 - 10 Write out the entire ______
> 10 Write out the entire _______
Exceptions:
Exceptions: Percentages always use #'s, Beginning of sentences, ages, numbers of measurements, sample size (mean median mode)
-
What are the 5 sections research articles contain?
- Abstract(summary of hypothesis, procedure,results)
- Introduction Outline pro-Past research-theories- ur hypot
- Methods detailed subs(participants,Mater, and Procedure)
- Results (Narrative form, stat language, and tables/graph)
- Discussion (results sup hyp? Results/past Res. Future res/ suggestions)
-
PsycInfo contains articles dated back in the _____/
1800s
-
What does SSCI stand for?
What is it for?
- Social Sciences Citation Index
- Allows you the ability to use the key article method
-
What should you look for in online articles?
Is web associated w/ major educational institution research organization?
- Is info provided on the people who are responsible for the site?
- Can you check the credentials of these individuals?
Is information current?
-
Stanley Milgram Study
Year:
Study:
Gender:
Age Group:
# of Participants that went to last switch:
What was the voltage for last switch:
Another word for Participants:
1960s
Measured if authority figure could get people to comply to a demand to hurt another by using pressure.
- 40 Diverse Male individuals ages 20- 50yo
- 460 Volts
- Confederate (fake participant)
-
Variable must...
have at least two levels.
Ex: age, gender, time etc
-
operational definition =
a definition of the variable in terms of the operations or techniques the researcher uses to measure or manipulate it:
-
Construct validity
What are the indicators of construct validity?
- Construct Validity = the degree to which a measurement device accurately measures the theoretical construct it is designed
- to measure
aka: It is measuring what it says it is measuring
Face Validity – (Just going with your gut feeling and the measure appears to measure what it is supposed to measure.)
Content Validity – (Make sure to check how other people are defining what you are a about to define.)
Criterion-Oriented Validity:
-
Positive linear Relationship:
Negative Linear Relationship:
Curvilinear relationship:
No Relationship:
Positive linear Relationship: Both increase or both Decease
Negative Linear Relationship:1 Inc. & 1 Dec or 1 Dec & 1 Inc
Curvilinear relationship: Increase then becomes decrease
No Relationship: None of the above.
-
Pearson Correlation Coefficient
Scale ranges from...
- Measure how strongly two variables are related.
- -1 --> +1
-
Research is aimed at reducing.... by.....
Random variability: (uncertainty abt relationships btwen variables)
By:Identifying systems between relationships
-
What are the two approaches to the study of relationships amongst variables?
- Nonexperimental (aka: Correlational Method): JUST OBSERVING RELATIONSHIP BETWEEN TWO VARIABLES. NOT A TRUE EXPERIMENT.
- ** Nonexp: allows us to observe covariation (aka correlation) between two variables but DOES NOT measure cause and effect
Experimental: 1 Variab. Manipulated & 1 Not = then Measure to determine if causal relationship exists
-
Which group receives the treatment and which group does not and is the comparison group?
- Treatment = Experimental
- No treatment = Control group
-
Independent variable = Variable being manipulated
Dependent Variable = Variable being measured
Where is the IV & DV plotted on a graph?
- Ex: Caffine vs Bloodpressure
- IV = Caffine
- DV = Blood Pressure
-
Validity = Truth / Accurate representation
Three types of Validity
Construct Validity
Internal Validity
External Validity
1) Construct validity = the degree to which a measurement device accurately measures the theoretical construct it is designed to measure.
- 2) Internal validity =
- the certainty with which results of an experiment can be attributed to the manipulation of the IV rather
- than to some other, confounding variable
- 3) External validity = the degree to which the
- results of an experiment may be generalized
- to other populations and settings.
Ex: Too small of a sample size can effect external validity (ask 5 ppl about tuition increase & generalize that to whole population)
- Solution:
- random sample and large enough to be representative for the whole population.
-
Extraneous Variables
Confounding Variables:
-
Reliability =
the degree to which a measure is consistent
ex: scale example = a reliable scale/test does not show much variability (change)
-
We can assess the sability of a measure using?
Symbolized by:
A correlation of 0 =
When negative =
- Pearson Correlation Coeficcient: -1 0 +1
- r
- 0 = Two variables not related
- When negative = there is a negative linear relationship
-
Methods of assessing reliability:(6)
For measure to accepted as reliable it has to be at least 80%
- Test-retest Reliability:
- A reliability coefficient determined by the correlation between scores on a measure given at one time with scores on the same measure given at a later time
- Alternate Forms Reliability
- is sometimes used and involves administering 2 different forms of the same test (to the same people at two points in time)
- Internal Consistency Reliability = Reliability
- assessed with data collected at one point in time with multiple measures of a psychological construct
- Split-Half Reliability
- You could determine the correlation between the total score on ½ the measure with the total score on the other ½ of the measure
- Cronbach’s Alpha
- another indicator of internal consistency reliability. (Cronbach Alpha compares every single item to seeif it is measuring same thing.)
- Inter-rater Reliability = An indicator of reliability that examines the agreement of observations made by 2 or more raters.
- e.g., Linda & Mike observe/record Billy’s
- aggressive behavior on the playground
-People make mistakes. At least 2 raters. Interobserver Reliabilty ( IOA)
-
Anecdotal Evidence:
One person’s experience / story
-
Illusory Correlation:
Belief of a relationship when one does not exist. OR belief in astronger relation THAN does exist.
-
Peer– review process:
Other ppl have read your research and agree on your research and methodology. Once accepted ~year later its publish.
-
What are the goals of science? (if listed out make sure you could recognize
them)
- Description of behavior
- Prediction of behavior
- Determine cause of behavior
- Explanation of behavior
-
What 3 things must happen to determine causal relationship?
1. Temporal Precedence: Cause must proceed effect
- 2. Covariation of Cause & effect:
- when cause is present effect occurs
- 3. Elimination of all others- Difference between basic research & applied research (ex: program
- evaluation DARE)
-
- Difference between basic research & applied research (ex: program evaluation DARE)
-
How do you correctly word a hypothesis?
- A hypothesis can be supported or rejected
- by the research
- We never say “we have proven” or “we proved” because there can be a level of
- error.
- Use
- If hypothesis was correct we say:
- “Our research supported our hypothesis”
- If our hypothesis was incorrect you state that by saying “our hypothesis was
- rejected..”
-
What is included in the anatomy of research article?
- Abstract
- Intro
- Method
- Results
-
Difference between PSYCINFO & PSYCARTICLES
PSYC Info: Computer based, Put out by American psychological association, only shows abstracts, then can be sent to full text if available.
PSYCArticles: Can get full text articles
-
What is social science index?
- Allows you to do key article methods
- It gives you a list of all articles that sited that article which you searched.
-
Zimbardo Prison Study
Year
Location:
Participant Makeup:
Length of Exp:
Why was it ended early?
- 1971
- Standford Basement
- Male College Students
- Assigned roles = Guards psychological toture
-
Belmont report reflects:
Define Beneficence:
Define Autonomy:
Reflects APA ethics code.
Beneficence: Principle that research should have more beneficial effect and minimal harmful.
- Autonomy: principles of individuals can make decision to
- participate or not. NEED INFORMED CONSENT. – Need signature – Minors cannot consent/mental retardation/major mental illnesses like schizophrenia. Parents must consent for child and then child
- must give assent.
-
Is it ok to use Deception:
What is IRB –
Deception: Still ok to use – but should be the last resort – and debriefing must be done ASAP – Access to professional help.
IRB – Institutional review board: reviews research and approves it or not – one member from outside source
-
Differences between lab & field research
Lab research: greater control over extraneous variables.
Field research: We might lose control but responses may be more authentic
-
Interval Scales:
Ratio Scale:
Ordinal Scale:
Nominal Scale:
- Interval Scales:involves meaningful and equal differences between the values on the scale (things with NO true zero)
- ex:e.g., temperature, Elevation -- Time --
- Ratio Scale:involve an absolute zero point that indicates the absence of the variable being measured. ( it CAN HAVE a true zero)
- Ordinal Scale:involve rank ordering (and numerical values are limited not precisely measurable)
- ex:movie ranking - One star, Two stars, Three stars, Four stars Freshman, Sophomore, Junior, Senior.
Nominal Scale:involve categories (and have NO numerical or quantitative properties)
-
Give an example of each of these:
Naturalistic Observation:
Systemic Observation:
Case Study:
Archival Research:
Systematic observation: usually in lab & already have hypothesis generated.
Case study: Usually conducted if someone possesses a rare trait.
Archival research: No need for informed consent * how to we know if data is reliable.
-
The Belmont Report outlined what 3 basic ethical principles:
- Beneficence
- Autonomy
- Justice
-
Tuskegee Syphilis Study, in which ___ poor
African Americans in ______ were not
treated for syphilis in order to track the long-term effects of the disease even after _______ was discovered.
- 399 of 600
- Alambama
- Penicillin
-
Types of criterion-oriented validity: (4)
- 1) Predictive validity – scores on the measure predict behavior on a criterion measured at a time in the future eX: students who score high on LSAT it also reflects on their grades.
- 2)Concurrent validity – scores on the measure are related to a criterion measured at the same time.
- ex: ppl score high on shyness scale & also score high on stress response in social setting.
- 3) Convergent validity – scores on the measure are related to other measures of the same construct. Ex: when ppl score high for depression they also score high on another consctruct for depression.
4) Discriminant validity – scores on the measure are NOT related to other measures that are theoretically different.
|
|