Jan 10, 2016
College Board - “Acorn Book” Course Description
8-10% (6-8% in past)
Unit 2. Research Methods
Scientific Bases of Psychology
Unit II. Methods3
Summary Outline
Unit II. Methods4
A. Experimental, Correlational, and Clinical Research
1. Correlational (e.g. observational, survey, clinical
2. Experimental B. Statistics
1. Descriptive 2. Inferential
C. Ethics in Research
A. Experimental, Correlational, and Clinical Research
Unit II. Methods5
Testable Hypotheses Operational Definitions Correlational Relationships
“Correlation does not imply causation”
Causal Relationships
A.1. Correlational (e.g. observational, survey,
clinical
Unit II. Methods6
Naturalistic ObservationCase StudiesSurveys Correlational Research
Natural Observation
Professor Wainwright’s painstaking field research to decode the language of bears comes to a sudden and horrific end
Unit II. Methods7
Natural Observation (Handouts)Naturalistic Observation Exercise / by Alan
FeldmanStudents work in teams to observe in public
placesThey observe alone, write up observations,
and compare observations later
Natural Observation in the Real World / by Marissa M. SarabandoStudents work in teams to observe in public
placesThey are asked to make a hypothesis of what
they expect to observe Share the results in classHypothesis supported or not?
Developing an Observation of Behavior Experiment / by Bates Mandel
Students in designated groups spend class timedesigning an observational experiment. Their design should include most of the scientific methodology concepts presented in lecture (hypothesis, control of variables, representative sample, observable activities, quantifiable results, etc.).
Basically the student group should design an experiment which is can either support or refute their hypothesis by either observing the subjects or through a simple questionnaire/interview
Bates provides several examples of experiments used by his students
Students then present a report of their findings to the class
Survey form of natural observation
Widely used to observe attitudes,, opinions, and reported behaviors
AdvantagesTargets specific informationCan gather large amounts of information in a
relatively short timeDisadvantages
Based on subject’s responses which can be distorted due toMisleading answers (Outright lying, bias, etc.)Misunderstanding of the questionPoorly devised questionsPlacebo effect
Survey QuestionsStructured (Fixed Response)
Yes/NoAre you a college graduate?
Multiple ChoiceWhich of the following:Which response describes you
Rating / Ranking questionsRank the following activities from favorite to least
favorite
Non-structured (Open ended)What do you like to do in your free time?
Partially structured (List of choices with other______ )
Survey Question Problems
Yes/NoNo can have many meanings
Have you finished college?Do you still beat your wife?
Range of meanings attached to terms in questionHave you ever been sexually harassed?
Offering irrelevant or inconsistent choicesHaving a choice that is out of place with the other
choices
Misleading information in the questionAre the teachers and students satisfied with
the lunch schedule at your school? (Double barreled / two different questions)
Biased or leading questionsIs the new president more communist than the old
president?
Correlation – Key ConceptsCorrelational research is a form of
observational researchCorrelation does not show causationCausation can only be inferred from the
experimental methodConfusion over the concept of experiment
Casual useUsed to describe demonstations
Confusion over positive vs. negative correlationStatistical methods give us Correlation from
0 to +/- 1
Unit II. Methods15
Correlation CoefficientsPositive CorrelationNegative Correlation
Discussion: Ways to explain and demonstrate this to students.
Source:Worth Psychology Instructors Resource CD-RomTo accompany David G. Myers Psychology 9th ed
Figure 1.2 Scatterplots, showing patterns of correlationMyers: Psychology, Ninth EditionCopyright © 2010 by Worth Publishers
Table 1.2Myers: Psychology, Ninth EditionCopyright © 2010 by Worth Publishers
Height and temperment scores for 20 men
Figure 1.3 Scatterplot for height and temperamentMyers: Psychology, Ninth EditionCopyright © 2010 by Worth Publishers
Insight into Negative Correlation
Unit II. Methods19
Rank order coefficient of correlation - Thomas Nordby Calculating a Rank-order Correlation Coefficient
Activity What I like to do
What the other
person likes to
do
DDifferenc
e
D2
Differenee
squared
Watch TVExercise
Walk in the woodsGo to a moviePlay video games
N = ∑D2=
Rank order coefficient of correlation - Thomas Nordby Calculating a Rank-order Correlation Coefficient
An exercise in computing the rank-order method of computing a coefficient of correlation.
Formula
rs = 1 - 6 (∑D2) N (N2–1)rs = rank order correlation coefficient D = difference∑ = sum ofN = number of characteristics ranked
Experimentation
“No amount of experimentation can ever prove me right, a single experiment can prove me wrong.”
Albert Einstein
Experimental & Control Groups
Unit II. Methods23
A.2. Experiments
Unit II. Methods24
Experimental DesignSelection of Participants
PopulationSampleRandom sampling
Assignment of Participants to GroupsExperimental GroupControl GroupRandom Assignment
Key Ideas in Experiment Design
Unit II. Methods25
Treatment of GroupsVariables
Independent Variable (IV) Dependent Variable (DV)
PlaceboExperimenter BiasSteps to control experimenter bias
double-blind design, etc.
Steps of the Scientific MethodAsk a question
Why does something happen? What is the cause?
Do background researchWho has already studied this? Related studies and ideas.
Form a hypothesisIf “a” then “b” / causal relationship
Test the hypothesis by doing an experimentAnalyze your data and draw a conclusion
Statistical analysis / Accept or reject hypothesis
Communicate you findingsFully report hypothesis, methodology, statistical methodsAllows for informed review and replication
Identifying Independent Variables and Dependent Variables (Handout)
Martin Anderson
For the following statements create an hypothesis (Your hypothesis should, theoretically, be testable). Then identify the IV and DV.
Blondes have more fun.Hypothesis: Changing people’s hair color to blonde will
increase the amount of fun that they have.IV ____________________ DV __________________
A rolling stone gathers no moss.Hypothesis: IV ____________________ DV __________________
A researcher is interested in how the activity level of 4-year-olds is affected by viewing Teenage Mutant Ninja Turtles. He shows one group a 30-minute video of Teenage Mutant Ninja Turtles and another group a 30-minute video of Barney.
IV:______________DV:_______________Experimental group:__________________Control group:_______________________
An Exercise in Designing Research (Handout)
Turn the saying “An apple a day keeps the doctor away” into a hypothesis and design an experiment to test its validity. (This chart can be used to analyze other experiments)
Need to state it as a testable hypothesis and identify the IV and DV
Use the following steps to design or analyze and experiment
Research Methods Martin A. Anderson, Ph.D.
An Exercise in Designing Research
Turn the saying “An apple a day keeps the doctor away” into a hypothesis and design an experiment to test its validity. (This chart can be used to analyze other experiments)
Research Step Your description of the Research Step Form a Hypothesis Hypothesis State the relationship you
expect to find.
The hypothesis needs to be testable. Think in terms of operational definitions.
Pick Subjects Subject Selection Describe the process you
will use to select subjects f or your experiment.
The population is the group you are studying, Your subjects are a sample f rom the population.
Assign Subjects Assignment to Group
Describe how you will divide the subjects into the control group and the experimental group.
The control group and experimental group should be as similar as possible to each other.
I ndependent Variable Experimental Group Control Group Describe your Operational
Definition - How are you going to measure the I V?
This group “gets” the I V.
This group doesn’t “get” the I V. (I t might get a placebo, however).
Dependent Variable Expected Result Expected Result Describe your Operational
Definition –
The DV is the same for both groups. You expect a measurable diff erence between the groups.
How are you going to measure the DV?
Analysis of Outcomes Comparison of Groups How are you going to see if
the groups are diff erent? (You do not need to identif y the exact statistical procedures)
The statistical analysis gives you an idea if the diff erences between the two groups are big enough to be greater than chance.
There are some f actors that might conf use the results of your study. How might you control them?
Research Methods Martin A. Anderson, Ph.D. There are some f actors that might conf use the results of your study. How might you control them?
Experimenter Bias
The experimenter may consciously or unconsciously do things that can aff ect the experiment so that it will confi rm the experimenter’s hypothesis.
Possible sources of Experimenter Bias
Ways to
control f or Experimenter Bias.
Confounding Variables
Variables (other than the variables that are being studied) that can have an aff ect on the outcome of the study.
Possible Confounding
Variables
Ways to control f or Confounding
Variables
Explain Blind and
Double Blind Designs
Blind and Double Blind Designs
Ethical
Considerations
Basic Ethical Principles I nformed Consent (Use of Deception?) Protection f rom harm and discomfort
Confi dentiality of inf ormation about participants Debriefi ng participants af ter the research
Describe how et hical considerations will be
dealt with in the research.
An Exercise in Designing Research Step One: Form an hypothesis
Form an Hypothesis
Hypothesis
State the relationship you expect to find.
The hypothesis needs to be testable. Think in terms of operational definitions.
An Exercise in Designing ResearchStep Two: Pick your subjects
Pick Subjects Subject Selection
Describe the process you will use to select subjects for your experiment.
The population is the group you are studying, Your subjects are a sample from the population.
An Exercise in Designing Research Step Three: Assign your subjects to groups
Assign Subjects
Assignment to Group
Describe how you will divide the subjects into the control group and the experimental group.
The control group and experimental group should be as similar as possible to each other.
An Exercise in Designing Research Step Four: Defining your independent variable
Independent Variable
Experimental Group
Control Group
Describe your Operational Definition - How are you going to measure the IV?
This group “gets” the IV.
This group doesn’t “get” the IV. (It might get a placebo, however).
An Exercise in Designing Research Step Five: Defining your dependent variable
Dependent Variable
Expected Result
Expected Result
Describe your Operational Definition – How are you going to measure the DV?
The DV is the same for both groups.
You expect a measurable difference between the groups.
An Exercise in Designing Research Step Six: Statistical analysis
Analysis of Outcomes Comparison of Groups
How are you going to see if the groups are different?(You do not need to identify the exact statistical procedures)
The statistical analysis gives you an idea if the differences between the two groups are big enough to be greater than chance.
Experimenter Bias
The experimenter may consciously or unconsciously
do things that can affectthe experiment so that it will confirm the experimenter’s
hypothesis.
Possible sources of
Experimenter Bias
Ways to control for
Experimenter Bias.
Confounding Variables Variables (other than the variables that are being
studied)that can have an affect on the outcome of the study.
Possible Confounding Variables
Ways to control for Confounding
Variables
Explain Blind and Double Blind
Designs
Does behavior change when the subjects know they are being observed (Hawthorne effect)
“When Dr. Henderson comes in, everybody play dead.”
Ethical Considerations
Basic Ethical Principles
•Informed Consent (Use of Deception?)
•Protection from harm and discomfort
•Confidentiality of information about participants
•Debriefing participants after the research
Describe how ethical considerations will be
dealt with in the research.
Flawed Experiment (H)(Source unknown) A psychologist wishes to study the effect of a
reinforcement of food on the performance of a fine motor skill involving eye hand coordination. To accomplish this, he had his subjects thread as many needles as possible in a five minute period.
The subjects were divided into two groups: Males Females TotalGroup A 20 30 50Group B 28 22 50
The psychologist explained the tests to each group in the same way. However, she offered Group A a voucher for a free lunch for every 20 needles threaded. After the five-minute time period had expired, he counted the number of needles threaded by each group.
Flawed Experiment The results were as follows:
Total Number of Needles Average Number of Needles Threaded Threaded per Person Group A 80 1.8 Group B 45 0.9
From these results, the psychologist concluded that the reward of food caused Group A to thread more needles that Group B.
What was the independent variable? What was the dependent variable?
Which of the two groups was the control group? Why? Which of the two groups was the experimental group?
Why? How could the following variables negate the psychologist’s
conclusions? Age of the subjects? Sex of the subjects?
How Psychologists Do Research (Handout)
B.1. Descriptive Statistics
Unit II. Methods46
Measures of Central TendencyModeMedianMean
Measures of VariabilityRangeStandard Deviation
Unit II. Methods47
Normal Curve - Normal Distribution68%
Skew – Skewed DistributionsPositive SkewNegative Skew
Creating A Living Frequency Distribution:A Way to Introduce Key Statistical Terms and Concepts (Handout)Martin Anderson
Overview This exercise demonstrates basic statistical concepts.
By forming a “living frequency distribution” based on height, students will gain direct, first-hand knowledge of the following terms and the concepts they represent:
Variable Discrete, Continuous
Nominal Classification Dichotomy / Trichotomy
Continuum Measures of Central Tendency
Median, Mode, Arithmetic Mean Measures of Variability
Range Distribution
Histogram, Normal Curve, Skew, Outlier
Creating A Living Frequency Distribution (2)
MaterialsCardboard sheets for signsMarking pen30’ length of cord (extension cords connected together
work well)Create signs labeled with key terms and
concepts as follows to give to designated students:Median, Mode (best to make several of these), Range
From , Range ToCreate additional signs to indicate various
heights from 4’6” through 6’5”: Time Required
This exercise is easily done in one class period.
Creating A Living Frequency Distribution (3)
Step One: Creating a DichotomyHave students to divide into two groups - tall
individuals on one side of the room and short individuals on the other
Step Two: Creating a ContinuumHave students to line up from shortest to tallest
Step Three: Identifying the MedianHave students count from each end until you
reach the middle
Step Four: Identifying the RangeSimply subtract the lowest score from the highest
score
Creating A Living Frequency Distribution (4)
Step Five: Identifying the Mode Step Five: Calculating Arithmetic MeanStep Six: Demonstrating Normal
Distribution
Creating A Living Frequency Distribution (5)
Step Seven: Demonstrating SkewStep Seven: DiscussionStep Eight: Follow-up
Figure 1.9 A Skewed DistributionMyers: Psychology, Ninth EditionCopyright © 2010 by Worth Publishers
Power point slide from Myers demonstrating skew
Why Variance is ImportantThree sets of scores in which the mean, mode,
and median are the sameo9,4,4,2,1o3,4,4,5,4o4,4,4,4,4
Variance can be thought of as how different scores are from one another
More specifically, variance is how different scores are from one specific score – the mean
Measures of dispersion give us more information about the groups we are comparing
Standard DeviationStandard deviation is computed as the
average distance from the meanThe larger the standard deviation, the more
spread out the scores areJust like the mean, the standard deviation is
sensitive to extreme scores.To get the standard deviation
Find the difference between the mean and each scoreSquare each differenceGet the sum of all the differencesDivide the sum by the size of the sample (-1)Take the square root of the result
Variance is simply the standard deviation squared (variance is a statistic that is used in some calculations)
Table 1.4Myers: Psychology, Ninth EditionCopyright © 2010 by Worth Publishers
Power point slide from Myers demonstrating the calculation and use of the standard deviation
A Three-Dimensional Model of the Normal CurveWilliam E. Addison & Kristine R. Hillman (H)A common problem is conceptualizing
relationships among areas under the normal curve
Students have access to a wooden model of the normal curve.
The model consists of a total of six pieces, two each of three different sections.2 of 34%, 2 of 14%, 2 of 2%
The pieces correspond in relative size and shape to approximate areas delineated by standard deviation units in an empirical normal distribution This helps them to visualize the concept of
symmetry And how the symmetry of the normal curve relates
to concepts such as central tendency, variability, relative standing
Figure 1.10 The normal curveMyers: Psychology, Ninth EditionCopyright © 2010 by Worth Publishers
Statistical Inference
“Not everything that counts can be counted, and not everything that can be counted counts.”
Albert Einstein
2. Inferential
Unit II. Methods60
Evaluation of chance Probability that results are by chance alone
Tests of SignificanceDetermine the likelihood that a specific outcome was obtained by chance alone
Importance of Random Assignment
Unit II. Methods61
Is it Representative? Can we Generalize? Sample / PopulationReplication
Unit II. Methods62
What is “Significance?”Common Usage
ImportantMeaningfuletc.
Term of Art: Statistical Significance ReliableRepeatable
Significance TestingSignificant Result in Research
Not necessarily large or importantNot necessarily dramaticBut probably did not occur by chance
Null HypothesisOpposite of Hypothesis
Hypothesis: Anxiety reduces test performance
Null Hypothesis: Anxiety does not effect test performance.
Significance Testing (continued)
p-level (Probability Level)Probability that your null hypothesis is
correctProbability that the statistic is really zero
Examples:Difference in meansCorrelation coefficient
p < .05 (p < .01)Your null hypothesis has less than a 5%
chance of being rightYou have less than a 5% chance of being
wrong
Prediction andType I and Type II Errors
Variable has an effect
Variable does not have an affect
Deciding that a variable has an
effect
Correct
Positive
Deciding that a variable does not
have an effect
Unit VIII. Motivation and
Emotion65
Prediction andType I and Type II Errors
Variable has an effect
Variable does not have an affect
Deciding that a variable has an
effect
CorrectPositive
Deciding that a variable does not
have an effect
Correct
Negative
Unit VIII. Motivation and
Emotion66
Type I and Type II ErrorsType I Error (false positive)
Deciding that one variable has an effect on (or relationship to another variable) when it doesn’t
Incorrectly rejecting the null hypothesis and accepting the hypothesis
p-level gives us the odds of making this kind of error
Prediction andType I and Type II Errors
Variable has an effect
Variable does not have an affect
Deciding that a variable has an
effect
CorrectPositive
False
Positive
Type I Error
Deciding that a variable does not
have an effect
FalseNegative
Type II Error
CorrectNegative
Unit VIII. Motivation and
Emotion68
Type II Error (false negative)Deciding that one variable does not have an effect on (or a relationship to) another variable when it does
Incorrectly accepting the null hypothesis and rejecting the hypothesis
There is no easy way to estimate the odds of this kind of error
Prediction andType I and Type II Errors
Variable has an effect
Variable does not have an affect
Deciding that a variable has an
effect
CorrectPositive
FalsePositive
Type I Error
Deciding that a variable does not
have an effect
False
Negative
Type II Error
CorrectNegative
Unit VIII. Motivation and
Emotion70
Example ofType I and Type II ErrorsColleges are faced with the decision to
admit or reject applicantsThey wish to accept appropriate applicants
and reject inappropriate applicantsHypothesis 1This student will be successful in collegeHypothesis 2This student will not be successful in
college
Example ofType I and Type II Errors
CollegeAdmission
Student is accepted
Student is rejected
Prediction: student will be
successful
Student succeeds
Correct positive
Prediction: student will not be
successful
Unit VIII. Motivation and
Emotion72
Example ofType I and Type II Errors
CollegeAdmission
Student is accepted
Student is rejected
Prediction: student will be
successful
Student succeedsCorrect positive
Prediction: student will not be
successful
Student would have done poorly
Correct negative
Unit VIII. Motivation and
Emotion73
Example ofType I and Type II Errors
CollegeAdmission
Student is accepted
Student is rejected
Prediction: student will be successful
Student succeedsCorrect positive
Prediction: student will not be
successful
Student fails
Type I Error
Student would have done poorlyCorrect negative
Unit VIII. Motivation and
Emotion74
Example ofType I and Type II Errors
CollegeAdmission
Student is accepted
Student is rejected
Prediction: student will be successful
Student succeedsCorrect positive
Student would have done well
Type II Error
Prediction: student will not be
successful
Student fails
Type I Error
Student would have done poorlyCorrect negative
Unit VIII. Motivation and
Emotion75
ReplicationThis is one reason why experiments must be
replicated.This is how science regulates, and minimizes,
the potential for Type I and Type II errors
Replication is often not possible in medical diagnosis so Type I and II errors are a factor
In the legal system fingerprinting and DNA have a possibility of false positives leading to false convictions.
C. Ethics in Research
Unit II. Methods77
Informed consentMinimize risk and discomfort
Potential benefits must outweigh risk to subjects
Confidentiality DebriefingEthics of animal researchApproval of research committee
Report on a Famous Experiment (Handout)
To research a topic: Select your partner or partners (two-three to a group). More than one group may work on the same topic. However, each report is to be
individual and unique. Identify the author. Check the various texts in the classroom for descriptions of that research. Check the bibliographies of the various texts in the classroom. Write down the specific information from the bibliography so that you will be able
to find this in a library. Get approval from teacher for your topic by having it registered on his/her list.
(Failure to get approval will result in a 10% penalty) Go to an extensive library such as Cal State LA and get a copy of the article. The research you pick may not fit nicely into the categories that I have assigned.
You may alter the report as necessary – but – MAKE SURE THE ALTERATIONS ARE NECESSARY.
Illustrations may include drawings or photographs. The assignment will be due on ___________. Bring the copy of the article to class and use it and the texts in the classroom
during class to work on your projects next week
Following are examples of acceptable topicsResearcher General Area Specific
ResearchAsch Social Group pressure
on judgementsAinsworth Developmental Infant-mother
attachmentBandura Learning Modeling
aggression (Bobo doll)
Gibson & Walk Developmental “The Visual Cliff”
Harlow Developmental “Cloth Monkey”
Loftus Memory “False” memories or memory construction