Download Research Methods - Solon City Schools

Research Methods
It is actually way more exciting
than it sounds!!!!
Move op definitions to hypothesis
Why do we have to learn this
stuff?
Psychology is first and foremost a science.
Thus it is based in research.
Be aware however of two hurdles that tend to skew our
logic when we research
Hindsight Bias
• The tendency to exaggerate
that you knew it all along
Morning
after learning the outcome, Monday
Quarterbacking!!!
• Consider findings to be
common sense
Example: After Solon loses to
Twinsburg, you say “I knew they
were going to lose”
Overconfidence
• Overconfidence –
tendency to think we
know more than we do.
• 82% of U.S. drivers consider
themselves to be in the top 30% of
their group in terms of safety.
• 81% of new business owners felt
they had an excellent chance of
their businesses succeeding. When
asked about the success of their
peers, the answer was only 39%.
(Now that's overconfidence!!!)
Overconfidence
“There
is no reason for anyone to have a computerin their home.” (Ken Olson, president
of Digital Equipment Company, 1977)
“Heavier-than-air flying machines are impossible.”(Lord Kelvin, British mathematician,
physicist, and president of the British Royal Society, 1895)
“Reagan doesn’t have the presidential look.”(United Artists executive when asked
whether Ronald Reagan should be offered the starring role in the movie The Best
Man, 1964)
“A severe depression like that of 1920–1921 is outside the range of probability.”
(Harvard Economic Society, Weekly Letter, November 16, 1929)
“Man will never reach the Moon, regardless of all future scientific advances.” (Lee
DeForest, inventor of the vacuum tube, 1957)
The Scientific Attitude
• Three main components
– Curious
– Skeptical
– Open-minded
Critical Thinking
• Critical Thinking - thinking that does
not blindly accept arguments and
conclusions
– “Smart thinking”
– Four elements
• Examines assumptions
• Detects hidden values
• Evaluates evidence
• Assesses conclusions
– Empirical Approach
Scientific Method
Theory – an explanation of behaviors
or events that have been observed
• Often starts as an hypothesis
• Developed through repeated
observation and testing
• Example: Sleep improves memory
Hypothesis – a testable prediction
• If/Then statement
• Explains what you expect will
happen
• Example: If sleep deprived, then
people will remember less from
the day before
Hypothesis Practice
• A researcher is evaluating the effectiveness of
a new physical education program for
elementary school children. The program is
designed to reduce competition.
• There is some evidence to suggest that
participation in class can have an effect on
human memory. A researcher plans to use a
standardized AP Psych exam to evaluate the
effects of class participation.
Operational Definitions
• Operational Definition A statement that tells a
person clearly
• Meaning of hypothesis
• measure of a variable
• Must be clear and
precise
• Must be measurable
• Allow experiment to be
replicated
• Example:
Participation
The number of times
a person raises
Their hand in class to
answer or ask a
Q question about AP
Psych content
Higher Score A 4 or 5 on the AP
Exam
3Types of Research
• Descriptive
To describe behavior
• Correlational • Experimental
To predict behavior
To explain behavior
3 Types of Descriptive Research
• The Case Study
• The Survey
• Naturalistic Observation
Case Studies
• A detailed picture of one or a
few subjects (with similar
conditions).
• Advantages
– Provides oppty to study unusual
cases in depth
– Offers suggestions for further
study
• Disadvantages
– Results often can’t be generalized
– Can’t establish cause and effect
Example: The ideal case
study was John and Kate.
Really interesting, but are
they typical of all families
Case Study Methodology
– Methodology
• Gather data from one
person (or small group)
through:
– One on one interviews
– Observations
– Testing
– Primary Resources
» Health Records
» School Records
Naturalistic Observation
• Gather data by watch
subjects in their
usual/normal
environment/public
setting
• Advantages
– Use when interference by an
observer may alter results
– May be done when it is not
ethical to manipulate variables
– Does not show cause and effect.
Example: Jane Goodall’s
research on chimpanzees
Survey
• Gather Data – self
reported
beliefs/attitudes
from a large sample
representing the
population
–
–
–
–
Personal facts
Behaviors
Attitudes
Opinions
Survey Method
Method:
•Questionnaire
•Interview
•
Can be Descriptive or Correlational
• Advantages:
– Use to gather data about a large population
– maintain anonymity
–Cheap and fast
• Disadvantages:
–Does not prove cause and effect
Example:
1.On ave. how many hours do you study per night?
2.What is your grade point ave?
Conducting a Survey
• Population - all the possible subjects
in a group you want to study
• Example: men and women 18-80
• Random Sampling – a portion of the
population that fairly represents the
population because each person has an
equal chance of getting chosen
 Ensures that the participants are
representative of the larger
population
• Helps avoid false generalizations
• Survey must have random sample to be
scientific
• Example: Use of a random computer
generator to select 1000 people in the
phone book for a survey to be sent to.
Survey Method: The Bad
1. Low Response Rate
2. Response Bias/social
desirability bias respondents answer
questions in a way that will
be viewed favorably by
others (See example left)
3. Wording Effects – subtle
changes in the order or
wording of questions can
have a major effect
How accurate would a survey be
about the frequency of diarrhea?
Wording Effects
• Do you think it is • Do you think it
important for
is important for
America to
America to
provide aid to
provide welfare?
the needy?
• Should the
• Should the
government
government
allow televised
censor cigarette
cigarette ads?
ads?
Think Pair Share
1. A researcher wants to investigate people's
attitudes toward violence on television.
Explain which of the following research
methods the researcher should use and why:
case study, survey, or naturalistic
observation.
2. A researcher wants to investigate sharing
behaviors of young children. Explain which
research method the researcher would use
and why. Provide a brief explanation on how
the research would be conducted.
Correlational Method
• Correlation - expresses a
relationship between two variables.
– Measures how well one variable
predicts the other
• Advantages
– Used when ethics prohibit
experimentation
– Can be efficient
– Can make predictions
– Can use pre-existing or archival data
• Disadvantages
– Make it difficult to assess the impact
of a third variable
– Does not show causation
As more ice cream is eaten,
more people are murdered.
Does ice cream cause murder,
or murder cause people to eat
ice cream?
Eating organic food causes autism.
A pirate shortage caused global
warming.
Results of Correlational
Studies
Positive Correlation
• The variables go in
the SAME direction.
Example: Studying and
grades hopefully has a
positive correlation.
Negative Correlation
• The variables go in
OPPOSITE directions.
Example: Heroin use and
grades probably has a
negative correlation.
Correlation Coefficient
Which is a
• Correlation Coefficient - A statistical
stronger
measure for Correlational Studies that
correlation?
measures the relationship between 2
• -.13 or +.38
variables.
• -.72 or +.59
• -.91 or +.04
• Range is from -1 to +1
– The relationship gets weaker the closer you
get to zero.
– (+) tells you the variables are going in the
same direction
– (-)tells you the variables are going in the
opposite direction
Think Pair Share
Which of the following would be a negative
correlation, and which would be a positive
correlation?
Education and years in jail
Weight and hours of TV watched
Education and income
Holding babies and crying
Food and calories ingested
•Scatterplot – a visual
representation of the
relationship between
the variables
– shown as a graphed
cluster of dots
Which of the following would be a
negative correlation, and which
would be a positive
correlation?
Education and years in jail
Weight and hours of TV watched
Education and income
Holding babies and crying
Food and calories ingested
Correlation
Correlation
Correlation
The table below lists the scores of eight research participants on a test to
measure anxiety, as well as the typical number of cigarettes each person
smokes daily. Scores on the anxiety test can range anywhere from a low of 0
(indicating very low anxiety) to a high of 30 (indicating very high anxiety).
Research
Participant
1
2
3
4
5
6
7
8
Anxiety
Cigarettes
Test Score____________
8
11
9
3
15
11
14
16
21
26
12
10
22
24
17
18
Construct a scatterplot to represent the correlation between smoking and
anxiety. Describe the direction of the correlation and give two possible
explanations for it.
Correlation
Illusory Correlations
• Illusory Correlation
–Perceived non-existent
correlation
–A random coincidence
Think Pair Share
• Speaking at a college graduation ceremony, Professor
Robson compared college graduates with adults who
are less educated. She correctly noted that college
graduates pay more taxes, vote more frequently,
engage in more volunteer activities in their
communities, and are less likely to go to jail than
less-educated adults. The professor concluded that
colleges obviously do great things for society. How
might you reasonably challenge the way the
professor reached her conclusion?
Experimental Method
• Experiment - Manipulation
of one or more variables
Advantages:
• Shows cause and effect
• Can verify results
• Can eliminate bias
• Disadvantage: Time and $
Smoking causes health issues.
Population and Sampling
• Theory/Hypothesis – always
• Population – all possible participants in the
experiment
– the group that you can choose your subjects from
(all SHS high school students, 5 period S.H. )
– This is the group you will generalize your results
too
• Sample – a subset of the population that you
will test
– N = sample size
– Usually not random, but can be
Independent Variable
• Independent Variable
- Whatever is being
manipulated in the
experiment.
• What changes in the
experiment
• Levels of IV – the
two conditions you
are comparing (ie.
drug and placebo)
Example:
Participation
If there is a drug in an
experiment, the drug is
almost always the
independent variable.
Dependent Variable
• Dependent Variable Whatever is being measured
in the experiment.
Example:
• It is dependent on the
•Score on the AP Exam
independent variable.
The dependent variable
would be the effect
of the drug.
Hypothesis and Operational Definitions
• Study: A scientist wants to study whether people
who make more money are happier
• Identify:
– Hypothesis If people make more money then they will be happier
– Operational Definitions
• IV Money is defined as > than $70,000/year
• DV Happier is defined as greater than 6 on a happiness scale
• Study: A scientist wants to study whether or not
people who drink become more aggressive. Identify
the following:
– Hypothesis If people drink alcohol, then they will become aggressive
– Operational Definitions
• IV Alcohol is defined as 2 or more 4oz alcoholic drinks
• DV Aggression is any aggressive act on a checklist ie. Kicking, biting ,
punching, yelling
Assignment
• Random Assignment
•
– Assigning participants in an
experiment to experimental and
control groups by chance
– Each person has an equal chance of
being assigned to either group
– Minimizes any preexisting
differences between groups
Examples:
Experimental - The group
that gets to participate
Control group – The group
that does not get to
participate
• Helps to insure the groups are equivalent
– Different than Random Sample
• Experimental Group – the group that’s
exposed to the treatment
• Control Group – the group not exposed
to the treatment
Beware of
Confounding Variables
• Confounding Variable A factor other than the
independent variable
that might produce an
effect on the
experiment
• Confounds often arise
due to differences
between the groups that
exist before the
independent variable is
imposed!
Examples:
motivation,
eagerness to
please, lifestyle,
age, intelligence,
experimenter bias,
placebo effect
(
2 important confounding
variables
• Experimenter Bias - expectations by the
experimenter that are subtly communicated
to the participants
– Example: - Experimenter knowing groups
& wants his drug to do well
• Placebo effect – an experimental effect
caused by expectations of participants or
caused by a substance which the recipient
assumes is the independent variable but is
not
– Example: A drug that has no effect is
assumed to be the drug that has an
effect
Double-blind Procedure
• Double Blind - Both the
researcher and the
participants are ignorant
about who is receiving the
treatment and who is
receiving a placebo ( a dummy
medication)
• Minimizes placebo effect and
experimenter bias
Replication
• Replication - Repeating
the research study to
see whether the basic
finding extends to other
participants and
circumstances.
• What helps the
researcher to insure the
study can be replicated?
Drawing Conclusions
• Only in Experiment – variables have
been manipulated
• Must have Random Assignment
• Results must be Statistically Significant
– Statistical measure that indicates the
results occurred due to the IV and NOT by
CHANCE
Quasi-experimental
• Quasi-experimental
No random
assignment
• Used to study
differences
between:
– men and women
– Boys and girls
– Young and old
• Confounding
variables so no cause
and effect
Controlled Observation
• Controlled
Observation - Type
of Observational
Research
– Conditions are
contrived by
researcher
– Measuring something,
but no IV
– Does not show cause
and effect
• Early Psych
Research
APA Ethical Guidelines for
Research
• IRB- Internal Review
Board
• Both for humans and
animals.
Animal Research
•
•
•
•
Clear Purpose
Acquired legally
Least Suffering
Treated Humanely
Human Research
•
•
•
•
Confidentiality
No Harm
Informed consent
Debrief
Statistics
• Recording the
results from our
studies.
• Must use a common
language so we all
know what we are
talking about.
• 2 Types:
– Descriptive
– Inferential
Descriptive Statistics
• Descriptive Statistics numbers that
summarize a set of data
obtained from a sample
Frequency Polygon
– describes sets of data.
• Examples:
• Frequency Distribution
(orderly arrangement of
scores) –see ex. left
• Measures of Central
Frequency Histogram
Tendency
• Measures of Variance
Measures of Central Tendency
• Mode - occurs the most
• Mean - arithmetic average
• Median - middle score
Central Tendency
• Mean, Median and Mode.
Let’s look at the salaries of the
employees at Dunder Mifflen Paper
in Scranton:
$25,000-Pam
$25,000- Kevin
$25,000- Angela
$100,000- Andy
$100,000- Dwight
$200,000- Jim
$300,000- Michael
The median salary looks good at $_______________________ 100,000
The mean salary also looks good at about $________________ 110,000
But the mode salary is only $___________________________ 25,000
Watch out for extreme scores or outliers.
________________
is a better measure than
Median
the mean when there are extremes/outliers
Normal Distribution
• In a normal
distribution, the
mean, median and
mode are all the
same.
Examples:
Height, Weight, IQ Scores
Distributions
• Outliers skew
distributions.
• Positive Skew – most
scores on the low end
• Mean is higher than
median, so median
better measure of
central tendency
• Negative Skew – most
scores on the high end
• Mean is lower than
median, so median
better measure of
central tendency
If most students scored well on a
test, what would the distribution look
like?
If most students scored poorly?
What does the data tell us?
Measures of variability
• Range: distance from highest to
lowest scores.
• Standard Deviation: the variance
of scores around the mean in the
same units as the mean
Shaq and Kobe
• The higher the variance or SD, the may both score
more spread out the distribution is. 30 ppg (same
mean).
• Do scientists want a big or small
But their SDs
SD?
are very
different…mea
• Variance - The average of the
ning?
squared differences from the mean
– In an experiment the less variable the
data is, but in squared units, the more
reliable
Calculating Standard Deviation
Step 1 – calculate the mean –
add all of the raw scores and
divide by the # of scores
Step 2 – calculate the deviation
from the mean by
subtracting each of the raw
scores from the mean
Step 3 – square the deviation
from the mean for each
score
• Step 4 – Sum the squared
deviations
• Step 5 – divide the sum of
the squared deviation by the
number of scores and find
the square root
Calculating the Standard
Deviation
Calculating the Standard Deviation
your turn
Scores – 10, 3, 7, 8, 7
Step 1 – calculate the mean – add
the all of the raw scores and
divide by the # of scores
Step 2 – calculate the deviation
from the mean by subtracting
each of the raw scores from the
mean
• Step 3 – square the deviation
from the mean for each score
• Step 4 – Sum the squared
deviations
• Step 5 – divide the sum of the
squared deviation by the number
of scores and find the square
root
35/5 = 7
10-7 = +3, 3-7 = -4, 7-7 =0,
8-7= +1, 7-7=0
3x3=9, 4x4=16, 0x0=0,
1x1=1, 0x0=0
9+16+0+1+0 = 26
26/5 = 2.28
Variance
• Variance - The average of
the squared differences
from the Mean.
• = Standard Deviation2
• Tells you the same thing as Standard
Deviation—how consistent/reliable
the data is
• Example:
Standard Deviation = 5
Variance = 25
• *if you know the variance, how can
you calculate the standard deviation?
Scores
• Z Scores - A unit that
measures the distance of a
score from the mean in
units of standard
deviations
• Observation – Mean
Standard Deviation
• 10-15 = -1
5
• Equals 0 at the mean
Example: If John scored a 72 on a test • A positive z score =
with a mean of 80 and a standard deviation number above the mean,
of 8, John’s z score would be
negative z score = number
-1
below the mean
Z Scores
Jack had an ACT score of
30 and Jill had an SAT score
of 690. Which student had
the better score?
Jack's ACT score was
1.71 standard
deviations above the
mean ACT score.
Jill's SAT score was 1.75
standard deviations above the
mean SAT score. Comparing
the standard scores, Jill's score
of 1.75 is slightly better than
Jack's score of 1.71.
Normal Distribution
What is the probability an observation is less than the
z score or more than the z score?
Normal Distribution
Calculating the probability that scores are
above or below the mean
Step 1 – calculate the mean
Step 2 - calculate/find the standard deviation
or variance. If you only have the variance you
must calculate the standard deviation
Step 3 draw a normal distribution curve and
find the scores for each standard deviation
from the mean and place them on the graph
Step 4: calculating the % of students who
scored within a range of scores by finding the
corresponding scores on the curve, then add
the percentages from each standard
deviation.
Inferential Statistics
• Inferential Statistics – using the
properties of the sample data to deduce
the properties of the population
– The purpose is to discover whether the finding
can be applied to the population
• Statistical Significance – determines
whether the difference in the means of
your control group and experimental group
occurred because of some fluke/ chance
rather than the dependent variable
• Measured by P-value= .05
– 5% likely the results are due to chance or
– 95% confidence level the results are due to the
independent variable
– You can apply the findings to the population
•
•
What does a p-value= .80 mean?
that you are only 20% confident the difference in means is due
to the independent variable
Statistical Significance
Key Ideas
• The bigger the difference between groups the less
likely it’s due to chance (regardless of sample size)
• Sample size matters. This is known as the "law of
large numbers."
– The larger the sample size, the smaller an
observed difference has to be in order to be
statistically significant.
– The smaller the sample size, the larger an
observed difference would have to be in order to
be statistically significant.
– Small sample, small difference not likely to be
statistically significant
Descriptive vs. Inferential Statistics
• Descriptive
• Inferential
– used to describe summarize a – Help researches draw
conclusions from data
data set
– Statistical Significance
– Make use of averages
• Mean
• Median
• Mode
– Address dispersion – how
widely the individual data
points are likely to be from
the mean
• Standard Deviation
• Variance
• P < .05
– Answers:
• Did the results occur by
chance?
• Did the independent
variable cause changes in
the dependent variable?
• Should the Hypothesis be
supported or rejected?
• Can I apply my findings to
the general population?
Practice
• Mr. Kopkas gave an AP Stats test. The Mean
on the test was a 50 with a standard deviation
of 12. Kurt scored a 23 on the test. What was
his z score? What was the variance on the
test?
• What percentage of students scored between
a 38 and 74?
Culture
• Culture – shared ideas, behaviors and
attitudes and traditions that are passed
from one generation to the next
– Example:
• Feelings of loneliness differ across cultures,
but in all cultures loneliness is demonstrated by
shyness and low self-esteem
• Hypothesis:
Milgram’s Study
– If individuals are in the presence of an authority figure, then they
will obey the authority
• Population
– All Males from New Haven/Yale Area
• Sample
– 40 males, ages 20-50 from New Haven Area
• IV
– Proximity of experimenter to teacher
– Op Def: Experimenter will stand 10’ from teacher in the same room
to or speak commands over the phone from a second room
• DV
– Level of Shock
– Op Def: record the maximum level of shock (up to 400 volts)
• Random Assignment: Not conducted so confounding
variables
Milgram’s Experiment
• Criticized for
deceiving “teachers”
and subjecting them
to stress
• Violating “No Harm”
• 65% of participants
followed the orders
to the maximum
shock level
Milgram’s Experiment
• Obedience High
– Experimenter in close
proximity to
“teacher”
– Learner placed in a
different room
– Experiment
associated with
prestigious location
(Yale)
• Obedience Lower
– Experimenter out of
the room giving
orders over a phone
– Other “teachers”
observed other
participants refuse
orders
– Experiment not
associated with
prestigious location