is psychology a science? · fortune telling, numerology, graphology, and astrology are not part of...
TRANSCRIPT
IS PSYCHOLOGY A
SCIENCE?
What is Psychology?
The Science of Psychology
What Psychologists Do
Critical and Scientific Thinking in Psychology
Descriptive Studies: Establishing the Facts
Correlational Studies: Looking for Relationships
The Experiment: Establishing Causes
Evaluating the Findings
IS PSYCHOLOGY A
SCIENCE ?
Defining Psychology
Psychology is a discipline concerned with the
study of behaviour and mental processes
and
how they are affected by an organism's:
physical state,
mental state,
and external environment
Scientific psychology has four
basic goals:
to describe
to explain
to predict
to change behaviour and mental
processes
HOW DO WE KNOW WHAT
WE THINK WE KNOW
IS TRUE?
Bordens and Abbott (2008)
Three types of explanation of human behaviour
Common sense Belief based Pseudoscience
Experience Religion Presented as scientific
but not
Intuition Political Vague
Not tested Personal Not reproducible
Consistent with a
framework of beliefs
Minimal evidence in
support of claims
Can we trust our common sense?
Do you think the following are true?
Birds of a feather
flock together
Absence makes the
heart grow fonder
Two heads are
better than one
Action speak louder
than words
Opposite attract
Out of sight, out of
mind
Too many cooks
spoil the broth
The pen is mightier
that the sword
Psychology is common sense
We learn and remember best
when we study intensively
over a concentrated period
Advertisers often use
subliminal persuasion to
influence our behaviour.
Punishment is the most
effective way to permanently
change behaviour
The more people present at
an emergency, the more likely
it is that at least one of them
will help.
Eyewitness testimony is the most
reliable kind of evidence
Most people use only about 10%
of their brain capacity
All people with dyslexia see words
backward (tac-cat)
In general, it’s better to express
anger than to hold it in.
The lie detector (polygraph) test is
90-95 % accurate at detecting
falsehoods.
People tend to be romantically
attracted to individuals who are
opposite to them in personality
and attitude
Well actually….
None of these statements are true, even if you
think they make sense.
In fact…..(see next slide)
Beliefs and intuitions
The idea that our beliefs and intuitions, are enough to answer questions about human nature is false.
Beliefs and intuition may help us to know what questions to ask, but they are not free from mistakes
We cannot rely on intuitions alone…….
Hindsight bias
The tendency to believe, after learning about
an outcome, that we would have foreseen it.
HINDSIGHT BIAS
When drilling the Deepwater
Horizon oil well in 2010, oil
industry employees took some
shortcuts and ignored some
warning signs, without
intending to harm any people,
the environment, or their
company’s reputation.
After the resulting Gulf oil spill,
with the benefit of 20/20
hindsight, the foolishness of
those judgments became
obvious.
Tendency to believe, after
learning an outcome, that
we could have predicted it.
Also known as the
I-knew-it-all-along
phenomenon.
Did We Know It All Along?
Hindsight Bias
Overconfidence in judgements
We may think we know more than we actually do (occurs in both academic and social behaviour)
How long do you think it would take to unscramble these anagrams?
People said it would take about 10 seconds, yet on average they took about 3 minutes (Goranson, 1978).
Anagrams
BARGE GRABE
ENTRY ETYRN
WATER WREAT
Psychology, Pseudoscience, and
Common Sense
Scientific Psychology bears little relationship to "Pop" Psychology
Fortune telling, numerology, graphology, and astrology are not part of psychology
Psychology is not just a fancy name for common sense
Psychological research often produces findings that contradict popular beliefs
CRITICAL AND
SCIENTIFIC THINKING IN
PSYCHOLOGY
Critical Thinking
Critical Thinking: The ability and willingness to
assess claims and make objective judgments
on the basis of well-supported reasons and
evidence, rather than emotion or anecdote
Critical Thinking Guidelines
Ask Questions: Be willing to wonder
Define Your Terms
Examine the Evidence
Analyze Assumptions and Biases
Avoid Emotional Reasoning
Don't Oversimplify
Consider Other Interpretations
Tolerate Uncertainty
What is science?
• Body of systematic knowledge that covers
general truths, principles and laws.
• Knowledge is found and tested using ‘scientific
methods’ – systematic process designed to
obtain objective information.
• Based on observable phenomena not opinion
What are the characteristics of a
scientific approach?
Must :
have a unified paradigm (a model for how to proceed)
use a scientific process for devising theories and testing hypotheses
test hypotheses empirically (experimentally)
be replicable and valid (discussed later)
generate findings that are generalizable and applicable to be of some use.
The role of paradigms
• A paradigm is a shared set of assumptions about the subject matter of the discipline and the methods used to study it.
• Kuhn (1996) claimed that psychology does not have a unifying paradigm – many different ones used e.g. • Psychoanalytic
• Behavioural
• Cognitive
• Neuro-biological
• Revolutions in thinking can cause a paradigm shift
• Many different paradigm shifts have already taken place in psychology
Paradigms change
Psychology is a
science
Science does not
develop continuously
and smoothly
Kuhn suggests that
this happens through
paradigm shifts
Paradigm shift
Unconscious
Drives
Urges
Introspection
Environment
Stimuli
Experiences
Empiricism
From psychoanalysis To behaviourism
Theory A theory is an explanation that integrates and organizes
principles and observations and predicts behaviour or events
A hypothesis is a testable prediction, arising from the theory, which enables us to accept, reject or revise the theory
An operational definition is a carefully worded statement of the exact procedures (operations) used in a research study
A replication is repeating the essence of a research study, usually with different participants in different situations, to see whether the basic finding extends to other participants and circumstances
The Scientific Method: how do theories advance
psychological science?
Theory
An organized system of assumptions and
principles that tries to explain a specified set of
phenomena and their interrelationships.
Principle of Falsifiability
The principle that a scientific theory must make
predictions that are specific enough to allow the
possibility that the theory can be shown to be untrue;
that is, the theory must predict not only what will
happen, but also what will not happen.
Principle of falsifiability & Freud
According to this principle Freudian „theory” is NOT a real „theory, because it can never be proved to be false.
Predictions in Freudian „theory” are very „woolly” and untestable
If something does not fit the theory, Freudians merely expand the theory to make it fit. They never reject any ideas which do not fit.
Freudian „theory” is not a theory because it cannot be tested to verify if it is true.
The Scientific Method: Constructing
Theories
Hypothesis
A statement that attempts to predict or to account for a
set of phenomena; scientific hypotheses specify
relationships among events or variables and are
empirically tested allowing the theory to be accepted,
rejected or revised.
Induction and Deduction Scientists use logic to
induce and deduce valid
conclusions
Induction
Moving from data to a
general theory of concept
Specific to general
Deduction
Moving from a theory to
particular statements
concerning data
General to specific
Data
Theory
Induction Deduction
The scientific process – Theory
construction and hypothesis testing
Observations Observations
Testable hypothesis
Conduct a study to test the hypothesis
Draw conclusions
Propose theory
Propose theory
Testable hypothesis
Conduct a study to test the hypothesis
Draw conclusions
Induction Deduction
Hypothetico-deductive method
Karl Popper (1935) – Philosopher of Science:
to be properly scientific, theories need to be stated first
and these should be used to generate expectations or
hypotheses which are capable of being falsified.
Falsification is the only way to be certain – as Popper
pointed out:
‘No amount of observations of white swans can allow the
inference that all swans are white, but the observation of a
single black swan is sufficient to refute that conclusion’
Hypothetico-deductive method
Identify a problem
Develop a hypothesis –
predictable and testable
Devise a study to
test the hypothesis
Analyse and
evaluate the results
Modify and repeat the
process
Develop a theory
Empirical Evidence
Evidence gathered by careful observation,
experimentation and measurement.
Empirical Testing
• Empiricism is the idea that knowledge is based on ‘direct experience’ and experimentation
• arguments, beliefs, ideas, hearsay, faith or superstition, however rational or logical, will not reveal true knowledge
• Experimental science – testing ideas - is the paradigm for gaining real knowledge
• Testing can be repeated to see if findings are the same – replication.
• Methods used must be objective.
Operationalizing concepts
In order to test hypotheses it is necessary to operationalise the concepts we are interested in, e.g.
How are we going to measure: Intelligence
Personality
Emotions
Memory
Does behaviourism (classical conditioning and operant conditioning) do this?
Operational Definition
A precise definition of a
term in a hypothesis,
which specifies the
operations for observing
and measuring the
process or phenomenon
being measured.
What makes Psychology less objective ….and
therefore less scientific?
• Confirmation bias
• Researcher bias
• Publisher bias
• Demand characteristics
• Cultural bias
• We cannot stand outside of human nature to
study it – we are it !!
• ‘Only the shallow know themselves’
Our bias to “prove” what we think we know
Confirmation bias Positive test bias or hypothesis confirmation bias
Snyder and Swann (1978)
• Interview person
Is he/she introvert/extrovert?
Given list of Qs to ask
some about being introverted (in what situation do you wish
you could be more outgoing?)
some about being extroverted (what would you do to liven
up a party?)
0
1
2
3
4
5
6
7
8
Extraversion Hypo Introversion Hypo
Extraversion
questions
Introversion
questions
Neutral questions
Confirmation bias
Causing people to act the way you expect
Word, Zanna & Cooper (1974) study
White interviewees perform “better”
White interviewers behave differently towards white and black interviewees
Trained interviewers to use “White” or “Black” style
White interviewees who get “White” style do better
Which cards did you turn over?
The answer was (b)
Only this option allows us to test the rule
properly – we need to try to falsify the rule and
not to confirm it.
Only turning A & 7 allow us to do this.
Vowels are the letters: A, E, I, O, U
See example below
Hypothesis Testing
Wason Selection task
If a card has a vowel on one side, then it has
an even number on the other side
E T 4 7
E T 4 7 2 A 5 U
Hypothesis Testing
Wason Selection task
If a card has a vowel on one side, then it has
an even number on the other side
E T 4 7 2 A 5 U
Hypothesis Testing
Wason Selection task
If a card has a vowel on one side, then it has
an even number on the other side
To check….
Watch video
https://www.youtube.com/watch?v=5NyAy8ux
Hio
https://www.youtube.com/watch?v=t7NE7apn-
PA
DESCRIPTIVE STUDIES:
HOW DO WE OBSERVE
AND DESCRIBE
BEHAVIOUR?
Testing hypothesis and refining theories using
Descriptive methods
Correlational methods
Experimental methods
To think critically, we need to understand these
methods and know what conclusions they will
allow.
The Scientific Method
How do psychologists use case studies, surveys
and naturalistic observations to observe
behaviour? Why is random sampling important?
Descriptive research is a systematic, objective
observation of people (as well as animals).
The goal when studying people is to provide a clear, accurate picture of behaviours, thoughts and attributes.
Methods used:
Case studies
Surveys and interviews
Naturalistic observations
The Scientific Method: Description
• Many cases in less depth; self-reported
• Wording effect
• Random sampling
• Utilizes random sampling of population for best results
The Survey
• Records behaviour in natural environment
• Describes but does not explain behaviour
• Can be revealing
Naturalistic Observation
• Examines one individual or group in depth
• Provides fruitful ideas
• Cannot be used to generalize
The Case Study
The Scientific Method: Description
Description is the starting point of any science
Research methods - the case study:
a technique in which one person is studied in
depth to reveal underlying behavioural principles.
Little Albert Experiment – James Watson
Research methods – the survey
http
://ww
w.ly
nnefeath
erstone.o
rg
Survey – random sampling
If each member of a population has an equal
chance of inclusion into a sample, it is called a
random sample (unbiased).
If the survey sample is biased, its results are not
valid. The fastest way to know about the marble colour
ratio is to blindly transfer a few into a smaller jar and
count them.
Survey: advantages, disadvantages
& problems
Can ask about things which people may not want to disclose to a researcher or that are unlikely to be observed
Free from interviewer bias
Low cost, easy data collection
Large samples, results generalisable
Only effective with educated & coperative respondents
May have a selection bias
Poor response rates
Responses may be „polite” or designed to „please” researchers or dishonest
Difficult to provide anonymity
Difficult to have control over/ slow to get results
Wording can affect results
Advantages Disadvantages
Research methods - Naturalistic Observation
Involves observing and recording human and animal behaviour in a real world setting
The researcher makes no attempt to interact with or change the behaviour of the people or animals observed.
Important because results of controlled laboratory studies often differ from those conducted in real-life. Remember that these descriptive
methods do not explain behaviour.
This illustrates how, without knowing anyone’s identity, big
data enable researchers to study human behaviour on a
massive scale.
NATURALISTIC OBSERVATION: TWITTER
MESSAGE MOODS, BY TIME AND BY DAY
Problems with bias
Problems with bias
Application and Generalisation
To apply psychological research we have to be able to generalise it to a wider population than our sample of participants.
Can psychology claim to be a
science?
• Scientific research is desirable
• Psychology shares the goals of all sciences, but does using the scientific method turn psychology into a science?
• Miller claims it is ‘dressing up’ – pseudoscience
• Kuhn claims it cannot be a science as it has no single paradigm unlike other sciences. A paradigm is a set of shared assumptions, in psychology there are a number of different paradigms or approaches to explaining behaviour.
• Can behaviour be measured objectively? Both experimenter bias and demand characteristics compromise validity. But Heisenberg found that you cannot even measure a subatomic particle without altering its behaviour (uncertainty principle).
• Psychology does explore issues like obedience in experiments where common-sense predictions are wrong.
Objections to the scientific
approach in psychology
Cannot measure people in the same way as
physical phenomena.
Study people in unnatural conditions
Control, isolation of variables not possible in
people
Ignores subjectivity of behaviour, superficial
Objectivity impossible, past experiences,
beliefs and ideas influence behaviour
What are the problems with a
scientific approach?
The scientific approach is reductionist, simplifying complex phenomena and theories down to basics.
Science is also determinist in its search for causal relationships, i.e. if X determines Y.
Science makes generalisations about people on the basis of data gained from samples not entire populations. Some psychologists argue that an individual approach is more suitable when treating patients.
Qualitative (descriptive rather than numerical) research is seen as less than scientific but triangulation can make this method more objective.
Also qualitative researchers must be reflective about their influence on their own research.
UNDERSTANDING
DATA
Reliability
Reliability is about consistency.
Reliability can also be thought of as the
extent to which data can be reproduced...
Reliable measures mean the same data
would have been obtained under similar
circumstances on another occasion
There are different types of reliability (see
next slide)
Four types of reliability
Threats to reliability
Bias in the data collection instrument is a
primary threat to reliability and can be
reduced by repeated testing and revision of
the instrument.
You cannot have a valid instrument if it is not
reliable.
Validity
Research is valid if it really measures what it is supposed to be measuring
Valid data is relevant data
This means that if we are trying to measure a construct such as concentration and we are trying to count the number of times someone looked away from their work, we should not be including the times they looked away because someone else attracted their attention e.g. by calling their name.
Types of validity
CORRELATIONAL
STUDIES: LOOKING FOR
RELATIONSHIPS
Correlation
Correlation: A measure of how strongly two
variables are related to one another
Variables: Characteristics of behaviour or
experience that can be measured or described
by a numeric scale
Correlation
When one trait or behaviour appears in a regular
relationship with another, we say the two correlate.
Correlation
coefficient
Indicates direction
of relationship
(positive or negative)
Indicates strength
of relationship
(0.00 to 1.00)
r = 0.37 +
Correlation coefficient is a statistical measure of the relationship
between two variables.
Correlation Studies
Correlation: A statistical measure of a
relationship.
A measure of how two or more variables are
linked together in an orderly way.
An indication of how one of the variables
predicts the other variable(s).
Positive Correlation:
An increase in one variable corresponds to an
increase in the other.
0
5
10
15
20
25
30
35
Grades 0 1 2 3 4
Act Scores
Negative Correlation
An increase in one variable corresponds to a
decrease in the other.
0
10
20
30
40
50
60
70
80
0 1 2 3 4
Parties
A scatterplot is a graph comprised
of points that are generated by
values of two variables.
The slope of the points shows the
direction, while the amount of
scatter depicts the strength of the
relationship.
Scatterplots of data
No relationship (0.00)
A weak correlation,
indicating little
relationship, has a
coefficient near zero.
Perfect negative
correlation (-1.00)
If 2 sets of scores relate
inversely (one set going
up as the other goes
down), the correlation is
negative. (Example:
toothbrushing & decay)
Scatterplots
Perfect positive
correlation (+1.00)
If 2 sets of scores tend to
rise or fall together, the
correlation is positive.
(Example: height & weight)
Note: Perfect correlations rarely
occur in the “real world”
Data Data showing height and temperament in people:
Is there a positive correlation, negative correlation, or little-to-no correlation?
Scatterplot of data from previous table The Scatterplot below shows the relationship between height and
temperament in people.
Coefficient of Correlation
Correlation: an observation that two variables (traits or attributes) are related to each other. The numbers that represent the strength and direction of a correlation.
Correlation coefficient: a statistical measure of how closely two things vary together, or how well you can predict a change in one from observing a change in the other
Positive correlation (above 0 to +1.00) Indicates a direct relationship, meaning that as one variable
increases, the other increases or both may decrease together
Negative correlation (below 0 to −1.00) Indicates an inverse relationship: As one thing increases, the
other decreases.
Zero correlation (0 to very low) Indicates no relationship
Prediction
The closer the coefficient is to 1 in either
direction, the stronger (more predictive) the
relationship
-.79 is a stronger relationship than +.34
or
Correlation and Causation Correlation does not mean causation!
Correlation is NOT causation
Just because two variables are related to each other
does not necessarily mean one causes the other.
EXPERIMENTAL
STUDIES
The search for causes
Do laboratory experiments help us to understand everyday life?
Purpose of experiments
Controlled, artificial environments are created in laboratory experiments to test general theoretical principles, not re-create exact everyday life behaviours
Resulting principles
Help explain everyday behaviour through resulting general principles, not specific findings
Psychological science
Focuses on seeking general principles that help explain many behaviours and less on particular behaviour
The Scientific Method:
Predicting Real Behaviour
Research Process
People low in self-esteem are more likely to report depression than
are those high in self-esteem. One possible explanation of this
negative correlation is that a bad self-image causes depressed
feelings. But, as the diagram indicates, other cause-effect
relationships are possible.
THREE POSSIBLE CAUSE-EFFECT RELATIONSHIPS
The Experiment
Defined by:
Control of variables (the things you want to
measure)
Manipulation of variables
Experimentation:
As in other sciences, experimentation is the backbone of psychological research.
Experiments isolate causes and their effects.
Exploring Cause and Effect
Experiments
Experiment: A controlled test of a hypothesis in
which the researcher manipulates one variable
to discover its effect on another.
How do experiments help to isolate cause and
effect?
Experiments: researchers focus on the possible
effects of one or more factors by
Manipulating the factors of interest to determine their
effects and
Holding constant (controlling) other factors.
They do so by randomly assigning people to:
An experimental group, in which people receive the
treatment,
A contrasting control group, whose members do not
receive treatment.
The Scientific Method: Experimentation
Experimental Design
Hypothesis: Nicotine in cigarettes impairs driving.
All conditions kept the same for both groups except nicotine.
Control condition is given placebo (inactive) cigarettes
Number of collisions is measured.
The Scientific Method: Types of Experimental
Procedure
Blind (uninformed) procedure: participants unaware of treatment
Double-blind procedure: participants and experimenter are unaware of treatment
Neither those in the study nor those collecting the data know which group is receiving the treatment.
Treatment’s actual effects can be separated from potential placebo effect.
Placebo effect: effect involves results caused by expectations alone.
Evaluating Therapies
When drug therapies are
evaluated, patients and
experimenters should
remain unaware of which
patients had the real
treatment and which
patients had the placebo
treatment (control group).
Double-blind Procedure
Experimental Variables
Independent Variable: A variable that an experimenter manipulates.
Dependent Variable:
A variable that an experimenter predicts will be affected by manipulations of the independent variable.
• Factor that is measured; the variable that may change when the independent variable is manipulated
Dependent variable in an experiment
• Factor other than the independent variable that might produce an effect
Confounding variable in an experiment
• Factor that is manipulated; the variable whose effect is being studied
Independent variable in an experiment
Variables
Experimentation: Independent and
Dependent Variables
Exploring Cause & Effect
Many factors influence our behaviour.
Experiments (1) manipulate factors of interest, while other factors are kept under (2) control.
Effects generated by manipulated factors isolate cause and effect relationships.
For example: the effects of bottle feeding vs. breast-feeding on intelligence
vs.
Independent Variable (IV)
An independent variable is a factor manipulated by the experimenter. The effect of the independent
variable is the focus of the study.
For example, when examining the effects of breast feeding upon
intelligence, breast feeding is the independent variable.
Dependent Variable (DV)
A dependent variable is a factor that may change in response to an independent variable.
In psychology, it is usually a behaviour or a mental process.
For example, in the study on the effect of breast feeding upon intelligence, intelligence is the dependent variable.
Experiment
A summary of steps during experimentation (effects of
bottle feeding vs. breast-feeding on intelligence.)
Look for the DV first when identifying variables in a study. Ask yourself, “What is the researcher trying to measure or look for in this study?”
Look for the IV second when identifying variables in a study. Ask yourself, “What are the researchers manipulating in order to determine its effects on the DV in this study?”
IV & DV
Confounding Variables:
Something that was not predicted or accounted for in designing/conducting the experiment that confused the relationship between the independent and dependent variables.
The Hawthorne Effect
The APA “Internet Isolation” study
Advantages of experimental work:
Establishes cause and effect relationships
Reduces or eliminates alternative explanations
Self-correcting through Replication
Limitations of experimental work:
Efforts to control may create very artificial
settings that may not validly reflect nature
EVALUATING THE
FINDINGS
Statistics:
The language used in science to communicate
the results of research
A tool used to determine if observed
differences are real and did not simply happen
by chance
Types of Statistics:
Descriptive
Inferential
Why Psychologists Use Statistics
Descriptive Statistics: Organize and
summarize data
Inferential Statistics: Assess how meaningful
results are, such as differences between
groups.
Significance tests assess how likely it is that a
study’s results occurred merely by chance
Descriptive Statistics:
Different ways of
describing and
summarizing data
collected in an
experiment.
They are used to express
how the observations
were alike or different for
different groups
Inferential statistics
Methods for drawing and
measuring the reliability
of conclusions about a
population based on
information from a sample
of the population
Used for hypothesis
testing
Making predictions
Assess reltionships
between variables
Statistical Reasoning
Statistical procedures analyze and interpret data
allowing us to see what the unaided eye misses.
Composition of ethnicity in urban locales
Descriptive statistics
“What’s the typical score (observation) in a
group of scores (observations)?
Specific statistics:
Mean
Mode
Median
Measures of Central Tendency
Mean: The arithmetic average of scores in a distribution obtained by adding the scores and then dividing by the number of scores that were added together.
Mode: The most frequently occurring score in a distribution.
Median: The middle score in a rank-ordered distribution.
The Mean
The arithmetic average
Add up all the scores and divide by the number of scores
5
4
3
2
1
__
15 / 5 = 3
Problems with the mean:
Easily influenced by the addition of a few extreme score
5 20
4 4
3 3
2 2
1 1
__ ___
15/5 = 3 30/5 = 6
The Median:
The middle score in a distribution of scores
5
4
3
2
1
The Mode:
The most frequently occurring score in a distribution of scores
6
5
4
4
3
2
1
Range:
The gap between the highest and the lowest
scores.
high score = 80 minus the low score = 20 means
the Range = 60.
Normal Curve – Gaussian distribution
A symmetrical, bell-shaped curve that describes the
distribution of many types of data (normal distribution).
Most scores fall near the mean.
The Standard Deviation:
A numerical way to describe how scores are
distributed above and below the mean
Gives the ability to express the distribution
visually
Standard Deviation
Measures of Central Tendency
A Skewed Distribution
Measures of Variation
Range: The difference between the highest and lowest scores in a distribution.
Standard Deviation: A computed measure of how much scores vary around the mean.
INFERENTIAL STATISTICS
Answers the questions
“Could the differences between two groups have
been caused by chance?”
and
“How confident can we be that we are right?”
When is a Difference Significant?
When sample averages are reliable and the difference
between them is relatively large, we say the difference has
statistical significance. It is probably not due to chance
variation
Use statistical tests: t-test, ANOVA, etc
Significance is stated as a probability figure
Psychology generally uses the .05 level as standard (95%)
although some research is reported at the .1 (90%) or .01
(99%) level
Significance is not about the importance of a difference, but
that the difference is big enough to matter and not caused by
some accidental difference between the groups
From the Laboratory to the Real
World
Choosing the Best Explanation
Sometimes there are competing explanations for
the same events
Judging the Result’s Importance
Statistical significance does not prove that a
result is important, only that it is reliable
Meta-analysis combines and analyzes data from
many studies
Advantages and Limitations of
Experiments
Experiments allow conclusions about cause-effect relationships.
Participants in experiments are not always representative of larger population.
Much psychology research is carried out using colleges students as participants.
Field Research: Descriptive or experimental research conducted in a natural setting outside the laboratory.
Research
Method Basic Purpose How Conducted
What Is
Manipulated Weaknesses
Descriptive To observe and
record behavior
Do case studies,
naturalistic
observations, or
surveys
Nothing
No control of
variables; single
cases may be
misleading
Correlational
To detect
naturally
occurring
relationships; to
assess how well
one variable
predicts another
Collect data on
two or more
variables; no
manipulation
Nothing Cannot specify cause
and effect
Experimental To explore cause
and effect
Manipulate one or
more factors; use
random
assignment
The
independent
variable(s)
Sometimes not
feasible; results may
not generalize to
other contexts; not
ethical to manipulate
certain variables
Comparing Research Methods
Illusory Correlation: A perceived, but nonexistent, correlation.
Illusory correlations can help explain many superstitious beliefs, such as the presumption that infertile couple who
adopt become more likely to conceive.
Confirming
evidence
Disconfirming
evidence
Do not
adopt
Disconfirming
evidence
Confirming
evidence Adopt
Do not
conceive Conceive
Mich
ael New
man Jr./ P
ho
to E
dit
Order in Random Events
“With a large enough sample, any outrageous thing is likely to
happen.” ~Diaconis and Mosteller
An event that happens to but one in 1 billion people every day
occurs about 6 times a day – 2000 times a year.
Angelo and Maria
Gallina won two
California lottery
games on the same
day.
Jerr
y T
elfe
r/ S
an F
ranci
sco C
hro
nic
le
During the 2010 World Cup, a
German octopus selected the box
with the right national flag,
correctly predicting (eight out of
eight times) the outcomes of
Germany’s matches and Spain’s
final win. Random or remarkable?
People perceive patterns to make sense of their world.
Even in random, unrelated data people often find order, because random sequences often do not look random.
The Need for Psychological Science:
Perceiving Order in Random Events