thinking critically with psychological science · thinking critically with psychological science ....
TRANSCRIPT
Chapter One
Thinking Critically With
Psychological Science
Intuition An effortless, immediate,
unreasoned sense of truth
David Myers- author of our text
said “Instinct has the power to hush
reason. But when is it safe to go
with your gut? Researchers may
remain uncertain about the
reliability of intuition, but it is a
difficult force to deny.”
Pitfalls of in thinking that make
intuition and common sense
untrustworthy:
Hindsight bias and overconfidence
Hindsight Bias: the tendency to believe, after learning an outcome, that one would have foreseen it.
Have you ever watched Jeopardy with someone, and after the answer is given that person says "I knew that one" or "That was an easy one"?
Take Ken Jennings…he won 2.5 Million on Jeopardy…but he did have this blooper…
Overconfidence is the tendency to think
we know more about an issue than we
actually do and to overestimate the
accuracy of that knowledge.
For example, for certain types of questions,
answers that people rate as "99% certain"
turn out to be wrong 40% of the time
Scientific Attitude Is being willing to accept only carefully and objectively verified
facts, and to hold a single fact above the authority of the oldest theories. Nothing can be called
scientific that is not based on such an attitude.
The guide to a scientific attitude is Curiosity, Skepticism, and Humility.
Critical Thinking
Thinking that does not blindly
accept arguments and conclusions.
Rather it assumptions, discerns
hidden values, evaluates evidence,
and assesses conclusions.
Such examples given by the text:
Massive losses of brain tissue early in
life may have minimal long term
effects.
Scientific Method
Theory- explains a set of principles that organizes observations and predicts behaviors or events.
Hypotheses- Educated Guess- the testable predictions often implied by a theory.
Bias-Particular belief that restrains openness of the scientific method outcomes
Operational definition- statement of the procedures used to define research variables. (What is the measure of say…anger? Or what is the independent variable or dependent variable)
Scientific Method
Replication-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.
What is the importance of
theories in Psychology?
Because they are trying to Explain,
Organize, and Predict Behavior of the
events under the study/research!
The Good Theory has two
elements:
1. Organizing and linking
observed facts
2. Implying hypotheses that offer
testable predictions and
sometimes practical
applications.
Research Goals
Descriptive Approach to Research-
observe, measure, describe.
An example:
An opinion poll to determine which Presidential candidate people plan to vote for in the next election.
Descriptive studies do not seek to measure the effect of a variable; they seek only to describe.
Research Goals
Correlational Approach to Research-
two different types of behavior and evaluate the relationship between them.
Example:
a study that looked at the proportion of males and females that would purchase either a classical CD or a jazz CD would be studying the relationship between gender and music preference.
Research Goals
Experimental Approach to Research- investigate cause and effect relationships by manipulating one aspect of the aspect that is thought to produce a change in that particular behavior.
When using experimental research scientists usually, but not always, conducted in a laboratory. The laboratory environment allows the experimenter to make controlled observations using the steps of the scientific method.
Example of Experimental Research 1. Theory or research Question- The study is about
whether certain environmental conditions improve or adversely affect motor performance.
2. The investigator might give operational definitions to the environmental condition of interest as “background music” and the motor performance as “typing speed.”
3. Next, the investigator proposes an answer to the research question (“What is the relationship between typing speed and background noise?), an answer called a hypothesis.
4.Define Variables: the relationship between two variables, an independent variable (that which the experimenter manipulates—in this case, the background music) and a dependent variable (that which changes as a consequence of manipulation of the independent variable—in this case, the typing speed). The experimenter hypothesizes that “an increase in loudness of background music will produce a decrease in typing speed.”
subjects would be taken to a laboratory for
testing and would use the same typewriters
to take the typing tests.
The experimenter would have to decide
whether to use two groups of subjects with
comparable typing skills and expose one
group to a music loudness level different
from that used with the other or
sequentially expose the same subjects to
music of two loudness levels.
Each procedure has advantages and
disadvantages.
Descriptive Studies/Research
Methods of study that try to
DESCRIBE a population
Case Study
Definition: an observation technique in
which one person is studied in depth in
the hope of revealing universal principles
Examples:
Genie the Wild Child
Phineas Gage
Anorexia Studies
Case Study
Advantages and Disadvantages
What’s good about
case studies?
One person can tell
us a lot about humans
in general
What’s bad about case studies?
One case may be misleading!!!
“My uncle smoked two packs a day for sixty years and never had health problems!”
Survey
Definition: asks people to report their
behavior or opinions
Examples:
Political polling
U.S. Census
Thomas Co. Youth
Survey
Survey
Advantages and Disadvantages
What’s good
about surveys?
Cheap to
administer
Gather a lot of
information about
a lot of people
quickly
What’s bad about
surveys?
Wording Effects
“affirmative action”
vs. “preferential
treatment”; “welfare”
vs. “aid to the needy”
Sampling Error
People Lie
Survey
Representative Sample-
Researcher attempts to select
individuals which are
representative of a larger
population.
Truly representative sampling is
very hard to accomplish and
researchers may dedicate a great
deal of time and funding to get
the most representative sample
as possible.
Survey
Random
Sample- fairly
represents a
population
because each
member has an
equal chance of
inclusion.
Experimentation- a research method
in which an investigator manipulates on or
more factors to observe the effect on some
behavior or mental process
Randomly assigning-
assigning participants
to experimental and
control groups by
chance, thus
minimizing preexisting
differences between
those assigned to
different groups
Grouping
Experimental- group that
is exposed to the treatment
(to one version of the
independent variable)
Control- group that is not
exposed to the treatment.
Serves as a comparison for
evaluating the effect of the
treatment.
Placebo-(placebo effect) results
caused by expectations alone
(belief in it). Substance or
condition which the recipient
assumes is an active agent.
Double Blind Procedure- both
researcher and participants are
ignorant about whether the
research participants have
received the treatment
or a placebo.
Naturalistic Observation
Definition:observing and recording
behavior in NATURALLY occurring situations
We do NOT interfere in naturalistic observations…we simply watch and record!
Example: Jane Goodall observing chimpanzees
Naturalistic Observation
Advantages and Disadvantages
What’s good about
naturalistic
observation?
See authentic
behavior
What’s bad about
naturalistic
observation?
Can’t interfere at all
Correlations
Correlations Coefficient
How closely two things vary together (how well one predicts the other).
Ex. This is a measure of the direction (positive or negative) and extent (range of a correlation coefficient is from -1 to +1) of the relationship between two sets of scores.
Scores with a positive correlation coefficient go up and down together (as with smoking and cancer).
A negative correlation coefficient indicates that as one score increases, the other score decreases (as in the relationship between self-esteem and depression; as self-esteem increases, the rate of depression decreases).
Scatter Plots
Depiction of the relationship between two
variables by means of a graphed cluster
of dots.
Is the following scatter plot positive or
negatively skewed in correlation?
Positive
Is the following scatter plot positive or
negatively skewed in correlation?
Negative
Guess the Correlation…Positive or
Negative.
Education and years in jail—people who
have more years of education tend to
have fewer years in jail (or phrased as
people with more years in jail tend to
have fewer years of education)
Negative
Correlation
Guess the Correlation…Positive or
Negative.
Happiness and helpfulness—as people’s
happiness level increases, so does their
helpfulness .
Positive
Guess the Correlation…Positive or
Negative.
SAT scores and college achievement—
among college students, those with higher
SAT scores also have higher grades
Positive
Guess the Correlation…Positive or
Negative.
Students with higher grades tend to spend
less time watching TV
Negative
Guess the Correlation…Positive or
Negative.
Cities with more stores selling
pornography have higher rates of
violence.
Positive
Guess the Correlation…Positive or
Negative.
Babies who are held less tend to cry more
Negative
Guess the Correlation…Positive or
Negative.
The longer couples have been together
the more similar they are in their
attitudes and opinions.
Positive
Guess the Correlation…Positive or
Negative.
A researcher finds that students who
have more absences get poorer grades.
Negative
As the number of absences increase, the grade declines. The variables are changing in the opposite direction.
We might find this relationship for many reasons:
(1) Students who are more absent miss important pieces of information that would increase their chances of performing better in the class.
(2) Students who have difficulty in a class may stop attending because they see no reason for going. Thus, does the greater class absence "cause" the poor grades or do poor grades "cause" the greater absence.
(3) A student who is not highly motivated may be absent more often and may do poorly. Thus, these two variables are related to other variables (such as motivation) which may be the real reason for the relationship between class absences and grades.
One big thing to know about
Correlations…
correlations does
not equal
causation
Copyright © Allyn & Bacon 2007
How Do We Make Sense
of the Data?
Researchers use statistics for
two major purposes:
(1) descriptively to characterize
measurements made on groups
or individuals and
(2) inferentially to judge whether
these measurements are the
result of chance
Copyright © Allyn & Bacon 2007
Organizing the Data
First results must be arranged in a
summary chart known as a frequency
distribution
We can convert the data into a bar graph
called a histogram
Copyright © Allyn & Bacon 2007
Frequency distribution
chart – shows how
frequently each score
occurred.
Histogram or bar chart – gives a
visual representation of how the
scores look. This helps us to “see”
whether or not the scores are evenly
distributed.
A histogram can
also show whether
or not the scores
are more clustered
around the middle
of the distribution
or if there are
outliers (extreme
scores).
Examples of
organizing the
data:
Descriptive Statistics
• In order to understand the data that was gathered,
statistics help to bring the data into sharper focus.
• When using statistics, researchers are looking for
the central point around which the numbers seem to
cluster. This is called “measures of central
tendency.”
• This will then help the researchers to make
inferences about the data to determine if the results
are reliable or simply due to chance (e.g. inferential
statistics).
Copyright © Allyn & Bacon 2007
Copyright © Allyn & Bacon 2007
Describing the Data With
Descriptive Statistics Descriptive statistics: Numbers that describe the
main characteristics of the data.
• The mean
• The median
• The mode
• The range
• The standard deviation
• The normal distribution
The Mean • The measure of central tendency most often used to describe a set of
data.
• Add all the scores and divide by the number of scores.
• It is the average.
• While it is a pretty good indicator of the center of the distribution, its
one flaw is that it can be skewed by extreme scores.
• So, if the distribution of the scores is relatively symmetrical (bell
shaped), there is no problem; however, if more scores fall toward
either end of the distribution, then the mean gets pulled in that
direction and distorts the overall inference of the data.
Copyright © Allyn & Bacon 2007
Examples of Skewed Distributions
Copyright © Allyn & Bacon 2007
On the last test, the class mean was 68. But, because it was not a symmetrical
distribution, that sounds like the class overall did poorly. When calculating the
median the scores look much better: the median score was 72. Due to low
extreme scores, the mean is a not a very good indicator of how the class did.
More low scores than high scores – but there are a few extremely
high scores (mean is higher than the median)
More high scores than low – but there are a few extremely low scores (mean
is lower than the median)
The Median • The “middle” score.
• Think of the “median divider” in the center of the road – it
divides the upper half of the scores from the lower half.
• This is a better measure of central tendency because it is not
affected by extreme scores.
• The scores are listed in order, and it is the number in the
middle. (e.g., 50, 55, 60, 65, 70)
• If you have an uneven set of numbers, take the two middle
numbers, add them, and divide by 2. (e.g., 50, 55, 60,
65, 70, 72..add 60+65/2=62.5).
Copyright © Allyn & Bacon 2007
The Mode
• A measure of central tendency that is
used to identify the score that occurs the
mode, ooops, the most!
• 55, 55, 55, 63, 68, 70, 70, 82, 95
• It is often the least useful measure of
central tendency, especially if the sample
is small.
Copyright © Allyn & Bacon 2007
The Range
• The simplest measure of central tendency
that represents the difference between the
highest and the lowest values.
• You use the range all the time in school
when you see what differentiates an A
from a B (90-100 and 80-89).
Copyright © Allyn & Bacon 2007
The Standard Deviation • Psychologists prefer to take all scores into consideration,
not just the highest and the lowest, so they use the standard
deviation instead.
• The SD is a measure of central tendency that shows an
average difference between each score and the mean.
• So, we are looking at the changes in the scores across the
spectrum of the scores.
• The larger the SD, the more spread out the scores are; the
smaller the SD, the more the scores bunch together at the
mean.
Copyright © Allyn & Bacon 2007
The Normal Distribution • Together, the SD and the mean tell us much about a
distribution of scores. They indicate where the
center of the distribution is and how closely the
scores cluster around the center.
• In a normal distribution, or a bell curve, the scores
are all equally distributed around the mean.
Copyright © Allyn & Bacon 2007
Normal Distribution
Copyright © Allyn & Bacon 2007
68% of values
% of scores
• 68% of scores fall within 1
SD above and below the
mean
•If you have 100 scores, 50
are above, and 50 are below
•Know how to compute
percentile
•Know how to compute Z
score
2% 14% 34% 34% 14% 2%
95% of values
99% of values
Mean
Percentiles
0
Standard
Deviations from
the Mean
Z Scores
-1 -2 -3 -4 +1 +2 +3 +4
0 2nd 16th 50th
+1 0 -1
-2 -3
-4
84th 98th
100th
+2 +3
+4
Copyright © Allyn & Bacon 2007
Making Inferences with Inferential
Statistics • Inferential statistics are used to assess whether the results of a study are reliable
or whether they might be simply the result of chance.
• Researchers use inferential statistics to determine whether or not the findings can
be applied to the larger population from which the sample was selected.
• Researchers compare the results of the experimental group to the control group
and determine (infer) whether the differences between the groups are a result of
the Independent Variable or could be the result of chance.
• To have confidence in the results, the researchers have to take into account the
magnitude of the differences in scores, and go back to make sure the sample was
large enough and that the sample was representative of the population at large.
While a sample can never truly represent the entire population, researchers do
look at sampling error, or how chance plays a factor in the results.
Making Inferences with Inferential
Statistics • Researchers then compute a “p” value for the scores, which states
how probable the results are due to the IV or chance.
• What you need to know is that, in psychology, the cutoff for
statistical significance, or that the results are probably due to the IV,
is a value of p<.05. This means that the probability of the results of
the experiment being due to chance are less than 5%, or 5 in 100.
• A “p” value can never equal zero because we can never be 100%
sure that results did not happen due to chance.
• Therefore, researchers often try to replicate their results to gather
more evidence that their initial findings were not due to chance.
Copyright © Allyn & Bacon 2007
Statistics- Numerical data
Statistics are used to make sense of the
data:
Researchers use statistics for two major
purposes:
1.
Limitations of Descriptive
Studies
These methods can contribute to overall understanding, but do not show causation.
Surveys and observation can show correlation
Correlation enables prediction.
Correlation does not equal causation!
Ice Cream Mystery
Statistical Reasoning in Everyday
Life
Statistics organize, summarize, and make inferences from data.
Three measures of Central Tendency :
1. Mode- most frequently occurring score in a distribution.
2. Mean is the arithmetic average of a distribution. (add scores then divide by number of scores)
3.Median is the middle score in a distribution; half the scores are above it and half are below it.
Two measures of Variation:
1. Range (of scores)- gap between the lowest and highest score (this shows only a rough estimate of variation)
2. Standard deviation – measures how scores deviate form one another. It better gauges whether scores are packed together or dispersed because it uses information from each score. Many types of scores are distributed alone a bell shaped curve or a normal curve.
Dark blue is less than one standard deviation from the mean. For the normal
distribution, this accounts for about 68% of the set (dark blue), while two
standard deviations from the mean (medium and dark blue) account for about 95%,
and three standard deviations (light, medium, and dark blue) account for
about 99.7%
How do psychologists decide whether
differences are meaningful?
Tests of Statistical significance
determines whether difference between
two groups are reliable. When the
averages (mean) of the samples drawn
from the groups are reliable and the
difference between them is relatively
large, we say the difference has statistical
significance.
Correlation Correlation can be:
causation (but not the other way around),
influenced by 3rd variables
pure chance
Correlation Coefficient
Scatterplots – illustrate correlation
Correlation?
Positive
Correlation
Statistically significant
inverse relationship
between pirates and
global temperature
Illusory Correlation
Psychologists studies with animals
and Humans Psychologists use animals because their
physiological and psychological processes enable them to better understand the similar processes that operate in humans.
Ethical guidelines in animals in experiments: Rarely do they experience pain in psychological experiments.
Ethical treatment of humans urge investigators to obtain informed consent, protect subjects from harm and discomfort, treat information about individuals confidentially and fully explain the research afterward.