Chapter Introduction

Section 1: What Is Research?

Section 2: Problems and Solutions in Research
Section 3: Statistical Evaluation
Main Idea
Psychologists must first decide how to
approach the research issue. Then
psychologists conduct the research in one of
a variety of ways to test a hypothesis, solve
a problem, or confirm previous findings.
Pre-Research Decisions
• Researchers begin by asking a specific
question about a limited topic or
hypothesis.
• Then they collect evidence.
• A sample is a relatively small group of the
total population under study.
• A sample must be representative.
Pre-Research Decisions (cont.)
• Ways to avoid a nonrepresentative
sample:
– Take a purely random sample.
– Deliberately pick individuals who
represent the various subgroups in the
population being studied, also known as
a stratified sample.

Jane Goodall
Methods of Research
• The goals of research are to:
– Describe behavior
– Explain its causes
– Predict the circumstances under which
certain behaviors may occur again
– Control certain behaviors
Methods of Research (cont.)
• Methods of research used to accomplish
these goals:
– Naturalistic observations
– Case studies
– Surveys
– Longitudinal Studies
– Cross-Sectional Studies
– Correlations
– Experiments – Controlled environment
A Correlation Study
naturalistic observation: research
method in which the psychologist
observes the subject in a natural setting
without interfering

Direct observation ?
case study: research method that
involves an intensive investigation of one
or more participants
survey: research method in which
information is obtained by asking many
individuals a fixed set of questions
longitudinal study: research method in
which data are collected about a group of
participants over a number of years to
assess how certain characteristics
change or remain the same during
development
cross-sectional study: research
method in which data are collected from
groups of participants of different ages
and compared so that conclusions can
be drawn about differences due to age
correlation: the measure of a
relationship between two variables or
sets of data
A Correlation Study
These charts display possible correlations between different variables.
Experimental
Research
Psychology is an
experimental science.
Psychologists follow the
same general procedures
when conducting
experimental research.
Which of the following do you think is
the best method of research?
A. Naturalistic observation
B. Case study
C. Survey A. A
B. B
D. Longitudinal study
C. C
D. D
Methods of Research (cont.)
• Every experiment has:
– hypothesis
– variables (independent and dependent)
– experimental group
– control group

Experimental Research
hypothesis: an educated guess about
the relationship between two variables
variable: any factor that is capable of
change
experimental group: the group to which
an independent variable is applied
control group: the group that is treated
in the same way as the experimental
group except that the experimental
treatment (the independent variable) is
not applied
What is the importance of a
control group?
A. It exhibits change during
an experiment.
B. It affects the results in
the experimental group.
A. A
C. It allows for a comparison B. B
to identify changes in the
C. C
experimental group.
D. D
D. None of the above.
Methods of Research (cont.)
• Ethics are the methods of conduct, or
standards, for proper and responsible
behavior.
• The APA has a list of ethical principles that
psychologists must follow.
Do you think that expectations of
behavior affect actual behavior?
A. Yes
B. No

A. A
B. B
Problems and Solutions in Research
• A self-fulfilling prophecy is a situation in
which a researcher’s expectations
influence that person’s own behavior, and
thereby influence the participant’s
behavior.
Avoiding a Self-Fulfilling Prophecy
• Ways to avoid self-fulfilling prophecy:
– Single-blind experiment
– Double-blind experiment

Single-Blind and Double-Bl

ind Experiments
single-blind experiment: an experiment
in which the participants are unaware of
which participants received the treatment
double-blind experiment: an
experiment in which neither the
experimenter nor the participants know
which participants received which
treatment
Single-Blind and Double-Blind Experiments
Researchers must take measures during experimentation to guard against seeing
only what they expect to see.
Do you agree or disagree that humans
often have preconceived notions about
what will happen in a situation?
A. Agree
B. Disagree
A. A
C. Not sure
B. B
C. C
The Milgram Experiment
• In the 1960s, Stanley Milgram wanted to
determine whether participants would
administer painful shocks to others merely
because an authority figure had instructed
them to do so.
• The result implied that ordinary individuals
could easily inflict pain on others if such
orders were issued by a respected
authority.
The Milgram Experiment (cont.)
• His experiment, although no one was
actually shocked, was controversial.
• Today, experiments are required to submit
a plan to a Human Subjects Committee.
Do you believe that Milgram’s decision
to use volunteers as he did was ethical
or unethical?
A. Ethical
B. Unethical
A. A
C. Not sure
B. B
C. C
The Placebo Effect
• The placebo effect is a change in a
participant’s illness or behavior that results
from a belief that the treatment will have
an effect rather than from the actual
treatment.
Do you think that is ethical to use a
placebo in an experiment?
A. Yes
B. No
C. Not sure A. A
B. B
C. C
Statistical Evaluation
• Statistics consist of the branch of
mathematics concerned with summarizing
and making meaningful inferences from
collections of data.

Kate’s Data
Kate’s Data
Kate’s data show the number of hours of television watched before and after the
quiz, the grade on the quiz, the number of products recognized, and participants’
height in inches.

* Highest grade possible is 10.

In your opinion, in which way are
statistics more likely to be used?
A. To distort the truth
B. To honestly support
a hypotheses
A. A
B. B
Descriptive Statistics
• Descriptive statistics involve the listing
and summarizing of data in a practical,
efficient way.
• One of the first steps that researchers take
to organize their data is to create
frequency tables and graphs.
Descriptive Statistics (cont.)
• A frequency distribution is a way of
arranging data so that we know how often
a particular score or observation occurs.

A Frequency Distribution
A Frequency Distribution
A frequency distribution shows how often a particular observation occurs.
Descriptive Statistics (cont.)
• Types of graphs:
– Histogram
– Frequency polygon/frequency curve

A Frequency Polygon
A Frequency Polygon
This graph shows the number of hours of TV watched the night before the quiz
and the night after the quiz.
Descriptive Statistics (cont.)
• A normal curve is a graph of frequency
distribution shaped like a symmetrical, bell-
shaped curve.

A Normal Curve
A Normal Curve
The maximum frequency lies in the center of a range of scores in a perfect
normal curve. The frequency tapers off as you reach the edges of the two sides.
Descriptive Statistics (cont.)
• A common way of summarizing is to
measure the central tendency. – A
number that describes something about
the “average” score of a distribution.

• Distributions also differ in their variability. –

Measuring the difference, or spread of data.

Measure of Central
Tendency
Measures of Central Tendency
It is often useful to summarize a set of scores by identifying a number that represents
the center, average, or most frequently occurring number of the distribution.
In relation to class test scores, which
of the following do you think is more
descriptive?
A. An average of 84
B. A median of 85
A. A
C. A mode of 79
B. B
C. C
Descriptive Statistics (cont.)
• Two commonly used measures of
variability are:
– Range – subtract the lowest number in a
data set from the highest number and
add 1. (“crude” measurement)
– Standard deviation

Standard Deviation
standard deviation: a measure of
variability that describes an average
distance of every score from the mean
Standard Deviation
Two distributions with the same mean and different standard deviations are shown.
Descriptive Statistics (cont.)
• Standard deviation is a better measure
because it uses all of the data points.
• A correlation coefficient describes the
direction and strength of the relationship
between two sets of observations.
• The most commonly used measure is the
Pearson correlation coefficient (r).
Descriptive Statistics (cont.)
• A coefficient with a plus sign (+) indicates
a positive correlation.
• A coefficient with a minus sign (–) indicates a
negative coefficient.
• A scatterplot is a graph of scores that
demonstrates the direction of the relationship
between two variables.

A Scatterplot
A Scatterplot
When there is little or no relationship between two variables, the points in the
scatterplot do not seem to fall into any pattern.
Inferential Statistics (cont.)
• Many researchers say that if the
probability that their results were due to
chance is less than 5%, they do not think
the results were due to chance.
• The results would then be considered
statistically significant.