A.

Experimental Psychology and the Scientific The Objectives of Psychological Science

Method
The Need for Scientific Methodology Description
● Description is the initial step toward understanding any phenomenon.
In psychological science, description refers to a systematic and
Commonsense psychology: the kind of everyday, nonscientific data
unbiased account of the observed characteristics of behaviors.
gathering that shapes our expectations and beliefs and directs our
Case study: an outside observer records the behaviors or experiences,
behavior toward others.
or both, of a single individual.
Confirmation bias: Once we believe we know something, we tend to
Field studies: observational studies of groups of people (or animals) in
overlook instances that might disconfirm our beliefs, and we seek,
real-life settings. Observers are able to gather descriptive data about
instead, confirmatory instances of behavior.
many kinds of social and cultural experiences.
Perceiving others by traits can be useful for predicting their behavior,
Prediction
but it can also lead to overestimations of the likelihood that they will
act in trait-consistent ways across a wide variety of different situations ● Prediction refers to the capacity for knowing in advance when certain
→ the process of stereotyping. behaviors would be expected to occur because we have identified other

Overconfidence bias: a cognitive error that leads individuals to conditions with which the behaviors are linked or associated.

overestimate their predictions guesses, and explanations, leading to Explanation

poor decision making ● When we explained a behavior, we also understand what causes it to
occur. Explanation includes knowledge of the conditions that reliably

The Characteristics of Modern Science reproduce the occurrence of a behavior.

Control
● Control refers to the application of what has been learned about
The Scientific Mentality
behavior. Once a behavior has been explained through experimentation,
Scientific mentality → Behavior must follow a natural order;
it may be possible to use that knowledge to effect change or improve
therefore, it can be predicted.
behavior.
● Alfred North Whitehead (1864-1947) postulated that faith in an
organized universe is essential to science.
The Scientific Method: Tools of Psychological
Gathering Empirical Data
Another important characteristic of empirical data, however, is that they Science
can be verified or disproved through investigation. This, gathering Observation
empirical data in a systematic and orderly way still cannot guarantee ● Observation is the systematic noting and recording of events. Only
that the correct conclusions will be reached. events that are observable can be studied scientifically
Seeking General Principles Measurement
Laws: principles that have the generality to apply to all situations. ● Measurement is the assignment of numerical values to objects or
● Theories: pull together, or unify, diverse sets of scientific facts into events or their characteristics according to conventional rules
an organizing scheme that can be used to predict new examples of Experimentation
behavior. ● Experimentation is a process undertaken to test a hypothesis that
Karl Popper, a modern philosopher of science, wrote that science particular behavioral events will occur reliably in certain, specifiable
progresses only through progressively better theories (Popper, 1963). situations. When we experiment, we systematically manipulate aspects
Good Thinking of a setting to verify our predictions about observable behavior under
● A central feature of the scientific method is good thinking. Our specific conditions.
approach to the collection and interpretation of data should be
systematic, objective, and rational.
Scientific Explanation in Psychological Science
principle of parsimony—simplicity, precision, and clarity of thought.
Antecedent conditions, or antecedents, are the circumstances that
Avoid making unnecessary assumptions to support an argument or
come before the event or behavior that we want to explain.
explanation
Comparing Treatment Conditions
Self-Correction
● In the psychology experiment, we create specific sets of antecedent
● Modern scientists accept the uncertainty of their own conclusions.
conditions that we call treatments. We compare different treatment
Publicizing Results
conditions so that we can test our explanations of behaviors
● Modern science has become a highly public activity.
systematically and scientifically.
This continuous exchange of information is vital to the scientific
A psychology experiment is a controlled procedure in which at least
process.
two different treatment conditions are applied to subjects
Replication
An experimental design in which subjects receive only one kind of
● Replication is another important part of the scientific approach. We treatment is called a between-subjects design.
should be able to repeat our procedures and get the same results again if present all treatments to each subject and measure the effect of each
we have gathered data objectively and if we have followed good treatment after it is presented. This experimental design is called a
thinking. within-subjects design.
The type of cause-and-effect relationship we establish through study’s significant prospective scientific, educational, or applied value
experiments is called a temporal relationship, because a time and that effective nondeceptive alternative procedures are not feasible.
difference occurs in the relationship.
Necessary vs Sufficient Conditions expected to cause physical pain or severe emotional distress.
The cause-and-effect relationships established through scientific
research commonly involve identifying sufficient conditions. When we ● Psychologists explain any deception that is an integral feature of the
seek causes, we rarely seek conditions that are both necessary and
design and conduct of an experiment to participants as early as is
sufficient.
feasible,
Anonymity and Confidentiality
From Pseudoscience to Psychological Science ● Maintaining anonymity and confidentiality is another important
consideration for researchers. It is our responsibility to protect the
privacy of research participants.
Phrenology
● Phrenology involved assessing traits and dispositions by measuring
the size and location of bumps on the skull. Protecting the Welfare of Animal Subjects\
Physiognomy
● Physiognomy involved using facial features to evaluate traits, mental Animal welfare: the human care and treatment of animals.
capacity and skills.
1. must enrich the environment of nonhuman primates
Mesmerism 2. provided with opportunities to socialize.
● Mesmerism was invented by an Austrian physician, Franz Mesmer institutional animal care and use committee (IACUC), to evaluate
who believed that fluids in the body ebbed and flowed by magnetic animal research before it can be conducted.
principles and that all possible alternatives to the use of animals must be carefully
both physical and mental illness could be cured by realigning fluids considered.
using magnets or his hands. written documentation that no other alternatives are feasible.
Spiritualism According to the animal-rights advocates, researchers need to uphold
● Spiritualism involved purported contact with ghosts and spirits of the the rights of both human beings and animals
dead.

1. Animals feel pain and their lives can be destroyed, as is true of

humans (Roberts, 1971);
B. Research Ethics
2. Destroying or harming any living thing is dehumanizing to the
Research Ethics and the APA and PAP Guidelines human scientist (Roberts, 1971); and
Responsible research is aimed at advancing our understanding of 3. Claims about scientific progress being helped by animal research
feelings, thoughts, and behaviors in ways that will ultimately benefit are a form of racism and are completely unwarranted and
humanity. unethical.
To protect the subjects of psychological research → Institutional
Review Board (IRB) must evaluate proposed studies before they are Arguments For Research with Animals
conducted.
● Ethical standards exist
● The primary duty of a review board is to ensure that the safety of
No ethical psychologist would deliberately inflict undue harm on an
research participants is adequately protected. The IRB’s first task if to
animal.
decide whether the proposed study puts the subjects at risk.
Risk/benefit analysis: The IRB must determine whether any risks to
the individual are outweighed by potential benefits or the importance of Fraud in Science and Plagiarism
the knowledge to be gained.
Informed consent means that the subject agrees to participate after
Fraud in Science
having been fully informed about the nature of the study.
Data falsification is a breach of the ethical principle stated succinctly in
APA standard 8.10a: “Psychologists do not fabricate data.”
LINE OF DEFENSE AGAINST DATA FALSIFICATION
1) Peer Review
Research articles submitted for publication are reviewed by the editor
of the periodical and by several experts in the field before they can be
accepted for publication.
(2) Replication
If data have been falsified, it is unlikely that the experiment will be

Deception and Full Disclosure successfully replicated.

The relationship between researcher and participants should be as open (3) Competitive Nature of Academic Psychology
and honest as possible. In some psychological studies, however, the Competition among colleagues for limited research resources can be a
true purpose of the study is disguised. strong deterrent to fraud.
Psychologists do not conduct a study involving deception unless they
have determined that the use of deceptive techniques is justified by the
Ethical Reports
Ethical Reports Researchers doing field studies often combine various types of data
Ethical Principles of Psychologists and Code of Conduct provides gathering to capitalize on the richness and range of behavior found
further guidance concerning ethics and research reports. Section 8.12(a) outside the laboratory.
states, “Psychologists take responsibility and credit, including Naturalistic observation is the technique of observing behaviors as they
authorship credit, only for work they have actually performed or to occur spontaneously in natural settings.
which they have substantially contributed” (APA, 2002). used extensively in animal behavior research, called ethology
Reactivity: tendency of subjects to alter their behavior or responses
when they are aware of an observer’s presence.
C. Alternatives to Experimentation:
Nonexperimental Design
Archival Study
Archival Study
Describing Research Activities ● An archival study is a descriptive research method in which already
existing records are reexamined for a new purpose.

Degree of manipulation of antecedent conditions: letting things

happen as they will OR setting up carefully controlled conditions Qualitative Research
Degree of imposition of units: the extent to which the researcher
it focuses on self-reports, personal narratives, and expression of ideas,
constrain, or limits, the responses a subject may contribute to the data
memories, feelings, and thoughts.
Qualitative research is used to study phenomena that are contextual,
meaning they cannot be understood without the context in which they
appear
Replicability: Qualitative researchers consider the reproducibility of
their conclusions. If another researcher would obtain the same results
with a similar sample, the study is a good one.

D. Alternatives to Experimentation: Surveys and

Interviews
Survey Research, Constructing Surveys and
Measuring Responses
Phenomenology Survey Research
Survey research is a useful way of obtaining information about people’s
opinions, attitudes, preferences, and behaviors simply by asking.
Phenomenology is the description of an individual’s immediate
Surveys allow us to gather data about experiences, feelings, thoughts,
experience. Rather than looking at behaviors and events that are
and motives that are hard to observe directly.
external to us, we begin with personal experience as a source of data.
Surveys allow us to gather large amounts of data efficiently.
The generalizability of survey and interview results is determined
Case Studies largely by the procedures we use to select our subjects.
Constructing Surveys
1. Map Out Your Research Objectives
The case study is a descriptive record of a single individual’s
a. Map out your research objectives, making them as specific as
experiences, or behaviors, or both, kept by an outside observer.
possible
Such a record may be produced by systematically recording
2. Design the Survey Items
experiences and behaviors as they have occurred over time
Closed questions, or structured questions, are answered by one of a
five major purposes:
limited number of alternatives.
1. They are a source of inferences, hypotheses, and theories.
Content analysis: responses are assigned to categories that are created
2. They are a source for developing therapy techniques.
from the data according to objective rules or guidelines.
3. They allow the study of rare phenomena.
Open-ended questions solicit information about opinions and feelings
4. They provide exceptions, or counterinstances, to accepted ideas,
by asking the question in such a way that the person must respond with
theories, or practices.
more than a yes, no, or 1-10 rating.
5. They have persuasive and motivational value.
3. Other Tips for Getting Started
Case studies frequently rely on retrospective data—data collected in
Keep items simple,
the present that are based on recollections of past events.
Use language that is easy to comprehend,
We cannot make cause-and-effect statements about the behaviors we
Avoid double-barreled questions, meaning they ask for responses about
observe.
two different ideas in the same question, and should be avoided.
If you are unsure, it is best to add a response category labeled “Other:
Field Studies __________”
Measuring Responses

Field Studies However, when creating closed questions, the type of format will
largely determine the kinds of statistical analyses researchers can
conduct on the data later, as different types of formats comprise Validity
different levels of measurement. ● refers to the extent to which a survey actually measures the intended
● Level of measurement: the kind of scale used to measure a topic.
response.
Selecting Levels of Measurement
Sampling (Probability and Nonprobability)
● The best type of scale to use in measuring survey responses will
Sampling
depend on two things:
The nature of the variable you are studying, and ● Sampling: deciding who the subjects will be and then selecting
them.
How much measurement precision you desire.
sample of subjects is a group that is a subset of the population of
interest.
Important Considerations for Survey Items
representativeness, or how closely the sample responses we observe
and measure reflect those we would obtain if we could sample the
According to Czaja and Blair (1996), the first questions should be: entire population.
Relevant to the central topic Probability sampling involves selecting subjects in such a way that the
Ineresting and easy to answer odds of their being in the study are known or can be calculated.

Answerable by most respondents Random selection: Use an unbiased method for selecting subjects.

Closed format Simple Random Sampling

Make sure your questions are value laden ● The most basic form of probability sampling is the simple random
a. Subjects do not have to think about a great deal sample, in which a portion of the whole population is selected in an

b. Subjects are able to answer without saying “I don’t know,” and unbiased way.

c. Subjects will think are relevant to the topic of the survey. Systematic Random Sampling
select every nth person from the population.
Stratified Random Sampling
Collecting Survey Data
A stratified random sample is obtained by randomly sampling from
people in each subgroup in the same proportions as they exist in the
Self-Administered Questionnaires population.
If you are using a written questionnaire, be sure the instructions are Cluster Sampling
simple and clear. If you are handing participants are randomly selected, but whole groups of people are
out your questionnaire in person, consider the possibility of reactivity. selected rather than individuals.
If possible, let subjects fill out the questionnaire in private. Nonprobability sampling: the subjects are not chosen at random
Mail Surveys Quota Sampling
Typical response rates for mailed surveys are somewhere between 45% ● In quota sampling, researchers select samples through predetermined
and 75% quotas that are intended to reflect the makeup of the population.
If you are sending a questionnaire in the mail, be sure to include a Convenience/Accidental Sampling
polite and professional cover letter.
● Convenience sampling is obtained by using any groups who happen
If you have the resources, including a small gift can increase the return
to be available.
rate
Purposive Sampling
One incentive technique that can be successful and cost-effective is to
● When nonrandom sample are selected because the individuals reflect
hold a drawing for a prize
a specific purpose of the study
On sensitive issues, some subjects just won’t answer, particularly if
Snowball Sampling
their answer would indicate they had engaged in socially undesirable,
deviant, or illegal activities. ● In snowball sampling, a researcher locates one or a few people who
Computer and Internet Survey fit the sample criterion and asks these people to locate or lead them to

there may be less concern with a social desirability response set additional individuals.

Interviews
● One of the best ways to gather high-quality survey data is to conduct E. Alternatives to Experimentation: Correlational
face-to-face interviews,
and Quasi-Experimental Designs
establishing rapport, avoiding judgmental statements, and knowing how
to keep the interview flowing.
Correlational Designs
Focus Groups Correlational and Quasi-Experimental Designs

● Focus groups are usually small groups of people with similar ● predict one set of behavior from others
characteristics who are brought together by an interviewer, called a ● establish relationships among pre-existing behaviors
facilitator, who guides the group in a discussion of specific issues. ● antecedents are neither manipulated or controlled
● show relationships between sets of antecedent conditions and
behavioral effects
○ Evaluating Surveys and Survey Data
Correlational Designs
The “goodness” of the survey itself is typically evaluated in two areas:
● A correlational study is designed to determine the correlation, or
Reliability
degree of relationship, between two traits, behaviors, or events.
● the extent to which the survey is consistent and repeatable.
In a correlational study, selected traits or behaviors of interest are
measured first.
Quasi-Experimental Designs
Simple correlations: relationships between pairs of scores from each
subject. KINDS OF QUASI-EXPERIMENTAL DESIGNS
A positive relationship, a negative relationship, and no relationship
Ex Post Facto Studies
● Ex post facto study: a study in which the researcher systematically
examines the effects of subject characteristics (often called subject
variables) but without actually manipulating them.
Ex post facto means “after the fact.” In effect, the researcher capitalizes
on changes in the antecedent conditions that occurred before the study.
Scatterplots In an ex post facto study, those preexisting differences become the
● Scatterplots, also known as scatter graphs or scattergrams: visual “manipulation,” and measuring the effects they produce is the objective
representations of the scores belonging to each subject in the study. of the research.
Regression lines, or lines of best fit: lines drawn on the scatterplots; Nonequivalent Groups Design
illustrate the mathematical equation that best describes the linear ● A nonequivalent groups design is one in which the researcher
relationship between the two measured scores. compares the effects of different treatment conditions on pre-existing
When the computed value of r is positive, there is a positive groups of participants.
correlation/direct relationship between vocabulary and TV viewing
Longitudinal Design
time
● Longitudinal designs: quasi-experiments that psychologists also use
A second possibility is a negative correlation/inverse relationship
to measure the behaviors of the same subjects at different points in time
between vocabulary and TV viewing time.
and look to see how things have changed.
A third possibility is no relationship
Pretest/Posttest Design
General linear model: the direction of the relationship between X and
● Sometimes we want to assess whether the occurrence of an event
Y generally remains the same. It does not change direction.
increases or decreases the existing level of a person’s behavior. We can
Correlation coefficients are also affected by range truncation, an
measure people’s level of behavior before and after the event and
artificial restriction of the range of values of X or Y.
compare these levels using a pretest/posttest design.
outliers (extreme scores) → a data value that is numerically distant
from a data set.
Linear Regression Analysis ● This design may be used to assess the effects of naturally occurring
events when a true experiment is not possible.
● Correlations can be used for prediction. When two behaviors are
Cross-sectional studies
strongly related, the researcher can estimate a score on one of the
measured behaviors from a score on the other → linear regression ● Cross-sectional study: another method that approximates results
analysis. from a longitudinal design. Instead of tracking the same group over a

Regression equation: a formula for a straight line that best describes long span of time, subjects who are already at different stages are

the relationship between the two variables. compared at a single point in time.

Partial correlation: allows the statistical influence of one measured

variable to be held constant while computing the correlation between
the other two—the partial correlation
multiple regression analysis can be used to predict the score on one
behaviors from scores on the others.

Causal Modeling
Path Analysis
● Path analysis can be used when subjects are measured on several
related behaviors where researchers create models of possible causal
sequences.
● Path analysis is another descriptive method, but it generates
important information for prediction and can generate experimental
hypotheses.
Cross-Lagged Panel Design
● Cross-lagged panel: uses relationships measure over time to suggest
the causal path.
● In a cross-lagged panel design, subjects are measured at two separate
points in time on the same pair of related behaviors or characteristics.
Then the scores from these measurements are correlated in a
particular way, and the pattern of correlations is used to infer the causal
path.
In a cross-lagged panel, we are looking for the largest diagonal
correlation to indicate the causal direction.