Beruflich Dokumente
Kultur Dokumente
Confirmation Bias
• Once we believe we know something, we tend to overlook instances that might
disconfirm our beliefs, and we seek confirmatory instances of behavior instead.
2. Nonscientific Inference
• When we understand people’s behavior, there is a strong bias to overlook situational data
in favor of data that substantiate trait explanation.
Overconfidence Bias
• Our predictions, guesses, and explanations tend to feel much more correct than they
actually are, and the more data we have available, the more confidence we have in our
judgments about behavior.
THE SCIENTIFIC METHOD: TOOLS OF PSYCHOLOGICAL SCIENCE
SCIENTIFIC EXPLANATION IN PSYCHOLOGICAL SCIENCE
Antecedent Conditions
• Circumstances that come before the event or behavior we want to explain
Psychology Experiment
• Controlled procedure in which at least 2 different treatment conditions are applied to
subjects.
• Subjects behaviors are measured and compared to test a hypothesis about the effects of
those treatment on behavior
Experimental psychology refers to work done by those who apply experimental methods to the
study of behavior and the processes that underlie it. Experimental psychologists employ human
participants and animal subjects to study a great many topics, including (among others) sensation
& perception, memory, cognition, learning, motivation, emotion; developmental
processes, social psychology, and the neural substrates of all of these.
Experimental Designs
• Between Subjects: receive only one kind of treatment
• Within Subjects: present all treatments to each subject and measure the effect of each
treatment after it is presented
Elements of an experiment
• in order to show that there is a cause-effect relationship between two variables we have
two goals:
• it must be shown that changes in one variable cause changes in he other variable
• an experiment must rule out the possibility that the changes are caused by some
other variable
• these two goals lead to two characteristics differentiating experiments and other research
strategies
• manipulation of one variable while measuring a second variable
• control of other, extraneous variables
Control by randomization
• randomization is the use of a random process to help avoid a systematic
relationship between two variables
• the intent of randomization is to disrupt any systematic relation between
extraneous variables and the independent variable and thereby prevent the
extraneous variable from becoming a confounding variable
• e.g. IQ and memory or time of the day
• random assignment is the use of a random process to assign participants to
treatment conditions
• randomization is a powerful tool for controlling extraneous variables; its
primary advantage is that it offers a method for controlling a multitude of
variables simultaneously and does not require specific attention to each
extraneous variable
Control groups
• sometimes a researcher wishes to evaluate only one treatment rather than compare a set
of different treatments; in such case he selects an experimental group and a control group
• the term experimental group refers to the treatment condition in an experiment
• the term control group refers to the no-treatment condition in an experiment
• there are two types of control groups:
1. no-treatment control groups
2. placebo control groups
• no-treatment control group
• is a condition in which the participants do not receive the treatment being
evaluated
• this group provides the standard of normal behavior or baseline against the
treatment condition
• e.g. anxiety treatment group vs. no treatment control group
• placebo control groups
• placebo is a term for a fake medical treatment such as a sugar pill or water
injection
• placebo effect refers to a response by a participant to an inert medication that has
no real effect on the body; the placebo effect occurs simply because the individual
thinks the medication is effective
• e.g. use of inactive drugs or non-specific psychotherapy (therapy with the
therapeutic components removed)
Manipulation checks
• The purpose of the manipulation check is to assess whether the independent variable had
the intended effect on the participant
• Two ways to check manipulation
• An explicit measure of the independent variable
• E.g. a measure of mood in an mood inducing experiment
• Questionnaire for participants after the experiment whether they perceived and
how they interpreted the manipulation
• E.g. masked priming
• Manipulation checks are especially important in
• Participant manipulations
• E.g. frustration task
• Simulations
• Real world situations in the lab
• Placebo controls
• Whether participants believed that they received a real drug
Researcher-Manipulated Variable
In true experiments, the researcher has to change or manipulate the variable that is hypothesized
to affect the outcome variable that is being studied. The variable that the researcher has control
over is called the independent variable. The independent variable is also called the predictor
variable because it is the presumed cause of the differences in the outcome variable.
The outcome or effect that the research is studying is called the dependent variable. The
dependent variable is also called the outcome/criterion variable because it is the outcome that
the research is studying. The researcher does not manipulate the dependent variable.
Random Assignment
Research participants have to be randomly assigned to the sample groups. In other words, each
research participant must have an equal chance of being assigned to each sample group. Random
assignment is useful in that it assures that the differences in the groups are due to chance.
Research participants have to be randomly assigned to either the control or experimental group.
Advantages
The results of a true experimental design can be statistically analyzed and so there can be
little argument about the results.
It is also much easier for other researchers to replicate the experiment and validate the
results.
For physical sciences working with mainly numerical data, it is much easier
to manipulate one variable, so true experimental design usually gives a yes or no answer.
Disadvantages
Whilst perfect in principle, there are a number of problems with this type of design. Firstly,
they can be almost too perfect, with the conditions being under complete control and not
being representative of real world conditions.
For psychologists and behavioral biologists, for example, there can never be any guarantee
that a human or living organism will exhibit ‘normal’ behavior under experimental
conditions.
True experiments can be too accurate and it is very difficult to obtain a complete rejection or
acceptance of a hypothesis because the standards of proof required are so difficult to reach.
True experiments are also difficult and expensive to set up. They can also be very
impractical.
While for some fields, like physics, there are not as many variables so the design is easy, for
social sciences and biological sciences, where variations are not so clearly defined it is
much more difficult to exclude other factors that may be affecting the manipulated variable.
RESEARCH STRATEGIES AND VALIDITY
Research strategy
• reflects the general approach and goals of a research study
types of research strategies
• Descriptive strategy
• the goal is to describe the state of affairs at the time of the study
• measures variables as they exist naturally
• e.g. 19% of eligible voters participated in the election
• Correlational strategy
• measures two variables, usually as they exist naturally
• the goal of this strategy is to describe a relationship between the two variables
without attempting to explain the cause of the relationship
• e.g. Are students GPA’s related to their parent’s income?
• Nonexperimental strategy
• Answers questions about the relationship between two variables by demonstrating
a difference between two groups or two threatment conditions
• E.g. verbal scores of 6-years old boy and 6-years old girls
• Experimental strategy
• the researcher manipulates one variable (called independent variable) while
observing or measuring a second variable (dependent variable)
• this is the ‘true’ experiment because independent variable is manipulated by the
researcher (e.g. room temperature)
• the goal of experimental strategy is to determine whether a causal relationship
exists between two variables
• Quasi-experimental strategy
• uses a nonmanipulated variable to define groups or conditions (e.g. time or age)
or pre and post threatment
• controls other variables as much as possible
• the goal is to obtain evidence in support of a cause-and-effect relationship
• however, a quasi-experimental strategy can not unambiguously establish a causal
relationship
Internal validity
• is concerned with factors within the research study that raise doubts about the results or
the interpretation
• any factor within the study that allows an alternative explanation for the results is a threat
to internal validity
• e.g. example with room temperature and performance
Threats to internal validity
• Extraneous variables
• any variable in a research study other than the two variables being studied (both
systematic and unsystematic)
• unsystematically changing variables are usually not a problem
• confounding variable is an extraneous variable that is allowed to change
systematically along with the two variables being studied (e.g. time of the day in the
temperature-performance study)
• sources of extraneous/confounding variables
• participant variables
• assignment bias – when the process used to assign different participants to
different threatments produces groups of individuals with noticeably different
characteristics (e.g. one group is smarter, more motivated)
• environmental variables
• size of room, time of day, or gender of the experimenter
• measurement variables
• practice effects – prior exposure to a measurement procedure provides
participants with additional skills that produce improved scores (e.g. the same
exam)
• fatigue – prior participation tires the participants so that their scores on
subsequent measurements are lower
In their classic book on experimental research, Campbell and Stanley (1966) identify and discuss
8 types of extraneous variables that can, if not controlled, jeopardize an experiment's internal
validity.
1. History--These are the unique experiences subjects have between the various
measurements done in an experiment. These experiences function like extra, and
unplanned, independent variables. Compounding this, the experiences are likely to vary
across subjects which has a differential effect on the subjects' responses. Studies that take
repeated measures on subjects over time are more likely to be affected by history
variables than those that collect data in shorter time periods, or that do not use repeated
measures.
2. Maturation--These are natural (rather than experimenter imposed) changes that occur as
a result of the normal passage of time. For example, the more time that passes in a study
the more likely subjects are to become tired and bored, more or less motivated as a
function of hunger or thirst, older, etc. As Isaac and Michael (1971) point out, subjects
may perform better or worse on a dependent variable not as a result of the independent
variable but because they are older, more/less motivated, etc.
3. Testing--Many experiments pretest subjects to establish that all the subjects are starting
the study at approximately the same level, etc. A consequence of pretesting
programs/protocols is that they can contaminate/change the subjects' performance on
later tests (e.g., those used as dependent variables) that measure the same domain beyond
any effects caused by the treatment itself.
4. Instrumentation--Changing the measurement methods (or their administration) during a
study affects what is measured. Additionally, if human observers are used, it may be the
judgment of the observer(s) that change over time rather than the subjects' performance.
5. Statistical Regression--When subjects in a study are selected as participants because
they scored extremely high or extremely low on some measure of performance (e.g., a
test, etc.), retesting of the subjects will almost always produce a different distribution of
scores, and the average for this new distribution will be closer to the population's. For
example, if the chosen subjects all had high scores initially, the group's average on the
retest will be lower (i.e, less extreme) than it was originally. Conversely, if the group's
mean was originally low, their retest mean would be higher.
6. Selection--The subjects in comparison (e.g., the control and experimental) groups should
be functionally equivalent at the beginning of a study. If they are, then observed
differences between the groups, as measured by the performance dependent variable(s),
at the end of the study are more likely to be caused only by the independent variable
instead of organismic ones. If the comparison groups are different from one another at the
beginning of the study the results of the study are biased.
7. Experimental Mortality--Subjects drop out of studies. If one comparison group
experiences a higher level of subject withdrawal/mortality than other groups, then
observed differences between groups become questionable. Were the observed
differences produced by the independent variable or by the different drop out rates?
(Mortality is also a threat when drop out rates are similar across comparison groups but
high.)
8. Selection Interactions--In some studies the selection method interacts with one or more
of the other threats (described above), biasing the study's results.
External validity
• concerns the extent to which the results obtained in a research study hold true outside the
constraints of the study
• Can the results be generalized to other populations, other settings, other measurements?
• e.g. can we generalize results from a well-controlled laboratory situation to the
uncontrolled chaos of the real world?
Nonexperimental Approaches
Used in situations in which an experiment is not practical or desirable.
Nonexperimental Method
Used to study behaviors in natural settings to explore unique or rare occurrences or to
sample personal information
1. Phenomenology
Description of an individual’s immediate experience
Rather than looking at behaviors and events that are external to us, we begin with
personal experience as a source of data
Antecedents are not manipulated, and data may consist of any immediate experience; no
constraints are imposed
Used by mental philosophers
Disadvantage of Phenomenology:
We cannot be sure that the process we are observing in ourselves is not altered in
some way by our attention to it.
We may not be able to achieve the degree of accuracy and objectivity.
It will be difficult for others to replicate our experiences and apply scientific criteria
to our findings. Without replication, it cannot be known if others would have the
same experiences.
Phenomenology cannot be used to understand the causes of behavior. It can describe
but not explain.
It may lead us into areas of discovery that may lead us to formulate hypotheses, but
experimentation is still required to determine which antecedent conditions produce
the behavior or experience.
2. Case Studies
Involved no manipulation of antecedent conditions.
Descriptive record of a single individual’s experiences, or behaviors, or both, kept by an
outside observer.
Used in clinical, forensic and organizational psychology
5 major purposes
They are a source of inferences, hypotheses and theories.
They are a source for developing therapy techniques.
They allow the study of rare phenomena.
They provide exceptions, or counterinstances, to accepted ideas, theories, or
practices.
They have persuasive motivational value
Deviant Case Analysis
An extension of the evaluative case study
Cases of deviant and normal individuals are compared for significant differences
Disadvantage of Case Studies
We cannot be sure the people we are evaluating are representative of the general
population
We are not able to observe an individual directly all the time, we cannot be sure
that we are aware of all the relevant aspects of that person's life
Subject or others providing data for case studies might neglect to mention
important information either because they believe it is irrelevant or because they
find it embarrassing
Case studies frequently rely on retrospective data – data collected in the present
that are based on recollection of past events
3. Field Studies
Nonexperimental approaches used in the field or in real life settings.
Antecedent conditions are not manipulated but degree of constraints on responses varies
from study to study
Participants are composed of groups
2 Types:
Naturalistic Observation Studies
Participant Observation Studies
Naturalistic Observation Studies
Technique of observing behaviors as they occur spontaneously in natural setting
Imposes very few constraints
Should remain unobtrusive (can use unobtrusive measures)
Ethology
Used in animal research
Study behavior in the wild as well as in captivity
Disadvantage of Naturalistic Observation Studies:
We are dealing with specific samples of time that may or may not contain the
behaviors we want to observe
We might find that behaviors become very different when the subjects know they
are being watched (Reactivity)
Participant-Observer Studies
The researcher actually becomes part of the group being studied
Sometimes this is the only method that can used to study a group – particularly if
the group would not reasonably be expected to cooperate voluntarily with a
research investigation
Disadvantage of Participant-Observer Studies
◦ There is a possibility that the mere presence of an observer can alter subject’s
behaviors in unknown ways
◦ Sometimes observers in these studies find if difficult to remain objective and
unbiased.
◦ Often, particularly if friendships form, it is hard to remain an objective scientist.
4. Archival Study
A descriptive research method in which already existing records are reexamined for a
new purpose
Disadvantage of Archival Study
◦ Causal inferences cannot be supported all the time
5. Qualitative Research
Relies on words rather than numbers for the data being collected
It focuses on self-reports, personal narratives and expression of ideas, memories, feelings,
and thoughts,
Without understanding qualitative methods, one cannot really appreciate the breadth of
research methodology used by contemporary psychological scientists.
Candidate for paradigm shift
Disadvantage of Qualitative Research
Interpretation of data might be influenced by the researcher’s point of view
The presence of a researcher could influence the way subjects response
There is always a concern about the accuracy of self-reports as well as the use of
retrospective data
Internal and External Validity are issued of concern
ALTERNATIVES TO EXEPERIMENTATION: SURVEYS AND INTERVIEWS
SURVEY RESEARCH
o It is a useful way of obtaining information about people’s opinions, attitudes, preferences,
and behaviors simply by asking. Survey allow us to gather data about experiences,
feelings, thoughts and motives that are hard to observe directly.
o Examples:
1. Written questionnaires
2. Face-to-face interviews
3. Conducted by computer
4. Over the telephone
CONSTRUCTING SURVEYS
o STEPS IN COSTRUCTING SURVEY
1. Map out your research objectives (specific)
Ex.
General
The attitudes of other psychology students toward animal research in psychology
Specific
Animal rights, animal welfare, benefits to humanity, pain and suffering, humane treatment,
euthanasia, different species, animals used for class demonstrations, etc.
2. Design the survey items
a. Closed Questions (Structured Questions): must be answered by one of a limited
number of alternatives.
b. Open-ended Questions (Open Questions): soliciting information about opinions
and feelings by asking the question in such a way that the person must respond
with more than a yes, no, or 1-10 rating.
MEASURING RESPONSES
Open-ended questions – content analysis
It is just a matter of writing a simply worded questions that requires subjects to
answer in narrative form.
Closed questions – level of measurement
The level of measurement is the kind of scale used to measure a response
Nominal, ordinal, interval and ratio
Scales of measurement
• Scales define the type categories we use in measurement and the selection of a scale has
direct impact on our ability to describe relationships between variables
• the nominal scale
• simply represents qualitative difference in the variable measured
• can only tell us that a difference exists without the possibility telling the direction
or magnitude of the difference
• e.g. majors in college, race, gender, occupation
• the ordinal scale
• the categories that make up an ordinal scale form an ordered sequence
• can tell us the direction of the difference but not the magnitude
• e.g. coffee cup sizes, socioeconomic class, T-shirt sizes, food preferences
• the interval scale
• categories on an interval scale are organized sequentially, and all categories are
the same size
• we can determine the direction and the magnitude of a difference
• May have an arbitrary zero (convenient point of reference)
• e.g. temperature in Farenheit, time in seconds
• the ratio scale
• consists of equal, ordered categories anchored by a zero point that is not arbitrary
but meaningful (representing absence of a variable
• allows us to determine the direction, the magnitude, and the ratio of the difference
• e.g. reaction time, number of errors on a test
B.
1. If you are collecting demographic information, consider placing those questions at the
end of the questionnaire. (People will be more likely to answer demographic items if they
have already invested their time and energy in answering the survey questions up to this
point)
C.
Make sure your questions are not value laden. (Do not word your questions in ways that
would make a positive (or negative) response seem embarrassing (or undesirable.)
Be sure to keep the ethical guidelines in mind when you write survey questions.
RESPONSE STYLES
Response Styles are tendencies to respond to questions or test items in specific ways,
regardless of the content
Different response styles: willingness to answer, position preferences, and yea-saying and
nay-saying
WILLINGNESS TO ANSWER
Comes into play whenever questions require specific knowledge about facts or issues.
When unsure, some people will leave questions blank; others will take a guess.
Ex.
Tell the subjects....
To guess if they are not sure of the answer to a question
That are no right or wrong answers to the questions (if that is true)
Other researchers say nothing – and hope for the best
POSITION PREFERENCE
If your questions are multiple-choice, response styles can influence the selection of
answers.
Ex.
When in doubt about the right answer on a multiple-choice exam, perhaps you always
answer C
CORRELATIONAL DESIGNS
Correlational study
is one that is designed to determine the correlation, or degree of relationship, between
two traits, behaviors, or events.
Use correlational studies to explain behaviors that are not yet well understood.
In the correlational study, the researcher measures events without attempting to alter the
antecedent conditions in any way; the researcher is simply how well the measures go
together.
Simple Correlation
relationships between pairs of scores from each subject.
Pearson Product Moment Correlation Coefficient (r) is the most commonly used
procedure for calculating simple correlations with three general possible outcomes: a
positive relationship, a negative relationship, or no relationship.
Correlation does not imply causation. Why? because the causal direction between two
variables cannot be determined by simple correlations.
Bidirectional causation: Variable #2 may affect variable #1 or the other way
around BUT NOT A CAUSE
Third variable problem: some third agent are causing two behaviors to appear to
be related.
Coefficient of determination (r2):
estimates the amount of variability in scores on one variable that can be explained by the
other variable – an estimate of the strength of the relationship between them.
CAUSAL MODELING
1. PATH ANALYSIS
- uses beta weights from multiple regression analysis to generate possible direction of
cause and effect from correlated variables
2. CROSS-LEGGED PANEL DESIGN
- measures the same pair of variables at two different points in time; look at patterns of
correlations across time for possible direction of cause and effect.
QUASI-EXPERIMENTAL DESIGNS
QUASI-EXPERIMENTAL DESIGNS
investigates differences in preexisting groups of subjects; group differences on some
variable may be explored or different treatments given to preexisting groups may be
compared.
like an experiment, typically involves a comparison of groups or conditions
however, it uses a nonmanipulated variable to define groups or conditions being
compared such as age, gender or time (before vs. after treatment)
within the context of quasi-experimental research, the variable that is used to differentiate
the groups of participants or the groups of scores being compared is called the quasi-
independent variable (e.g. age)
the variable that is measured to obtain a score for each individual is called the dependent
variable (e.g. IQ score)
Types
EX POST FACTO STUDIES: explores characteristics, behaviors, or effects of naturally
occurring events in preexisting groups of subjects
NONEQUIVALENT GROUPS: compares the effects of different treatment conditions
on preexisting groups of subjects
LONGITUDINAL DESIGN: investigate changes across time by measuring behavior of
same group of subjects at different points in time.
CROSS-SECTIONAL STUDIES: investigates changes across time by comparing
groups of subjects already at different stages at a single point in time
PRETEST/POSTTEST DESIGN: explores the effects of an event (or treatment) by
comparing behavior before and after the event (or treatment)
Disadvantages
• large number of participants (problem with special populations)
• individual differences
• characteristics that differ from one participant to another are called individual
differences
• individual differences can become confounding variables
• individual differences can produce high variability in the scores
Confounding variables in between subjects designs
• individual differences
• participant characteristics differ from one group to another
• e.g. the participants in one group may be older, smarter, taller etc. than the
participants in another group
• environmental variables
• characteristics of the environment differ between groups
• e.g. one group may be tested in a large room and another group in a
smaller room
• Equivalent groups
• in a between-subjects experimental design, the researcher does have control over
the assignment of individuals to groups
• the separate groups must be:
• created equally
• treated equally (except for the treatment conditions)
• composed of equivalent individuals
• order effects
• carryover effects
• changes in behavior or performance that are caused by participation in an earlier
treatment condition
• carryover effects exist whenever one treatment condition produces a change in
the participants that affects their scores in subsequent treatment conditions (e.g.
new skill from treatment 1 can influence results in treatment 2)
• progressive error
• changes in participant's behavior or performance that are related to experience
over time in a research study but not related to a specific treatment or treatments
(e.g. practice effects and fatigue)
controlling time
• if the different treatment conditions are scheduled over a period of weeks, the chances
greatly increase that the results will be influenced by some outside event (history) or
maturation or change in the measurement instrument
when a within-subjects design is not a good idea
• e.g. comparing two methods of teaching reading to first-grade children (carryover effects)
counterbalancing
• involves changing the order in which treatment conditions are administered from one
participant to another
• the goal is to use every possible order of treatment with an equal number of individuals
participating in each sequence
• the purpose of counterbalancing is to eliminate the potential for confounding by
disrupting any systematic effects from factors related to time or the order of treatments
• e.g. with two treatments one half of the participants begins in treatment 1, then moves to
treatment 2 and the other half begins in treatment 2, then receives treatment1
• two-treatment designs
• a repeated-measures t test or an analysis of variance can be used to evaluate the
statistical significance of the mean difference
• if the data are measured on an ordinal scale, a Wilcoxon test can be used to
evaluate significant differences
• multiple-treatment designs
• with too many treatment conditions, the distinction between treatments may
become too small to generate significant differences in behavior
• statistical analysis – repeated-measures analysis of variance to test for any
significant differences among the treatment means
Matched-subjects designs
• each individual in one group is matched with a participant in each of the other groups
• the matching is done so that the matched individuals are equivalent with respect to a
variable that the researcher considers to be relevant to the study (e.g. IQ)
• maintains all the advantages of between-subjects and within-subjects designs without the
limitations of either (e.g. eliminates individual differences, time-related factors and order
effects)
FACTORIAL DESIGNS
Research attempts to answer a general question about a large group of individuals, as opposed to
a specific question about a few, unique individuals. therefore, researchers typically want to
generalize or extend their results beyond the individuals who participate in a study
Population
• is the entire set of individuals of interest to a researcher
• although the entire population usually does not participate in a research study, the results
from the study are generalized to the entire population
Sample
• a set of individuals selected from a population and usually is intended to represent the
population in a research study
Target population
• the entire set of individuals who have the characteristics required by the researcher
• e.g. the whole population of people with eating disorders in the world or the US
Accessible population
• a subset of the target population, consisting of those individuals who are accessible to be
recruited as participants in the study
• e.g. people with eating disorders in local clinics
the sample
• a subset of the accessible population, consisting of those individuals who are selected to
participate in the research study
• 10% of the people with eating disorders in local clinics
• representative samples
• representativeness of a sample
• refers to the extent to which the characteristics of the sample accurately
reflect the characteristics of the population
• a representative sample
• is a sample with the same characteristics as the population
• a biased sample
• is a sample with different characteristics from those of the population
• selection bias
• occurs when participants or subjects are selected in a manner that
increases the probability of obtaining a biased sample
• e.g. a sample from the people in a university parking lot is not
representative of the adult population
SAMPLING BASICS
• sampling
• is the process of selecting individuals for a study
• probability sampling
• the entire population is known, each individual in the population has a
specifiable probability selection and sampling is a random process
• nonprobability sampling
• the population is not completely known, individual probabilities cannot be
known
• we try to avoid bias and maintain representativeness
Convenience sampling
• the most commonly used sampling method in psychological research
• researchers simply use as participants those individuals who are easy to get (e.g. INDV
students or volunteers)
• two strategies to help correct most of the serious problems associated with convenience
sampling
• researchers try to ensure that their samples are reasonably representative and not
strongly biased
• researchers provide a clear description of how the sample was obtained who the
participants are in their research studies
Quota sampling
• researcher first identifies specific subgroups to be included in the sample and then
establishes quotas for individuals to be selected from each subgroup
• e.g. 30-preschool children, parents respond to an ad, you don’t take the first 30 but
impose a quota of 15 girls and 15 boys
Purposive sampling
nonrandom samples are selected because the individuals reflect a specific purpose of the
study
these have set of criteria
Snowball sampling
A researcher locates one or a few people who fit the sample criterion and asks these
people to locate or lead them to additional individuals.