CHAPTER 3 - ALTERNATIVES TO EXPERIMENTATION: NONEXPERIMENTAL DESIGNS
NON EXPERIMENTAL APPROACHES PHENOMENOLOGY
➔ do not create levels of an independent ➔ involves a subject's description of personal
variable nor randomly assign subjects to subjective experience. Phenomenology is
these levels. They are used where low in manipulation of antecedent conditions
experiments are not ethical or possible, or and low in imposition of units (low-low).
where we want to test hypotheses in realistic
CASE STUDIES
conditions.
➔ Nonexperimental studies are more frequently
conducted in real-world settings with a more ➔ a researcher compiles a descriptive study of
diverse sample of participants than a subject's experiences, observable
experiments. behaviors, and archival records kept by an
outside observer.
➔ Case studies range from low-low to low-high.
INTERNAL VALIDITY
Case studies have several advantages:
● source of inferences, hypotheses, and
➔ is the degree to which a researcher can theories
establish a causal relationship between the ● source of therapy techniques
independent and dependent variables. ● allow study of rare phenomena
➔ An experiment has high internal validity ● provide exceptions to accepted ideas,
when we can demonstrate that only the theories, and practices
antecedent conditions are responsible for ● persuasive and motivational value
group differences in behavior. (advertising)
➔ An internally valid experiment allows us to Case studies have several limitations:
draw cause-and-effect conclusions. ● representativeness of sample
➔ Laboratory experiments are often higher in ● completeness of data
internal validity because of their control of ● reliance on retrospective data
extraneous variables.
DEVIANT CASE ANALYSIS
➔ Researchers create levels of the IV and use
procedures like matching and random
assignment to conditions. ➔ researchers examine differences between
deviant and normal individuals to identify
etiological factors.
EXTERNAL VALIDITY
➔ This approach may also be applied to
nonclinical issues such as social trends and
➔ is the degree to which research findings can adult morale.
be generalized to other settings and
individuals.
RETROSPECTIVE DATA
DEGREE OF MANIPULATION OF ANTECEDENT
➔ are recollections of past events that are
CONDITIONS
collected in the present.
➔ While your childhood memories constitute
➔ concerns assignment of subjects to retrospective data, your undergraduate
antecedent conditions created for the portfolio does not since it was collected in
experiment. the past.
WHAT ARE THE RISK OF RETROSPECTIVE
DEGREE OF IMPOSITION OF UNITS
DATA?
➔ This information may be compromised by
➔ is how much you limit a subject's responses faulty memory, current mood, and the
on the DV. retrieval cues that are present when you are
asked to recall an event.
NON EXPERIMENTAL APPROACHES PHENOMENOLOGY
➔ do not create levels of an independent ➔ involves a subject's description of personal
variable nor randomly assign subjects to subjective experience. Phenomenology is
these levels. They are used where low in manipulation of antecedent conditions
experiments are not ethical or possible, or and low in imposition of units (low-low).
where we want to test hypotheses in realistic
CASE STUDIES
conditions.
➔ Nonexperimental studies are more frequently
conducted in real-world settings with a more ➔ a researcher compiles a descriptive study of
diverse sample of participants than a subject's experiences, observable
experiments. behaviors, and archival records kept by an
outside observer.
➔ Case studies range from low-low to low-high.
INTERNAL VALIDITY
Case studies have several advantages:
● source of inferences, hypotheses, and
➔ is the degree to which a researcher can theories
establish a causal relationship between the ● source of therapy techniques
independent and dependent variables. ● allow study of rare phenomena
➔ An experiment has high internal validity ● provide exceptions to accepted ideas,
when we can demonstrate that only the theories, and practices
antecedent conditions are responsible for ● persuasive and motivational value
group differences in behavior. (advertising)
➔ An internally valid experiment allows us to Case studies have several limitations:
draw cause-and-effect conclusions. ● representativeness of sample
➔ Laboratory experiments are often higher in ● completeness of data
internal validity because of their control of ● reliance on retrospective data
extraneous variables.
DEVIANT CASE ANALYSIS
➔ Researchers create levels of the IV and use
procedures like matching and random
assignment to conditions. ➔ researchers examine differences between
deviant and normal individuals to identify
etiological factors.
EXTERNAL VALIDITY
➔ This approach may also be applied to
nonclinical issues such as social trends and
➔ is the degree to which research findings can adult morale.
be generalized to other settings and
individuals.
RETROSPECTIVE DATA
DEGREE OF MANIPULATION OF ANTECEDENT
➔ are recollections of past events that are
CONDITIONS
collected in the present.
➔ While your childhood memories constitute
➔ concerns assignment of subjects to retrospective data, your undergraduate
antecedent conditions created for the portfolio does not since it was collected in
experiment. the past.
WHAT ARE THE RISK OF RETROSPECTIVE
DEGREE OF IMPOSITION OF UNITS
DATA?
➔ This information may be compromised by
➔ is how much you limit a subject's responses faulty memory, current mood, and the
on the DV. retrieval cues that are present when you are
asked to recall an event.
