Textbook Notes (280,000)
US (110,000)
UMD (1,000)
CCJS (70)
Chapter 3

CCJS 300 Chapter Notes - Chapter 3: Spurious Relationship, Internal Validity, Measuring Instrument

Criminology and Criminal Justice
Course Code
CCJS 300
Alan Lehman

This preview shows pages 1-2. to view the full 6 pages of the document.
-Research design: the plan or blueprint for a study, includes who, what, where, when, why and
how of the investigation
-Most studies are variations of the experimental model
-X: treatment (independent variable)
-Y: outcome (dependent variable), usually subject of the study
-Z: any rival causal factor
-O: observation
-E: equivalence
-1, 2: time
-Ultimate purpose of all scientific investigation is to isolate, define, and explain the relationship
between key variables in order to predict and understand the underlying nature of reality
-Causation lies at the basis of reality
-Three steps for resolving causality problem:
-Demonstration of a relationship or covariance between variables
-Specifying or indicating the time sequence of the relationship
-Exclusion of rival causal factors, elimination of other variables that could conceivably
explain away the original relationships the researcher had claimed
-Rival causal factors: variables other than X, that may be responsible for the outcome
-By excluding rival causal factors, researchers are trying to show a nonspurious relationship
-Spurious relationship: a false relationship that can be explained away by other variables
-Correlation or relationship does not imply causation
-Rival causal factors can either be internal or external
-Internal: other variables within the study itself that may tend to invalidate one’s findings
-External: elements outside of one’s immediate study that may imperil the researcher’s
attempts to draw generalizations from the study and infer one’s findings to be true of larger
-Internal factors question internal validity, extern factors question external validity
-Internal validity: accuracy within the study itself
-External validity: accuracy in the ability to generalize or infer findings from a study to a larger
-Internal factors:
-History: specific events other than the treatment that during the course of a study may
be responsible for producing the results
-Maturation: biological or psychological changes in the respondents during the course of
a study that are not due to the treatment variable
-Testing: the bias and foreknowledge introduced to respondents as a result of having
been pretested
-Instrumentation: changes in the measuring instrument during the course of a study
that invalidate comparisons
-Statistical Regression: tendency of groups that have been selected for study on the
basis of extreme high or low scores to regress (fall back) toward the mean on second

Only pages 1-2 are available for preview. Some parts have been intentionally blurred.

-Selection bias: involves choosing nonequivalent groups for comparison
-Experimental Mortality: loss of subjects over the course of time
-Selection-Maturation Interaction: combination of errors introduced by selection bias
plus the differential maturation of groups
-External factors:
-Testing effects: pretest effects or bias that is introduced as a result of having been
pretested, may also invalidate the ability to generalize to larger populations
-Selection bias
-Reactivity/Awareness of Being Studied: atypical or artificial behavior produced by
respondent’s awareness of being studied
-Multiple-Treatment Interferences: outcome produced by combinations of treatments;
it may be difficult to isolate the specific combination(s) responsible
-Related Rival Causal Factors
-Hawthorne effect: subjects behave atypically if aware of being studied
-Halo effect: Observer bias; observers follow an initial tendency to rate certain objects
or subjects in a biased manner
-Self-fulfilling prophecy: has a major bearing upon bias of the researcher, a
researcher’s hidden biases and expectations may influence his or her perception
of events so as to bring about that which was assumed
-Post Hoc Error: incorrect assumption that because one variable precedes another in
time, it is the cause of the outcome
-Placebo effect: tendency of control groups to react to believed treatment in a positive
-Double-blind experiment: neither the subjects nor administrators in an
experiment know which group is receiving the treatment
-Research designs: means of controlling for invalidity in research through experimental design
-Three types:
-Experimental: random assignment to treatment and control groups and include the
classical, posttest only control group, and Solomon four-group designs
-Quasi-experimental: do not use random assignment of groups and instead employ
matching or other means of obtaining equivalence of groups, include time-series and
counterbalanced designs
-Pre-experimental designs: lack any equivalence of groups and include one- and two-
group ex post facto and one-group before-after designs
-Classic experimental design: E O1 X O2
E O1 O2
-Serves as a prototype for all other research designs and contains three elements: equivalence,
pretests and posttests, and experimental and control groups
-Equivalence: the attempt to select and assign subjects to experimental and control
groups in such a manner that they are as similar as possible
-Randomization: the random assignment of subjects from a similar population to one or
another group
You're Reading a Preview

Unlock to view full version