An experiment evaluating the effectiveness of an intervention for improving attitudes
about something finds that the mean posttest score of the experimental group is 70,
which is better than the control group’s mean posttest score of 65. The significance level
is .05, and the p value is .01. The standard deviation is 5.
The results certainly are substantively significant.
Managed care companies tend to be disinterested in the outcomes of program
evaluations.
Concepts are mental images that summarize collections of seemingly related
observations and experiences.
Multiple measurement points during baseline control for statistical regression.
Because of their philosophical differences, qualitative and quantitative methods are
inherently incompatible.
The tendency to give a favorable impression of oneself reduces the reliability of a
measure.
The best way to avoid contaminating the control condition is to locate the experimental
and control conditions in the same building
Our ego involvement can influence us to disregard evidence that contradicts our beliefs.
Each alternative form of measurement (written self-reports, interviews, direct
behavioral observation and examining available records) is vulnerable to measurement
error.
Conceptual equivalence ensures metric equivalence.
There is only one acceptable operational definition for any given variable in social work
research.
Quasi-experiments using nonequivalent comparison groups without random assignment
can be credible, assuming that the comparability of the experimental and comparison
groups is plausibleespecially if the researcher provides substantial evidence of that
comparability.
Random assignment to experimental and control groups controls for research reactivity.
Because social scientists rarely plan studies that could physically harm subjects, the
issue of no harm to subjects is not a real problem.
The problem of external validity refers to the generalizability of results.
Qualitative methods emphasize precise and generalizable statistical findings.
The standards for appraising the trustworthiness of qualitative research are the same
regardless of one’s epistemological paradigm.
Linguistic equivalence ensures conceptual equivalence.