1979
DOI: 10.1111/j.1745-3984.1979.tb00094.x
|View full text |Cite
|
Sign up to set email alerts
|

Internal Invalidity in Studies Employing Self‐report Instruments: A Suggested Remedy

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

5
103
0

Year Published

1981
1981
2024
2024

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 123 publications
(108 citation statements)
references
References 4 publications
5
103
0
Order By: Relevance
“…The findings of the present study favor the retrospective pre/post self-report measure of change in providing a measure of self-reported change that better reflects the objective index of change on a construct of knowledge rating. This finding is in line with previous psychometric research (e.g., Hoogstraten, 1982;Howard & Dailey, 1979;Howard, Schmeck, & Bray, 1979;Spranger & Hoogstraten, 1989), and is most likely a result of the self-report posttest and the retrospective selfreport pretest being filled out with respect to the same internal standard, the same metric. This, therefore, mitigates the treatment-induced response shift bias, minimizes errors of measurement, and provides an unconfounded and unbiased estimate of the treatment effect .…”
Section: Treatment Effects In the Retrospective Pre/post Designsupporting
confidence: 90%
See 4 more Smart Citations
“…The findings of the present study favor the retrospective pre/post self-report measure of change in providing a measure of self-reported change that better reflects the objective index of change on a construct of knowledge rating. This finding is in line with previous psychometric research (e.g., Hoogstraten, 1982;Howard & Dailey, 1979;Howard, Schmeck, & Bray, 1979;Spranger & Hoogstraten, 1989), and is most likely a result of the self-report posttest and the retrospective selfreport pretest being filled out with respect to the same internal standard, the same metric. This, therefore, mitigates the treatment-induced response shift bias, minimizes errors of measurement, and provides an unconfounded and unbiased estimate of the treatment effect .…”
Section: Treatment Effects In the Retrospective Pre/post Designsupporting
confidence: 90%
“…The conventional self-report pretest and the recalled self-report pretest were only separated by four months, which may have in part mitigated the effect of memory distortion. Previous research (e.g., Finney, 1981;Howard, Dailey, & Gulanick, 1979;Howard, Schmeck, & Bray, 1979;Maisto et al, 1982), nonetheless, suggests that a pretesting effect can be mitigated and moderate-to-high recall accuracy is possible when cognitive constructs are measured (such as knowledge ratings) and when retrospective questions are specific and anchors on response scales are explicit (these conditions are consistent with those used in this study).…”
Section: Testing For Threats To Validitysupporting
confidence: 84%
See 3 more Smart Citations