X hits on this document

598 views

0 shares

0 downloads

0 comments

110 / 156

Questions 7-23 are concerned with the implementation/effectiveness (I/E) aspects of the study.

  • 7.

    What type of experimental design was used in the I/E and F/B portions of the study?

    • See algorithm adapted from Zaza et al. (2000; Figure E.1)

    • Choose the one design that best fits the I/E portion of the study.

    • If your study has both I/E and F/B portions, then select the appropriate design(s) and indicate to which portion of the study the design is applicable with the use of “I/E” and “F/B” in the accompanying text box. Include both I/E and F/B in the same text box, if both portions of the study use the same design.

  • 8.

    Are you confident that the means of selecting and maintaining the sample minimized bias in the I/E portion of the study?

    • In the comment box following your response, note the rationale for your selection.

    • This question addresses sampling bias, selection bias, bias due to withdrawals, selection threat to internal validity,34 or any other bias arising from the selection and maintenance of the sample

      • o

        Sampling bias: systematic error due to study of a non-random sample of a population

        • o

          Selection bias: error due to systematic differences in characteristics between those who take part in a study and those who do not

        • o

          Bias due to withdrawals: A difference between the true value and that actually observed in a study due to the characteristics of those subjects who choose to withdraw.

        • o

          Selection threat to internal validity: A threat to internal validity arising from differing characteristics of subjects in the intervention and comparison groups

Intervention-only studies

  • Before-after and time-series-without-comparison-group designs are unlikely to receive a response of “yes”, because the workplace selected for the study is typically not randomly selected

  • Studies with samples comprised of volunteers are unlikely to receive a response of “yes” because volunteers are typically different than the target population.

34 This term is from the key reference on quasi-experimental designs: Cook TD, Campbell DT (1979) Quasi-experimentation design & analysis issues for field settings. Boston: Houghton Mifflin. It also appears in the updated chapter: Cook TD et al. (1990) Quasi experimentation In: Dunnette MD, Hough LM (eds.) Handbook of Industrial and Organizational Psychology, 2nd ed. Palo Alto, Ca.: Consulting Psychologists Press.

Effectiveness of Occupational Health & Safety Management Systems: A Systematic Review

107

Document info
Document views598
Page views602
Page last viewedWed Jan 18 16:39:27 UTC 2017
Pages156
Paragraphs3709
Words49639

Comments