Agreement And Rating Scales

Karanicolas PJ, Bhandari M, Kreder H, Moroni A, Richardson M, Walter SD, Norman GR, Guyatt GH. Cooperation for the evaluation of results in musculoskeletal surgical studies G: evaluation of the agreement: completion of a reliability study. J Bone Joint Surg Am. 2009;91 (Suppl 3):99-106. Alternatively, Likert-scale responses can be analyzed using an orderly probit model, while maintaining the order of responses without a range scale being retained. Using an orderly probit model can prevent errors that occur when processing ordered assessments as a measure of interval level. [18] Sackett DL, Rosenberg WMC, Gray JAM, Haynes RB, Richardson WS. Evidence-based medicine: what it is and what it is not – it`s about integrating individual clinical expertise and the best external evidence. Br Med J. 1996;312 (7023):71-2. The studies of Labovitz[23] and Traylor[24] show that Likert-Artige elements, even in the case of fairly significant distortions of perceived distance between scales, work closely with scales perceived as identical intervals.

Therefore, these and other scales that appear identical in the questionnaires are robust against offences at the same distance that many researchers consider necessary for parametric statistical methods and tests. From the first survey to the second survey, 12% of the evaluations of all participants changed in three points, 25% on the five-point scale and 32% on the nine-point scale (Table 3). Sensitivity analysis shows that after the transformation, 9% of the evaluations of participants in the second survey were changed on the nine-point scale. With the exception of the nine-point scale, participants assessed treatment goals in the second phase of the survey with significantly higher expectations than the first survey. The objective of the Delphi study [34] in this manuscript was to identify the “primary treatment objectives” of patients who were intended for PCDs. In order to examine the influence of different scales of evaluation on the resulting consensus, we compared the proportion of proposed treatment targets, which reached a consensus on the “main objectives” between the three scales, as a precondition for the Delphi study itself [34]. To allow for comparability of the results, treatment objectives considered “very important” on the five-point scale or, rather, “9, 8, 7” on the nine-point scale, were presented as “the primary objective.”