Skip to main content

Table 3 Descriptive statistics and reliability values for study measures

From: Validity evidence for the Hamburg multiple mini-interview

  N M SD Min / Max Skewness Shapiro-Wilk Test Reliability
MMI 196 3.63 .47 2.38 / 4.69 −.35 W = 0.99, p < .05 Overall = .65a: ICC = .68
Study 1:
 Global Trait Emotional Intelligence (TEIQue-SF) 247 5.38 .62 3.57 / 6.63 −.51 W = 0.98, p < .001 α = .86
 Emotion Management (STEM) 247 1.11 .23 .71 / 2.38 1.59 W = 0.90, p < .001 α = .94
Study 2:
 GP psychosocial competencies 195 4.53 .72 1.00 / 5.00 −2.46 W = 0.68, p < .01 α = .94b: ICC = .88 / .92b
 GP suitability 193 3.71 .54 1.00 / 4.00 −2.20 W = 0.60, p < .01 ICC = .73 / .61c
Study 3:
 OSCE 301 199.65 10.17 164 / 221 −1.13 W = 0.93, p < .001 α = .53d
  1. N = number of students, M = mean, SD = standard deviation, Min / Max = minimum and maximum value, α = Cronbach’s Alpha, ICC = intraclass correlation for interrater reliability
  2. MMI = multiple mini-interview, TEIQue-SF = Trait Emotional Intelligence Questionnaire Short Form, STEM = Situational Test of Emotion Management, GP = general practitioner, OSCE = objective structured clinical examination
  3. aOverall reliability was estimated by means of a mixed-model. See Hissbach, et al. [15] for more details on the formula
  4. bAlpha refers to the internal consistency of five items. ICCs refer to the interrater-agreement for the average measure of the five items in cases of two raters (first value, n = 53) and in cases of three raters per subject (second value, n = 74)
  5. cInterrater-agreement for one item in cases of two raters (first value, n = 51) and in cases of three raters per subject (second value, n = 74)
  6. cAlpha refers to the internal consistency of twelve station scores