Skip to main content

Advertisement

Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Table 5 Multinomial regression of number of lessons per week on PL

From: The standard setting process: validating interpretations of stakeholders

Criterion Predictors Model A Model B Model C Model D
OR SE log odds OR SE log odds OR SE log odds OR SE log odds
0 vs. 1 Science 0.65 0.31 0.72 0.30 0.72 0.30 0.77 0.31
Mathematics    0.83 0.11 0.84 0.11 0.93 0.07
German      0.98 0.07 1.00 0.06
School type        1.49 0.35
1 vs. 2 Science 0.58* 0.15 0.62* 0.15 0.63* 0.15 0.66* 0.15
Mathematics    0.73* 0.05 0.73* 0.04 0.80* 0.04
German      0.95 0.04 1.01 0.04
School type        1.54* 0.16
2 vs. 3 Science 0.55* 0.08 0.55* 0.08 0.56* 0.09 0.58* 0.09
Mathematics    0.85* 0.04 0.81* 0.04 0.84* 0.05
German      0.91 0.06 1.05 0.06
School type        1.65* 0.19
3 vs. 4 Science 0.53* 0.12 0.52* 0.12 0.53* 0.13 0.53* 0.14
Mathematics    0.86 0.08 0.72 0.23 0.66 0.25
German      0.81 0.28 1.00 0.39
School type        2.00 0.75
  1. For each cut score, the reference category of the dependent variable PL in science is the consecutive cut score. Mplus does not provide Pseudo R2 for multinomial logistic regressions. The Nagelkerke R2 for the four models calculating manifest regressions in SPSS for all five PVs are: \(R^{2}_{{{\text{Model}}\;{\text{A}}}}\) = 0.17–0.20, \(R^{2}_{{{\text{Model}}\;{\text{B}}}}\) = 0.21–0.23, \(R^{2}_{{{\text{Model}}\;{\text{C}}}}\) = 0.21–0.23, \(R^{2}_{{{\text{Model}}\;{\text{D}}}}\) = 0.22–0.24. OR = odds ratio, SElog odds = standard error of the log odds
  2. p < 0.05