Skip to main content

Table 4 Parameter estimation of id2 versus id4

From: Regression models for analyzing radiological visual grading studies – an empirical comparison

Model

GWscore

GQscore

BGscore

Est.

P-value

Est.

P-value

Est.

P-value

regressa

−0.050

0.199

−0.017

0.641

−0.054

0.141

(−0.126, 0.026)

(−0.087, 0.054)

(−0.126, 0.018)

ologita

−0.322

0.164

−0.13

0.603

−0.374

0.127

(−0.775, 0.131)

(−0.621, 0.361)

(−0.854, 0.107)

gologit2a

−0.215

0.488

−0.393

0.185

−0.596

0.046

=2

(−0.823, 0.392)

(−0.975, 0.189)

(−1.182, −0.010)

gologit2a

−0.472

0.182

0.629

0.228

0.104

0.82

=3

(−1.166, 0.221)

(−0.394, 1.653)

(−0.788, 0.996)

slogita

−0.592

0.194

−0.408

0.281

−0.743

0.052

(−1.485, 0.301)

(−1.150, 0.334)

(−1.491, 0.005)

mixedb

−0.050

0.176

−0.017

0.640

−0.054

0.14

(−0.122, .022)

(−0.087, 0.053)

(−0.126, 0.018)

meologitb

−0.3217

0.164

−0.126

0.598

−0.336

0.152

(−0.775, 0.131)

(−0.597, 0.344)

(−0.794, 0.123)

  1. 95 % confidence limits given in parentheses
  2. aregression model with fixed effects only
  3. bregression model with fixed and random effects