Table 5

Parameter estimates from the final model of the logistic regression analysis (stepwise forward procedure) performed using CCSVI as the dependent variable.

Parameter Estimates


CCSVIa

B

Std Error

Wald

df

Sig.

Exp(B)

95% Confidence interval for Exp(B)


Lower limit

Upper limit


1

Intercept

1.204

1.153

1.089

1

.297

[CENTRE = 1]

-2.199

1.056

4.338

1

.037

.111

.014

.878

[CENTRE = 2]

.356

1.190

.089

1

.765

1.427

.139

14.695

[CENTRE = 3]

-.183

1.260

.021

1

.885

.833

.070

9.844

[CENTRE = 4]

-2.534

1.056

5.764

1

.016

.079

.010

.628

[CENTRE = 5]

-2.217

1.157

3.671

1

.055

.109

.011

1.052

[CENTRE = 6]

0b

.

.

0

.

.

.

.

EDSS

.228

.080

8.066

1

.005

1.256

1.073

1.470

Age at onset

.047

.018

6.778

1

.009

1.049

1.012

1.087


The centre-defining variable (5 df) was forced to enter. Positive B values indicate a higher probability of CCSVI+.

Bastianello et al. BMC Neurology 2011 11:132   doi:10.1186/1471-2377-11-132

Open Data