Skip to main content

Table 4 Comparison of Brier Score and Area Under the Curve (AUC) between Bayesian and Multiple Imputation models for the prediction of overseas travel status of campylobacteriosis cases

From: Filling gaps in notification data: a model-based approach applied to travel related campylobacteriosis cases in New Zealand

Accuracy measure

Complete dataa

Missing datab

Frequentist

Bayesian

Multiple Imputation

Bayesian

  

10 %

50 %

65 %

80 %

10 %

50 %

65 %

80 %

Brier Score

0.062

0.062

0.067

0.24

0.18

0.19

0.062

0.063

0.062

0.063

AUCc

0.67

0.67

0.64

0.49

0.42

0.49

0.67

0.67

0.65

0.64

  1. a n = 44,285
  2. bFour categories of artificially introduced missing data (10 %, 50 %, 65 % and 80 % missing overseas travel status)
  3. cArea Under the Receiver Operating Characteristic Curve
Back to article page

BMC Infectious Diseases

ISSN: 1471-2334

Contact us