Skip to main content

Table 1 Percentage of missing values in each field in the two datasets

From: A blinded evaluation of privacy preserving record linkage with Bloom filters

 

Hospital Morbidity

Mortality

Number of records

5,580,353

68,955

Fields (% missing)

 Given Name 1

1.9%

0.1%

 Given Name 2

50.6%

23.2%

 Given Name 3

99.0%

93.5%

 Surname

0.0%

0.0%

 Sex

0.0%

0.0%

 Date of birth

0.0%

0.1%

 Address

0.0%

0.3%

 Suburb

0.0%a

0.5%

 Postcode

0.0%b

1.3%

  1. aIncreased to 0.1% after data cleaning
  2. bIncreased to 0.1% after data cleaning