Skip to main content

Table 4 Quality indicators for cell deviations from target (full population version of BHP)—district#3-digit-industry level—with censoring

From: Population aggregates from administrative data samples–how good are they?

 

Workers

 

BHP 50%

fixed weight (uncensored)

BHP 50%

fixed weight (censored)

SIAB Individual File—fixed weight (uncensored)

SIAB Individual File—fixed weight (censored)

SIAB Individual File—rand. weight (censored)

Absolute deviation

 Mean

− 2.5

− 2.5

− 1.0

− 12.5

− 0.8

 p-value

0

0.002

0

0

0.001

 rmse

596.3

699.2

148.8

228.7

209.1

 mae

144.1

250.5

82.9

149.4

111.4

 Ratio

0.323

0.561

0.186

0.334

0.249

Percentage deviation

 Mean

0

12

0

1.452

0.179

 p-value

0.679

0

0.893

0

0.004

 mape

0.519

12.354

0.787

2.292

1.008

Percentage deviation (size weighted)

 Mean

− 0.006

− 0.006

− 0.002

− 0.028

− 0.002

 p-value

0

0.002

0

0

0.001

 mape

0.323

0.561

0.186

0.334

0.249

 N

789,616

789,616

789,616

789,616

789,616

  1. The table shows various quality indicators for cell deviations from the target dataset (the full population version of the BHP) at the district#3-digit-industry level, including absolute deviations, percentage deviations and percentage deviations weighted by cell size. Approximations are calculated for the number of workers, and censored cells are replaced by the year-specific mean cell size. Calculations are based on the 50 percent sample of the BHP (fixed weight: censoring below 20 establishments) and the SIAB Individual File (fixed weight: censoring below 20 workers; random weight: censoring below 4 workers), respectively. Indicators are the mean error (mean), root mean squared error (rmse), mean absolute error (mae), mean absolute percentage error (mape) and ratio of the total sum of errors to the total sum of cell counts (ratio). p-values for a test of (mean) against zero are shown in (p-value)
  2. Sources: Establishment History Panel (BHP)—Version 7519 v2 (https://doi.org/10.5164/IAB.BHP7519.de.en.v2); Sample of Integrated Labour Market Biographies (SIAB)—Version 7519 v1 (https://doi.org/10.5164/IAB.SIAB7519.de.en.v1), own calculations