Skip to end of metadata
Go to start of metadata

 

From Eurostat Wilhelmus Kloek

 

3) Integrate data 5.1 contains many different things: national accounts, data linking, data matching, data integration. It requires more analysis, and probably some further distinctions

In addition to point 3 on integrate data comes the concrete question on how to describe datawarehouses. We should convince some colleagues that GSBPM cannot only be used to describe stovepipe processes, but also integrated systems.

Please indicate your support for this change using the stars and legend below

  • 5* (We should do this)
  • 4* (Good idea, but need to discuss)
  • 3* (I am not sure, we need to discuss)
  • 2* (Should not make the change, but need to discuss)
  • 1* (Should not make this change)

 

 

  • No labels

2 Comments

  1. ABS comment

    We agree that 5.1 should be more inclusive of any data (e.g. micro and macro level datasets).  It can also be undertaken using both exact matching and statistical (probabilistic) matching techniques.  In the ABS, we've changed the name of this sub-process to 'Link datasets', as the term 'Data integration' was perceived to also cover other activities covered elsewhere in the Process phase (e.g. derivation, imputation, validation).

     

  2. 12/11: It would be nice to have this as broader...but what to change?

    How does National Accounts fit here? 

    This is where the results of phase 4 processes are combined. Add words to this effect.

    A possibility is to call it data linking, is this actually a narrower term? There are a number of reasons while you are linking, combined and pulling data - weights creation etc, other than just producing a linked dataset.