Administrative Data and their Use in Economic Statistics

  • Slides: 27
Download presentation
Administrative Data and their Use in Economic Statistics Vladimir Markhonko United Nations Statistics Division

Administrative Data and their Use in Economic Statistics Vladimir Markhonko United Nations Statistics Division Vladimir Markhonko 12/7/2007

Contents Ø Definitions Ø Advantages of using administrative data Ø Common problems Ø Quality

Contents Ø Definitions Ø Advantages of using administrative data Ø Common problems Ø Quality of administrative data Ø Using administrative data in practice Ø Conclusions Vladimir Markhonko 12/7/2007

Narrow Definition Vladimir Markhonko 12/7/2007

Narrow Definition Vladimir Markhonko 12/7/2007

Wider Definition Vladimir Markhonko 12/7/2007

Wider Definition Vladimir Markhonko 12/7/2007

Administrative sources are sources containing information which is not primarily collected for statistical purposes.

Administrative sources are sources containing information which is not primarily collected for statistical purposes. Vladimir Markhonko 12/7/2007

Reasons for this Definition Ø Privatisation of some government functions Ø Growth of private

Reasons for this Definition Ø Privatisation of some government functions Ø Growth of private sector “value-added re-sellers” Ø User interest in new types of data Vladimir Markhonko 12/7/2007

Benefits of Administrative Data Ø Cost l Surveys / censuses are expensive, administrative data

Benefits of Administrative Data Ø Cost l Surveys / censuses are expensive, administrative data are often “free” Ø Response burden Reduced burden on data suppliers l Statistics can be compiled more frequently with no extra burden l Vladimir Markhonko 12/7/2007

Benefits of Administrative Data Ø Coverage Full coverage of target population l No survey

Benefits of Administrative Data Ø Coverage Full coverage of target population l No survey errors and lower non-response l Better small-area data l Ø Timeliness (sometimes!) Ø Public image l Making use of existing data can enhance the prestige of a statistical organisation by making it seem more efficient Vladimir Markhonko 12/7/2007

Population Census Costs 2000 -2001 Ø UK, € 367 m, € 6. 2 person

Population Census Costs 2000 -2001 Ø UK, € 367 m, € 6. 2 person Ø Austria, € 56 m, € 6. 9 person Ø Finland, € 0. 8 m, € 0. 2 person Source: Eurostat – Documentation of the 2000 round of population and Housing censuses in the EU, EFTA and Candidate Countries; Table 22 Vladimir Markhonko 12/7/2007

Common Problems Ø Administrative units do not always coincide with statistical units Ø Conversion

Common Problems Ø Administrative units do not always coincide with statistical units Ø Conversion via automatic rules for simple cases Ø Profiling for more complex cases Gives a better understanding of complex business structures l Expensive and needs trained staff l Vladimir Markhonko 12/7/2007

Vladimir Markhonko 12/7/2007

Vladimir Markhonko 12/7/2007

Common Problems Ø Different definitions and classifications Administrative and statistical priorities are often different

Common Problems Ø Different definitions and classifications Administrative and statistical priorities are often different l Conversion matrices needed for different classifications l Ø Timeliness Data arrive too late l Data relate to a different time period l Vladimir Markhonko 12/7/2007

VAT Birth Lags Vladimir Markhonko 12/7/2007

VAT Birth Lags Vladimir Markhonko 12/7/2007

VAT Birth Lags Ø 2/3 of businesses are on the register within 2 months

VAT Birth Lags Ø 2/3 of businesses are on the register within 2 months of start-up Ø Mean lag = 4 months due to “outliers” Ø Median = Approx. 40 days Ø Some pre-register - negative lags Vladimir Markhonko 12/7/2007

Common Problems Ø Change management Risk of changes in government policy, thresholds, definitions, coverage

Common Problems Ø Change management Risk of changes in government policy, thresholds, definitions, coverage etc. l Need contingency plans l Ø Data from multiple sources Matching / linking issues l Data conflicts – priority rules l Vladimir Markhonko 12/7/2007

Quality of Administrative Data Ø There are many aspects to quality Ø Administrative data

Quality of Administrative Data Ø There are many aspects to quality Ø Administrative data will be better than survey data in some aspects but not in others Ø It is important to look at overall quality Ø Do the data meet the needs of users? Vladimir Markhonko 12/7/2007

Three Aspects of Quality Ø Quality of incoming data Ø Quality of processing (matching,

Three Aspects of Quality Ø Quality of incoming data Ø Quality of processing (matching, merging, . . . ) Ø Quality of outputs - likely to be different to survey based outputs, but are they better? Vladimir Markhonko 12/7/2007

Quality Measurement Ø How to measure the quality of data from administrative sources? Comparing

Quality Measurement Ø How to measure the quality of data from administrative sources? Comparing sources l Quality check surveys l Knowledge of source (metadata) l Quality reports / templates l Vladimir Markhonko 12/7/2007

Quality Templates Vladimir Markhonko 12/7/2007

Quality Templates Vladimir Markhonko 12/7/2007

Using Administrative Data Ø Conversion to statistical concepts and definitions Ø Linking / Matching

Using Administrative Data Ø Conversion to statistical concepts and definitions Ø Linking / Matching – – Exact Matching - linking records from two or more sources, often using common identifiers Probabilistic Matching - determining the probability that records from different sources should match, using a combination. Vladimir of variables Markhonko 12/7/2007

UK Business Register Vladimir Markhonko 12/7/2007

UK Business Register Vladimir Markhonko 12/7/2007

Vladimir Markhonko 12/7/2007

Vladimir Markhonko 12/7/2007

Satellite Registers Vladimir Markhonko 12/7/2007

Satellite Registers Vladimir Markhonko 12/7/2007

Examples of Satellite Registers Ø Tourism - hotel register (category, number of beds) Ø

Examples of Satellite Registers Ø Tourism - hotel register (category, number of beds) Ø Transport - vehicle or ship register (type, capacity) Ø Distributive trades - buildings register (building size, sales area) Vladimir Markhonko 12/7/2007

Conclusions Ø Administrative sources should be defined in the widest sense Ø There are

Conclusions Ø Administrative sources should be defined in the widest sense Ø There are many benefits in using administrative data, particularly reduced costs Ø There are problems when using administrative data, but usually someone has found a solution Vladimir Markhonko 12/7/2007

Conclusions Ø Most problems can be reduced by effective planning and detailed knowledge of

Conclusions Ø Most problems can be reduced by effective planning and detailed knowledge of the source Ø The benefits are often greater than the costs Vladimir Markhonko 12/7/2007

Thank you for your attention. Vladimir Markhonko 12/7/2007

Thank you for your attention. Vladimir Markhonko 12/7/2007