SlideShare a Scribd company logo
1
Selective editing and
automated correction of
micro data in the SBS, Norway
Jakob Kalko, Statistics Norway
1
Agenda
• Background
• Editing of enterprises – R-type consistency indicator
• Editing of MME’s (multiple establishment enterprises) -
P-type consistency indicator
• Automated correction of SBS data
2
Background
• For years, large focus at micro level. Flagging of soft/absolute errors.
Too much editing at microlevel ?
• Publishing of current SBS: t +17 months.
Several reasons for improving this:
- relevance of the data in general
- give NA access to data earlier
- future demands from Eurostat concerning earlier delivery of data ?
- increased demand to effectiveness within SSB (LEAN focus)
3
Enterprises. R-type consistency indicators
• Statistical unit is enterprise. Unweighted indicators at micro level are
established, showing the development in the relationship between two
selected variables in year t and t-1
• Weighted indicators at micro level are established, giving higher weights
to large units (measured by employment or man-years)
• Indicators are established at macro level (2-5 digit NACE), based on
indicators at micro level
• We choosed to focus on three indicators and one total indicator, based
on the three indicators.
4
R-type consistency indicator -
micro level
• Target variable: Employment Auxiliary variable: Man-years.
• Un-weighted R-type consistency indicator (𝑅 𝑒𝑚 ):
𝑅 𝑒𝑚 = (employment t / man-years t) / (employment t-1 / man-years t-1)
• Weighted R-type consistency indicator (𝐑 𝒆)
Weight (w): 𝐸𝑚𝑝𝑙𝑜𝑦𝑚𝑒𝑛𝑡 𝑡 / 10
• 𝐑 𝒆= Rem
w
5
R-type consistency indicator -
micro level
• Target variable: Wages Auxiliary variable: Man-years.
• Un-weighted R-type consistency indicator (𝑅 𝑣𝑚 ):
𝑅 𝑣𝑚 = (wages t /man-years t) / (wages t-1 / man-years t-1)
• Weighted R-type consistency indicator (𝐑 𝐚 )
Weight (w): 𝑚𝑎𝑛 − 𝑦𝑒𝑎𝑟𝑠 𝑡 / 10
• 𝐑 𝐚= Rvm
w
6
R-type consistency indicator -
micro level
• Target variable: Turnover Auxiliary variable: Employment
• Un-weighted R-type consistency indicator (𝑅𝑡𝑒 ):
𝑅𝑡𝑒 = (turnover t / employment t) / (turnover t-1 / employment t-1)
• Weighted R-type consistency indicator (𝐑 𝐭 )
Weight (w): 𝐸𝑚𝑝𝑙𝑜𝑦𝑚𝑒𝑛𝑡 𝑡 / 10
• 𝐑 𝐭= Rte
w
7
Total weighted R-type consistency
indicator
• Total weighted R-type consistency indicator (𝑹𝒕𝑾)
• 𝑅𝑡𝑊 = (𝐑 𝒆 x 𝐑 𝒂 x 𝐑 𝒕) 1/3
• At micro level a R-indicator=1, indicates no change in the relationship
between the target variable and auxiliary variable
8
R-type consistency indicator,
macro level
• Given a R-type consistency indicator R for the e-th unit, in the n-th
NACE
• Let 𝑠 𝑛𝑒 = turnover for the e-th unit, in the n-th NACE
• Let 𝑆 𝑛𝐸 = turnover for the population for the units e=1,2...E , in the n-th
NACE
• 𝑊𝑒 = 𝑠 𝑛𝑒 / 𝑆 𝑛𝐸
• R-type consistency indicator, macro level (𝑅 𝑚) for 𝑅𝑡:
𝑅 𝑚 = 𝑊𝑒
𝐸
𝑒=1 𝑙𝑜𝑔10 (𝑅𝑡).
• 𝑅 𝑚= 0 indicates no change at macro level
9
Practical use of R-type consistency indicator
• Preliminary data 2011
- 3. digit nacegroups with R>0,1 were listed out
- Enterprises within these nace groups were listed out,
including the R-indicator.
- Units with unreasonable indicators were examined/corrected
New lists were created. Editing stopped when indicator became stable
- The R-indicators (turnover/employment) and the total
weighted indicator showed up to be especially useful
10
P-type consistency indicator
• Is made for MME’s and is measuring the development in the relationship
between two selected variables in year t and t-1
• Takes into account the weights of the variables measured in the MME in
the referenceperiods t and t-1 (Fischer index)
• Practical use: No practical experience but intention is to follow the
same principles as for the R-indicator:
- MME’s where P-indicator differs significantly from1 are
localized. Establishments being the worst outliers in the MME are listed
and examined. New P-indicator is then created.
11
P-type consistency indicator –
practical example
12
L-index:(20/68) x 0,72 + (14/68) x 0,935 + (34/68) x 1,2868=1,0477
P-index:(18/65) x 0,72 + (12/65) x 0,935 + (35/65) x 1,2868=1,0649
F-index: 1,0477 x 1,0649 = 1,0563
P-indicator =F-index /(P ) = 1,0563/1,0444=1,0114
Establish-
ment
Turnover
(t)
Operation.
costs (t)
Turnover
(t-1)
Operation.
costs (t-1)
R -
indicator
K=1 18 15 20 12 0,7200
K=2 12 11 14 12 0,9350
K=3 35 28 34 35 1,2868
P 65 54 68 59 1,0444
tt
Dir
,1
tt
Dir
,1
tt
Dir
,1
Practical experiences – R and P-indicators
• The R-indicator 𝐑 𝐭 (turnover/employment) and the total
weighted indicator 𝑹 𝒕𝑾 showed up to be especially useful
• Indicators can not replace the administration of the population
• Reasonable indicators are not necessarily an indication of no significant
changes in absolute variables (eg. mergers/splits)
• Unreasonable indicators might be correct (weak connection between
variables creating the indicator, mergers/splits)
13
Practical experiences – R and P-indicators
• Irregular R-indicators in MME’s should be treated differently in the
estimation of the P-indicator.
• No practical experience, using the P-indicator so far. Should consider
further wether the current indicator gives us the information we need.
14
Automatic correction of SBS data
• Basic idea: Replace manual corrections of certain variables in MME’s
with automatic corrections, to increase productivity
• Following variables are received broken down from enterprise level to
establishment level through the SBS survey:
Employment, wages, turnover, operational costs and gross investments.
• Only wages, turnover and operational costs are automatic corrected
• Variables are only corrected if they do not sum up to enterprise level
15
Automatic correction of SBS data
• Corrections are based on information from year t-1
• Wages are corrected, based on man-years
• Turnover is corrected, based on employment
• Operational costs are corrected, based on turnover
• New distribution of data among establishments:
- using keys based on the raw data or
- using keys based on an alternative distribution based on year t-1
16
Automatic corrections – practical example
Period t t-1 t t-1
Establishments Employment Employment
Turnover,
raw data Turnover
1 2 4 4.468 7.561
2 2 1 2.431 840
Sum, establish. 4 5 6.899 8.401
Sum, enterprise 4 5 8.985 8.401
Difference 0 0 - 2.086 0
17
Establishments Alternative suggested distributrion, Turnover
1: (7.561/4) x 2 3.780,5
2: ( 840/1) x 2 1.680,0
Sum 5.460,5
Difference 5.460 – 8.985 = -3.524,5
Automatic corrections – practical example
• Distribution of turnover in this example will be based on the
distribution of raw data.
• Sum of turnover should = 8.985 (enteprise level)
18
Establishment Turnover,
raw- data
Distribution Corrected
turnover
1: 4.468 0,648 5.819
2 2.431 0,352 3.166
Sum 6.899 1,000 8.985
Automatic corrections - experiences
• Increased effectivenes, editing large MME’s
• In MME’s where data for only one establishment is given, no
automatic corrections are done for the other establishments
• MME’s in industries with weak connection between turnover and
employment should be paid extra attention
• Establishments founded in year t-1 might have a different relationship between
variables in year t. May lead to errors in the automatic correction
• In the long run – automatic corrections may be based on earlier automatic
corrections. Problem ?
19

More Related Content

Viewers also liked

Kommunikasjon: Kvalitetsredovisning i webpanelundersökningar
Kommunikasjon: Kvalitetsredovisning i webpanelundersökningarKommunikasjon: Kvalitetsredovisning i webpanelundersökningar
Kommunikasjon: Kvalitetsredovisning i webpanelundersökningar
Nordisk statistikermøte 2013
 
Rammeverk: Kompetanseutfordringer ved svar-og veiledningstjenesten i SSB
Rammeverk: Kompetanseutfordringer ved svar-og veiledningstjenesten i SSBRammeverk: Kompetanseutfordringer ved svar-og veiledningstjenesten i SSB
Rammeverk: Kompetanseutfordringer ved svar-og veiledningstjenesten i SSB
Nordisk statistikermøte 2013
 
Produksjonsprosessen: Kvaliteten på den norske tidsbruksundersøkelsen i 2010
Produksjonsprosessen: Kvaliteten på den norske tidsbruksundersøkelsen i 2010Produksjonsprosessen: Kvaliteten på den norske tidsbruksundersøkelsen i 2010
Produksjonsprosessen: Kvaliteten på den norske tidsbruksundersøkelsen i 2010
Nordisk statistikermøte 2013
 
Oppgavegiveren: Measurement of innovation activity
Oppgavegiveren: Measurement of innovation activityOppgavegiveren: Measurement of innovation activity
Oppgavegiveren: Measurement of innovation activity
Nordisk statistikermøte 2013
 
Oppgavegiveren: Show cards implications for survey response
Oppgavegiveren: Show cards implications for survey responseOppgavegiveren: Show cards implications for survey response
Oppgavegiveren: Show cards implications for survey response
Nordisk statistikermøte 2013
 
Rammeverk: Developing basic competences in Statistics Denmark
Rammeverk: Developing basic competences in Statistics DenmarkRammeverk: Developing basic competences in Statistics Denmark
Rammeverk: Developing basic competences in Statistics Denmark
Nordisk statistikermøte 2013
 
Avslutning: Nordic statistics ready for the future?
Avslutning: Nordic statistics ready for the future?Avslutning: Nordic statistics ready for the future?
Avslutning: Nordic statistics ready for the future?
Nordisk statistikermøte 2013
 
Produksjonsprosessen: Improved quality with spatial information
Produksjonsprosessen: Improved quality with spatial informationProduksjonsprosessen: Improved quality with spatial information
Produksjonsprosessen: Improved quality with spatial information
Nordisk statistikermøte 2013
 
Kommunikasjon: Improving the quality of foreign affiliates statistics
Kommunikasjon: Improving the quality of foreign affiliates statisticsKommunikasjon: Improving the quality of foreign affiliates statistics
Kommunikasjon: Improving the quality of foreign affiliates statistics
Nordisk statistikermøte 2013
 
Seminar: Statistics and democracy
Seminar: Statistics and democracySeminar: Statistics and democracy
Seminar: Statistics and democracy
Nordisk statistikermøte 2013
 
Produksjonsprosessen: Kontinuerlig forbedring av intervjubaserte datainnsamli...
Produksjonsprosessen: Kontinuerlig forbedring av intervjubaserte datainnsamli...Produksjonsprosessen: Kontinuerlig forbedring av intervjubaserte datainnsamli...
Produksjonsprosessen: Kontinuerlig forbedring av intervjubaserte datainnsamli...
Nordisk statistikermøte 2013
 
Rammeverk: Mutual competence development in international capacity development
Rammeverk: Mutual competence development in international capacity developmentRammeverk: Mutual competence development in international capacity development
Rammeverk: Mutual competence development in international capacity development
Nordisk statistikermøte 2013
 
Produksjonsprosessen: Kvalitetsmåling av populasjonsregistre i SSB
Produksjonsprosessen: Kvalitetsmåling av populasjonsregistre i SSBProduksjonsprosessen: Kvalitetsmåling av populasjonsregistre i SSB
Produksjonsprosessen: Kvalitetsmåling av populasjonsregistre i SSB
Nordisk statistikermøte 2013
 
Oppgavegiveren: Non response from a qualitative perspective
Oppgavegiveren: Non response from a qualitative perspectiveOppgavegiveren: Non response from a qualitative perspective
Oppgavegiveren: Non response from a qualitative perspective
Nordisk statistikermøte 2013
 
Rammeverk: Effektivisering av HR-forvaltingen
Rammeverk: Effektivisering av HR-forvaltingenRammeverk: Effektivisering av HR-forvaltingen
Rammeverk: Effektivisering av HR-forvaltingen
Nordisk statistikermøte 2013
 
Rammeverk: ISO20252 - ett stöd i SCBs kvalitetsarbete
Rammeverk: ISO20252 - ett stöd i SCBs kvalitetsarbeteRammeverk: ISO20252 - ett stöd i SCBs kvalitetsarbete
Rammeverk: ISO20252 - ett stöd i SCBs kvalitetsarbete
Nordisk statistikermøte 2013
 
Åpningssesjon: Infectious disease modelling
Åpningssesjon: Infectious disease modellingÅpningssesjon: Infectious disease modelling
Åpningssesjon: Infectious disease modelling
Nordisk statistikermøte 2013
 

Viewers also liked (17)

Kommunikasjon: Kvalitetsredovisning i webpanelundersökningar
Kommunikasjon: Kvalitetsredovisning i webpanelundersökningarKommunikasjon: Kvalitetsredovisning i webpanelundersökningar
Kommunikasjon: Kvalitetsredovisning i webpanelundersökningar
 
Rammeverk: Kompetanseutfordringer ved svar-og veiledningstjenesten i SSB
Rammeverk: Kompetanseutfordringer ved svar-og veiledningstjenesten i SSBRammeverk: Kompetanseutfordringer ved svar-og veiledningstjenesten i SSB
Rammeverk: Kompetanseutfordringer ved svar-og veiledningstjenesten i SSB
 
Produksjonsprosessen: Kvaliteten på den norske tidsbruksundersøkelsen i 2010
Produksjonsprosessen: Kvaliteten på den norske tidsbruksundersøkelsen i 2010Produksjonsprosessen: Kvaliteten på den norske tidsbruksundersøkelsen i 2010
Produksjonsprosessen: Kvaliteten på den norske tidsbruksundersøkelsen i 2010
 
Oppgavegiveren: Measurement of innovation activity
Oppgavegiveren: Measurement of innovation activityOppgavegiveren: Measurement of innovation activity
Oppgavegiveren: Measurement of innovation activity
 
Oppgavegiveren: Show cards implications for survey response
Oppgavegiveren: Show cards implications for survey responseOppgavegiveren: Show cards implications for survey response
Oppgavegiveren: Show cards implications for survey response
 
Rammeverk: Developing basic competences in Statistics Denmark
Rammeverk: Developing basic competences in Statistics DenmarkRammeverk: Developing basic competences in Statistics Denmark
Rammeverk: Developing basic competences in Statistics Denmark
 
Avslutning: Nordic statistics ready for the future?
Avslutning: Nordic statistics ready for the future?Avslutning: Nordic statistics ready for the future?
Avslutning: Nordic statistics ready for the future?
 
Produksjonsprosessen: Improved quality with spatial information
Produksjonsprosessen: Improved quality with spatial informationProduksjonsprosessen: Improved quality with spatial information
Produksjonsprosessen: Improved quality with spatial information
 
Kommunikasjon: Improving the quality of foreign affiliates statistics
Kommunikasjon: Improving the quality of foreign affiliates statisticsKommunikasjon: Improving the quality of foreign affiliates statistics
Kommunikasjon: Improving the quality of foreign affiliates statistics
 
Seminar: Statistics and democracy
Seminar: Statistics and democracySeminar: Statistics and democracy
Seminar: Statistics and democracy
 
Produksjonsprosessen: Kontinuerlig forbedring av intervjubaserte datainnsamli...
Produksjonsprosessen: Kontinuerlig forbedring av intervjubaserte datainnsamli...Produksjonsprosessen: Kontinuerlig forbedring av intervjubaserte datainnsamli...
Produksjonsprosessen: Kontinuerlig forbedring av intervjubaserte datainnsamli...
 
Rammeverk: Mutual competence development in international capacity development
Rammeverk: Mutual competence development in international capacity developmentRammeverk: Mutual competence development in international capacity development
Rammeverk: Mutual competence development in international capacity development
 
Produksjonsprosessen: Kvalitetsmåling av populasjonsregistre i SSB
Produksjonsprosessen: Kvalitetsmåling av populasjonsregistre i SSBProduksjonsprosessen: Kvalitetsmåling av populasjonsregistre i SSB
Produksjonsprosessen: Kvalitetsmåling av populasjonsregistre i SSB
 
Oppgavegiveren: Non response from a qualitative perspective
Oppgavegiveren: Non response from a qualitative perspectiveOppgavegiveren: Non response from a qualitative perspective
Oppgavegiveren: Non response from a qualitative perspective
 
Rammeverk: Effektivisering av HR-forvaltingen
Rammeverk: Effektivisering av HR-forvaltingenRammeverk: Effektivisering av HR-forvaltingen
Rammeverk: Effektivisering av HR-forvaltingen
 
Rammeverk: ISO20252 - ett stöd i SCBs kvalitetsarbete
Rammeverk: ISO20252 - ett stöd i SCBs kvalitetsarbeteRammeverk: ISO20252 - ett stöd i SCBs kvalitetsarbete
Rammeverk: ISO20252 - ett stöd i SCBs kvalitetsarbete
 
Åpningssesjon: Infectious disease modelling
Åpningssesjon: Infectious disease modellingÅpningssesjon: Infectious disease modelling
Åpningssesjon: Infectious disease modelling
 

Similar to Produksjonsprosessen: Selective editing and automated correction of micro data

Index numbersF.ppt
Index numbersF.pptIndex numbersF.ppt
Index numbersF.ppt
mckjkj
 
Perfmeasure.ppt
Perfmeasure.pptPerfmeasure.ppt
Perfmeasure.ppt
Mmdmmd4
 
Chapter 7 demand forecasting in a supply chain
Chapter 7 demand forecasting in a supply chainChapter 7 demand forecasting in a supply chain
Chapter 7 demand forecasting in a supply chain
sajidsharif2022
 
Services in EU what kinds of regulatory policy enhance productivity van der M...
Services in EU what kinds of regulatory policy enhance productivity van der M...Services in EU what kinds of regulatory policy enhance productivity van der M...
Services in EU what kinds of regulatory policy enhance productivity van der M...
OECD, Economics Department
 
Index numbers
Index numbersIndex numbers
Index numbers
Poonam Jangid
 
Turkey financial stress risk index and econometric modeling using garch and m...
Turkey financial stress risk index and econometric modeling using garch and m...Turkey financial stress risk index and econometric modeling using garch and m...
Turkey financial stress risk index and econometric modeling using garch and m...
YUNUS EMRE Ozcan
 
forecasting
forecastingforecasting
forecasting
RINUSATHYAN
 
INTRODUCTION TO TIME SERIES REGRESSION AND FORCASTING
INTRODUCTION TO TIME SERIES REGRESSION AND FORCASTINGINTRODUCTION TO TIME SERIES REGRESSION AND FORCASTING
INTRODUCTION TO TIME SERIES REGRESSION AND FORCASTING
SPICEGODDESS
 
Tutorial 8 Solutions.docx
Tutorial 8 Solutions.docxTutorial 8 Solutions.docx
Tutorial 8 Solutions.docx
LinhLeThiThuy4
 
Forecasting of demand (management)
Forecasting of demand (management)Forecasting of demand (management)
Forecasting of demand (management)
Manthan Chavda
 
Chapter13EquityValuation.ppt
Chapter13EquityValuation.pptChapter13EquityValuation.ppt
Chapter13EquityValuation.ppt
rekhabawa2
 
Production Function & cost elasticity Maruti Suzuki
Production Function & cost elasticity Maruti Suzuki Production Function & cost elasticity Maruti Suzuki
Production Function & cost elasticity Maruti Suzuki
Akhilendra Tiwari
 
index numbers, which is required for the mba students
index numbers, which is required for the mba studentsindex numbers, which is required for the mba students
index numbers, which is required for the mba students
SoujanyaLk1
 
Forecasting demand planning
Forecasting demand planningForecasting demand planning
Forecasting demand planning
ManonmaniA3
 
Production function
Production function Production function
Production function Daksh Bapna
 
Session 8 c 8 c oulton-slides (kz)
Session 8 c 8 c   oulton-slides (kz)Session 8 c 8 c   oulton-slides (kz)
Session 8 c 8 c oulton-slides (kz)
IARIW 2014
 
Importance of Performance Management And Measurement of Productivity
Importance of Performance Management  And Measurement of ProductivityImportance of Performance Management  And Measurement of Productivity
Importance of Performance Management And Measurement of Productivity
National Productivity Secretariat
 
Chapter-3_Heizer_S1.pptx
Chapter-3_Heizer_S1.pptxChapter-3_Heizer_S1.pptx
Chapter-3_Heizer_S1.pptx
EdwardDelaCruz14
 
Eng econ lecture
Eng econ lectureEng econ lecture
Eng econ lecture
Arul Kumar
 

Similar to Produksjonsprosessen: Selective editing and automated correction of micro data (20)

Index numbersF.ppt
Index numbersF.pptIndex numbersF.ppt
Index numbersF.ppt
 
Perfmeasure.ppt
Perfmeasure.pptPerfmeasure.ppt
Perfmeasure.ppt
 
Chapter 7 demand forecasting in a supply chain
Chapter 7 demand forecasting in a supply chainChapter 7 demand forecasting in a supply chain
Chapter 7 demand forecasting in a supply chain
 
Services in EU what kinds of regulatory policy enhance productivity van der M...
Services in EU what kinds of regulatory policy enhance productivity van der M...Services in EU what kinds of regulatory policy enhance productivity van der M...
Services in EU what kinds of regulatory policy enhance productivity van der M...
 
Index numbers
Index numbersIndex numbers
Index numbers
 
Turkey financial stress risk index and econometric modeling using garch and m...
Turkey financial stress risk index and econometric modeling using garch and m...Turkey financial stress risk index and econometric modeling using garch and m...
Turkey financial stress risk index and econometric modeling using garch and m...
 
forecasting
forecastingforecasting
forecasting
 
INTRODUCTION TO TIME SERIES REGRESSION AND FORCASTING
INTRODUCTION TO TIME SERIES REGRESSION AND FORCASTINGINTRODUCTION TO TIME SERIES REGRESSION AND FORCASTING
INTRODUCTION TO TIME SERIES REGRESSION AND FORCASTING
 
Tutorial 8 Solutions.docx
Tutorial 8 Solutions.docxTutorial 8 Solutions.docx
Tutorial 8 Solutions.docx
 
Forecasting of demand (management)
Forecasting of demand (management)Forecasting of demand (management)
Forecasting of demand (management)
 
Chapter13EquityValuation.ppt
Chapter13EquityValuation.pptChapter13EquityValuation.ppt
Chapter13EquityValuation.ppt
 
Economics project maruti
Economics project marutiEconomics project maruti
Economics project maruti
 
Production Function & cost elasticity Maruti Suzuki
Production Function & cost elasticity Maruti Suzuki Production Function & cost elasticity Maruti Suzuki
Production Function & cost elasticity Maruti Suzuki
 
index numbers, which is required for the mba students
index numbers, which is required for the mba studentsindex numbers, which is required for the mba students
index numbers, which is required for the mba students
 
Forecasting demand planning
Forecasting demand planningForecasting demand planning
Forecasting demand planning
 
Production function
Production function Production function
Production function
 
Session 8 c 8 c oulton-slides (kz)
Session 8 c 8 c   oulton-slides (kz)Session 8 c 8 c   oulton-slides (kz)
Session 8 c 8 c oulton-slides (kz)
 
Importance of Performance Management And Measurement of Productivity
Importance of Performance Management  And Measurement of ProductivityImportance of Performance Management  And Measurement of Productivity
Importance of Performance Management And Measurement of Productivity
 
Chapter-3_Heizer_S1.pptx
Chapter-3_Heizer_S1.pptxChapter-3_Heizer_S1.pptx
Chapter-3_Heizer_S1.pptx
 
Eng econ lecture
Eng econ lectureEng econ lecture
Eng econ lecture
 

More from Nordisk statistikermøte 2013

Kommunikasjon: A Nordic PIAAC database
Kommunikasjon: A Nordic PIAAC databaseKommunikasjon: A Nordic PIAAC database
Kommunikasjon: A Nordic PIAAC database
Nordisk statistikermøte 2013
 
Kommunikasjon: A tool for managing product quality
Kommunikasjon: A tool for managing product qualityKommunikasjon: A tool for managing product quality
Kommunikasjon: A tool for managing product quality
Nordisk statistikermøte 2013
 
Kommunikasjon: Brugerne i centrum
Kommunikasjon: Brugerne i centrumKommunikasjon: Brugerne i centrum
Kommunikasjon: Brugerne i centrum
Nordisk statistikermøte 2013
 
Kommunikasjon: Communicating accuracy of register statistics
Kommunikasjon: Communicating accuracy of register statisticsKommunikasjon: Communicating accuracy of register statistics
Kommunikasjon: Communicating accuracy of register statistics
Nordisk statistikermøte 2013
 
Kommunikasjon: Formidling af Øresundsstatistik
Kommunikasjon: Formidling af ØresundsstatistikKommunikasjon: Formidling af Øresundsstatistik
Kommunikasjon: Formidling af Øresundsstatistik
Nordisk statistikermøte 2013
 
Kommunikasjon: Kvalitetshåndbøger om statistik
Kommunikasjon: Kvalitetshåndbøger om statistikKommunikasjon: Kvalitetshåndbøger om statistik
Kommunikasjon: Kvalitetshåndbøger om statistik
Nordisk statistikermøte 2013
 
Kommunikasjon: Statistical storytelling and quality in the age of open data
Kommunikasjon: Statistical storytelling and quality in the age of open dataKommunikasjon: Statistical storytelling and quality in the age of open data
Kommunikasjon: Statistical storytelling and quality in the age of open data
Nordisk statistikermøte 2013
 
Kommunikasjon: Åpne data - en åpning for statistikkbyråene
Kommunikasjon: Åpne data - en åpning for statistikkbyråeneKommunikasjon: Åpne data - en åpning for statistikkbyråene
Kommunikasjon: Åpne data - en åpning for statistikkbyråene
Nordisk statistikermøte 2013
 
Oppgavegiveren: Att försöka minska bortfallet genom att minska den upplevda b...
Oppgavegiveren: Att försöka minska bortfallet genom att minska den upplevda b...Oppgavegiveren: Att försöka minska bortfallet genom att minska den upplevda b...
Oppgavegiveren: Att försöka minska bortfallet genom att minska den upplevda b...
Nordisk statistikermøte 2013
 
Oppgavegiveren: Cooperation and coordination in data collection
Oppgavegiveren: Cooperation and coordination in data collectionOppgavegiveren: Cooperation and coordination in data collection
Oppgavegiveren: Cooperation and coordination in data collection
Nordisk statistikermøte 2013
 
Oppgavegiveren: Developing the web data collection in personal surveys
Oppgavegiveren: Developing the web data collection in personal surveysOppgavegiveren: Developing the web data collection in personal surveys
Oppgavegiveren: Developing the web data collection in personal surveys
Nordisk statistikermøte 2013
 
Oppgavegiveren: Kvalitetssikring ved dataindsamlinger til registre
Oppgavegiveren: Kvalitetssikring ved dataindsamlinger til registreOppgavegiveren: Kvalitetssikring ved dataindsamlinger til registre
Oppgavegiveren: Kvalitetssikring ved dataindsamlinger til registre
Nordisk statistikermøte 2013
 
Oppgavegiveren: Mixed mode inom insamlingen av data
Oppgavegiveren: Mixed mode inom insamlingen av dataOppgavegiveren: Mixed mode inom insamlingen av data
Oppgavegiveren: Mixed mode inom insamlingen av data
Nordisk statistikermøte 2013
 
Oppgavegiveren: Non-response and motivation measures
Oppgavegiveren: Non-response and motivation measuresOppgavegiveren: Non-response and motivation measures
Oppgavegiveren: Non-response and motivation measures
Nordisk statistikermøte 2013
 
Oppgavegiveren: Quality of the diaries in the finnish and swedish time use su...
Oppgavegiveren: Quality of the diaries in the finnish and swedish time use su...Oppgavegiveren: Quality of the diaries in the finnish and swedish time use su...
Oppgavegiveren: Quality of the diaries in the finnish and swedish time use su...
Nordisk statistikermøte 2013
 
Oppgavegiveren: Registerbaserad aktivitetsstatistik RAKS
Oppgavegiveren: Registerbaserad aktivitetsstatistik RAKSOppgavegiveren: Registerbaserad aktivitetsstatistik RAKS
Oppgavegiveren: Registerbaserad aktivitetsstatistik RAKS
Nordisk statistikermøte 2013
 
Oppgavegiveren: Meeting user needs cost-effectively
Oppgavegiveren: Meeting user needs cost-effectivelyOppgavegiveren: Meeting user needs cost-effectively
Oppgavegiveren: Meeting user needs cost-effectively
Nordisk statistikermøte 2013
 
Produksjonsprosessen: Beste praksis for revisjon ved sesongjustering
Produksjonsprosessen: Beste praksis for revisjon ved sesongjusteringProduksjonsprosessen: Beste praksis for revisjon ved sesongjustering
Produksjonsprosessen: Beste praksis for revisjon ved sesongjustering
Nordisk statistikermøte 2013
 
Produksjonsprosessen: GIS som stöd i granskningsarbete
Produksjonsprosessen: GIS som stöd i granskningsarbeteProduksjonsprosessen: GIS som stöd i granskningsarbete
Produksjonsprosessen: GIS som stöd i granskningsarbete
Nordisk statistikermøte 2013
 
Produksjonsprosessen: Imputering i ældredokumentationsprojektet
Produksjonsprosessen: Imputering i ældredokumentationsprojektetProduksjonsprosessen: Imputering i ældredokumentationsprojektet
Produksjonsprosessen: Imputering i ældredokumentationsprojektet
Nordisk statistikermøte 2013
 

More from Nordisk statistikermøte 2013 (20)

Kommunikasjon: A Nordic PIAAC database
Kommunikasjon: A Nordic PIAAC databaseKommunikasjon: A Nordic PIAAC database
Kommunikasjon: A Nordic PIAAC database
 
Kommunikasjon: A tool for managing product quality
Kommunikasjon: A tool for managing product qualityKommunikasjon: A tool for managing product quality
Kommunikasjon: A tool for managing product quality
 
Kommunikasjon: Brugerne i centrum
Kommunikasjon: Brugerne i centrumKommunikasjon: Brugerne i centrum
Kommunikasjon: Brugerne i centrum
 
Kommunikasjon: Communicating accuracy of register statistics
Kommunikasjon: Communicating accuracy of register statisticsKommunikasjon: Communicating accuracy of register statistics
Kommunikasjon: Communicating accuracy of register statistics
 
Kommunikasjon: Formidling af Øresundsstatistik
Kommunikasjon: Formidling af ØresundsstatistikKommunikasjon: Formidling af Øresundsstatistik
Kommunikasjon: Formidling af Øresundsstatistik
 
Kommunikasjon: Kvalitetshåndbøger om statistik
Kommunikasjon: Kvalitetshåndbøger om statistikKommunikasjon: Kvalitetshåndbøger om statistik
Kommunikasjon: Kvalitetshåndbøger om statistik
 
Kommunikasjon: Statistical storytelling and quality in the age of open data
Kommunikasjon: Statistical storytelling and quality in the age of open dataKommunikasjon: Statistical storytelling and quality in the age of open data
Kommunikasjon: Statistical storytelling and quality in the age of open data
 
Kommunikasjon: Åpne data - en åpning for statistikkbyråene
Kommunikasjon: Åpne data - en åpning for statistikkbyråeneKommunikasjon: Åpne data - en åpning for statistikkbyråene
Kommunikasjon: Åpne data - en åpning for statistikkbyråene
 
Oppgavegiveren: Att försöka minska bortfallet genom att minska den upplevda b...
Oppgavegiveren: Att försöka minska bortfallet genom att minska den upplevda b...Oppgavegiveren: Att försöka minska bortfallet genom att minska den upplevda b...
Oppgavegiveren: Att försöka minska bortfallet genom att minska den upplevda b...
 
Oppgavegiveren: Cooperation and coordination in data collection
Oppgavegiveren: Cooperation and coordination in data collectionOppgavegiveren: Cooperation and coordination in data collection
Oppgavegiveren: Cooperation and coordination in data collection
 
Oppgavegiveren: Developing the web data collection in personal surveys
Oppgavegiveren: Developing the web data collection in personal surveysOppgavegiveren: Developing the web data collection in personal surveys
Oppgavegiveren: Developing the web data collection in personal surveys
 
Oppgavegiveren: Kvalitetssikring ved dataindsamlinger til registre
Oppgavegiveren: Kvalitetssikring ved dataindsamlinger til registreOppgavegiveren: Kvalitetssikring ved dataindsamlinger til registre
Oppgavegiveren: Kvalitetssikring ved dataindsamlinger til registre
 
Oppgavegiveren: Mixed mode inom insamlingen av data
Oppgavegiveren: Mixed mode inom insamlingen av dataOppgavegiveren: Mixed mode inom insamlingen av data
Oppgavegiveren: Mixed mode inom insamlingen av data
 
Oppgavegiveren: Non-response and motivation measures
Oppgavegiveren: Non-response and motivation measuresOppgavegiveren: Non-response and motivation measures
Oppgavegiveren: Non-response and motivation measures
 
Oppgavegiveren: Quality of the diaries in the finnish and swedish time use su...
Oppgavegiveren: Quality of the diaries in the finnish and swedish time use su...Oppgavegiveren: Quality of the diaries in the finnish and swedish time use su...
Oppgavegiveren: Quality of the diaries in the finnish and swedish time use su...
 
Oppgavegiveren: Registerbaserad aktivitetsstatistik RAKS
Oppgavegiveren: Registerbaserad aktivitetsstatistik RAKSOppgavegiveren: Registerbaserad aktivitetsstatistik RAKS
Oppgavegiveren: Registerbaserad aktivitetsstatistik RAKS
 
Oppgavegiveren: Meeting user needs cost-effectively
Oppgavegiveren: Meeting user needs cost-effectivelyOppgavegiveren: Meeting user needs cost-effectively
Oppgavegiveren: Meeting user needs cost-effectively
 
Produksjonsprosessen: Beste praksis for revisjon ved sesongjustering
Produksjonsprosessen: Beste praksis for revisjon ved sesongjusteringProduksjonsprosessen: Beste praksis for revisjon ved sesongjustering
Produksjonsprosessen: Beste praksis for revisjon ved sesongjustering
 
Produksjonsprosessen: GIS som stöd i granskningsarbete
Produksjonsprosessen: GIS som stöd i granskningsarbeteProduksjonsprosessen: GIS som stöd i granskningsarbete
Produksjonsprosessen: GIS som stöd i granskningsarbete
 
Produksjonsprosessen: Imputering i ældredokumentationsprojektet
Produksjonsprosessen: Imputering i ældredokumentationsprojektetProduksjonsprosessen: Imputering i ældredokumentationsprojektet
Produksjonsprosessen: Imputering i ældredokumentationsprojektet
 

Recently uploaded

Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
Cheryl Hung
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
DanBrown980551
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
Laura Byrne
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
Thijs Feryn
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Ramesh Iyer
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
Paul Groth
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
Elena Simperl
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
Elena Simperl
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
Ana-Maria Mihalceanu
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
UiPathCommunity
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
OnBoard
 
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
Product School
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Jeffrey Haguewood
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
Safe Software
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
RTTS
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 

Recently uploaded (20)

Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
 
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
From Daily Decisions to Bottom Line: Connecting Product Work to Revenue by VP...
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 

Produksjonsprosessen: Selective editing and automated correction of micro data

  • 1. 1 Selective editing and automated correction of micro data in the SBS, Norway Jakob Kalko, Statistics Norway 1
  • 2. Agenda • Background • Editing of enterprises – R-type consistency indicator • Editing of MME’s (multiple establishment enterprises) - P-type consistency indicator • Automated correction of SBS data 2
  • 3. Background • For years, large focus at micro level. Flagging of soft/absolute errors. Too much editing at microlevel ? • Publishing of current SBS: t +17 months. Several reasons for improving this: - relevance of the data in general - give NA access to data earlier - future demands from Eurostat concerning earlier delivery of data ? - increased demand to effectiveness within SSB (LEAN focus) 3
  • 4. Enterprises. R-type consistency indicators • Statistical unit is enterprise. Unweighted indicators at micro level are established, showing the development in the relationship between two selected variables in year t and t-1 • Weighted indicators at micro level are established, giving higher weights to large units (measured by employment or man-years) • Indicators are established at macro level (2-5 digit NACE), based on indicators at micro level • We choosed to focus on three indicators and one total indicator, based on the three indicators. 4
  • 5. R-type consistency indicator - micro level • Target variable: Employment Auxiliary variable: Man-years. • Un-weighted R-type consistency indicator (𝑅 𝑒𝑚 ): 𝑅 𝑒𝑚 = (employment t / man-years t) / (employment t-1 / man-years t-1) • Weighted R-type consistency indicator (𝐑 𝒆) Weight (w): 𝐸𝑚𝑝𝑙𝑜𝑦𝑚𝑒𝑛𝑡 𝑡 / 10 • 𝐑 𝒆= Rem w 5
  • 6. R-type consistency indicator - micro level • Target variable: Wages Auxiliary variable: Man-years. • Un-weighted R-type consistency indicator (𝑅 𝑣𝑚 ): 𝑅 𝑣𝑚 = (wages t /man-years t) / (wages t-1 / man-years t-1) • Weighted R-type consistency indicator (𝐑 𝐚 ) Weight (w): 𝑚𝑎𝑛 − 𝑦𝑒𝑎𝑟𝑠 𝑡 / 10 • 𝐑 𝐚= Rvm w 6
  • 7. R-type consistency indicator - micro level • Target variable: Turnover Auxiliary variable: Employment • Un-weighted R-type consistency indicator (𝑅𝑡𝑒 ): 𝑅𝑡𝑒 = (turnover t / employment t) / (turnover t-1 / employment t-1) • Weighted R-type consistency indicator (𝐑 𝐭 ) Weight (w): 𝐸𝑚𝑝𝑙𝑜𝑦𝑚𝑒𝑛𝑡 𝑡 / 10 • 𝐑 𝐭= Rte w 7
  • 8. Total weighted R-type consistency indicator • Total weighted R-type consistency indicator (𝑹𝒕𝑾) • 𝑅𝑡𝑊 = (𝐑 𝒆 x 𝐑 𝒂 x 𝐑 𝒕) 1/3 • At micro level a R-indicator=1, indicates no change in the relationship between the target variable and auxiliary variable 8
  • 9. R-type consistency indicator, macro level • Given a R-type consistency indicator R for the e-th unit, in the n-th NACE • Let 𝑠 𝑛𝑒 = turnover for the e-th unit, in the n-th NACE • Let 𝑆 𝑛𝐸 = turnover for the population for the units e=1,2...E , in the n-th NACE • 𝑊𝑒 = 𝑠 𝑛𝑒 / 𝑆 𝑛𝐸 • R-type consistency indicator, macro level (𝑅 𝑚) for 𝑅𝑡: 𝑅 𝑚 = 𝑊𝑒 𝐸 𝑒=1 𝑙𝑜𝑔10 (𝑅𝑡). • 𝑅 𝑚= 0 indicates no change at macro level 9
  • 10. Practical use of R-type consistency indicator • Preliminary data 2011 - 3. digit nacegroups with R>0,1 were listed out - Enterprises within these nace groups were listed out, including the R-indicator. - Units with unreasonable indicators were examined/corrected New lists were created. Editing stopped when indicator became stable - The R-indicators (turnover/employment) and the total weighted indicator showed up to be especially useful 10
  • 11. P-type consistency indicator • Is made for MME’s and is measuring the development in the relationship between two selected variables in year t and t-1 • Takes into account the weights of the variables measured in the MME in the referenceperiods t and t-1 (Fischer index) • Practical use: No practical experience but intention is to follow the same principles as for the R-indicator: - MME’s where P-indicator differs significantly from1 are localized. Establishments being the worst outliers in the MME are listed and examined. New P-indicator is then created. 11
  • 12. P-type consistency indicator – practical example 12 L-index:(20/68) x 0,72 + (14/68) x 0,935 + (34/68) x 1,2868=1,0477 P-index:(18/65) x 0,72 + (12/65) x 0,935 + (35/65) x 1,2868=1,0649 F-index: 1,0477 x 1,0649 = 1,0563 P-indicator =F-index /(P ) = 1,0563/1,0444=1,0114 Establish- ment Turnover (t) Operation. costs (t) Turnover (t-1) Operation. costs (t-1) R - indicator K=1 18 15 20 12 0,7200 K=2 12 11 14 12 0,9350 K=3 35 28 34 35 1,2868 P 65 54 68 59 1,0444 tt Dir ,1 tt Dir ,1 tt Dir ,1
  • 13. Practical experiences – R and P-indicators • The R-indicator 𝐑 𝐭 (turnover/employment) and the total weighted indicator 𝑹 𝒕𝑾 showed up to be especially useful • Indicators can not replace the administration of the population • Reasonable indicators are not necessarily an indication of no significant changes in absolute variables (eg. mergers/splits) • Unreasonable indicators might be correct (weak connection between variables creating the indicator, mergers/splits) 13
  • 14. Practical experiences – R and P-indicators • Irregular R-indicators in MME’s should be treated differently in the estimation of the P-indicator. • No practical experience, using the P-indicator so far. Should consider further wether the current indicator gives us the information we need. 14
  • 15. Automatic correction of SBS data • Basic idea: Replace manual corrections of certain variables in MME’s with automatic corrections, to increase productivity • Following variables are received broken down from enterprise level to establishment level through the SBS survey: Employment, wages, turnover, operational costs and gross investments. • Only wages, turnover and operational costs are automatic corrected • Variables are only corrected if they do not sum up to enterprise level 15
  • 16. Automatic correction of SBS data • Corrections are based on information from year t-1 • Wages are corrected, based on man-years • Turnover is corrected, based on employment • Operational costs are corrected, based on turnover • New distribution of data among establishments: - using keys based on the raw data or - using keys based on an alternative distribution based on year t-1 16
  • 17. Automatic corrections – practical example Period t t-1 t t-1 Establishments Employment Employment Turnover, raw data Turnover 1 2 4 4.468 7.561 2 2 1 2.431 840 Sum, establish. 4 5 6.899 8.401 Sum, enterprise 4 5 8.985 8.401 Difference 0 0 - 2.086 0 17 Establishments Alternative suggested distributrion, Turnover 1: (7.561/4) x 2 3.780,5 2: ( 840/1) x 2 1.680,0 Sum 5.460,5 Difference 5.460 – 8.985 = -3.524,5
  • 18. Automatic corrections – practical example • Distribution of turnover in this example will be based on the distribution of raw data. • Sum of turnover should = 8.985 (enteprise level) 18 Establishment Turnover, raw- data Distribution Corrected turnover 1: 4.468 0,648 5.819 2 2.431 0,352 3.166 Sum 6.899 1,000 8.985
  • 19. Automatic corrections - experiences • Increased effectivenes, editing large MME’s • In MME’s where data for only one establishment is given, no automatic corrections are done for the other establishments • MME’s in industries with weak connection between turnover and employment should be paid extra attention • Establishments founded in year t-1 might have a different relationship between variables in year t. May lead to errors in the automatic correction • In the long run – automatic corrections may be based on earlier automatic corrections. Problem ? 19