This document summarizes a meeting about Wage Indicator, Webdatanet, and eduworks. It discusses how Wage Indicator provides quick, reliable wage data internationally through continuous voluntary web surveys across 75 countries. However, web surveys have drawbacks compared to traditional surveys in terms of coverage and non-response. The document outlines various methodological approaches used by Wage Indicator to address biases, calculate weights, test innovations, and conduct research. It also introduces Webdatanet as a multidisciplinary network that aims to foster scientific use of web-based data through working groups and task forces focused on quality, innovation, and implementation. Specific task forces highlighted include measuring wages via web surveys, integrating web data with official statistics
1. Wage Indicator, WEBDATANET &
eduworks
Eduworks kick off meeting, Amsterdam December 11th, 2013.
Pablo de Pedraza
2. 1.- Wage Indicator: Quick, reliable and internationally comparable
data
1.1.- Continuous Voluntary Web Surveys (CVWS): Drawbacks
1.2.- Methodological approaches and research examples
2.- Webdatanet
3. 1.-Wage Indicator: Quick, reliable and internationally comparable data
The current economic crisis
requires fast information for quick reaction
to predict economic behavior early
difficult at times of structural changes.
4. 1.-Quick, reliable and internationally comparable data
Web vs traditional Labour Surveys
CURRENT CONTEXT
Global Economy
Quick changes
5. 1.-Quick, reliable and internationally comparable data
Web vs traditional Labour Surveys
CURRENT
CONTEXT
Global Economy
Quick changes
Traditional Surveys
Slow
National/regional coverage
International comparisons
6. 1.-Quick, reliable and internationally comparable data
Web vs traditional Labour Surveys
CURRENT
CONTEX
Global Economy
Quick changes
Traditional Surveys
Slow
National/regional coverage
Web surveys
Fast
(collecting & processing)
Multi-country/Multi-lingual homogenized
surveys (75 countries)
International comparisons
International comparisons
HOWEVER…
7. 1.- Wage Indicator: Quick, reliable and internationally comparable
data
1.1.- Continuous Voluntary Web Surveys (CVWS): Drawbacks
1.2.- Methodological approaches and research examples
2.- Webdatanet
9. 2.- Advantages and drawbacks
CVWS
process
TRADITIONAL CONCEPTS OF SURVEY METHODOLOGY:
-Coverage
-Non-response…
Total Survey Error APPROACH
And other surveys…
10. 1.- Wage Indicator: Quick, reliable and internationally comparable
data
1.1.- Continuous Voluntary Web Surveys (CVWS): Drawbacks
1.2.- Methodological approaches and research examples
2.- Webdatanet
11. 1.2.- Methodological approaches and research examples
1.2.a.- Bias description
1.2.b.- Design base approach
1.2.c.- Model base approach: Calculate and test weights
1.2.d.- Test innovations and use paradata
1.2.e.- Wage Indicator Research examples
12. 1.2.- Methodological approaches: present & future
1.2.a.- Bias description
– National (Labour Force Survey & Structures of Earnings S.)
Bias description: National Reference Surveys vs Wage Indicator sample
Reference Survey proportions vs Wage Indicator proportions
(using demographic variables)
13. 3.- Methodological approaches: present & future
1.2.a- Bias description
MARKETING MEASSURES
- Attract large masses of visitors
1.2.b.- Design based approach
- Address underrepresented groups
1.2.c- Model base approach: Calculate and test weights
Able to correct socio-demographic bias
Ex. Spain, Germany
1.2.d.- Test innovations and use paradata
Provide internet access
Mixed modes
Offline questionnaires
1.2.e.- Wage Indicator Research examples
Costs (LISS PANEL)
But less and less
Low Income Countries
& Middle-Low Income Countries
14. 1.2.- Methodological approaches and research examples
1.2.a.- Bias description
1.2.b.- Design base approach
1.2.c.- Model base approach: Calculate and test weights
1.2.d.- Test innovations and use paradata
1.2.e.- Wage Indicator Research examples
15. 1.2.- Methodological approaches: present & future
1.2.c- Model base approach: Calculate and test
weights
-Post-stratification: weight=
npopulation / nsample
16. 1.2.- Methodological approaches: present & future
1.2.c.- Model base approach: Calculate and test
weights
-Post-stratification: weight=
-Probability functions
npopulation/nsample
predicted probability
weight=1/calc.prob.
17. 1.2.- Methodological approaches: present & future
1.2.c.- Model base approach: Calculate and test
weights
-Post-stratification: weight=
-Probability functions
npopulation/nsample
predicted probability
example
weight=1/calc.prob.
18. 1.2.- Methodological approaches: present & future
SES
WI
Proportional
PSW
Structures of
Wage Indicator
Wage Indicator
Wage Indicator
18 888.18€
22 902.81€
21 903.06€
21 288.67€
(33.46)
(212.63)
(251.95)
(351.81)
0.3687
0.3596
0.3593
0.3645
Earnings Survey
Mean salary
(standard error)
Wage-Gini-index
Theoretical model of Subjective Job Insecurity
- WI Wages > SES Wages → Education
Corroborated for five EU countries
- Same (EJIR, determinants
salary Pedraza & Bustillo 2009)
- Good special campaigns
- Good performance of Propensity Score Weights
- Corroborate Life Satisfaction literature2010)DP)
(REIS, Pedraza et al. (IZA
- New findings regarding
- Employment status
- Crisis impact on Life Satisfaction determinants
19. 1.2.- Methodological approaches and research examples
1.2.a.- Bias description
1.2.b.- Design base approach
1.2.c.- Model base approach: Calculate and test weights
1.2.d.- Test innovations and use paradata
1.2.e.- Wage Indicator Research examples
20. 1.2.- Methodological approaches: present & future
1.2.d.- Test innovations and use paradata
Dynamic testing for Occupational questions
(Ulf D. Reips)
Study of paradata to improve quality
Ex. study drop out
(AIAS Working Paper, K.Tijdens, 2011)
Other web based data collection methods
21. 1.2.- Methodological approaches and research examples
1.2.a.- Bias description
1.2.b.- Design base approach
1.2.c.- Model base approach: Calculate and test weights
1.2.d.- Test innovations and use paradata
1.2.e.- Wage Indicator Research examples
22. 1.2.- Wage Indicator content research examples and opportunities
1.2.e.-Bias study→ weights→ efficiency of w.→ content research
Spain: Job Insecurity, Life Satisfaction
Brazil: Life satisfaction
International comparisons (BRICS)
- National: LFS
- International: ILO LFS,
World Values Survey;
European Social Survey.
23. 1.- Wage Indicator: Quick, reliable and internationally comparable
data
2.- Continuous Voluntary Web Surveys (CVWS): Drawbacks
3.- Methodological approaches and research examples
4.- Webdatanet
24. 4.- Webdatanet: Who we are? What are our goals? How? Why?
Webdatanet is a Multidisciplinary Network of web-based data collection
experts funded by the European Commission
Who
Sociologists, Psychologists, Economists, Media researchers, Computer scientists…
-Universities
-Data collection Institutes
-Research Institutes
-Companies
-Statistical Institutes
We are researchers from EU but also outside the EU
(80 members, 30 countries)
25. 4.- Webdatanet: Who we are? What are our goals? How? Why?
Webdatanet is a Multidisciplinary Network of web-based data collection
experts funded by the European Commission
Scientific goal
- Foster scientific usage of web-based data:
Surveys,
Experiments,
Tests,
Non-reactive data collection,
Mobile Internet research.
-Benefit society giving behavioral and social scientist high quality web data
26. 4.- Webdatanet: Who we are? What are our goals? How? Why?
Webdatanet is a Multidisciplinary Network of web-based data collection
experts funded by the European Commission
How
- Enhancing quality, integrity and legitimacy of these new forms of data collection,
- Methodological issues: Theoretical and empirical foundations,
- Stimulating its integration into the entire research process (i-science),
- Increasing interaction and communication across disciplines,
27. 4.-Webdatanet: Scientific Structure (WGs & TFs).
WG1 Quality
WG2 Innovation
WG3 Implementation
TF1 Measuring wages via web surveys
(S. Steinmetz)
TF6 New types of measurement
(U. Reips)
TF10 TSE Categorization
(F. Thorsdottir & S. Biffignandi)
TF2 Evaluating questionnaire quality
(A. Slavec)
TF7 Webdatametrics Workshops
(U. Reips & K. Kissau)
TF 11 How web change empirical world
(S. Steinmetz & K. Manfreda)
TF3 Mixed modes & representativ.
(A.Jonsdottir & K. Kalgraff)
TF8 Dissemination WG2
(U. Reips & A. Selkala)
TF16 Selecting surveys (M. Revilla)
TF4 Internet Panels Europe
(A. Scherpenzeel)
TF9 iScience portals (U. Reips)
TF17 Web data & Official Statistics
(S. Biffignandi)
TF15 Non-reactive data (N. Fornara)
TF21 GenPopWeb (G.Nicolas)
TF19 Mobile research
(R. Pinter & A. Wijnant)
TF25 Applied Economics and web
data (P. Pedraza)
TF20 Paradata (I. Andreadis)
TF26 Web data journal
(Konstantinos T.)
TF24 Experiments on students samples
(K. L. Manfreda)
TF22 German Elections, Facebook &
Twitter (R. Vatrapu, L. Kaczmirek)
TF14 Development & supervision of the web (F. Serrano & C. Zimmerman)
TF12 Master in webdatametrics (Alberto Villacampa)
TFs for Meetings, training schools, workshops, WebSM (TF18, TF13...)
SGs (Small Group meetings)
28. 2.-Scientific Structure (WGs & TFs).
WG1 Quality
WG2 Innovation
WG3 Implementation
TF1 Measuring wages via web surveys
TF6 New types of measurement
(S.WGs & TFs: www.webdatanet.eu
Steinmetz)
(U. Reips)
TF10 TSE Categorization
(F. Thorsdottir & S. Biffignandi)
TF2 Evaluating questionnaire quality
TF7 Webdatametrics Workshops
(A.-Slavec)
Conferences & Meetings (U. Reips & K. Kissau)
TF 11 How web change empirical world
(S. Steinmetz & K. Manfreda)
TF3 Mixed modes & representativ.
(A.Jonsdottir & K. Kalgraff)
- STSMs (2500€)
TF8 Dissemination WG2
(U. Reips & A. Selkala)
TF16 Selecting surveys (M. Revilla)
TF4 Internet Panels Europe
(A.-Scherpenzeel) Schools
Training
TF9 iScience portals (U. Reips)
TF17 Web data & Official Statistics
(S. Biffignandi)
(TS) (Ljubljana April 2013)
TF15 Non-reactive data (N. Fornara)
TF24 Experiments on students samples
(K.-L. Manfreda)
TF19 (WW)
Webdatametrics Workshops Mobile research
(R. Pinter & A. Wijnant)
Bergamo, January 2013
TF21 GenPopWeb (G.Nicolas)
TF23 Applied Economics and web
data (P. Pedraza)
TF20 Paradata (I. Andreadis)
- Involvement of ESR & PhD students (STSM, TS,&WW, TFs ...)
TF22 German Elections, Facebook
Twitter (R. Vatrapu, L. Kaczmirek)
- AIAS-WEBDATANET Working papers & C. Zimmerman)
TF14 Development & supervision of the web (F. Serrano (IJIS)
TF12 Master in webdatametrics (Alberto Villacampa)
TFs for Meetings, training schools, workshops, WebSM (TF18, TF13...)
SGs (Small Group meetings)
29. 4.- Webdatanet: Some Examples of TFs:
- TF1.- Measuring wages in web surveys
- TF17.- Web data & official statistics
- TF23.- Web data and Applied Economics
- TF12.- Master in Webdatametrics
30. 4.- Some Examples of TFs:
TF 1.- Measuring wages in web surveys
www.wageindicator.org
Measurement & comparability
70 countries
ILO and Decent Work Projects
Also labor conditions and satisfaction variables
Paradata (Quality of data)
31. 2.- Webdatanet scientific structure (WGs & TFs).
TF 17.- Integrating web data with Official Statistics
ESSNet
Eurostat & Statistical Institutes
Contribute web data to expansion to:
ILO
UN www.unglobalpulse.org
World Bank
32. 4.- Some Examples of TFs:
TF 12.- Master in webdatametrics
WEBDATAMETRICS
Multidisciplinary Academic Board
“General concept that emerges from the existing diverse variety of disciplines
September 2014
related to web data collection methods and analyses. Putting this knowledge
together webdatametricsOnline & F2F teachings
aim to generate new knowledge to take advance of
ICT to collect data for scientific proposes”
Core: 5 types of web base data
TF12 Master in webdatametrics (Alberto Villacampa)
Elective: implementation to specific disciplines
33. 4.- Some Examples of TFs:
TF 25.- Web data & Applied Economics
- Systematically explore all the possibilities web data Applied Economic research;
- identify & classify limits of any kind -scientific, ethical, legal, institutional, related
to data access...
- work overcame those limits and open new research opportunities aiming to
benefit society;
- foster the Webdatanet international multidisciplinary networking process with
leading academics, companies and national and international institutions;
-Apply for the necessary institutional and private support for all the above.