Abstract
Statistical sources on the demand side of the labour market have been historically developed later than those on the supply side. A quarterly business survey was set up by ISTAT in 2003 to contribute to fill in some of these gaps, in particular, those on job vacancies and hours worked. Attention has been paid, when designing the survey and especially for the processing procedures, to the already existing sources, in order to fully exploit the available information in the editing and imputation and grossing up phases, and to ensure consistency among aggregate data produced by different sources. In this paper, it is discussed how the integration between the data collected by the job vacancy and hours worked and two other Istat business surveys has shaped the data processing methods which are used to produce the quarterly job vacancy indicators and differentiated them from others used in short-term business statistics.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Regulation (EC) No 453/2008 of the European Parliament and of the Council, completed by two Commission Regulations, No 1062/2008 and 19/2009.
- 2.
See Di Giuseppe et al. (2004) for a description of the software and its methodological basis.
- 3.
The job vacancy survey methodologies have been described by the large majority of EU countries on the basis of a common template for the 1st International Workshop on Methodologies for Job Vacancy Statistics, held in Nuremberg in December 2008 (see http://circa.europa.eu/Members/irc/dsis/jobvacancy/library).
- 4.
In the VELA survey the sample, and hence also the list of firms with at least 500 employees included in it, is updated annually, on the basis of the most recent annual release of the SBR. This ensures that this part of the population (as represented in the frame) is completely included in the VELA sample. When designing the sample the LES firms which have less than 500 employees in the most recent SBR release are treated as all the other frame units below this size threshold. However, in the editing and imputation and grossing up phases they are treated as all the other LES units.
- 5.
The resistant fences method is an approach for outlier detection which is outlier-resistant. It is based on sample quartiles. Let \(q_1\) be the first quartile, \(q_3\) the third quartile, and \(H = q_3-q_1\), the interquartile range. The standard resistant fences rules define outliers as ratios less than \(q_1 - k\cdot H\) or greater than \(q_3+k\cdot H\), where \(k\) is a constant, which is usually set between 1.5 (inner fence) and 3 (outer fence). In our case, for some particular economic activities, we have set the constant to values larger than or equal to 4, to cope with sample distributions with very narrow interquartile ranges.
- 6.
- 7.
For the methodological bases for calibration estimation, see Deville and Särndal (1992).
- 8.
The geographical area is not used to define calibration classes, because for firms with more than one local unit the collected data do not allow to identify to which local units the job vacancies measured at the firm level actually refer to.
References
Bethel, J. (1989). Sample allocation in multivariate surveys. Survey Methodology, 15, 46–57.
Ceccato, F., Cimino, E., Congia, M. C., Pacini, S., Rapiti, F. M., & Tuzi, D. (2011). I nuovi indicatori trimestrali delle retribuzioni lorde, oneri sociali e costo del lavoro della rilevazione Oros in base 2005 e Ateco 2007. Mimeo, ISTAT.
Chen, J., & Shao, J. (2000). Nearest neighbor imputation for survey data. Journal of Official Statistics, 16, 113–131.
Deville, J. C., & Särndal, C. E. (1992). Calibration estimators in survey sampling. Journal of the American Statistical Association, 87, 367–382.
Di Giuseppe, R., Giaquinto, P., & Pagliuca, D. (2004). MAUSS (Multivariate allocation of units in sampling surveys): un software generalizzato per risolvere il problema dell’allocazione campionaria nelle indagini ISTAT. Contributi 7.
Kalton, G., & Kasprzyk, D. (1982). Imputing for missing survey responses. In Proceedings of the Section on Survey Research Methods (pp. 22–31). American Statistical Association.
Pagliuca, D. (Ed.). (2005). GENESEES v. 3.0 Funzione Riponderazione. Manuale utente ed aspetti metodologici. Tecniche e Strumenti 2, ISTAT.
Thompson, K. J., & Sigman, R. S. (1996). Statistical methods for developing ratio edit tolerances for economic data. Journal of Official Statistics, 15, 517–535.
Yohai, V. J. (1987). High breakdown-point and high efficiency robust estimates for regression. The Annals of Statistics, 15, 642–656.
Acknowledgments
This paper builds on the work done in the last years at ISTAT on the quarterly survey on job vacancies and hours worked. Ciro Baldi, Luisa Cosentino, Annalisa Lucarelli, Gian Paolo Oneto, Luisa Picozzi, Fabio Rapiti, Leonello Tronti have all participated in it in different roles, degrees of responsibility and periods of time. We wish to express our gratitude to all of them. ISTAT bears no responsibility for the analysis or interpretation of the data. All usual disclaimers apply.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Bellisai, D., Fivizzani, S., Sorrentino, M. (2013). A Business Survey on Job Vacancies: Integration with Other Sources and Calibration. In: Davino, C., Fabbris, L. (eds) Survey Data Collection and Integration. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21308-3_9
Download citation
DOI: https://doi.org/10.1007/978-3-642-21308-3_9
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21307-6
Online ISBN: 978-3-642-21308-3
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)