In undeclared work research, the estimation of the magnitude of the phenomenon (i.e., the amount of income and/or the percentage of workers involved) is of major interest. This has been done either using indirect methods or by means of ad hoc surveys such as the Eurobarometer special survey on undeclared work, our motivating study. The extent of undeclared work can be measured by means of two different outcomes: the event of working off-the-book (binary variable) and, when the event occurs, the amount of earnings deriving from the undeclared activity (continuous variable). This setup has been typically modeled via the so called two-part model: a binary choice model for the probability of observing a positive-versus-zero outcome and then, conditional on a positive outcome, a regression model for the positive outcome. We propose an extension of the two-part model that goes in two directions. The first regards the measurement error that, given the very nature of undeclared activities, is most likely to affect both the outcomes of interest. The second is that we generalize the linear regression part of the model to allow individual-level means. We also conduct an extensive simulation study to investigate the performance of the proposed model and compare it with traditional approaches.

A two-part measurement error model to estimate participation in undeclared work and related earnings / Arezzo, Maria Felice; Arima, Serena; Guagnano, Giuseppina. - In: STATISTICAL MODELLING. - ISSN 1471-082X. - (2023), pp. 1-19. [10.1177/1471082X221145240]

A two-part measurement error model to estimate participation in undeclared work and related earnings

Arezzo, Maria Felice
Primo
Membro del Collaboration Group
;
Arima, Serena
Membro del Collaboration Group
;
Guagnano, Giuseppina
Membro del Collaboration Group
2023

Abstract

In undeclared work research, the estimation of the magnitude of the phenomenon (i.e., the amount of income and/or the percentage of workers involved) is of major interest. This has been done either using indirect methods or by means of ad hoc surveys such as the Eurobarometer special survey on undeclared work, our motivating study. The extent of undeclared work can be measured by means of two different outcomes: the event of working off-the-book (binary variable) and, when the event occurs, the amount of earnings deriving from the undeclared activity (continuous variable). This setup has been typically modeled via the so called two-part model: a binary choice model for the probability of observing a positive-versus-zero outcome and then, conditional on a positive outcome, a regression model for the positive outcome. We propose an extension of the two-part model that goes in two directions. The first regards the measurement error that, given the very nature of undeclared activities, is most likely to affect both the outcomes of interest. The second is that we generalize the linear regression part of the model to allow individual-level means. We also conduct an extensive simulation study to investigate the performance of the proposed model and compare it with traditional approaches.
2023
Eurobarometer survey; measurement error; two-part model; undeclared work; undersampling
01 Pubblicazione su rivista::01a Articolo in rivista
A two-part measurement error model to estimate participation in undeclared work and related earnings / Arezzo, Maria Felice; Arima, Serena; Guagnano, Giuseppina. - In: STATISTICAL MODELLING. - ISSN 1471-082X. - (2023), pp. 1-19. [10.1177/1471082X221145240]
File allegati a questo prodotto
File Dimensione Formato  
Arezzo_two-part-measurement_2023.pdf

solo gestori archivio

Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 282.53 kB
Formato Adobe PDF
282.53 kB Adobe PDF   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1668719
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 2
social impact