# Estimation of the size of informal employment based on administrative records with non-ignorable selection mechanism

## TL;DR

This paper introduces a novel method using administrative data and advanced statistical modeling to estimate the prevalence of informal employment at the company level in Poland, addressing non-ignorable selection bias.

## Contribution

It presents the first company-level estimates of informal employment based solely on administrative records and extends Heckman's model to non-Gaussian error correlations with random effects.

## Key findings

- 5.7% of registered enterprises engage in informal employment
- The method can be applied to other countries' administrative data
- Provides new insights into informal employment prevalence

## Abstract

In this study we used company level administrative data from the National Labour Inspectorate and The Polish Social Insurance Institution in order to estimate the prevalence of informal employment in Poland. Since the selection mechanism is non-ignorable we employed a generalization of Heckman's sample selection model assuming non-Gaussian correlation of errors and clustering by incorporation of random effects. We found that 5.7% (4.6%, 7.1%; 95% CI) of registered enterprises in Poland, to some extent, take advantage of the informal labour force. Our study exemplifies a new approach to measuring informal employment, which can be implemented in other countries. It also contributes to the existing literature by providing, to the best of our knowledge, the first estimates of informal employment at the level of companies based solely on administrative data.