ECB paper suggests faster methods for estimating eurozone employment

A working paper published by the European Central Bank presents a new approach to estimating the performance of the eurozone’s labour market.

In Nowcasting employment in the euro area, Marta Bańbura, Irina Belousova, Katalin Bodnár and Máté Barnabás Tóth aim at improving the timeliness of labour data. Official statistics on the eurozone’s labour market “are published with a considerable lag, longer than in the case of real GDP”, the authors note.

They present a suite of models designed to provide a rapid estimate of the eurozone’s quarterly employment growth. The suite includes several different dynamic factor models and bridge equation specifications.

The authors evaluate their suite against real eurozone data from 2013 to 2022. It performs favourably compared with the tools used by the staff of the ECB and the eurosystem, they say.

While their suite’s forecasting performance deteriorated temporarily at the beginning of the Covid-19 pandemic, it then improved to outperform the ECB models, the authors say. They find the use of monthly indicators provides useful data on employment.

Unemployment rates and indicators of market sentiment contain most of the relevant information. “The performance of small-scale models is comparable to those based on a larger information set,” the authors say.

They say future research could examine making the models “more robust and accurate also in very volatile periods such as the Covid-19 pandemic”. It could also examine the use of data from sources such as search engine trends, social media or job websites.