Hours worked in the euro area

Prepared by Vasco Botelho, Agostino Consolo and António Dias da Silva

Published as part of the ECB Economic Bulletin, Issue 6/2021.

1 Introduction

This article analyses the evolution of hours worked per worker in the euro area, in the light of their relevance for the labour contribution to the production of goods and services and for the capacity of the labour market to adjust to macroeconomic developments.^[1] First, it looks at the factors behind the trend decline in hours worked per worker over the last 25 years. It then goes on to consider the importance of hours worked per worker for labour market adjustment during economic expansions and recoveries. The long-term decline in hours worked per worker may affect labour input, depending on its interplay with labour market participation. Cyclical movements in hours worked per worker allow flexibility during downturns, as firms can adjust labour costs by reducing hours instead of employment (labour hoarding) in the event of adverse shocks to the profitability of the firms concerned. The contribution of average hours to the cyclical adjustment affects the measurement of labour market strength and slack. This is an important determinant of the dynamics of wage and price inflation, making it relevant for the conduct of monetary policy.

The decline in hours worked per worker is a long-term phenomenon. Annual hours worked per worker declined by more than a thousand hours in France, Germany, Italy and the Netherlands between 1870 and 1973.^[2] Similar developments occurred in other countries, such as Australia, Canada, Japan, the United Kingdom and the United States. The pace of the decline decelerated somewhat after 1973 and became more uneven across countries. There are several reasons for the long-term decline in hours worked per worker, with technological progress as a common factor or even enabler.^[3] In fact, technological progress over the last 150 years changed the nature of production work and led to the creation of large numbers of jobs in the services sector. Fast productivity gains allowed wages to increase and the cost of leisure activities to decrease, altering the optimal allocation of time between work and leisure. This article zooms in on the last 25 years for a detailed analysis of the evolution of hours worked per worker in the euro area.

Between 1995 and 2019, annual hours worked per worker in the euro area declined by more than a hundred. On a weekly basis, hours worked per worker in the euro area fell from 38.6 in 1995 to 36.4 in 2019 (Chart 1). The decline in hours worked per worker was particularly large in 2020, on account of the coronavirus (COVID-19) pandemic, although most of this decline is expected to be only temporary. Moreover, while the pandemic affected the number of hours effectively worked in the euro area, it did not lead to significant changes in the usual duration of the work week for the average worker during 2020 compared to the period preceding the pandemic.

The decline in hours worked per worker in the euro area over the last 25 years is mainly associated with trends in labour force participation and part-time work. From a theoretical perspective, the reduction in hours worked per worker could reflect a reduction in hours worked in full-time or part-time jobs as well as an increase in the share of part-time work. The main factor behind the decline in hours worked per worker in the euro area over the last 25 years is an increase in the share of part-time work. From a household perspective, higher labour force participation increases aggregate income and may lead to lower average hours worked due to income effects, i.e. the income is higher with two members of the household working, who may decide to work fewer hours on average. At the same time, joint taxation systems may discourage the labour supply of second earners, leading to a higher likelihood of the second earner working part time.^[4] Both the income effects and joint taxation systems may trigger lower hours worked per worker. Moreover, changes in regulations and workers’ preferences affect working time. For example, there were changes in working time regulations (e.g. the introduction of the 35-hour week in France in the early 2000s) coupled with preference shifts, with workers calling for a reduction of weekly hours worked instead of negotiating for higher wages.^[5] The increase in labour force participation and in the share of part-time employment have mainly been driven by a higher female labour force participation rate, as women are also more likely to take up part-time jobs. The increase in female participation results in part from a shift in home production to the market economy (known as marketisation of home production), a phenomenon that is considered to have occurred later and to a more limited extent in Europe than in the United States.^[6]

Developments in hours worked per worker are important to gauge the strength of the euro area labour market over the business cycle. The fallout from the global financial crisis and the euro area sovereign debt crisis has had a lasting effect on labour input as measured by total hours worked. During the crisis period, labour hoarding by reducing hours worked limited the increase in unemployment in the euro area. The adjustment in hours worked is an important part of any comprehensive analysis of the strength and timing of labour market recoveries, as the unemployment rate may not fully reflect the state of the labour market. For example, the number of hours worked per worker became even more important for the capacity of the labour market to adjust to the COVID-19 pandemic, as euro area countries deployed job retention schemes to protect employment (Chart 2).^[7]

2 Long-term developments in hours worked

Structural changes over the last 25 years have had a considerable impact on hours worked per worker. These transformations include a larger share of employment in the services sector, greater female labour force participation, an increased share of part-time work and an ageing society.^[8] The increase in labour market participation contributed to higher total hours worked and higher hours worked per capita.^[9] However, to the extent that new labour market entrants worked fewer hours, they contributed to a decrease in hours worked per worker. This section analyses developments in hours worked per worker in the euro area in the last 25 years. It concludes that the main driver of the decline is higher labour market participation by women, which is also reflected in an increased employment-to-population ratio.

Hours worked per worker declined across all sectors, while shifts towards services put further downward pressure on this metric. A shift-share analysis shows that most of the secular decline in average hours worked in the euro area is driven by within-sector dynamics, as average hours worked declined in most sectors. However, composition effects also play a role, accounting for roughly 20% of the decline in hours worked per worker in the euro area since 1995 (Chart 3). These composition effects are driven by a decline in the employment share of agriculture and industry and a corresponding increase in the employment share of professional services and administrative and support activities. The shift from manufacturing to services is often labelled as the “servitisation” of the economy, with manufacturing firms changing their business models to start selling both goods and services.^[10] More broadly, sectoral differences in hours worked per worker are also related to technological differences across the different sectors and to the different conditions offered by employers across sectors. The technological channel implies differences in hours worked per worker across sectors resulting from differences in the production methods used at the firm level in different sectors. The different conditions offered by employers across sectors is driven instead by changes in labour demand and in the bargaining power of workers as they negotiate their labour contracts.

The decline in hours worked per worker in the euro area was accompanied by a corresponding increase in the employment-to-population ratio. Chart 4 (panel a) compares the employment-to-population ratio with the quarterly hours worked per worker in the euro area. It shows that in the last 25 years, the significant decline in hours worked was accompanied by higher labour market participation (about 8 percentage points), hinting at a substitution effect in the labour market as more people started participating with fewer hours. Taken together, the increase in the employment-to-population ratio and the decline in average hours worked also suggest the existence of income effects and long-term changes in labour supply decisions taken by households in the euro area. Such substitutability between average hours worked and labour market participation is a feature peculiar to the euro area as this is not present in the data for the United States in this period. In the United States, employment and hours worked per worker tend to co-move and depend mostly on business cycle conditions (Chart 4, panel b).^[11] Also, the reduction in hours worked per worker during the last 25 years was smaller in the United States than in the euro area. Such differences highlight the importance of careful analysis of hours worked per worker when assessing the euro area labour market.

The largest euro area countries share a secular decline in hours worked per worker, although the level of hours worked varies and is negatively related to the employment-to-population ratio. Chart 5 shows that countries with relatively fewer hours worked per worker have a relatively higher employment-to-population ratio (e.g. Germany), while countries with higher levels of quarterly hours worked per worker have lower employment-to-population ratios (e.g. Italy and Spain). Beyond differences in the level of average hours worked and employment-to-population ratios, both variables face a common trend across countries. Larger declines in average hours tend to be associated with larger increases in employment-to-population ratios. France, Germany and Italy contributed the bulk of the decline in average hours worked in the euro area (around 78%) over the last 25 years.

The higher labour market participation of women is the main driver behind the increase in the employment-to-population ratio in the euro area. The euro area labour force participation rate was 59.8% in 2000, rising to 64.6% in 2019.^[12] The increase in labour force participation in the euro area was mostly driven by more women participating in the labour market, with the rate increasing by around 9 percentage points over the last two decades to reach 59.4% in 2019. Thus, increased female participation contributed 90% of the increase in labour force participation in the euro area between 2000 and 2019.^[13]

The increase in female labour force participation is also associated with an increase in part-time employment.^[14] Women are more likely to work part-time than men.^[15] In the euro area, women make up a disproportionate share of part-time workers, accounting for more than 75% of part-time employment. 29% of employed women and 5% of employed men worked part-time in 2000, rising to 36% of employed women and 10% of employed men in 2019. Most part-time employment is voluntary and allows for more people to participate in the labour market at any given point in time (see also Chart 16 in Section 3).^[16] Yet some institutional features, such as insufficient childcare arrangements, may hamper the ability of some people to work full time.

The increase in part-time employment is the main factor behind the decline in hours worked per worker. Conceptually, hours worked per worker can decrease either when full-time or part-time workers work fewer hours or when there is an increase in the share of part-time work in the economy. Over the last two decades, the average full-time worker in the euro area saw their average hours worked fall by about half an hour per week, while the average part-time worker saw their average hours worked increase by slightly more than half an hour per week (Chart 6, panel a).^[17] These developments did not contribute much to the decline in average hours worked in the euro area. By contrast, the euro area has faced a remarkable increase in part-time work, with the share of part-time employment in the euro area rising from 15.4% in 2000 to 22.1% in 2019.^[18] While workers are traditionally more likely to work part-time in some countries (such as Germany or the Netherlands) than in others (such as Italy or Spain), the increase in part-time employment is common to all the larger euro area countries (Chart 6, panel b).^[19]

The negative relationship between hours worked per worker and part-time employment is a long-term feature of the euro area labour market. The growth rate of average hours worked is lower as part-time employment increases during both expansions and recessions. However, this relation is asymmetric with the business cycle, with changes in part-time employment having a stronger impact on the growth of average hours worked during recessions than during expansions. Table 1 proposes a set of reduced-form regressions quantifying the negative relationship between average hours worked and the share of part-time employment. To account for cross-sectoral variability across countries, panel data across all euro area countries are used to estimate the relationship between the year-on-year growth rate of average hours worked and the year-on-year changes in the share of part-time employment. An increase of one percentage point in the share of part-time employment serves to slow year-on-year growth in average hours worked by 0.12 percentage points during expansions and by 0.57 percentage points during recessions.^[20] The cyclical conditions of the labour market are also an important factor contributing to the dynamics of average hours worked. Year-on-year changes in the unemployment rate also have an impact on the growth rate of average hours worked asymmetrically with the business cycles. During expansions, decreases in the unemployment rate lead to a higher growth rate of average hours worked.^[21] By contrast, increases in the unemployment rate during recessions also lead to increases in the growth rate of average hours worked, as workers who work fewer hours are usually laid off first. This implies that the dynamics of average hours worked also have an important cyclical component on top of the declining long-run trend.

The documented decline in hours worked per worker depends on both demand and supply factors. Most people working part-time do so voluntarily, as they choose to work fewer hours than full-time workers. However, a not insignificant share of part-time workers report doing so because they could not find a full-time job, suggesting that demand is a factor determining the numbers of hours worked. The EU-LFS asks all workers whether they would like to work more hours. In the total sample, about 10% of workers report that they would like to work more hours than they currently do (Chart 7). Among part-time workers, more than one in five would like to work more hours than they usually do.

Part-time employment features a cyclical component related to “involuntary” part-time employment, which acts as a buffer in the adjustment of the labour market during crisis periods. Chart 8 shows the evolution of part-time employment in the euro area between 2006 and 2019, focusing on disentangling the trend increase in “voluntary” part-time employment from the more cyclical “involuntary” part-time employment. “Voluntary” part-time employment reflects increases in the aggregate labour supply stemming from increasing flexibility in the labour market, which allows workers to work if they wish and to work fewer hours than a full-time job. By contrast, “involuntary” part-time employment comprises all workers who work part-time because they could not find a full-time job. In this way, involuntary part-time captures fluctuations in labour demand, in workers’ bargaining power and in the matching efficiency of the euro area labour market. This all means that involuntary part-time employment is considerably more cyclical than voluntary part-time employment. Voluntary part-time employment has been trending upwards over time, without many major cyclical fluctuations. At the same time, involuntary part-time employment in the euro area increased during the global financial crisis and the sovereign debt crisis periods, before falling slowly during the economic expansion that ensued following a stabilisation during the first years of the recovery.^[22] The share of involuntary part-time work can also be linked to labour underutilisation beyond that captured by the unemployment rate, with this factor instead being observed in a decline in average hours worked.

The differences in hours worked per worker across demographic groups are largest for women. To analyse differences across individuals, hours per week usually worked are regressed on five age groups, three education groups, gender, occupation, economic activity sector, country and year. The regression analysis is carried out for the period 1998-2019 using the EU-LFS microdata for workers aged 20-65 reporting between ten and 60 hours usually worked per week; the agriculture sector and armed forces are excluded. Chart 9 displays the estimation results for individual characteristics. It shows that the more marked differences in weekly hours worked occur for gender, with usual hours worked per week being about five hours fewer for women than for men. This result is partly explained by the larger share of women working part-time. All age groups work higher hours on average than the 20-24 age group. Among prime-age workers, the 35-44 age group reports slightly lower hours, which may be related to childcare activities. Across education groups, workers with high levels of education tend to work more hours than workers with middle and low levels. These are average results for 1998-2019; the patterns are relatively stable over this period for gender but differ for both age and education. The 20-24 age group saw a larger decline in hours worked than any other age group; and workers with a high level of education had a smaller decline in hours worked than workers with low and middle levels of education.

The incidence of part-time work varies across demographic groups and activity sectors, and these differences may offer insights on the future evolution of hours worked per worker. Female and older workers have been two important forces driving the increase in labour force participation in the euro area. It is expected that these two groups will continue to increase their share in the labour market, in view of the large heterogeneity in their labour force participation rates across the euro area countries and the ageing of the population. These developments are likely to continue to contribute to lower hours worked per worker as these workers are more likely to work part-time. ^[23] In addition, the incidence of part-time varies greatly across economic activity sectors. For example, accommodation, healthcare and social activities, and education are three sectors where the incidence of part-time work is above average and which have also gained employment shares since the global financial crisis. An increase in employment in sectors with higher shares of part-time work may lead to lower average hours worked per worker in the future. The skill level is another factor explaining the incidence of part-time work. Part-time work increased across all education groups, with faster increases for low- and middle-skilled workers than for high-skilled workers, from about 16% in 2000 to 24% in 2020. In the same period, part-time employment among high-skilled workers increased from 13% to 18%. The increasing employment share of high-skilled workers may moderate the downward pressure on hours worked per worker.

Self-employment is another important factor driving the decline in average hours worked in the euro area. Self-employment contributes to the decline in average hours worked directly – with the average self-employed worker decreasing their hours worked by more than the average employee – and indirectly via composition effects in the economy.^[24] The direct effects can be assessed by looking at the relative decline in average hours worked across the two groups of workers. While employees reduced their average hours worked by 5.2% between 1995 and 2019, the average self-employed worker reduced their hours by 7% over the same period (Chart 10, left panel). The indirect contribution of self-employment to the decline in average hours worked stems from composition effects, as self-employed workers worked longer hours on average than the average employee (Chart 10, middle panel) and their share in total employment decreased (Chart 10, right panel).

3 Hours worked during the pandemic

The adjustment of the labour market during the COVID-19 pandemic featured only limited changes in the standard unemployment rate. Measures to contain the spread of the coronavirus severely limited activity in some sectors. This situation would normally lead to a sharp increase in unemployment. However, policy support in the form of job retention schemes helped to protect employment and facilitated labour market adjustment via average hours worked (Chart 11). This led the standard measure of the unemployment rate to be mostly unaffected during the pandemic. However, a broader measure of labour underutilisation, the “U7” rate, can account for both people unemployed and workers in job retention schemes. The U7 rate thus better captures the strong response of the labour market to the sharp contraction in economic activity during the pandemic (Chart 12).^[30]

Hours worked per worker played an important role in the adjustment of the labour market during the pandemic. The year-on-year growth rate of real GDP can be decomposed into developments in total hours worked and labour productivity per hour worked. The developments in total hours worked are further decomposed in Chart 13 to account for the different margins of adjustment in the labour market, such as changes in average hours worked, the unemployment rate, labour force participation and population growth. These different margins can have either a persistent or a cyclical impact on the growth rate of total hours worked. Of these factors, changes in hours worked per worker represent on average a persistent drag on the growth rate of real GDP over time, which is stronger during recessions and milder during expansions. The importance of hours worked per worker increased considerably during the pandemic, boosted by the strong policy support in the form of job retention schemes.

The adjustment in hours worked per worker varied greatly across sectors, reflecting the nature of the pandemic and subsequent containment measures. In the first half of 2020, average hours worked declined by 14.3%. The decline was much stronger in contact-intensive sectors such as trade and transport and recreation – which also saw their activity substantially curtailed due to social distancing measures – than for sectors such as ICT or financial services, which are less contact-intensive and have a higher proportion of potentially teleworkable jobs (Chart 14).^[31] Average hours worked recovered substantially from the lows recorded in the second quarter of 2020. That said, average hours worked were still 5% lower in the first quarter of 2021 than in the last quarter of 2019. The trade and transport and recreation sectors remain the worst affected by the pandemic, with average hours worked in the first quarter of 2021 standing 11% below the levels seen in the fourth quarter of 2019.

Job retention schemes facilitated the preservation of employment in these sectors.^[32] A great advantage of these schemes is that they help activity to resume swiftly as soon as containment measures are lifted. However, they need to be flexible enough to be adjusted quickly as soon as activity recovers so as to allow labour reallocation across firms.

4 Concluding remarks

The analysis of hours worked per worker plays an important role in explaining both the long-term trends and the cyclical fluctuations in the euro area labour market. A secular downward trend in hours worked per worker is mainly related to technological progress, sectoral shifts towards the services sector, changes in labour and tax regulations, increases in labour force participation and the increased preference for part-time jobs. At the same time, cyclical changes in hours worked per worker have provided an important margin of labour market flexibility to withstand adverse shocks to firms’ profitability during the global financial crisis, the euro area sovereign debt crisis and the COVID-19 pandemic.

Various factors help to explain the decline in hours worked per worker over the last 25 years, while the future path after the pandemic is uncertain. Increases in self-employment and in the participation rate of women and the related increase in part-time employment explain some of the decline in hours worked per worker over the last 25 years. While hours worked per worker played a prominent role as a margin of adjustment during the pandemic, it remains unclear whether hours worked will recover to pre-pandemic levels.

The cyclical adjustment of hours worked per worker is a distinct feature of the euro area, making it important for assessing the labour market. The use of part-time contracts and, more recently, the widespread use of job retention schemes mean that the standard measure of unemployment is not fully capable of capturing labour underutilisation in the euro area. Consequently, any analysis of the labour market needs to include the intensive margin. Hours worked and the share of (involuntary) part-time employment are thus important metrics to complement standard labour market indicators. Moreover, hours worked per worker in the euro area tend to decline faster during cyclical downturns and then not fully recover during the upturn. Real-time analysis has become more difficult and uncertain as different permanent and cyclical factors are at play in the dynamics of hours worked per worker, which can blur potential scarring effects from recessions.

Labour market heterogeneity measured in terms of full-time and part-time workers is an important factor affecting the Phillips curve. When looking at the wage-unemployment relationship in the euro area, Eser et al.^[33] conclude that the sensitivity of wages to the output gap can be lower to the extent that there are many people underemployed or inactive. Thus, assessing the intensive margin and considering differences across job types may provide a better signal of the strength of the labour market as well as the implications for wages and inflation. In addition, labour market heterogeneity is relevant for income inequality. This is especially the case when either average hours worked or part-time workers are more persistently affected following an economic recession. Hysteresis effects on hours worked can further contribute to a higher income dispersion across workers, as also suggested by Heathcote et al.^[34] for the United States.

The future path in hours worked per worker is difficult to predict, while the balance of factors seems to point towards the downward trend continuing. The expected increase in labour market participation of female and older workers is likely to exert downward pressure on hours worked per worker. A higher employment share in the services sector with higher rates of part-time employment may also lead to lower average hours worked. By contrast, the ongoing upskilling of the labour force may moderate the decline in hours worked per worker, as individuals with higher education levels tend to work more hours on average. Preferences regarding the allocation of time will continue to play a key role on the evolution of hours worked.