The significance of occupations, family responsibilities, and gender for working from home: Lessons from COVID-19

Abstract

Before the pandemic, many employers were hesitant to offer their employees the option of working from home. However, remote working has been widely adopted during the pandemic as one of the key methods of controlling the spread of the virus. The measure encountered a widespread acceptance and it is likely that the demand for work from home as a flexible work arrangement will persist also after the pandemic has ended. Although numerous studies have addressed the role of remote work during this crisis, as of yet we lack thorough research jointly addressing the question on how occupations/job characteristics on the one hand and family/household responsibilities on the other are associated with the propensity of working from home, and how gender cuts across those aspects. Using the COVID-19 survey of the German Family Panel (pairfam), covering the peak of the first wave of the pandemic in 2020, together with information from pairfam panel waves conducted before the pandemic, as well as a special evaluation of the 2019 German Labor Force Survey, we are able to address this gap. Employing linear probability models on a sample of 1,414 men (N = 641) and women (N = 773), our results show that occupational traits, especially the gender composition of an occupation, are an important predictor for working from home. Women employed in female-dominated occupations are less often in a position to work from home. Furthermore, our study confirms that it is particularly the highly educated, as well as those who work in high-prestige occupations, who are able to work from home. Family configurations and care obligations are less influential upon the transition to homeworking, even in times of an unprecedented situation of school and daycare closures and increased parental responsibilities for children's (early) education.

Fig 1

Work from home by gender (A), educational level (B), care (C) and household chores (D). Note: Based on pairfam-COVID-19 survey and pairfam Release 12.0, own calculations, weighted.

Fig 2. Work from home regressed on family responsibilities, occupational characteristics, and education.

Note: Plot of Linear Probability Model coefficients (see S2 Table for the full models). Based on pairfam-COVID-19 survey and pairfam, release 12.0, and a special evaluation of the German LFS 2019, own calculations, not weighted. Reference groups: Care: split even/mostly partner/completely partner; Chore: split even/mostly partner/completely partner; mixed occupation; intermediate education. Controls (not shown): enrolled in education, East, migration background, rural, cohorts. ⁺ p < 0.10 * p < 0.05, ** p < 0.01, *** p < 0.001.

Fig 3. Work from home regressed on family responsibilities, occupational characteristics, education, and WFH prior to COVID-19.

Note: Plot of Linear Probability Model coefficients (see S3 Table for the full models). Based on pairfam-COVID-19 survey and pairfam, release 12.0, and a special evaluation of the German LFS 2019, not weighted. Reference groups: Care: split even/mostly partner/completely partner; Chore: split even/mostly partner/completely partner; mixed occupation; intermediate education. Controls (not shown): enrolled in education, East, migration background, rural, cohorts. ⁺ p < 0.10 * p < 0.05, ** p < 0.01, *** p < 0.001.