Impact of COVID-19 lockdowns on mental health: Evidence from a quasi-natural experiment in England and Scotland

Abstract

The COVID-19 pandemic has been associated with worsening mental health but it is unclear whether this is a direct consequence of containment measures, like "Stay at Home" orders, or due to other considerations, such as fear and uncertainty about becoming infected. It is also unclear how responsive mental health is to a changing situation. Exploiting the different policy responses to COVID-19 in England and Scotland and using a difference-in-difference analysis, we show that easing lockdown measures rapidly improves mental health. The results were driven by individuals with lower socioeconomic position, in terms of education or financial situation, who benefited more from the end of the strict lockdown, whereas they suffered a larger decline in mental health where the lockdown was extended. Overall, mental health appears to be more sensitive to the imposition of containment policies than to the evolution of the pandemic itself. As lockdown measures may continue to be necessary in the future, further efforts (both financial and mental health support) are required to minimize the consequences of COVID-19 containment policies for mental health.

Keywords: COVID-19; health; health inequality; lockdown; mental health.

FIGURE 1

Natural experiment setup. Figure (a) reports the evolution of the Oxford stringency index which measures the strictness of lockdown‐style closure and containment policies that restrict people's behavior (Hale et al., 2020). Shaded areas represent the fieldwork days for each UK Household Longitudinal Study survey wave. The areas between the colorful vertical lines represent the reference period for each survey wave regarding the mental health questions. Mental health questions were framed as how the respondent was feeling “over the last few weeks”. Then, we assumed a reference period of two weeks prior to answering the survey, so that if for wave Covid 2 the fieldwork dates were between May 27 and June 02, then the reference period would be May 13–June 02. Important to note that most of the interviews in Scotland at Wave 2 (68%) were carried out during the days May 17 and 28 when the region was still at the maximum level of restrictions. Figure (b) reports the 7‐day rolling average of COVID‐19 deaths based on the publish date. Data source: UK government (https://coronavirus.data.gov.uk/details/download). (a) Evolution of COVID‐19 containment policies (Oxford stringency index); (b) Evolution of COVID‐19 deaths

FIGURE 2

Difference‐in‐difference (DiD) results of the effect of easing restrictions on General Health Questionnaire (GHQ)‐caseness. Figure A reports the weighted mean of the GHQ‐caseness scale over nation and UK Household Longitudinal Study wave. Figure B reports the coefficients and the 95% confidence intervals of the interaction between the England dummy and the wave dummies (${\beta }_2$ in model of Equation 1), leaving survey wave Covid 1 (Late April) as base category. Full results of this model are reported in Table A1 of Supporting Information S1 (Column [3]). (a) Descriptive statistics (Weighted mean over region and time); (b) DiD model coefficients

FIGURE 3

Difference‐in‐difference (DiD) effect of easing lockdown by dimension of General Health Questionnaire (GHQ)‐caseness. This figure reports the coefficients and the 95% confidence intervals of the interaction between the England dummy and the Covid survey wave 2 dummy (within ${\beta }_2$ in model of Equation 1). Each coefficient comes from a different regression where the dependent variable is equal 1 if the correspondent GHQ dimension is equal to 3 or 4, and zero otherwise. Full results of these regressions are reported in Table A2 of Supporting Information S1

FIGURE 4

Difference‐in‐difference (DiD) effect of easing lockdown by socioeconomic group. General Health Questionnaire (GHQ)‐caseness. This figure reports the coefficients and the 95% confidence intervals of the interaction between the England dummy and the Covid survey wave 2 dummy (within ${\beta }_2$ in model of Equation 1). Each coefficient comes from a different regression using the corresponding subsample of each socioeconomic group. Age groups are based on respondent age by April 2020. Full results of these regressions are reported in Tables A3 and A4 of Supporting Information S1. Household earning loss is based on the question “Is your household is now earning less than in January/February 2020?”. Self‐reported financial situation is based on the question “How well would you say you yourself are managing financially these days?”; those who responded “living comfortably” or “doing alright” were classified as Good financial situation, whereas those who responded “Just about getting by”, “Finding it quite difficult” or “Finding it very difficult” were classified as Bad financial situation. The evolution of the mean GHQ‐caseness by socioeconomic group and nation is reported in Figures A3–A8 of Supporting Information S1