Fig. 3.

Heterogenous effects Note: Each circle shows the exponentiated coefficients for the months of March, April, May, June and July, respectively, interacted with Year2020 from a Poisson regression for the number of calls to Línea 100 per 100,000 people. Within each figure, a separate regression is estimated for the sample above (blue) and below (red) the median of the baseline characteristic. Controls include those in column 3 of Table 1: year, state and month fixed effects in addition to state-specific and month-specific trends. Confidence intervals at the 95% are calculated using robust standard errors clustered at the state-year level. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)