Parameter estimates for interrupted time series regression analysis of weekly Kentucky resident drug overdose fatality numbers in service-related industries versus non-service-related industries, 2018–2021
| Service-related industries | Non-service-related industries | |||
| Parameter estimate (95% CI) | P value | Parameter estimate (95% CI) | P value | |
| Pre-COVID-19 level | 6.57 (5.59 to 7.54) | <0.0001 | 8.56 (7.21 to 9.90) | <0.0001 |
| Pre-COVID-19 trend | 0.0055 (−0.0092 to 0.0202) | 0.4646 | 0.028 (0.0074 to 0.049) | 0.0082 |
| Level change after the week of 22 March 2022 | 1.25 (−2.73 to 5.23) | 0.5358 | −1.43 (−6.48 to 3.63) | 0.5784 |
| Trend change after the week of 22 March 2022 | 0.73 (0.042 to 1.413) | 0.0374 | 1.80 (1.01 to 2.57) | <0.0001 |
| Level change after business resumed | −5.22 (−8.6 to −1.76) | 0.0033 | −11.89 (−16.40 to 7.38) | <0.0001 |
| Trend change after business resumed | −0.72 (−1.40 to −0.032) | 0.0403 | −1.80 (−2.58 to −1.02) | <0.0001 |