Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2020 Dec 19;104:297–299. doi: 10.1016/j.ijid.2020.12.045

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© 2021 The Authors

Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre - including this research content - immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active.

PMC Copyright notice

Estimates of excess deaths from all causes based on an ARIMA (3,0,1) model with drift, number of confirmed COVID-19 deaths, and number of probable COVID-19 deaths in Ecuador between January 1 and October 22, 2020. Data on confirmed and probable COVID-19 deaths were obtained from the National Risk and Emergency Management Service of Ecuador (Servicio Nacional de Gestión de Riesgos y Emergencias, 2020).

*The National Risk and Emergency Management Service of Ecuador defines a confirmed COVID-19 death as a case that had laboratory confirmation of SARS-CoV-2 infection before death.

^†A probable COVID-19 death is defined by the National Risk and Emergency Management Service of Ecuador as a case that exhibited known COVID-19 symptoms but did not have laboratory confirmation of SARS-CoV-2 infection before death.

Notes:

- The website of the National Institute of Statistics and Census (Instituto Nacional de Estadística y Censos, 2020) reports all-cause mortality data until December 31, 2019. For the period from January 1, 2020 to October 22, 2020 all-cause mortality data were obtained from the website of the National Civil Registry (Dirección General del Registro Civil, Identificación y Cedulación, 2020).

- Levels of all-cause mortality from December 24, 2019 to December 31, 2019 were on average lower than those registered on previous days. Deaths not registered on these vacation days were probably only registered on January 1, 2020, and as a result excess mortality was estimated to be much higher than 0 for that day. Levels of deaths in the period from March 13, 2020 to March 19, 2020 were also unusually low and as a result negative estimates of excess deaths were obtained in a systematic way for those days. These results were obtained in a first analysis with the ARIMA (3,0,1) model with drift, which showed the best performance with the OOS evaluation. To improve the fit of the model, we fitted a simple exponential smoothing model with multiplicative errors (ETS(M,N,N)) on the time series data preceding each of these periods and used the corresponding forecasts to replace the actual values of these days. ETS(M,N,N) produced the lowest RMSE in a last block evaluation for each of these 2 periods when compared with other models of exponential smoothing, cubic smoothing splines, simple moving average, and ARIMA. Reported results in Figure 1 and Table 1 are based on these modified data.

- Data on confirmed and probable COVID-19 deaths from the National Risk and Emergency Management Service of Ecuador were negative for some days. We set those values to 0 in the plot shown in Figure 1.

- A number of 362 probable COVID-19 deaths on October 8, 2020 appears to be an outlier with respect to levels of COVID-19 deaths around that period of time. Many of them may represent deaths that possibly occurred at an earlier point in time and that were only registered on October 8.