Long-Term Time Prediction of Cumulative Number of Deaths in Brazil, China, Germany, Italy, Spain, the United States: an application to COVID-19 S-shaped models
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Research, Society and Development |
Texto Completo: | https://rsdjournal.org/index.php/rsd/article/view/6565 |
Resumo: | This research aims to adjust the Gompertz and Bertalanffy nonlinear regression model for the accumulated deaths by COVID-19 in six countries Brazil, United States, Germany, Italy, China, and Spain. It employed three different performance measures in the training process, adjusted determination coefficient , Akaike Information Criterion (AIC), and Residual Mean Square (RMS). The Mean Absolute Percentage Error (MAPE) and the Relative Error (RE) criterion were used to select the best model in the test dataset. On the training dataset, the Bertalanffy model was the one that best described the growth of deaths for China, while the Gompertz model was the best for Brazil, Germany, Italy, Spain, and the United States. In contrast, the Bertalanffy model was the best for Spain in the test dataset, according to MAPE and RE. According to the Gompertz model, 214,100 CI (175,929;267,008) people will die in Brazil, that will reach a maximum of 1,577 with a prediction interval [1,367; 1,819] of daily new deaths at its disease peak. The nonlinear models studied described the number of deaths growth curve satisfactorily, providing parameters with practical interpretations. Evidence was found that Brazil may surpass the United States regarding the total number of deaths. Short and long-term time prediction, as well as the turning point of each country, are presented and compared to other predictive models of the literature. |
id |
UNIFEI_cd1b848f7c4af53e03eb89ce2309d40f |
---|---|
oai_identifier_str |
oai:ojs.pkp.sfu.ca:article/6565 |
network_acronym_str |
UNIFEI |
network_name_str |
Research, Society and Development |
repository_id_str |
|
spelling |
Long-Term Time Prediction of Cumulative Number of Deaths in Brazil, China, Germany, Italy, Spain, the United States: an application to COVID-19 S-shaped modelsPredicción a largo plazo del número acumulado de muertes en Brasil, China, Alemania, Italia, España, Estados Unidos: una aplicación a los modelos con forma de S de COVID-19Previsão a longo prazo do número acumulado de óbitos no Brasil, China, Alemanha, Itália, Espanha, Estados Unidos: uma aplicação aos modelos em forma de S da COVID-19Curva SPandemiaCoronavirusPrevisão.S curvaPandemiaCoronavirusPronóstico.S-CurvePandemicCoronavirusForecast.This research aims to adjust the Gompertz and Bertalanffy nonlinear regression model for the accumulated deaths by COVID-19 in six countries Brazil, United States, Germany, Italy, China, and Spain. It employed three different performance measures in the training process, adjusted determination coefficient , Akaike Information Criterion (AIC), and Residual Mean Square (RMS). The Mean Absolute Percentage Error (MAPE) and the Relative Error (RE) criterion were used to select the best model in the test dataset. On the training dataset, the Bertalanffy model was the one that best described the growth of deaths for China, while the Gompertz model was the best for Brazil, Germany, Italy, Spain, and the United States. In contrast, the Bertalanffy model was the best for Spain in the test dataset, according to MAPE and RE. According to the Gompertz model, 214,100 CI (175,929;267,008) people will die in Brazil, that will reach a maximum of 1,577 with a prediction interval [1,367; 1,819] of daily new deaths at its disease peak. The nonlinear models studied described the number of deaths growth curve satisfactorily, providing parameters with practical interpretations. Evidence was found that Brazil may surpass the United States regarding the total number of deaths. Short and long-term time prediction, as well as the turning point of each country, are presented and compared to other predictive models of the literature.Este trabajo tiene como objetivo ajustar el modelo de regresión no lineal de Gompertz y Bertalanffy para las muertes acumuladas por COVID-19 en seis países Brasil, Estados Unidos, Alemania, Italia, China y España. Empleó tres medidas de rendimiento diferentes en el proceso de capacitación, coeficiente de determinación ajustado , Criterio de información de Akaike (AIC) y Cuadrado medio residual (RMS). El error de porcentaje absoluto medio (MAPE) y el criterio de error relativo (RE) se utilizaron para seleccionar el mejor modelo en el conjunto de datos de prueba. En el conjunto de datos de entrenamiento, el modelo de Bertalanffy fue el que mejor describió el crecimiento de muertes para China, mientras que el modelo de Gompertz fue el mejor para Brasil, Alemania, Italia, España y los Estados Unidos. Por el contrario, el modelo Bertalanffy fue el mejor para España en el conjunto de datos de prueba, según MAPE y RE. Según el modelo de Gompertz, 214,100 CI (175,929; 267,008) personas morirán en Brasil, que alcanzará un máximo de 1,577 con un intervalo de predicción [1,367; 1,819] de nuevas muertes diarias en su pico de enfermedad. Los modelos no lineales estudiados describieron la curva de crecimiento del número de muertes satisfactoriamente, proporcionando parámetros con interpretaciones prácticas. Se encontró evidencia de que Brasil puede superar a los Estados Unidos con respecto al número total de muertes. La predicción del tiempo a corto y largo plazo, así como el punto de inflexión de cada país, se presentan y comparan con otros modelos predictivos de la literatura.Esta pesquisa objetiva ajustar o modelo de regressão não linear de Gompertz e Bertalanffy para as mortes acumuladas pelo COVID-19 em seis países Brasil, Estados Unidos, Alemanha, Itália, China e Espanha. Empregou três medidas de desempenho diferentes no processo de treinamento, coeficiente de determinação ajustado , Critério de Informação de Akaike (AIC) e Quadrado Médio Residual (RMS). O erro da porcentagem absoluta média (MAPE) e o erro relativo (ER) foram usados para selecionar o melhor modelo no conjunto de dados de teste. No conjunto de dados de treinamento, o modelo Bertalanffy foi o que melhor descreveu o crescimento de mortes na China, enquanto o modelo Gompertz foi o melhor para o Brasil, Alemanha, Itália, Espanha e Estados Unidos. Por outro lado, o modelo Bertalanffy foi o melhor para a Espanha no conjunto de dados de teste, de acordo com MAPE e RE. De acordo com o modelo de Gompertz, 214.100 IC (175.929; 267.008) pessoas morrerão no Brasil, atingindo um máximo de 1.577 com um intervalo de previsão [1.367; 1.819] de novas mortes diárias no pico da doença. Os modelos não lineares estudados descreveram satisfatoriamente a curva de crescimento do número de óbitos, fornecendo parâmetros com interpretações práticas. Foram encontradas evidências de que o Brasil pode superar os Estados Unidos em relação ao número total de mortes. A previsão de tempo a curto e longo prazo, bem como o ponto de virada de cada país, são apresentados e comparados com outros modelos preditivos da literatura.Research, Society and Development2020-07-30info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://rsdjournal.org/index.php/rsd/article/view/656510.33448/rsd-v9i8.6565Research, Society and Development; Vol. 9 No. 8; e749986565Research, Society and Development; Vol. 9 Núm. 8; e749986565Research, Society and Development; v. 9 n. 8; e7499865652525-3409reponame:Research, Society and Developmentinstname:Universidade Federal de Itajubá (UNIFEI)instacron:UNIFEIenghttps://rsdjournal.org/index.php/rsd/article/view/6565/5855Copyright (c) 2020 André Luiz Pinto dos Santos, Marcela Portela Santos de Figueiredo, Tiago Alessandro Espínola Ferreira, Maitê Priscila Lima Jota de Queirozhttp://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessFigueiredo, Marcela Portela Santos deSantos, André Luiz Pinto dosFerreira, Tiago Alessandro EspínolaQueiroz, Maitê Priscila Lima Jota de2020-08-20T18:00:17Zoai:ojs.pkp.sfu.ca:article/6565Revistahttps://rsdjournal.org/index.php/rsd/indexPUBhttps://rsdjournal.org/index.php/rsd/oairsd.articles@gmail.com2525-34092525-3409opendoar:2024-01-17T09:29:39.229157Research, Society and Development - Universidade Federal de Itajubá (UNIFEI)false |
dc.title.none.fl_str_mv |
Long-Term Time Prediction of Cumulative Number of Deaths in Brazil, China, Germany, Italy, Spain, the United States: an application to COVID-19 S-shaped models Predicción a largo plazo del número acumulado de muertes en Brasil, China, Alemania, Italia, España, Estados Unidos: una aplicación a los modelos con forma de S de COVID-19 Previsão a longo prazo do número acumulado de óbitos no Brasil, China, Alemanha, Itália, Espanha, Estados Unidos: uma aplicação aos modelos em forma de S da COVID-19 |
title |
Long-Term Time Prediction of Cumulative Number of Deaths in Brazil, China, Germany, Italy, Spain, the United States: an application to COVID-19 S-shaped models |
spellingShingle |
Long-Term Time Prediction of Cumulative Number of Deaths in Brazil, China, Germany, Italy, Spain, the United States: an application to COVID-19 S-shaped models Figueiredo, Marcela Portela Santos de Curva S Pandemia Coronavirus Previsão. S curva Pandemia Coronavirus Pronóstico. S-Curve Pandemic Coronavirus Forecast. |
title_short |
Long-Term Time Prediction of Cumulative Number of Deaths in Brazil, China, Germany, Italy, Spain, the United States: an application to COVID-19 S-shaped models |
title_full |
Long-Term Time Prediction of Cumulative Number of Deaths in Brazil, China, Germany, Italy, Spain, the United States: an application to COVID-19 S-shaped models |
title_fullStr |
Long-Term Time Prediction of Cumulative Number of Deaths in Brazil, China, Germany, Italy, Spain, the United States: an application to COVID-19 S-shaped models |
title_full_unstemmed |
Long-Term Time Prediction of Cumulative Number of Deaths in Brazil, China, Germany, Italy, Spain, the United States: an application to COVID-19 S-shaped models |
title_sort |
Long-Term Time Prediction of Cumulative Number of Deaths in Brazil, China, Germany, Italy, Spain, the United States: an application to COVID-19 S-shaped models |
author |
Figueiredo, Marcela Portela Santos de |
author_facet |
Figueiredo, Marcela Portela Santos de Santos, André Luiz Pinto dos Ferreira, Tiago Alessandro Espínola Queiroz, Maitê Priscila Lima Jota de |
author_role |
author |
author2 |
Santos, André Luiz Pinto dos Ferreira, Tiago Alessandro Espínola Queiroz, Maitê Priscila Lima Jota de |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Figueiredo, Marcela Portela Santos de Santos, André Luiz Pinto dos Ferreira, Tiago Alessandro Espínola Queiroz, Maitê Priscila Lima Jota de |
dc.subject.por.fl_str_mv |
Curva S Pandemia Coronavirus Previsão. S curva Pandemia Coronavirus Pronóstico. S-Curve Pandemic Coronavirus Forecast. |
topic |
Curva S Pandemia Coronavirus Previsão. S curva Pandemia Coronavirus Pronóstico. S-Curve Pandemic Coronavirus Forecast. |
description |
This research aims to adjust the Gompertz and Bertalanffy nonlinear regression model for the accumulated deaths by COVID-19 in six countries Brazil, United States, Germany, Italy, China, and Spain. It employed three different performance measures in the training process, adjusted determination coefficient , Akaike Information Criterion (AIC), and Residual Mean Square (RMS). The Mean Absolute Percentage Error (MAPE) and the Relative Error (RE) criterion were used to select the best model in the test dataset. On the training dataset, the Bertalanffy model was the one that best described the growth of deaths for China, while the Gompertz model was the best for Brazil, Germany, Italy, Spain, and the United States. In contrast, the Bertalanffy model was the best for Spain in the test dataset, according to MAPE and RE. According to the Gompertz model, 214,100 CI (175,929;267,008) people will die in Brazil, that will reach a maximum of 1,577 with a prediction interval [1,367; 1,819] of daily new deaths at its disease peak. The nonlinear models studied described the number of deaths growth curve satisfactorily, providing parameters with practical interpretations. Evidence was found that Brazil may surpass the United States regarding the total number of deaths. Short and long-term time prediction, as well as the turning point of each country, are presented and compared to other predictive models of the literature. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-07-30 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://rsdjournal.org/index.php/rsd/article/view/6565 10.33448/rsd-v9i8.6565 |
url |
https://rsdjournal.org/index.php/rsd/article/view/6565 |
identifier_str_mv |
10.33448/rsd-v9i8.6565 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
https://rsdjournal.org/index.php/rsd/article/view/6565/5855 |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Research, Society and Development |
publisher.none.fl_str_mv |
Research, Society and Development |
dc.source.none.fl_str_mv |
Research, Society and Development; Vol. 9 No. 8; e749986565 Research, Society and Development; Vol. 9 Núm. 8; e749986565 Research, Society and Development; v. 9 n. 8; e749986565 2525-3409 reponame:Research, Society and Development instname:Universidade Federal de Itajubá (UNIFEI) instacron:UNIFEI |
instname_str |
Universidade Federal de Itajubá (UNIFEI) |
instacron_str |
UNIFEI |
institution |
UNIFEI |
reponame_str |
Research, Society and Development |
collection |
Research, Society and Development |
repository.name.fl_str_mv |
Research, Society and Development - Universidade Federal de Itajubá (UNIFEI) |
repository.mail.fl_str_mv |
rsd.articles@gmail.com |
_version_ |
1797052655226322944 |