Impacto da COVID-19 nos principais indicadores econômicos do Brasil

• Autor(a) principal: Mazuqueli, Juliana Ricci
• Data de Publicação: 2022
• Tipo de documento: Trabalho de conclusão de curso
• Idioma: por
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://hdl.handle.net/11449/217367
• topic: Temporal decomposition models; Dummy variables; Periodogram; Economic indicators; COVID-19; Modelos de decomposição temporal; Variáveis dummy; Periodograma; Indicadores econômicos

In the years 2020 and 2021, the world faced the COVID-19 pandemic, reflecting directly on the economy of countries, this change is noticeable by the analysis of economic indicators. In this work, in order to be able to identify the changes present in the Brazilian economy, temporal regression models were applied, composed of dummy and harmonic variables, with periods defined in advance through the analysis of the periodogram. For analysis, monthly values of Gross Domestic Product (GDP), General Market Price Index, Unemployment Rate, National Consumer Price Index and Broad Consumer Price Index, from January 2018 to September 2021. For the model, the dummy variables were defined, Zit , representing whether there was a change between the pre-pandemic period (2018-2019) and during the pandemic (2020- 2021), and Zitt, representing whether there was a change in the slope of the line between the two periods. Residual analysis consisted of the ShapiroWilk test, Runs test and Durbin-Watson test, the metrics for adequacy were the root squared error (RMSE), mean absolute error (MAE) and the coefficient of determination (R2). The models for the National Consumer Price Index, Broad Consumer Price Index, GDP and General Market Price Index passed the tests applied, and all showed changes between the periods under study, in addition to changes in the straight line, however, only the GDP obtained an adequate result in relation to the coefficient of determination, for the Unemployment Rate, we did not obtain satisfactory results in the residual analysis, even applying transformations to the data.