• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Google Trends para previsão de variáveis macro: uso no Brasil através do algoritmo autometrics

Guimarães Filho, Samuel 10 February 2017 (has links)
Submitted by Samuel Guimarães Filho (samuelgf@gmail.com) on 2017-03-07T01:39:40Z No. of bitstreams: 1 tese_samuel_revisao_1.pdf: 2212736 bytes, checksum: eef717244d02ccf54ceb936354c64525 (MD5) / Approved for entry into archive by Renata de Souza Nascimento (renata.souza@fgv.br) on 2017-03-07T23:43:25Z (GMT) No. of bitstreams: 1 tese_samuel_revisao_1.pdf: 2212736 bytes, checksum: eef717244d02ccf54ceb936354c64525 (MD5) / Made available in DSpace on 2017-03-08T15:56:07Z (GMT). No. of bitstreams: 1 tese_samuel_revisao_1.pdf: 2212736 bytes, checksum: eef717244d02ccf54ceb936354c64525 (MD5) Previous issue date: 2017-02-10 / This work aims to test if the use of Google Trends as an exogenous variable improves the prediction of the monthly data for Brazilian Formal Job Creation (CAGED) compared to a model that uses only the lags themselves. For the selection of the model was used the algorithm Autometrics and for model comparison the Model Confidence Set. In addition, the model that uses Google Trends data will be compared with some market analyst’s forecasts. The results show that the model the uses the Google data as an exogenous variable is superior to the model that only uses the lag itself. However, this model was not able to overcome the market analysts. / Este trabalho tem como objetivo testar se o uso do Google Trends como variável exógena melhora a previsão do dado mensal do CAGED em relação a modelos que usam apenas as próprias defasagens. Para a seleção do modelo foi utilizado o algoritmo Autometrics e para comparação de modelos o utilzado o Model Confidence Set. Além disto, o modelo que utiliza o Google Trends foi comparado com previsões dos analistas de Mercado. Os resultados encontrados apontam que o modelo que utliza o Google Trends como variável exógena é superior ao modelo que utiliza apenas a própria defasagem. No entanto, este modelo, não foi capaz de superar os analistas de mercado.

Page generated in 0.1053 seconds