• 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

[en] ON THE MISSING DISINFLATION PUZZLE: A DATA-DRIVEN APPROACH / [pt] SOBRE O MISSING DISINFLATION PUZZLE: UMA ABORDAGEM COM APRENDIZADO DE MÁQUINA

23 September 2021 (has links)
[pt] O presente trabalho investiga as potenciais explicações para o fenômeno do Missing Disinflation Puzzle. Nós montamos uma base de dados contendo apenas variáveis associadas com o fenômeno, e utilizamos métodos de Machine Learning para calcular estimativas para a inflação do Consumer Price Index durante o período de interesse. Esses métodos podem lidar com bases de dados extensas, e realizar seleção de variáveis. Um exercício de seleção de melhores modelos utilizando a técnica de Model Confidence Set sobre previsões pseudo out-of-sample é proposto. Nós analisamos o padrão de seleção de variáveis entre os melhores modelos selecionados e encontramos evidência a favor das explicações associadas ao uso de diferentes métricas de expectativas de inflação - em especial aquelas ligadas a pesquisas feitas com consumidores. / [en] This paper examines the potential explanations for the Missing Disinflation Puzzle (MDP). We construct a data set containing only variables associated with the puzzle, and use of Machine Learning (ML) methods to compute estimates for U.S. Consumer Price Index inflation over the period of interest. These methods can handle large data sets, and perform variable selection. A model selection exercise using Model Confidence Set over pseudo-out-of-sample forecasts is proposed to assess forecasting performance and to analyze the variable selection pattern of these models. We analyze the variable selection performed by the best models and find evidence for explanations associated with different metrics for inflation expectations - in particular those linked to consumers surveys.

Page generated in 0.0222 seconds