This paper applies a Factor-Augmented VAR model proposed by Bernanke, Boivin and Eliasz (2005) to measure the impact of the monetary policy in Taiwan. Our empirical results show that, first, the more the factors added in the benchmark VAR, the more we can explain the price puzzle problem. Second, the effect of the tightening in the monetary policy (the increase in the interbank overnight lending rate) is inconsistent with the results expected by the credit channel.

This study proposes one plausible procedure to address two methodological issues, which are common in micro- and macro- econometric analyses, for the full realization of research potential brought by recently available high dimensional data. To address the issue of how to infer the causal structure from empirical regularities, graphical causal models are proposed to inductively infer causal structure from non-temporal and non-experimental data. However, the (probabilistic) stability condition for the graphical causal models can be violated for high dimensional data, given that close co-movements and thus near deterministic relations are oftentimes observed among variables in high dimensional data. Aggregation methods are proposed as one possible way to address this matter, allowing one to infer causal relationships among disaggregated variables based on aggregated variables. Aggregation methods also are helpful to address the issue of how to incorporate a large information set into an empirical model, given that econometric considerations, such as degrees-of-freedom and multicollinearity, require an economy of parameters in empirical models. However, actual aggregation requires legitimate classifications for interpretable and consistent aggregation. Based on the generalized condition for the consistent and interpretable aggregation derived from aggregation theory and statistical dimensional methods, we propose plausible methodological procedure to consistently address the two related issues of causal inference and actual aggregation procedures. Additional issues for empirical studies of micro-economics and macro-economics are also discussed. The proposed procedure provides an inductive guidance for the specification issues among the direct, inverse, and mixed demand systems and an inverse demand system, which is statistically supported, is identified for the consumer behavior of soft drink consumption. The proposed procedure also provides ways to incorporate large information set into an empirical model with allowing structural understanding of U.S. macro-economy, which was difficult to obtain based on the previously used factor augmented vector autoregressive (FAVAR) framework. The empirical results suggest the plausibility of the proposed method to incorporate large information sets into empirical studies by inductively addressing multicollinearity problem in high dimensional data.

Exports are one of the key aggregates in the Argentina’s economy, both because to its links with thedomestic demand and by its influence on the behaviour of the trade balance and current account.Have adequate forecasts for this variable is useful to design policies to keep surpluses in the externalsector and prevent recurring crises seen in the past. In this work, we considered some modelsfor forecasting the performance of this aggregate, which could be an alternative to the estimationof structural econometric models. For this purpose, we used two approaches: the first is based instandard and Bayesian VARs (Minnesota prior, Gibbs sampler, partial BVAR and BVAR-Kalman). Thelatter combines the evidence in the data with any prior information that may also be available. Thesecond approach considers the FAVAR (Factor-augmented VAR) models, which combines the standardVAR with factor analysis. Finally, we evaluated the forecasting ability of different models. / Las exportaciones representan uno de los agregados más importantes de la economía argentina,tanto por su vinculación con la demanda doméstica como por su influencia en el comportamientode la balanza comercial y de la cuenta corriente. Disponer de adecuados pronósticos deesta variable resulta útil a fin de diseñar políticas que permitan mantener superávit en el sectorexterno y evitar las recurrentes crisis observadas en el pasado. En este trabajo, se consideran algunosmodelos destinados a la realización de pronósticos de dicho agregado, los cuales podrían seruna alternativa a la estimación de sistemas econométricos estructurales. A tal efecto, se utilizandos propuestas: la primera se basa en modelos de VAR sin restricciones y Bayesianos (‘Minnesota’prior, ‘Gibbs sampler’, parcial BVAR y BVAR-Kalman). Estos últimos consideran supuestos a priori(‘prior’) e información histórica de las series de tiempo empleadas. La segunda propuesta descansaen modelos FAVAR (Factor-aumentado VAR), que combinan los VAR con el análisis de factores.Finalmente, se evalúa la capacidad de pronóstico de los distintos modelos.

Submitted by FAUSTO JOSE ARAUJO VIEIRA (ytcfausto@yahoo.com.br) on 2017-04-28T21:36:08Z No. of bitstreams: 1 tese_final.pdf: 2272430 bytes, checksum: df5f5e915ef009c6c4008d83f8789967 (MD5) / Approved for entry into archive by Vera Lúcia Mourão (vera.mourao@fgv.br) on 2017-04-28T22:15:52Z (GMT) No. of bitstreams: 1 tese_final.pdf: 2272430 bytes, checksum: df5f5e915ef009c6c4008d83f8789967 (MD5) / Made available in DSpace on 2017-05-02T12:04:19Z (GMT). No. of bitstreams: 1 tese_final.pdf: 2272430 bytes, checksum: df5f5e915ef009c6c4008d83f8789967 (MD5) Previous issue date: 2017-04-19 / This thesis presents three chapters about forward-looking indicators. In the first two chapters, we propose a factor augmented VAR that combines Nelson and Siegel yield curve factors and principal components extracted from a large dataset. We find that the factor augmented VAR models do a very good job in fitting the level, slope and curvature of the yield curve. The out-of-sample forecasting using principal components beats consistently the predictions from autoregressive and extant literature models in the short- and long-term horizons. We apply this methodology for Brazilian and US economy in the first and second chapter, respectively. Despite the differences between these countries, the results are quite similar. Additionally, we show that forecasting improvement comes from the nature of our dataset that gather mainly forward-looking series. In the last chapter, we study the behavior of macroeconomic predictions made by professional forecasters, specifically, 1-year inflation expectation. We conclude that apart of biased and inefficient forecasting, forecasters misestimate the inflation seasonality. This conclusion is not a country specific. We find seasonality in 1-year inflation for Brazil, Chile, Israel, New Zealand, US and Euro Zone. / Esta tese apresenta três capítulos sobre indicadores antecedentes. Nos dois primeiros, propomos um modelo VAR aumentado por fatores, que combina os fatores latentes da curva de juros sugerido por Nelson e Siegel com os principais componentes extraídos de uma ampla base de dados. O modelo VAR aumentado por fatores apresenta um bom ajuste para o nível, inclinação e curvatura da curva de juros. As projeções fora da amostra para o modelo com principais componentes é significativamente superior às previsões feitas pelos modelos auto-regressivos e pelos sugeridos na literatura, tanto nos horizontes de curto e de longo prazo. Aplicamos esta metodologia para o Brasil e os Estados Unidos no primeiro e segundo capítulo, respectivamente. Apesar das diferenças entre estes países, os resultados encontrados são semelhantes. Adicionalmente, mostramos que a melhora nas projeções é resultado da natureza da nossa base de dados, que coleta indicadores antecedentes. No último capítulo, discutimos o comportamento de projeções macroeconômicas feitas por analistas profissionais, especificamente, as estimações para a inflação 1 ano à frente. Concluímos que além das previsões serem viesadas e ineficientes, os analistas erram a estimação da sazonalidade da inflação. Esta conclusão não é algo específico para um único país. Encontramos sazonalidade na expectativa de inflação 1 ano à frente para o Brasil, Chile, Israel, Nova Zelândia, Estados Unidos e Zona do Euro.