We provide a flexible means of estimating time-varying parameter models in a Bayesian framework. By specifying the state innovations to be characterized trough a threshold process that is driven by the absolute size of parameter changes, our model detects at each point in time whether a given regression coefficient is constant or time-varying. Moreover, our framework accounts for model uncertainty in a data-based fashion through Bayesian shrinkage priors on the initial values of the states. In a simulation, we show that our model reliably identifies regime shifts in cases where the data generating processes display high, moderate, and low numbers of movements in the regression parameters. Finally, we illustrate the merits of our approach by means of two applications. In the first application we forecast the US equity premium and in the second application we investigate the macroeconomic effects of a US monetary policy shock. / Series: Department of Economics Working Paper Series

This thesis develops a new Bayesian approach to structural break modeling. The focuses of the approach are the modeling of in-sample structural breaks and forecasting time series allowing out-of-sample breaks. Our model has some desirable features. First, the number of regimes is not fixed and is treated as a random variable in our model. Second, our model adopts a hierarchical prior for regime coefficients, which allows for the regime coefficients of one regime to contain information about regime coefficients of other regimes. However, the regime coefficients can be analytically integrated out of the posterior distribution and therefore we only need to deal with one level of the hierarchy. Third, the implementation of our model is simple and the computational cost is low. Our model is applied to two different time series: S&P 500 monthly returns and U.S. real GDP quarterly growth rates. We linked breaks detected by our model to certain historical events.

<p>This dissertation is a collection of four essays on nonstationary time series econometrics, which are grouped into four chapters. The first chapter investigates the inference in mildly explosive autoregressions under unconditional heteroskedasticity. The second chapter develops a new approach to forecasting a highly persistent time series that employs feasible generalized least squares (FGLS) estimation of the deterministic components in conjunction with Mallows model averaging. The third chapter proposes new bootstrap procedures for detecting multiple persistence shifts in a time series driven by nonstationary volatility. The last chapter studies the problem of testing partial parameter stability in cointegrated regression models.</p>

La thèse se propose, dans une première partie, de décrire l'origine des débats sur la nécessité d'une banque centrale jusqu'aux formulations actuelles. Sont examinés les éléments qui ont posé les bases d'un prêteur ultime et favorisé la maturation de ce métier, de même que sont mis en relief les résultats accumulés depuis deux siècles. Notre attention porte sur la Réserve Fédérale des Etats-Unis. Les économistes sont en quête de solutions afin de prévenir les crises financières. Ainsi a été proposé un élargissement du tableau de bord de manière à contenir les prix d'actif dans une approche macro et micro-prudentielle. Parallèlement, sont analysés les canaux par lesquels la politique monétaire influence les variables réelles et financières de l'économie, et qui attestent alors du rôle pouvant être théoriquement assumé par la banque centrale sur les marchés financiers. La deuxième partie concentre le propos sur les ressorts des crises financières. Nous nous intéressons au paradoxe de la surliquidité et du surendettement, en insistant sur les particularités des marchés financiers devenant plus vulnérables. La contribution de la thèse dans cette étape consiste à vérifier si la banque centrale contribue à la manifestation de comportements abusifs et excessifs sur les marchés financiers par l'abondante création de liquidité. Notre étude empirique devrait permettre de répondre à cette question à travers une modélisation économétrique et des tests statistiques (dont le test de Chow) appliqués à une politique monétaire active (type règle de Taylor). En ce sens, cette recherche sur les actions de la Fed vise à forger une opinion sur le métier de banquier central et sur son devenir. / The thesis proposes, in a first part, to describe the origin of the debate on the need for a central bank up until the recent formulations. They were examined the elements which have posed the bases of an "ultimate lender" and promoted the maturation of this function, as were highlighted the results accumulated over two centuries. Our attention is drawn to the Federal Reserve of the United States. The economists are always in search for solutions to prevent financial crises. It has thus been proposed to extend the dashboard of central banks as to contain asset prices in a macro and micro-prudential approach. In parallel, in order to support this debate, we analyze the mechanisms by which the monetary policy affects the real and financial variables of the economy, which also affirm the role that can be assumed in theory by a central bank on financial markets. The second part focuses on the recurrence and intensity of financial crises. We consider the paradox of excess liquidity and over-indebtedness, with an emphasis on properties of financial markets becoming more vulnerable and their recent development. The contribution of the thesis in this stage consists of checking whether the central bank is responsible of abusive and excessive behavior on the financial markets by the abundant creation of liquidity. Our empirical study should help to answer this question through an econometric modeling and statistical tests (including the Chow test) applied to an active monetary policy (type Taylor rule). In this way, our research on the actions of the Fed aims to forge an opinion on the profession of modern central bankers, and perhaps on the future of central banks themselves.

This thesis examines dynamic relationships between inflation and monetary policy in a sample of African economies using quarterly data over the period 1980:01 to 2012:04. The literature on inflation dynamics and monetary policy focuses on developed economies, with little attention devoted to the African economies, which is potentially explained by the fact that in the past monetary policy played second fiddle because of fiscal policy dominance following episodes of high inflation and stabilization policies that occurred in the 1980's. This thesis fills an important gap in assessing African's monetary policy. The thesis predominantly uses the Vector-Autoregression (VAR) framework to examine the monetary policy frameworks of the African economies. The thesis finds that an interest rate shock on average explain a more significant proportion of the variance in the output gap and inflation than the exchange rate, in terms of analysing the decomposition of shocks to the economy. This shows a shift in the monetary policy focus away from exchange rate management to interest rate targeting as the African economies have become more market oriented. The monetary policy reveal strong asymmetric responses with respect to the macroeconomic variables when inflation exceeds its threshold value. The analysis suggests that monetary policy in the African economies is regime-dependent, propagated through the inflation thresholds, such that the authorities strongly implement policy changes when inflation goes beyond a certain threshold. The thesis reveals that by taking into account the prior belief of the monetary authorities, it helps produce better estimates of the performance of the monetary policy transmission mechanism, as it combines prior information with the sampling information which is contained in the data. The overall novelty of the thesis is that some African economies are adopting inflation targeting policies instead of exchange rate management. It is imperative that the subsequent inflation targeting frameworks will achieve monetary policy objectives for the African economies and the use of interest rate management should be continued.

This thesis, “Empirical Asset Pricing and Investment Strategies”, examines a number of topics related to portfolio choice, asset pricing, and strategic and tactical asset allocation. The first two papers treat the predictability of asset returns. Since at least the mid-1980s until quite recently, the conventional wisdom has been that it is possible to predict the return on, for example, an index of stocks. However, a series of recent papers have challenged this conventional wisdom. I answer this challenge and show that it is possible to predict returns if structural changes in the underlying economy are taken into account. The third paper examines the comovement between stocks and bonds. I show how it is possible to improve the composition of a portfolio consisting of these two asset classes by taking into account how the comovement changes over time. All three papers are self-contained and can therefore be read in any order. The first paper is entitled “Structural Breaks in Asset Return Predictability: Can They Be Explained?” Here I investigate whether predictability has changed over time and, if so, whether it is possible to tie the change to any underlying economic variables. Dividend yield and the short interest rate are often used jointly as instruments to predict the return on stocks, but several researchers present evidence that the relation has undergone a structural break. I use a model that extends the conventional structural breaks models to allow both for smooth transitions from one state to another (with a break as a special case), and for transitions that depend on a state variable other than time. The latter allows me to directly test whether, for example, the business cycle influences how the instruments predict returns. The results suggest that this is not the case. However, I do find evidence of a structural change primarily in how the instruments predict returns for large firms. The change differs from a break in that it appears to be an extended non-linear transition during the period 1993—1997. After the change, the short rate does not predict returns at all. Dividend yield, on the other hand, is strongly significant, and the return has become more sensitive to it. In the second paper, “Restoring the Predictability of Equity Returns,” I take another perspective on predictability and structural shifts. Several recent papers have questioned the predictability of equity returns, potentially implying serious negative consequences for investment decision-making. With return data including the 1990s, variables that previously predicted returns, such as the dividend yield, are no longer significant and results of out-of-sample tests are often weak. A possible reason is that the underlying structure of the economy has changed. I use an econometric model that allows for regime shifts over time as well as due to changes in a state variable, in this case the price-earnings ratio. This makes it possible to separate influences from these two sources and to determine whether one or both sources have affected return predictability. The results indicate that, first, a structural change occurred during the 1990s, and, second, that the unusually high level of price earnings in the late 1990s and early 2000s temporarily affected predictability at the 12-month horizon. In the third paper, “Coupling and Decoupling: Changing Relations between Stock and Bond Market Returns,” I investigate stock-bond comovement. The correlation between stocks and bonds has changed dramatically over the last ten years, introducing a new type of risk for portfolio managers, namely, correlation risk. I use GARCH estimates of stock volatility, simple regressions, and regime-switching econometric models to assess whether level of volatility, or changes in volatility, can be used to explain some of the changes in comovement in seven different countries. As regards volatility level, strong support is found in almost all countries to suggest that high volatility predicts lower, or negative, comovement. I argue that this can be evidence of a market-timing type of behavior. As for changes in volatility, the results are more mixed. Only for the U.S. market do I find strong support to conclude that large changes tend to coincide with lower, or negative, comovement. This could be evidence of a flight-to-quality (or cross-market hedging) type of behavior. / <p>Diss. Stockholm : Handelshögskolan, 2007</p>

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / This work seeks to analyze at different frequencies, the transmission of volatility in the prices of crude oil produced by OPEC members and other producing and exporting countries that are not part of this organization and to analyze the presence of structural breaks in dynamic correlation between crude oil spot and future prices. The Wavelets methodology employed aims to decompose the series to verify its behavior at different frequencies, revealing additional information or confirming trends. To check the transmission process of the volatility it is proposed the application of Granger Causality Test. This made it possible to understand the functioning of this important market and answer the following question: How behaves the volatility of oil prices when analyzed considering several time horizons in an analysis in the frequency domain? The analysis of volatility transmission shows a strong integration of the international oil market, the correlation structural breaks tests results shows that structural break point is not static for any analysis, it moves, depending the frequency scale and the time window. / Este trabalho busca analisar em diferentes frequências, o sentido e a transmissão da volatilidade nos preços do petróleo bruto produzido pelos países membros da OPEP (Organização dos Países Exportadores de Petróleo) e dos demais países produtores e exportadores que não fazem parte desta organização; bem como analisar a presença de quebras estruturais na correlação dinâmica entre os preços à vista e futuro do petróleo. A metodologia de Wavelets empregada tem por objetivo decompor as séries estudas a fim de verificar seu comportamento em diferentes frequências, revelando informações adicionais ou confirmando tendências observadas. Para a verificação do processo de transmissão da volatilidade foi proposta a utilização do método de Causalidade de Granger. Desta forma foi possível compreender o funcionamento deste importante mercado e responder a seguinte questão: Como se comporta a volatilidade do preço do petróleo quando se analisam variados horizontes de tempo em uma análise no domínio da frequência? A análise da transmissão da volatilidade aponta para uma forte integração do mercado internacional do petróleo, enquanto o resultado da análise das quebras na correlação mostra que o ponto de quebra estrutural não é estático para toda e qualquer análise, ele se move, dependendo da frequência e do horizonte temporal.

Submitted by Maike Costa (maiksebas@gmail.com) on 2016-04-12T13:00:18Z No. of bitstreams: 1 arquivo total.pdf: 1701778 bytes, checksum: 4e6e0ca5635cf810784f97567b64095f (MD5) / Made available in DSpace on 2016-04-12T13:00:18Z (GMT). No. of bitstreams: 1 arquivo total.pdf: 1701778 bytes, checksum: 4e6e0ca5635cf810784f97567b64095f (MD5) Previous issue date: 2014-03-10 / This paper conducts tests for structural breaks in the reaction function of the Central Bank of Brazil to evaluate possible changes in the conduct of monetary policy in Brazil, taking into account the reaction function of the regressors are potentially endogenous variables. For this, we uses the methodology developed by Hall et al. (2012) who, using an extension of the framework developed by Bai and Perron (1998), develops a method capable of identifying multiple structural breaks at unknown periods. The main results indicate presence of structural breaks in the three reaction functions studied. Furthermore, the actions of monetary policy through interest rate Selic seem to suffer greater influence of deviations of inflation around its target, compared to changes in the output gap and the exchange rate. / Este estudo realiza testes de quebra estrutural na função de reação do Banco Central do Brasil para avaliar possíveis mudanças na condução da política monetária doméstica, levando-se em conta que os regressores da função de reação são potencialmente variáveis endógenas. Para isto, é utilizada a metodologia desenvolvida por Hall et al. (2012) que, utilizando uma extensão da estrutura desenvolvida por Bai e Perron (1998), elaboram um método capaz de identificar múltiplas quebras estruturais em períodos desconhecidos. Os principais resultados apontam para a presença de quebras estruturais nas três funções de reação estudadas. Além disso, as ações da política monetária, por meio da taxa de juros Selic, parecem sofrer maior influência dos desvios da inflação em torno de sua meta, comparativamente a variações no hiato do produto e na taxa de câmbio.

Made available in DSpace on 2016-03-15T19:31:02Z (GMT). No. of bitstreams: 1 Edward Bernard Bastiaan de Rivera y Rivera.pdf: 1871035 bytes, checksum: cf35ada408d6ca217674838231a332e2 (MD5) Previous issue date: 2014-04-09 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / The contribution of this thesis is the application of a new perspective in the assessment of the rational expectations model at the enterprise level, conducted in Nasseh and Straus (2004), Goddard, McMillan and Wilson (2008) and Rivera Rivera, Martin, Marçal and Basso (2012). These works investigate micro efficiency hypothesis in the sense presented in Jung and Shiller (2005) and adopt the restrictive hypotheses of independence in the error terms of the sample companies, as well as the absence of structural breaks. Common movements in stock prices characterize the systematic risk from unobserved common factors and structural breaks, such as financial crises, induce shifts in the relationship between prices and fundamentals. The objective of this investigation is the analysis of the rational expectations model at the enterprise level with constant and time-varying returns under the presence of multiple structural breaks and cross-sectional dependence. Recent econometric procedures of panel unit root and cointegration that contain properties of structural breaks and dependences are applied to Sao Paulo Stock Exchange (Bovespa) and S&P100 companies quarterly data covering the period of 1994-2012. Considering a multifactor error structure, results indicate a failure in the rejection of a unit root in (log) prices and (log) dividends. Panel cointegration analysis allowing structural breaks and cross-sectional dependence controlling to the presence of bubbles indicate that established procedures might not detect present structural breaks or generate oscilating statistics in size and power depending on the panel dimensions. A computational extention is developed allowing for enterprise-level structural breaks and cross-sectional dependence through bootstrap techniques. Results fail to reject the rational expectations model at the enterprise level and are consistent with the statistical significance and break dates detected in time-series cointegration routines. Evidences favor rationality and unforecastability of returns, where investors cannot profit consistently through speculation and active portfolio management. / A contribuição deste estudo é a aplicação de uma nova perspectiva na análise do modelo de expectativas racionais ao nível da empresa, conduzida em Nasseh e Strauss (2004), Goddard, McMillan e Wilson (2008) e Rivera Rivera, Martin, Marçal e Basso (2012). Estes trabalhos investigam a hipótese de micro eficiência analisada em Jung e Shiller (2005) e adotam hipóteses restritivas de independência nos termos de erro das empresas, assim como a ausência de quebras estruturais. Movimentos comuns nos preços dos ativos caracterizam o risco sistemático a partir de fatores não observados e as quebras estruturais, como crises financeiras, provocam mudanças nas relações entre preços e seus fundamentos. Neste sentido, o objetivo do estudo consiste na análise do modelo de expectativas racionais ao nível da empresa com taxas requeridas de retorno constantes e variáveis no tempo, admitindo-se a presença de múltiplas quebras estruturais e dependência nas seções transversais. Aplicam-se procedimentos econométricos recentemente desenvolvidos de raiz unitária e cointegração em painel que contenham as propriedades de quebras estruturais e dependências para dados trimestrais das empresas da Bovespa e S&P100 no período de 1994 a 2012. Os resultados indicam que, com uma estrutura de erro multifatorial, falha-se em rejeitar a hipótese nula de raiz unitária para (log de) preços e (log de) dividendos. Na análise de cointegração em painel com quebras estruturais e dependências que controlam a presença de bolhas racionais, procedimentos estabelecidos podem não detectar quebras presentes ou possuem estatísticas que oscilam em tamanho e poder conforme as dimensões do painel. Desenvolve-se uma extensão computacional que comporta quebras desconhecidas invididuais para as empresas e lida com dependências por meio de técnicas de reamostragens. Os resultados falham em rejeitar o modelo de expectativas racionais ao nível da empresa e são consistentes em significância estatística e datas de quebras detectadas em rotinas de cointegração para séries temporais aplicadas individualmente às empresas. Evidências favorecem a racionalidade dos agentes e imprevisibilidade de retornos, em que os investidores não poderiam obter lucros consistentes por meio da especulação e gerenciamento ativo de carteiras.

Thesis (Ph.D. (Statistics)) -- University of Limpopo, 2022 / Using the ARFIMA (autoregressive and fractionally integrated moving aver age) model extended with sGARCH (standard generalised autoregressive con ditional heteroscedasticity) and ’gjrGARCH (Glosten-Jagannathan-Runkle gen eralised autoregressive conditional heteroscedascity) innovations, fractional in tegration approach and state space model, this study has empirically examined persistency of inflation dynamics of Ghana and South Africa, the only two coun tries in Sub-Saharan Africa with Inflation Targeting (IT) monetary policy. The first part of the analysis employed monthly CPI (Consumer Price Index) in flation series for the period January 1971 to October 2014 obtained from the Bank of Ghana (BoG), and for the period January 1995 to December 2014 ob tained from Statistics South Africa. The second part involves the estimation of threshold effect of inflation on economic growth using annual data obtained from the IMF (International Monetary Fund) database for the period 1981 to 2014, for both countries. Results from the study showed that structural breaks, long memory and non linearities (or regime shifts) are largely responsible for inflation persistence, hence the ever-changing nature of inflation rates of Ghana and South Africa. ARFIMA(3,0.35,1)-‘gjrGARCH(1,1) under Generalised Error Distribution (GED) and ARFIMA(3,0.50,1)-‘gjrGARCH(1,1) under Student-t Distribution (STD) mod els provided the best fit for persistence in the conditional mean (or level) of CPI for Ghana and South Africa, respectively. The results from these models pro vided evidence of time-varying conditional mean and volatility in CPI inflation rates of both countries. The two models also revealed an asymmetric effect of inflationary shocks, where negative shocks appear to have greater impact than positive shocks, in terms of persistence on the conditional mean with time varying volatility. This thesis proposes a model that combines fractional integration with non linear deterministic terms based on the Chebyshev polynomials in time for the analysis of CPI inflation rates of Ghana and South Africa. We tested for non-linear deterministic terms in the context of fractional integration and esti mated the fractional differencing parameters, d to be 1.11 and 1.32 respectively, for the Ghanaian and the South African inflation rates, but the non-linear trends were found to be statistically insignificant in the two series. New ev idence from this thesis depicts that inflation rate of Ghana is highly persistent and non-mean reverting, with an estimated fractional differencing parameter, d > 1.0, and will therefore require some policy action to steer inflation back to stability. However, the South African inflation series was found to be a cyclical process with an order of integration estimated to be d = 0.7, depicting mean reversion, with the length of the cycles approximated to last for 80 months. Finally, the thesis incorporated structural breaks, long memory, non-linearity, and some explanatory variables into a state space model and estimated the threshold effect of inflation on economic growth. The empirical results suggest that inflation below the estimated levels of 9% and 6% for Ghana and South Africa respectively, will be conducive for economic growth. The policy implications of these results for both countries are as follows. First, both series had similar properties responsible for inducing inflation persistence such as structural breaks, non-linearities, long memory and asymmetric re sponse to negatives shocks - but with varied degrees of magnitude. For both countries, the conditional mean and unobserved components such as volatility for both countries were found to be time-varying. This thesis, therefore, recom mends to the BoG and the South African Reserve Bank (SARB) - responsible for monetary policies, and the Finance Ministers of both governments - respon sible for fiscal policies, to take the above-mentioned properties into account in the formulation of their monetary policies. Second, the thesis recommends that the BoG and the SARB consolidate the IT policy, since keeping inflation below the targets set of 9% and 6%, respectively for Ghana and South Africa, will boost economic growth. Third, policymakers could also design measures (monetary and fiscal policies) such as increase in interest rates, credit control, and reduction of unnecessary expenditure, among others, to control inflation due to its adverse effects on market volatility. Even though an increase in interest rates could assist in curtailing the recent and anticipated increase in inflation rates in both countries, where targets have been missed by Ghana and South Africa, it will also be prudent to legislate monetary policies around demand-supply side since the problem of both coun tries appears to be more of a structuralist than a monetarist. It is, therefore, recommended that both countries tighten the IT monetary policy in order to re duce inflation persistence. This will eventually impact on poverty and income distribution with ramifications for economic growth and/or development. The fourth implication of these results is that governments and central banks should be mindful of the actions and decisions they take, in the sense that unguarded decisions and unnecessary alarms could raise uncertainties in the economy, which could, in turn, affect the future trajectory of inflation. Finally, the thesis recommends that governments of both countries strengthen the pri vate sector, which is the engine of growth. For small and open economies such as Ghana and South Africa, this will grow the economy through job creation and restore investor confidence. / National Research Foundation (NRF), Department of Science and Technology (DST), Telkom’s Tertiary Education Support Programme (TESP) and the NRF-DST Centre of Excellence for Mathematical and Statistical Sciences (CoE-MaSS)