Seminal papers of Solow (1957) and Swan (1956) stimulated debate among economists on the role of technical change in productivity improvements and for that matter economic growth. The consensus is that technological change accounts for a significant proportion of gross national product (GNP) growth in industrialised economies. In the case of Australia, the aggregate productivity performance was poor in the 1970s and 1980s, but picked up very strongly by the 1990s, and was above the OECD average growth level for the first time in its productivity growth history. However, this high productivity growth rate could not be sustained and Australia started to experience a slowdown in productivity growth since 2000. This study empirically measures the performance of productivity in Australia’s economy for the period 1950-2005, using an econometric approach. Time-series data are used to develop econometric models that capture the dynamic interactions between GDP, fixed capital, labour units, human capital, foreign direct investment (FDI) and information and communication technology (ICT). The Johansen (1988) cointegration techniques are used to establish a long-run steady-state relation between or among economic time series. The econometric analysis pays careful attention to the time-series properties of the data by conducting unit root and conintegration tests for the variables in the system. / This study finds that Australia experienced productivity growth in the 1950s, a slow down in the mid 1960s, a very strong productivity growth in the mid 1990s and another slowdown from 2000 onwards. The study finds evidence that human capital, FDI and ICT are very strong determinants of long-run GDP and productivity growth in Australia. The study finds that the three, four and the five factor models are likely to give better measures of productivity performance in Australia as these models recognise human capital, FDI and ICT and include them as separate factors in the production function, This study finds evidence that the previous studies on the Australia’s productivity puzzle have made a very significant omission by not considering human capital, FDI and ICT as additional exogenous variables and by excluding them from the production function for productivity analysis.

This article considers the evolution of international business cycle interdependencies among 27 developed and developing countries since the beginning of 1870s, utilising the generalized vector autoregressive (VAR)-based spillover index of Diebold and Yilmaz (2012), which allows the construction of a time-varying measure of business cycle spillovers. We find that, on average, 65% of the forecast error variance of the 27 countries' business cycle shocks is due to international spillovers. However, the magnitude of international business cycle spillovers varies considerably over time. There is a clear increasing trend since the end of World War II and until the middle 1980s. After that, international business cycle interdependencies declined during the period that was dubbed the Great Moderation, and stabilized around the beginning of the twenty-first century. During the Great Recession of 2008-2009, international business cycle spillovers increased to unprecedented levels. Finally, developed countries are consistently ranked as net transmitters of cyclical shocks to developing counties throughout the sample. (authors' abstract)

This study examines the linkages between output growth and output volatility in the G7 countries over the period 1958M2-2013M8. Using the VAR-based spillover index approach by Diebold and Yilmaz (2012) we find that: i) output growth and volatility are highly intertwined; ii) spillovers have reached unprecedented levels during the global financial crisis; and iii) the US has been the largest transmitter of growth and volatility shocks. Generalized impulse response analyses suggest moderate growth spillovers and sizable volatility spillovers across countries. Cross-variable effects indicate that volatility shocks lead to lower growth, while growth shocks reduce output volatility.

This research examines the impact of external shocks on Nigeria’s output performance for the period 1981 – 2015. It aims to bring to the fore the importance of considering external shocks during policy design and implementation. The multivariate VAR and VECM frameworks were used to evaluate the impact of the shock variables on Nigeria’s output performance and to achieve the stated objectives. Findings show that the external shock and domestic policy variables have short-run effects on Nigeria’s output performance. Also, all the measures of external shocks and domestic policies display some viable information in explaining the variabilities in Nigeria’s output performance over the horizon. The comparison between the results of the VECM and the unrestricted VAR shows that the unrestricted VAR model outperformed the VECM. The overall result of the study confirms the view about the vulnerability of the Nigerian economy to external shocks. These shocks explain more than half of the variance in real output performance and have varying effects on output performance in Nigeria. The dynamic response of output performance to each of the defined shock variables show that output performance responds rapidly to the shock variables, while its response to the domestic economic variables is seemingly moderate. Finally, the variance decomposition show that international crude oil price and terms of trade have the largest share in accounting for the variability in output performance, followed closely by the shares of capital inflows and monetary policy.

Asset pricing implications of a DSGE model with recursive preferences and nominal rigidities. I study jointly macroeconomic dynamics and asset prices implied by a production economy featuring nominal price rigidities and Epstein-Zin (1989) preferences. Using a reasonable calibration, the macroeconomic DSGE model is consistent with a number of stylized facts observed in financial markets like the equity premium, a negative real term spread, a positive nominal term spread and the predictability of stock returns, without compromising the model's ability to fit key macroeconomic variables. The interest rate smoothing in the monetary policy rule helps generate a low risk-free rate volatility which has been difficult to achieve for standard real business cycle models where monetary policy is neutral. In an application, I show that the model provides a framework for analyzing monetary policy interventions and the associated effects on asset prices and the real economy. Macroeconomic news and the stock market: Evidence from the eurozone. This paper is an empirical study of excess return behavior in the stock market in the euro area around days when important macroeconomic news about inflation, unemployment or interest rates are scheduled for announcement. I identify state dependence such that equity risk premia on announcement days are significantly higher when the interests rates are in the vicinity of the zero lower bound. Moreover, I provide evidence that for the whole sample period, the average excess returns in the eurozone are only higher on days when FOMC announcements are scheduled for release. However, this result vanishes in a low interest rate regime. Finally, I document that the European stock market does not command a premium for scheduled announcements by the European Central Bank (ECB). The impact of ECB monetary policy surprises on the German stock market. We examine the impact of ECB monetary policy surprises on German excess stock returns and the possible reasons for such a response. First, we conduct an event study to asses the impact of conventional and unconventional monetary policy on stock returns. Second, within the VAR framework of Campbell and Ammer (1993), we decompose excess stock returns into news regarding expected excess returns, future dividends and future real interest rates. We measure conventional monetary policy shocks using futures markets data. Our main findings are that the overall variation in German excess stock returns mainly reflects revisions in expectations about dividends and that the stock market response to monetary policy shocks is dependent on the prevailing interest rate regime. In periods of negative real interest rates, a surprise monetary tightening leads to a decrease in excess stock returns. The channels behind this response are news about higher expected excess returns and lower future dividends.

Par un développement en série de Taylor, une relation analytique générale est établie pour calculer l’incertitude de la réponse du modèle, en assumant l'indépendance des entrées. En utilisant des relations de puissances et exponentielles, il est démontré que l’approximation souvent utilisée permet d’évaluer de manière satisfaisante l’incertitude sur la réponse du modèle pourvu que l’incertitude d’entrée soit négligeable ou que le modèle soit presque linéaire. La méthode est appliquée à l’étude d’un réseau de distribution électrique et à un modèle d’ordre économique.La méthode est étendue aux cas où les variables d’entrée sont corrélées. Avec la méthode généralisée, on peux déterminer si les corrélations d'entrée doivent ou non être considérées pour des applications pratiques. Des exemples numériques montrent l'efficacité et la validation de notre méthode dans l'analyse des modèles tant généraux que spécifiques tels que le modèle déterministe du VIH. La méthode est ensuite comparée à celle de Sobol. Les résultats montrent que la méthode de Sobol peut surévaluer l’incidence des divers facteurs, mais sous-estimer ceux de leurs interactions dans le cas d’interactions non linéaires entre les paramètres d’entrée. Une modification est alors introduite, aidant à comprendre la différence entre notre méthode et celle de Sobol. Enfin, un modèle numérique est établi dans le cas d’un jeu virtuel prenant en compte la formation de la dynamique de l'opinion publique. L’analyse théorique à l’aide de la méthode de modification d'un paramètre à la fois. La méthode basée sur l'échantillonnage fournit une analyse globale de l'incertitude et de la sensibilité des observations. / By means of taylor series expansion, a general analytic formula is derived to characterise the uncertaintypropagation from input variables to the model response,in assuming input independence. By using power-lawand exponential functions, it is shown that the widelyused approximation considering only the first ordercontribution of input uncertainty is sufficiently good onlywhen the input uncertainty is negligible or the underlyingmodel is almost linear. This method is then applied to apower grid system and the eoq model.The method is also extended to correlated case. Withthe extended method, it is straightforward to identify theimportance of input correlations in the model response.This allows one to determine whether or not the inputcorrelations should be considered in practicalapplications. Numerical examples suggest theeffectiveness and validation of our method for generalmodels, as well as specific ones such as thedeterministic hiv model.The method is then compared to Sobol’s one which isimplemented with sampling based strategy. Resultsshow that, compared to our method, it may overvaluethe roles of individual input factors but underestimatethose of their interaction effects when there arenonlinear coupling terms of input factors. A modificationis then introduced, helping understand the differencebetween our method and Sobol’s one.Finally, a numerical model is designed based on avirtual gambling mechanism, regarding the formation ofopinion dynamics. Theoretical analysis is proposed bythe use of one-at-a-time method. Sampling-basedmethod provides a global analysis of output uncertaintyand sensitivity.

Submitted by Amanda Cappellazzo Arabage (amanda_arabage@msn.com) on 2013-06-11T18:18:08Z No. of bitstreams: 1 Dissertação - Amanda Arabage.pdf: 2257979 bytes, checksum: 53712e3dfdc43c2acc992b86c428c1ef (MD5) / Approved for entry into archive by Suzinei Teles Garcia Garcia (suzinei.garcia@fgv.br) on 2013-06-11T19:48:47Z (GMT) No. of bitstreams: 1 Dissertação - Amanda Arabage.pdf: 2257979 bytes, checksum: 53712e3dfdc43c2acc992b86c428c1ef (MD5) / Made available in DSpace on 2013-06-11T20:19:22Z (GMT). No. of bitstreams: 1 Dissertação - Amanda Arabage.pdf: 2257979 bytes, checksum: 53712e3dfdc43c2acc992b86c428c1ef (MD5) Previous issue date: 2013-05-27 / Neste trabalho estudamos a evolução da desigualdade de salários no mercado formal de trabalho no Brasil utilizando dados da Relação Anual de Informações Sociais (RAIS) no período entre 1994 e 2009. Utilizamos a variância do log do salário real por hora contratual de trabalho como medida de desigualdade e, através do uso de métodos de decomposição da variância em seus componentes permanente e transitório, verificamos que, no Brasil, cerca de 84% da desigualdade é explicada pelo componente permanente, ou seja, por características individuais invariantes no tempo. A educação responde por uma parcela expressiva deste componente (54% em média). Ao longo do período em questão houve uma redução da desigualdade de salários, sendo esta explicada pela redução do componente transitório entre 1994 e 1998 e pela diminuição do componente permanente entre 1999 e 2009. / This study analyzes the evolution of wage inequality in the formal labor market in Brazil in the years 1994-2009 using administrative data (RAIS). We use the variance of log hourly wages as a way to access wage inequality. Decomposing variance into its permanent and transitory components, we find that 84% of Brazilian wage inequality is due to its permanent component, in other words, it can be explained by individual characteristics that do not change over time. Regarding this permanent component, we show that education responds to approximately 54% of it. From 1994 to 2009, Brazil experienced a reduction in wage inequality. This reduction was caused by a decrease in the transitory component from 1994 to 1998 and by a decrease in the permanent component from 1999 to 2009.

This study examines the dynamic relationship between changes in oil prices and the economic policy uncertainty index for a sample of both net oil-exporting and net oil-importing countries over the period 1997:01-2013:06. To achieve that, we extend the Diebold and Yilmaz (2009, 2012) dynamic spillover index using structural decomposition. The results reveal that economic policy uncertainty (oil price shocks) responds negatively to aggregate demand oil price shocks (economic policy uncertainty shocks). Furthermore, during the Great Recession of 2007-2009, total spillovers increase considerably, reaching unprecedented heights. Moreover, in net terms, economic policy uncertainty becomes the dominant transmitter of shocks between 1997 and 2009, while in the post-2009 period there is a significant role for supply-side and oil specific demand shocks, as net transmitters of spillover effects. These results are important for policy makers, as well as, investors interested in the oil market. (authors' abstract) / Series: Department of Economics Working Paper Series

This study examines the dynamic relationship between changes in oil prices and the economic policy uncertainty index for a sample of both net oil-exporting and net oil-importing countries over the period 1997:01-2013:06. To achieve that, an extension of the Diebold and Yilmaz (2009, 2012) dynamic spillover index based on structural decomposition is employed. The results reveal that economic policy uncertainty (oil price shocks) responds negatively to aggregate demand oil price shocks (economic policy uncertainty shocks). Furthermore, during the Great Recession of 2007-2009, total spillovers increase considerably, reaching unprecedented heights. Moreover, in net terms, economic policy uncertainty becomes the dominant transmitter of shocks between 1997 and 2009, while in the post-2009 period there is a significant role for supply-side and oil specific demand shocks, as net transmitters of spillover effects. These results are important for policy makers, as well as, investors interested in the oil market. (authors' abstract)

La colinéarité rend difficile l’utilisation de la régression linéaire pour estimer l’importance des variables dans les études de marché. D’autres approches ont donc été utilisées.Concernant la décomposition de la variance expliquée, une démonstration de l’égalité entre les méthodes lmg-Shapley et celle de Johnson avec deux prédicteurs est proposée. Il a aussi été montré que la méthode de Fabbris est différente des méthodes de Genizi et Johnson et que les CAR scores de deux prédicteurs ne s’égalisent pas lorsque leur corrélation tend vers 1.Une méthode nouvelle, weifila (weighted first last) a été définie et publiée en 2015.L’estimation de l’importance des variables avec les forêts aléatoires a également été analysée et les résultats montrent une bonne prise en compte des non-linéarités.Avec les réseaux bayésiens, la multiplicité des solutions et le recours à des restrictions et choix d’expert militent pour utilisation prudente même si les outils disponibles permettent une aide dans le choix des modèles.Le recours à weifila ou aux forêts aléatoires est recommandé plutôt que lmg-Shapley sans négliger les approches structurelles et les modèles conceptuels.Mots clés :régression, décomposition de la variance, importance, valeur de Shapley, forêts aléatoires, réseaux bayésiens. / AbstractLinear regression is used in Market Research but faces difficulties due to multicollinearity. Other methods have been considered.A demonstration of the equality between lmg-Shapley and and Johnson methods for Variance Decomposition has been proposed. Also this research has shown that the decomposition proposed by Fabbris is not identical to those proposed by Genizi and Johnson, and that the CAR scores of two predictors do not equalize when their correlation tends towards 1. A new method, weifila (weighted first last) has been proposed and published in 2015.Also we have shown that permutation importance using Random Forest enables to take into account non linear relationships and deserves broader usage in Marketing Research.Regarding Bayesian Networks, there are multiple solutions available and expert driven restrictions and decisions support the recommendation to be careful in their usage and presentation, even if they allow to explore possible structures and make simulations.In the end, weifila or random forests are recommended instead of lmg-Shapley knowing that the benefit of structural and conceptual models should not be underestimated.Keywords :Linear regression, Variable Importance, Shapley Value, Random Forests, Bayesian Networks