|
on Econometric Time Series |
| By: | Marc Hallin; Davide La Vecchia; Hang Liu |
| Abstract: | We develop a class of tests for semiparametric vector autoregressive (VAR) models with unspecified innovation densities, based on the recent measure-transportation-based concepts of multivariate center-outward ranks and signs. We show that these concepts, combined with Le Cam's asymptotic theory of statistical experiments, yield novel testing procedures, which (a) are valid under a broad class of innovation densities (possibly non-elliptical, skewed, and/or with infinite moments), (b) are optimal (locally asymptotically maximin or most stringent) at selected ones, and (c) are robust against additive outliers. In order to do so, we establish a Hajek asymptotic representation result, of independent interest, for a general class of center-outward rank-based serial statistics. As an illustration, we consider the problems of testing the absence of serial correlation in multiple-output and possibly non-linear regression (an extension of the classical Durbin-Watson problem) and the sequential identification of the order p of a vector autoregressive (VAR(p)) model. A Monte Carlo comparative study of our tests and their routinely-applied Gaussian competitors demonstrates the benefits (in terms of size, power, and robustness) of our methodology; these benefits are particularly significant in the presence of asymmetric and leptokurtic innovation densities. A real data application concludes the paper. |
| Keywords: | Multivariate ranks; Distribution-freeness; Hájek representation; Local asymptotic normality; Durbin-Watson; VAR order identification |
| URL: | http://d.repec.org/n?u=RePEc:eca:wpaper:2013/314257&r=all |
| By: | Luca Nocciola |
| Abstract: | We show that extending the estimation window prior to structural breaks in cointegrated systems can be beneficial for forecasting performance and highlight under which conditions. In doing so, we generalize the Pesaran & Timmermann (2005)'s forecast error decomposition and show that it depends on four terms: 1) a period ahead risk; 2) a bias due to a conditional mean shift; 3) a bias due to a variance mismatch; 4) a gap term valid only conditionally. We also derive new expressions for the estimators of the adjustment matrix and a constant, which are auxiliary to the decomposition. Finally, we introduce new simulation based estimators for the finite sample forecast properties which are based on the derived decomposition. Our finding points out that, in some cases, we can neglect parameter instability by extending the window backward and be insured against higher forecast risk under this model class as well, generalizing Pesaran & Timmermann (2005)'s result. Our result gives renewed importance to break tests, in order to distinguish cases when break-neglection is (not) appropriate. |
| Keywords: | Finite sample forecast properties; MSE; structural breaks; cointegration; expanding window estimator |
| URL: | http://d.repec.org/n?u=RePEc:not:notgts:19/07&r=all |
| By: | Yuta Yamauchi (Graduate School of Economics, The University of Tokyo); Yasuhiro Omori (Faculty of Economics, The University of Tokyo) |
| Abstract: | In the stochastic volatility models for multivariate daily stock returns, it has been found that the estimates of parameters become unstable as the dimension of returns increases. To solve this problem, we focus on the factor structure of multiple returns and consider two additional sources of information: first, the realized stock index associated with the market factor, and second, the realized covariance matrix calculated from high frequency data. The proposed dynamic factor model with the leverage effect and realized measures is applied to ten of the top stocks composing the exchange traded fund linked with the investment return of the S&P500 index and the model is shown to have a stable advantage in portfolio performance. |
| Date: | 2020–11 |
| URL: | http://d.repec.org/n?u=RePEc:tky:fseres:2020cf1158&r=all |
| By: | Swati Singh (Madras School of Economics, Chennai, India); Naveen Srinivasan (Professor, Madras School of Economics, Chennai, India) |
| Abstract: | It is not to be doubted that the oil price shocks adversely impact the economy. Enough literature is present in support of this fact but, at the same time, it is equivalently important to determine the changing nature of this relationship. This paper studies the changing behavior of this relation from 1948-2018 and shows that the oil prices are no more as effective in explaining the changes in the output of the economy as it had been before the 1970s. Our results also show the extent to which oil intensity has reduced in effecting the output of the US economy along with explaining the short term and long term impacts of oil shocks. Through variance decomposition analysis, the paper explains the reason for this decline in oil importance in recent time. Various factors like changing technology and political and strategic implications are found to be a few of the many reasons behind this change. |
| Keywords: | Macroeconomic Fluctuations; Oil shocks; Energy and the Macroeconomy; ARDL Model; VAR; Granger causality test;Error Variance Decomposition |
| JEL: | E32 C22 C32 Q43 |
| URL: | http://d.repec.org/n?u=RePEc:mad:wpaper:2020-197&r=all |
| By: | Ooft, Gavin (The Johns Hopkins Institute for Applied Economics, Global Health, and the Study of Business Enterprise) |
| Abstract: | An accurate forecast for inflation is mandatory in the conduction of monetary policy. This paper presents models that forecast monthly inflation utilizing various economic techniques for the economy of Suriname. The paper employs Autoregressive Integrated Moving Average models (ARIMA), Vector Autoregressive models (VAR), Factor Augmented Vector Autoregressive models (FAVAR), Bayesian Vector Autoregressive models (BVAR) and Vector Error Correction (VECM) models to model monthly inflation for Suriname over the period from 2004 to 2018. Consequently, the forecast performance of the models is evaluated by comparison of the Root Mean Square Error and the Mean Average Errors. We also conduct a pseudo out-of-sample forecasting exercise. The VECM yields the best results forecasting up to three months ahead, while thereafter, the FAVAR, which includes more economic information, outperforms the VECM, based on the assessment of the pseudo out-of-sample forecast performance of the models. |
| Keywords: | Inflation; Forecasting; Time-Series Models; Suriname |
| JEL: | C32 E31 |
| Date: | 2020–01 |
| URL: | http://d.repec.org/n?u=RePEc:ris:jhisae:0144&r=all |
| By: | Bhaghoe, Sailesh (The Johns Hopkins Institute for Applied Economics, Global Health, and the Study of Business Enterprise); Ooft, Gavin (The Johns Hopkins Institute for Applied Economics, Global Health, and the Study of Business Enterprise) |
| Abstract: | This paper estimates a model of exchange-rate volatility that includes commodity prices as an exogenous determinant. We apply this model to the mining-based economy of Suriname. Fluctuations of the exchange rate are detrimental for the economy. This was evident in 2015 and 2016 when the economy of Suriname considerably contracted due to persistent negative commodity price shocks. First, we calibrate higher order General Autoregressive Conditional Heteroscedastic (GARCH) models to model the conditional variances of the exchange rate with available monthly data for the period 1994 to 2019. We obtained useful results from Exponential, Asymmetric, Threshold, Component and combined Mean-GARCH models calibrated with standardized error distributions. Then, we perform in-sample forecasts with the calibrated models for the period 2012 to 2019. Lastly, we select the best-performing models to forecast conditional variances of the exchange rate. |
| Keywords: | Exchange Rate Volatility; GARCH models; Heteroscedasticity |
| JEL: | C52 E44 E47 |
| Date: | 2020–10 |
| URL: | http://d.repec.org/n?u=RePEc:ris:jhisae:0165&r=all |
| By: | Deepanshu Sharma; Kritika Phulli |
| Abstract: | The advancement in the field of statistical methodologies to economic data has paved its path towards the dire need for designing efficient military management policies. India is ranked as the third largest country in terms of military spender for the year 2019. Therefore, this study aims at utilizing the Box-Jenkins ARIMA model for time series forecasting of the military expenditure of India in forthcoming times. The model was generated on the SIPRI dataset of Indian military expenditure of 60 years from the year 1960 to 2019. The trend was analysed for the generation of the model that best fitted the forecasting. The study highlights the minimum AIC value and involves ADF testing (Augmented Dickey-Fuller) to transform expenditure data into stationary form for model generation. It also focused on plotting the residual error distribution for efficient forecasting. This research proposed an ARIMA (0,1,6) model for optimal forecasting of military expenditure of India with an accuracy of 95.7%. The model, thus, acts as a Moving Average (MA) model and predicts the steady-state exponential growth of 36.94% in military expenditure of India by 2024. |
| Date: | 2020–11 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2011.06060&r=all |
| By: | Bo Zhang; Jamie Cross; Na Guo |
| Abstract: | We investigate whether a class of trend models with various error term structures can improve upon the forecast performance of commonly used time series models when forecasting CPI inflation in Australia. The main result is that trend models tend to provide more accurate point and density forecasts compared to conventional autoregressive and Phillips curve models. The best short term forecasts come from a trend model with stochastic volatility in the transitory component, while medium to long-run forecasts are better made by specifying a moving average component. We also find that trend models can capture various dynamics in periods of significance which conventional models can not. This includes the dramatic reduction in inflation when the RBA adopted inflation targeting, the a one-off 10 per cent Goods and Services Tax inflationary episode in 2000, and the gradually decline in inflation since 2014. |
| Keywords: | trend model, inflation forecast, Bayesian analysis, stochastic volatility |
| Date: | 2020–11 |
| URL: | http://d.repec.org/n?u=RePEc:bny:wpaper:0092&r=all |
| By: | Leonardo Bargigli; Giulio Cifarelli |
| Abstract: | We identify two sources of heteroskedasticity in high-frequency financial data. The first source is the endogenous changing participation of heterogeneous speculators to the market, coupled with the time varying behavior of the market maker. The second source is the exogenous flow of market relevant information. We model the first one by means of a Markov switching (MS) SVAR process, and the second one by means of a GARCH process for the MS-SVAR structural errors. Using transaction data of the EUR/USD market in 2016, we detect three regimes characterized by different levels of endogenous volatility. The impact of structural shocks on the market depends on both sources, but the exogenous information is channeled to the market mostly through price. This suggests that the market maker is better informed than the speculators, who act as momentum traders. The latter are able to profit from trade because, unlike noise traders, they respond immediately to price shocks. |
| Keywords: | heteroskedasticity, asset pricing model, heterogeneous beliefs, market making, foreign exchange market, Markov switching, GARCH,SVAR, high frequency data. |
| JEL: | G12 D84 F31 C32 C55 |
| Date: | 2020 |
| URL: | http://d.repec.org/n?u=RePEc:frz:wpaper:wp2020_17.rdf&r=all |