Modeling the Taiwan Stock Market and International Linkages

This paper analyzes the Taiwan stock market and examines its price and volatility linkages with those of the United States. In particular, it tests the hypothesis that the short-term volatility and price changes spill over from the developed markets, mainly the United States, to the emerging Taiwan stock market. The model and the test are built upon Engle's ARCH (autoregressive conditional heteroskedasticity) and Engle and Kroner's M-GARCH (multivariate generalized ARCH) models. The paper differs from previous studies on the Taiwan stock market in three respects. First, instead of using daily closing prices, it uses close-to-open and open-to-close returns to avoid the problem of overlapping samples. It carefully models the day-of-the-week effect in daily data to avoid misspecification of the model. Second, to circumvent the generated regressor problem arising from the two-step estimation procedure, it also employs the M-GARCH model where all parameters are estimated simultaneously. Third, the misspecification test is carried out on various kinds of asymmetric ARCH factors. A substantial volatility spillover effect is found from the US stock market to the Taiwan stock market, especially for the model using close-to-open returns. There is also evidence supporting a spillover effect in price changes. The findings can be explained by the recent gradual opening of the Taiwan stock market to foreign investors.     

Asymmetric and Time‐Varying Causality between Inflation and Inflation Uncertainty in G‐7 Countries

We use Granger causality tests within a conditional Gaussian Markov switching vector autoregressive (MS‐VAR) model using monthly data for G‐7 countries covering the period 1959:12–2008:10 to examine the relationship between inflation and inflation‐uncertainty. The MS‐VAR model allows us to model parameter time‐variation so as to reflect changes in Granger causality, assuming that these changes are stochastic and governed by an unobservable Markov chain. Inflation uncertainty is measured as the conditional variance generated by a Fractionally Integrated Smooth Transition Autoregressive Moving Average‐Asymmetric Power ARCH (FISTARMA‐APARCH) model. The distinguishing feature of our approach from the previous studies is the determination of the sign of the Granger causality relationship between inflation and its uncertainty over time. First, using a rolling VAR model, we show that the relationship between inflation and inflation uncertainty is time varying with frequent breaks. Second, using the MS‐VAR model, we obtain strong evidence in favour of the Holland's ‘stabilizing Fed hypothesis’ for Canada, France, Germany, Japan, United Kingdom, and the United States. We also find evidence in favour of the Friedman hypothesis for Canada and the United States.     

Extreme observations and non-normality in ARCH and GARCH

Most studies employing ARCH and GARCH models document the existence of severe excess kurtosis in the estimated residuals. This non-normality may be due to model misspecifications, structural changes, or outliers. We conduct simulation experiments to examine the impact of extreme observations on the estimated parameters and residuals in the ARCH models. Then, we propose an iterative algorithm to detect and correct for the non-normality generated by extreme observations and additive outliers. Results for the simulated data, US equity returns and $/£ exchange rates are presented. Correcting outliers dramatically reduces the non-normality and bias in the estimated coefficients for small samples.     

Market efficiency and the Euro: the case of the Athens stock exchange

The behaviour of an emerging market, the Athens Stock Exchange, after the introduction of the euro is investigated. The latter would make its returns easier to compare; reduce uncertainty; eliminate the exchange rate risk and as a result we expect the new currency to strengthen the argument, in favour of the EMH. The General ASE Composite Index and the FTSE/ASE 20, which consists of “high capitalisation” companies, are used. Five statistical tests are employed to test the residuals of the random walk model: the BDS, McLeod-Li, Engle LM, Tsay and Bicovariance test. Bootstrap and asymptotic values of these tests are estimated. Alternative models from the GARCH family (GARCH, EGARCH and TGARCH) are also presented in order to investigate the behaviour of the series. Lastly, linear, asymmetric and non-linear error correction models are estimated and compared. The preferred model (TGARCH) suggests that leverage effects are present and the news impact curve is asymmetric.     

The effect of inflation uncertainty on inflation: Stochastic volatility in mean model within a dynamic framework

This paper investigates the effect of inflation uncertainty innovations on inflation over time by considering the monthly United States data for the time period 1976–2006. In order to investigate the effect of inflation uncertainty innovation on inflation, a Stochastic Volatility in Mean model (SVM) has been employed. SVM models are generally used to capture the innovation to inflation uncertainty, which cannot be achieved in the framework of popular deterministic ARCH type of models. Empirical evidence provided here suggests that innovations in inflation volatility increases inflation persistently. This evidence is robust across various definitions of inflation and different sub-periods.     

Non-storables, Simultaneity and Price Determination: The Australian (Finished) Live Cattle Market

Empirical studies of simultaneous rational expectations (RE) models of spot and futures markets for non-storable commodities, such as finished live cattle, are rare. Indeed, only two countries, the US and Australia, have produced data sets for the study of such markets. This paper develops, and presents estimates of a simultaneous RE model of the live cattle market in Australia, the world's leading beef exporting country. The model contains functional relationships for short hedgers and short speculators, long hedgers and long speculators, and consumers, and is completed with a spot price equation and market clearing identity. Augmented Dickey-Fuller and Phillips-Perron tests for unit roots are executed, and Johansen cointegration tests are employed to investigate whether the I(1) variables are cointegrated. Structural equations are estimated by maximum likelihood when ARCH effects are present, by instrumental variables in the absence of serial correlation, and by non-linear least squares when a correction for autocorrelation is required. The estimates of all structural parameters are significant at the five per cent level. Post-sample, the model forecasts spot and futures prices with per cent RMSE's of 4.4 per cent and 2.5 per cent, respectively. In forecasting the spot price, the model outperforms but not significantly, a random walk, an ARIMA model, and a lagged futures price as a predictor of the spot price. The outcome of this last comparison implies that the efficient markets hypothesis cannot be rejected.     

Beta-convergence and sigma-convergence in corporate governance in Europe

This paper tests for beta-convergence and sigma-convergence in the corporate governance models, using a sample of corporate governance ratings for 198 European corporations listed on the FTSE Eurofirst 300 index. A piecewise linear regression is deployed to select a model and the Poisson pseudo-maximum likelihood estimator is also applied to estimate an exponential model. It concludes that there is statistical evidence of beta- and sigma-convergence within countries and the results suggest that institutional differences between countries are statistically relevant.     

A comparison of two methods for estimating income uncertainty with an application to aggregate consumption behaviour

Econometric theory now provides various techiniques for estimating the variance of a variable for which only a single. Observation is available at each sample point. This paper compares the autoregressive conditional heteroskedastic (ARCH) and linear moment (LM) estimated of the variance of disposable labour income as measures of income uncertainty. Consumer theory postulates a negative relationship between uncertainty about future income and current consumption. Using quarterly post-world war II data with income modelled as a random walk with drift, both ARCH and LM estimates of the variance of income are included in a standard specification of the consumption function. It is found that while noth the ARCH and LM estimates of income uncertainty provide essentially the same predicted reduction in consumption growth as uncertainty increases the LM estimates yield a statistically significant influence on consumption while the ARCH estimated do not. However, both uncertainty measures provide a statistically significant imporvement in the specification of the consumption function relative to estimating the equation in the absence on an uncertainty measure. Thus, recent advances in estimation techniques, for post-world waf II data, show that the uncertainty theorists of over two decades ago were correct, that is estimation of a consumption function in the absence of an uncertainty measure relults in an equation with a biased estimate of the marginal propensity to consume as well as biased estimates of coefficients for all other included variables (see e.g. Leland, 1968, PP. 470-472).     

SETAR模型在中国股市波动率研究中的应用

文章对上证指数2006年1月6日-2011年5月23日收盘价的波动率进行了研究,介绍并使用随机系数SETAR模型与ARCH族模型进行对比拟合,根据数据的特点,文章构建了一种新型的SETAR模型,即AR(r)-SETAR(l,p1,p1)模型,模型利用ADF检验和AIC准则进行识别和估计。结果表明:可用AR(4)-SETAR(2,1,1)模型来拟合中国股市中的上证指数,研究其波动率特点,上证指数波动率呈不对称的响应,而且"负"响应比"正"响应高出约1.3倍。用ARCH族模型也证明了这种不对称响应的特征,但无法度量波动的强度,预测效果也没有SETAR模型精确。说明上证指数波动率不对称响应明显且呈现非线性的趋势,这种非线性的趋势更适合用SETAR模型来拟合。     

Volatility spillover and multivariate volatility impulse response analysis of GFC news events

This article applies two measures to assess spillovers across markets: the Diebold and Yilmaz’s (2012) spillover index and the Hafner and Herwartz’s (2006) analysis of multivariate GARCH models using volatility impulse response analysis. We use two sets of data, daily realized volatility (RV) estimates taken from the Oxford-Man RV library, for the S&P500 and the FTSE, plus 10 years of daily returns series for the New York Stock Exchange Index and the FTSE 100 index. Both data sets capture both the global Financial Crisis (GFC) and the subsequent European Sovereign Debt Crisis (ESDC). The spillover index captures the transmission of volatility to and from markets, plus net spillovers. The Volatility Impulse Responses (VIRF) have to be calibrated to conditional volatility estimated at a particular point in time. We explore the impact of three different shocks, the onset of the GFC, the height of the GFC, and the impact of the ESDC. Our modelling includes leverage and asymmetric effects applying a multivariate GARCH model, and further analysis using both BEKK and diagonal BEKK (DBEKK) models. We find the impact of negative shocks is larger, but shorter in duration, in this case a difference between 3 and 6 months.     

Adaptive ARFIMA models with applications to inflation

Many previous analyses of inflation have used either long memory or nonlinear time series models. This paper suggests a simple adaptive modification of the basic ARFIMA model, which uses a flexible Fourier form to allow for a time varying intercept. Simulation evidence suggests that the model provides a good representation of various forms of structural breaks and also that the new model can be efficiently estimated by a QMLE approach. We investigate monthly CPI inflation series for the G7 countries and find evidence of stable long memory parameters across regimes and also of significant nonlinear effects. The estimated adaptive ARFIMA models generally have less persistent long memory parameters than previous studies, with the estimated time dependent intercept being an important component. The model is also supplemented with an adaptive FIGARCH component, yielding a double nonlinear long memory model.     

Price volatility of south-east fishery's quota species: an empirical analysis

This study investigates the autoregressive conditional heteroscedasticity (ARCH) and generalized-ARCH (GARCH) effects in the price series of Australian South-East Fishery's quota species. It is found that in all cases significant ARCH and/or GARCH effects are present. To search for the origins of these effects a weakly exogenous variable (trading volume) is introduced to the conditional variance equation of the ARCH and GARCH models, provided that such effects are observed in the first stage of investigation. It is found that in 14 cases the estimated coefficients of the trading volume are negative. In all cases, the 'trading volume' variable does not contribute to the removal of the ARCH and/or GARCH effects. Finally, the policy implications of the findings are discussed.     

FORECASTING US INFLATION USING DYNAMIC GENERAL‐TO‐SPECIFIC MODEL SELECTION

We forecast US inflation using a standard set of macroeconomic predictors and a dynamic model selection and averaging methodology that allows the forecasting model to change over time. Pseudo out‐of‐sample forecasts are generated from models identified from a multipath general‐to‐specific algorithm that is applied dynamically using rolling regressions. Our results indicate that the inflation forecasts that we obtain employing a short rolling window substantially outperform those from a well‐established univariate benchmark, and contrary to previous evidence, are considerably robust to alternative forecast periods.     

Short-run exchange rate uncertainty in Latin America

This paper to obtain an ex ante measure of exchange rate uncertainty in 11 Latin American countries. As a preliminary issue, the purchasing power parity (PPP) condition is tested using Engle and Granger two-step procedure and Johansen method. The argument is that exchange rate uncertainty could be lower if PPP holds in the long run. The expected exchange rate uncertainty is estimated according to an extended version of the autoregressive, conditionally heteroscedastic (ARCH) model. The results show that the ARCH adjusment produces more efficient estimates in seven countries and that the acceptance of PPP has little effect on exchange rate uncertainty.     

Wages,work, and unemployment

This paper provides new evidence on unemployment durations for individuals in Great Britain using a three state Markov framework in a competing risk setting and a nationally representative data set. The analysis is based on the premise that an individual's movements between labour market states can be represented by a Markov process. The modelling procedure combines the dynamic properties of the search approach to unemployment while using the labour supply decision at each moment in time in response to the expected wage to include participation decisions. Using this framework, we are able to determine the effect of individual characteristics, including the expected wage, on labour market behaviour. The model is estimated separately for men and women, and for young and mature workers, to investigate whether labour market behaviour differs for these groups. The validity of the Markov assumptions are tested using different model specifications, and changes in the model over calendar time are also presented.     

金融危机前后我国CPI涨跌的路径分析——基于结构突变理论的实证研究

本文从结构突变的视角对金融危机前后我国CPI涨跌（耵）序列进行了内生结构变动的单位根检验,证明了其数据生成过程（DGP）为两次结构突变的趋势平稳过程而非单位根过程。并运用考虑结构突变的时序模型对盯序列进行了拟合,拟合优度达到了97．28％,克服了简单地用差分序列进行建模而造成数据信息大量损失的缺陷,同时,对模型的残差序列进行ARCH效应检验,结果显示,金融危机前后我国CPI涨跌的波动并不存在ARCH效应。     

Tobit or OLS? An empirical evaluation under different diary window lengths

Researchers analysing time-use data often estimate limited dependent variable models because time spent must be nonnegative and cannot be more than the total amount of time in a given observation period. While the traditional empirical technique applied to such cases is maximum likelihood estimation of a Tobit (censored regression) model, recent debate has questioned whether linear models estimated via Ordinary Least Squares (OLS) are preferable. On the one hand, Tobit models are deemed necessary to address the significant censoring (i.e. large numbers of zeroes) typically found in time-use data, in the face of which OLS estimators would be biased and inconsistent. Yet, optimization occurs over a longer period than that covered by the typical time diary (often a day), and thus some argue that reported zeroes represent a measurement problem rather than true nonparticipation in the activity, in which case OLS would be preferred. We provide direct empirical evidence on this question using the Australian Time Use Surveys, which record time-use information for two consecutive diary days, by estimating censored and linear versions of a parental child care model for both 24-hour and 48-hour windows of observation in order to determine the empirical consequences of estimation technique and diary length.     

Analysis on structural changes in the macroeconomic data series with the empirical evidence from China

Analysis on structural changes in macroeconomic data series has been the key issue for studying data quality. This paper studies the structural changes in China’s 36 macroeconomic time series using joint estimation model, and we find out the characteristics and movement pattern for the outliers. Our results show that most outliers show up more or less in groups, indicating that there is a significant correlation between them. The isolated outliers are not the main characteristic of China’s macroeconomic time series. Nearly all the original series contain the obvious skewness and kurtosis; hence, the hypothesis of normality is significantly rejected. Most original and outlier correction series show the non-autoregressive conditional heteroskedasticity (ARCH) characteristic, but the p value for ARCH2, ARCH4, and ARCH8 is very different. __________ Translated from Economic Research Journal (经济研究), 2005, (1) (in Chinese)     

Calendar anomalies in cash and stock index futures: International evidence

This paper examines calendar anomalies (day-of-the-week and monthly seasonal effects) in cash and stock index futures returns. We consider daily data from FTSE100 (UK), FTSE/ASE-20 (Greece), S&P500 (US) and Nasdaq100 (US) spot and future indexes over the period 2004–2011. We employ a Regime-Switching specification which allows us to distinguish between different regimes corresponding to high and low volatile periods. The results show differences in the seasonal patterns in cash and futures indexes due to the existence of basis risk. Calendar effects are also conditioned to the market situation. During a low volatile situation these calendar effects tend to be positive, but these effects turn negative if the market is under a high volatile period. These findings are recommended to financial risk managers dealing with futures markets.     

A Cross-Country Comparison of Okun's Coefficient

In this paper Okun's law is tested for the G7 countries in order to compare the responsiveness of unemployment to economic growth. Cyclical unemployment and output are extracted using Harvey's structural time series model. Okun's coefficient is estimated by OLS, rolling OLS, and SUR. The coefficient seems to be highest for North America and lowest for Japan, a result that can be explained in terms of differences in labor market rigidities. The rising absolute value of the coefficients over time indicated by the results of rolling OLS is explained in terms of labor market reform.J. Comp. Econom.,June 1997,24(3), pp. 335–356. La Trobe University, Bundoora, Victoria 3083, Australia.