Time-varying Cointegration Research Articles

Time-varying cointegration with an application to the UK Great Ratios

We build on an estimation method which can accommodate time variation in a cointegrating relationship and present a test for cointegration under this setup. We apply our test procedure to the UK Great Ratios and find little evidence for cointegration when the parameters are assumed constant, but strong evidence when allowing them to drift slowly over time.

Purchasing power parity vs. uncovered interest rate parity for NAFTA countries: The value of incorporating time-varying parameter model

In 1994, the United States, Canada, and Mexico signed the North American Free Trade Agreement (NAFTA) to strengthen economic cooperation. To examine the effects of the NAFTA, this study revisits Purchasing Power Parity (PPP) for NAFTA countries by applying a time-varying cointegration model. Under the time-varying assumption, it improves the explanatory power of reality via the model specification test. Given that, the validity of PPP for NAFTA countries varies over time. Especially, the PPP elasticity based on the consumer price index (CPI) is more volatile than the producer price index (PPI) -based. Thus, the stabilization policy of the consumption sector must be a high priority over the production sector. Moreover, the validity of the Uncovered Interest Rate Parity (UIRP) is examined by the time-varying cointegration model. The aim is to compare the results of the PPP and UIRP. This suggests that the PPP is more useful than the UIRP in evaluating the movement of the exchange rate in the long-run.

유가정보공개가 가격결정에 미친 영향 : 시변 공적분 모형의 이용

유가정보공개가 가격결정에 미친 영향 : 시변 공적분 모형의 이용

Observation Driven Long Run Equilibria

In this paper the Fractional Vector Error Correction Model (FVECM) is extended by allowing three of its parameters to vary with time: the equilibrium relationship parameter beta , the variance sigma ^{2} and the cointegration degree parameter b. These parameters are independently updated based on the Generalized Autoregressive Score (GAS) framework. In this way three new FVECM–GAS models are created, and also the concept of ‘time-varying cointegration’ is introduced. Data from these models are simulated, and the models are compared with their fixed parameter counterparts. We show that the FVECM–GAS models perform better in the cases shown here, and thus extend the FVECM model in a useful way. We also note that an approach with fixed parameters may lead to negligence of the cointegration relationship, providing another source of errors.

Housing markets’ linkage between China and Taiwan

PurposeThis paper aims to examine the linkage of regional housing markets between Taiwan and China as increasing economic integration.Design/methodology/approachTwo time-varying estimations of cointegration tests, Gregory and Hansen (1996) cointegration test with structural break and the recursive coefficients of cointegration (Hansen and Johansen, 1993) are applied to trace the possible dynamic linkage of cross-border regional housing prices between Taiwan and China.FindingsFirst, the estimating results of the long-run relationships show that increasing housing prices in Beijing and Shanghai decrease Taipei’s house prices, while Shenzhen and Chengdu have converse effects. The technologies’ levels of Taiwanese industries surrounding the cities in China will affect the direction of the linkage of regional housing prices between the two economies. Second, in light of causalities of these five housing prices’ changes, Beijing and Shanghai lead Taipei and Shanghai leads Chengdu, which, in turn, leads Shenzhen. Finally, the results of time-varying cointegration tests show that some critical economic and political incidents changed the linkages of housing prices between Taipei and the four cities in China.Originality/valueAlthough some empirical works examined the linkages between cross-border house prices in Europe and the USA, study has looked at the linkages of cross-border housing prices between Taiwan and China. This is an interesting topic insofar as house price integration has implications for wealth effects that feed into consumer expenditure in both Taiwan and China. The empirical evidence overall displays the existence of the integration of regional housing markets between Taiwan and China. For the longer-term future, increasing economic integration between China and other Asia countries will result in greater and more diversified cross-border housing markets and pools of investors.

Time-varying Cointegration and the UK Great Ratios

We re-examine the great ratios associated with balanced growth models and ask whether they have remained constant over time. We first use a benchmark DSGE model to explore how plausible smooth variations in structural parameters lead to movements in great ratios that are comparable to those seen in the UK data. We then employ a nonparametric methodology that allows for slowly varying coefficients to estimate trends over time. To formally test for stable relationships in the great ratios, we propose a statistical test based on these nonparametric estimators devised to detect time varying cointegrating relationships. Small sample properties of the test are explored in a small Monte Carlo exercise. Generally, we find no evidence for cointegration when parameters are constant, but strong evidence when allowing for time variation. The implications are that in macroeconometric models allowance should be made for shifting long-run relationships, including DSGE models where smooth variation should be allowed in the deep structural relationships.

Welfare cost of inflation in Brazil: an approach with time-varying cointegration and Kalman filter

This paper compares the time-varying cointegration and the Kalman filter techniques to estimate the Brazilian money demand between 1996 and 2015. The estimation using Kalman filtering performs better and is subsequently used to calculate the welfare cost of inflation. Taking into consideration the time variability of the interest-rate elasticity during the period, the average welfare cost amounts to 0.24% of the GDP, for an average annual inflation of 6.63%.

A Time-Varying Fiscal Reaction Function for Brazil

Abstract This paper evaluates the sustainability of public debt in Brazil using monthly data from January 2003 to June 2016, based on the estimation of fiscal reaction functions with time-varying coefficients. Three estimation methods are considered: Kalman filter, penalized spline smoothing and time-varying cointegration. Besides indicating that the reaction of the primary deficit to variations in the debt/GDP ratio declined over most of the analyzed period, all these methods lead to the conclusion that the Brazilian public debt, given the parameters then in force, reached an unsustainable trajectory in the last years of the sample.

MCMC for Markov-switching models—Gibbs sampling vs. marginalized likelihood

This article proposes a method to estimate Markov-switching vector autoregressive models that combines (integrated over latent states) marginal likelihood and Hamiltonian Monte Carlo. The method is compared to commonly used implementations of Gibbs sampling. The proposed method is found to be numerically robust, flexible with respect to model specification and easy to implement using the Stan software package. The methodology is illustrated on a real data application exploring time-varying cointegration relationships in a data set consisting of crude oil and natural gas prices.

Empirical test of purchasing power parity using a time-varying cointegration model for China and the UK

This study revisits purchasing power parity (PPP) for China and the United Kingdom (UK) by applying a time-varying cointegration model. When traditional linear unit root tests and a time-invariant cointegration test are performed, we find fixed long-run equilibrium in China and the UK. However, we cannot check the movement of the cointegration vector. To solve this limitation, we perform a time-varying cointegration. The result of a time-varying cointegration model shows that the validity of PPP for China varies over time. On the other hand, PPP does not hold for all periods for the UK. This study shows that the effect of government policy varies depending on the degree of openness. In China with a low degree of openness, export-oriented policies have had a positive impact on PPP. However, in the UK with a high degree of openness, PPP was not valid due to the role of the exchange rate as an asset price and the downward rigidity of wage.

ECONOMIC POLICY UNCERTAINTY, GLOBAL OIL PRICES, INTEREST RATE, AND STOCK MARKET RETURNS - A COINTEGRATION AND CAUSALITY ANALYSIS

This study examines the time-varying cointegration and causal relationship between stock market indices, economic policy uncertainties, changes in global oil price and variation in short-term interest rates in two countries such as Russia and China, the largest oil exporting and importing countries respectively. The empirical analysis is based on the Johanssen (1996) cointegration and VEC Granger and Morris’s (1976) causality test with the selected variables in view of monthly data over the period from 1996:01 to 2016:12. The outcome of the Johansen tests indicated the existence of a long-run relationship among variables both in China and Russia. In the short run, the Block Exogeneity Wald Tests have indicated the presence of unidirectional granger causality between variables in both countries. The study has taken into account the 1998 Russian crisis and the 2008/09 global financial crisis.

Spot and Futures Prices of Bitcoin: Causality, Cointegration and Price Discovery from a Time-Varying Perspective

Recent papers that have explored spot and futures markets for Bitcoin have concluded that price discovery takes place either in the spot, or the futures market. Here, we consider the robustness of previous price discovery conclusions by investigating causal relationships, cointegration and price discovery between spot and futures markets for Bitcoin, using appropriate daily data and time-varying mechanisms. We apply the time-varying Granger causality test of Shi et al. (2018); time-varying cointegration tests of Park & Hahn (1999), and time-varying information share methodologies, concluding that futures prices Granger cause spot prices and that futures prices dominate the price discovery process.

Do credit default swaps affect the time-varying cointegration between PIIGS sovereign interest rates

This paper shows that the linkages between the sovereign interest rate spreads of Greece, Ireland, Italy, Portugal and Spain, during the period from the beginning of 2008 till the end of 2014, were significantly dependent on credit default swaps (CDSs). Three rolling autoregressive distributed lag (ARDL) models were used to estimate the interest rates cointegration: one restricted model that includes only interest rates as variables, one restricted model that includes CDSs and the unrestricted model that joins CDSs to interest rates in the estimations. The frequency of cointegration phases is higher both in the restricted model with credit default swaps and in the unrestricted model than in the restricted model with interest rates. However, the non-cointegration phases were predominant in all the models. The output of rolling ARDL estimations was included in logit models which give the probability that a cointegration phase in one domestic market occurs simultaneously with an identical phase in the other markets.

Do credit default swaps affect the time-varying cointegration between PIIGS's sovereign interest rates

Do credit default swaps affect the time-varying cointegration between PIIGS's sovereign interest rates

Robustness of demand for money analysis in Vietnam: A time-varying cointegration approach

Robustness of demand for money analysis in Vietnam: A time-varying cointegration approach

Predicting stock market movements with a time-varying consumption-aggregate wealth ratio

We develop a time-varying measure of cay (cayTVP) using time-varying cointegration, and then compare the predictive ability of cayTVP with cay and a Markov-switching cay (cayMS) for excess stock returns and volatility in the US over the period 1952:Q2-2015:Q3, using a k-th order nonparametric causality-in-quantiles test. We find that time-varying cointegration exists between consumption, asset wealth, and labor income. In addition, while there is no evidence of predictability of volatility of excess returns from cay, cayMS, or cayTVP, they tend to act as strong predictors of stock returns, with cayTVP being important during the bearish phases of the equity market.

Time-varying cointegration model using wavelets

This work proposes a wavelet based Vector Error Correction Model with time-varying cointegration. The maximum likelihood estimators and likelihood ratio statistics were evaluated based on Monte Carlo and Bootstrap simulations. The model was used to study the Purchasing Power Parity hypothesis.

Income elasticity of overnight stays over seven decades

This article provides new evidence on the stability of the long-run income elasticity of tourism and travel demand by use of the recently developed smooth time-varying cointegration regression model. The estimations control for relative purchasing power parity of the source country and make use of a specific country dataset where domestic and foreign overnight stays are available over a longer period of time (Switzerland, 1934–2015). Results show that the income elasticity of foreign overnight stays peaks at approximately two in the early 1960s, drops to around one in the early 1980s and from then on remains stable until the end of the sample. Domestic income elasticity reaches its highest levels in the 1930s, then steadily falls towards one in the mid-1960s, and therefrom remains stable until 2015. Different phases in the tourism area life cycle might be a major explanatory factor for variation in income elasticities over time.

Uncovering long term relationships between oil prices and the economy: A time-varying cointegration analysis

Establishing the relation between oil price movements and macroeconomic performance is of great importance for firms and policymakers, alike. Prior studies established this relation using the assumption that the long-run relation is intertemporally constant. However, there is much recent evidence demonstrating that this assumption may not hold in practice. To address this issue and go beyond the restrictive time-invariant environment, we employ the use of the time-varying cointegration framework of Bierens and Martins (2010). We present evidence of the long-run oil-economy relation evolving over the 1974–2015 period, with major events such as the Gulf War and the financialisation of commodity markets proving to be driving forces across the U.S., European and G7 economies considered.

Decoupling of CO2 emissions and GDP: A time-varying cointegration approach

The relationship between CO2 emissions, the main gas responsible for global warming, and economic growth is among the most studied themes of environmental economics. Reducing overall emissions while keeping a high pace of economic development is at the heart of the sustainable development concept. When emissions grow less rapidly than GDP environmental economists speak of relative decoupling; if emissions even decrease relative to the pace of economic growth, then decoupling is absolute. Assessing these options requires an empirical analysis of the emissions-GDP relationship. The study of this nexus has special importance for developed countries, given their historical responsibility towards global warming. At the same time, in the last decades, the same countries have been at the forefront of the fight against climate change in terms of emissions-reduction efforts. By applying cutting-edge econometric techniques, this paper aims to investigate the decoupling options, if any, for a group of European economies which can be considered as pioneers in pursuing the sustainable development goals. This question gains further importance considering that some recent studies have found positive GDP elasticities of emissions for certain developed countries, which may be seen as a cause of concern for the sustainable development path of such countries. Unlike the bulk of the literature, in this paper, we allow the income elasticity of emissions – a critical indicator for the study of decoupling – to vary over time. The reason is that the elasticity might change through the time due to the factors affecting the main drivers of the CO2 emissions. We use a time-varying coefficients cointegration approach to investigate the CO2 emissions-GDP relationship for 12 Western European countries over a long time period ranging from 1861 to 2015. Our main finding is that the income elasticity of CO2 emissions is positive in all investigated countries. In addition, we find evidence in favor of relative decoupling in 8 out of the 12 European countries. This is in line with the fact that the selected European countries have shown more determination in adopting carbon reduction policies before and after the Kyoto protocol period and toward the Paris agreement compared to other leading economies such as China, United States, and Russia. For the remaining 4 cases, the income elasticity of CO2 emissions is in excess of unity. This can be considered as a call for policymakers to take quick and relevant measures to mitigate emissions level without harming the economic development.