The Extreme Value Forecasting in Dynamics Situations for Reducing of Economic Crisis: Cases from Thailand, Malaysia, and Singapore

Abstract

This chapter was successfully proposed to clarify the complicated issue which is the dynamic prediction in the extreme events in economic cycles and computationally estimated its impacts on economic systems in ASEAN-3 countries such as Thailand, Malaysia, and Singapore by employing econometric tools, including the Markov-Switching Bayesian Vector Autoregressive model (MSBVAR), Bayesian Non-Stationary Extreme Value Analysis (NEVA), and Bayesian Dynamic Stochastic General Equilibrium approach (BDSGE). Technically, the yearly time-series variables such as Thailand’s gross domestic products, Malaysia’s gross domestic products, and Singapore’s gross domestic products were observed during 1961–2016. Empirically, the results showed the economic trends in the countries containing fluctuated movements relied on the real business cycle concept (RBC model). Additionally, these trends had unusual points called “extreme events” which should be mentioned as an economic alarming signal. Furthermore, the speedy economic adjustments estimated by BDSGE indicated that the extreme fluctuated rates of GDP in ASEAN-3 countries can be the harmful factor to face capital bubble crises, chronic unemployment, and even overpricing indexes. Accordingly, practical policies and private collaboration regarding economic alarming announcements in advance should be intensively considered.

Appendices

Keywords Definitions

Real Business Cycle

Real business cycle theory (RBC theory) is a class of macroeconomics models and theories, which regards to the periodic up and down movements in the economy, which are measured by fluctuations in real GDP and other macroeconomic factors. There are sequential phases of the business cycle that demonstrate rapid growth (defined as expansions or booms) followed by periods of stagnation or decline (known as recessions or declines).

Bayesian Statistics

Bayesian statistics is a mathematical procedure that applies probabilities to statistical problems. It provides people the tools to update their beliefs in the evidence of new data. In the Bayesian paradigm, degrees of belief in states of nature are specified. These are non-negative, and the total belief in all states of nature is fixed to be one. Bayesian statistical inferences start with existing “prior” beliefs, and update these using data to give “posterior” beliefs, which may be used as the basis for inferential decisions.

Markov Chain Monte Carlo Simulation (MCMC)

The MCMC technique is the method for sampling from probability distributions using Markov chains. This method is used in data modeling, especially for Bayesian inference and numerical integration.

Metropolis–Hastings (MH) Algorithm

The MH algorithm is a Markov chain Monte Carlo (MCMC) method for obtaining a sequence of random samples from a probability distribution, which direct sampling is often difficult. The key idea is to construct a Markov Chain that converges to the given distribution as its stationary distribution. After that, drawing samples from a Markov Chain’s stationary distribution can be approximated by simulating the Markov Chain.

Markov Process

A Markov process is either discrete state space or discrete index set (often representing time). The defining property of the Markov process is commonly called the Markov property; it was first stated by A.A. Markov.

Extreme Event

An extreme event analysis is relied on the extreme value theory or extreme value analysis (EVA), which is a branch of statistics dealing with the extreme deviations from the median of probability distributions. The EVT provides a solid probabilistic foundation for studying the distribution of extreme events in many academic fields such as hydrology, climate sciences, even finance and insurance etc.

Non-stationary Data

Non-stationary data are unpredictable and cannot be modeled or forecasted. The results obtained by using non-stationary time series may be spurious in that they may indicate a relationship between two variables where one does not exist. The non-stationary process contains a variable variance and a mean that do not closely remain, or return to a long-run mean over time.

Dynamic Stochastic General Equilibrium (DSGE)

Dynamic stochastic general equilibrium modeling is a branch of applied general equilibrium theory that influences in contemporary macroeconomics. Technically, the DSGE methodology is proposed to explain aggregate economic phenomena, including economic growth, business cycles, and the effects of monetary and fiscal policies.

Speedy Economic Adjustment

Economic adjustments usually involve a combination of free market policies such as privatization, fiscal austerity, free trade and deregulation. In recent moment, the adjustments have been also defined to structurally relate to ‘poverty reduction’.

Appendix

Fig. 3.5

Presentation extreme information for booming cycles in Thailand

Fig. 3.6

Presentation extreme information for recessing cycles in Thailand

Fig. 3.7

Presentation extreme information for booming cycles in Malaysia

Fig. 3.8

Presentation extreme information for downsizing cycles in Malaysia

Fig. 3.9

Presentation extreme information for booming cycles in Singapore

Fig. 3.10

Presentation extreme information for recessing cycles in Singapore

Fig. 3.11

Prior and posterior distributions of Thailand by BDSGE modeling

Fig. 3.12

Prior and posterior distributions of Malaysia by BDSGE modeling

Fig. 3.13

Prior and posterior distributions in economic booming cases of Singapore

Fig. 3.14

Speedy adjustments of structurally economic variables in normal situations of Thailand

Fig. 3.15

Speedy adjustments of structurally economic variables in boom and recess periods of Thailand

Fig. 3.16

Speedy adjustments of structurally economic variables in normal situations of Malaysia

Fig. 3.17

Speedy adjustments of structurally economic variables in boom and recess periods of Malaysia

Fig. 3.18

Speedy adjustments of structurally economic variables in normal situations of Singapore

Fig. 3.19

Speedy adjustments of structurally economic variables in boom and recess periods of Singapore