An Introduction to Bootstrap Theory in Time Series Econometrics

While often simple to implement in practice, application of the bootstrap in econometric modeling of economic and financial time series requires establishing validity of the bootstrap. Establishing bootstrap asymptotic validity relies on verifying often nonstandard regularity conditions. In particular, bootstrap versions of classic convergence in probability and distribution, and hence of laws of large numbers and central limit theorems, are critical ingredients. Crucially, these depend on the type of bootstrap applied (e.g., wild or independently and identically distributed (i.i.d.) bootstrap) and on the underlying econometric model and data. Regularity conditions and their implications for possible improvements in terms of (empirical) size and power for bootstrap-based testing differ from standard asymptotic testing, which can be illustrated by simulations.

Trade Mis-Invoicing Between India & USA: An Empirical Exercise

India shares its majority of international trade with the United States of America. But a huge amount of discrepancy is frequently observed in the recorded bilateral trade statistics between these two countries. The main reasons are caused by several restrictions prevailing on the account of international trade in India. Export is found to be under-reported consistently whereas import data shows both over and under mis-invoicing in a periodic swing. This paper focuses on the determinants of this data fabrication with the help of empirical exercises. Several macroeconomic policy variables are taken to build up an econometric model and are tested statistically with the help of time series econometrics. Among all, relative interest rate plays the most important role to influence export and import mis-invoicing, followed by spot exchange rate and forward exchange rate. The exercise also finds a uni-directional causal relationship from import mis-invoicing of a period to export mis-invoicing of the next period. JEL Codes: C10, C13, C61, F13, F14, F21, K42

Forward-looking financial risk management and the housing market in the United Kingdom: is there a role for sentiment indicators?

Purpose In the current low-interest market environment, more and more asset managers have started to consider to invest in property markets. To implement adequate and forward-looking risk management procedures, this market should be analyzed in more detail. Therefore, this study aims to examine the housing market data from the UK. More specifically, sentiment data and house prices are examined, using techniques of time-series econometrics suggested by Toda and Yamamoto (1995). The monthly data used in this study is the RICS Housing Market Survey and the Nationwide House Price Index – covering the period from January 2000 to December 2018. Furthermore, the authors also analyze the stability of the implemented Granger causality tests. In sum, the authors found clear empirical evidence for unidirectional Granger causality from sentiment indicator to the house prices index. Consequently, the sentiment indicator can help to forecast property prices in the UK. Design/methodology/approach By investigating sentiment data for house prices using techniques of time-series econometrics (more specifically the procedure suggested by Toda and Yamamoto, 1995), the research question whether sentiment indicators can be helpful to predict property prices in the UK is analyzed empirically. Findings The empirical results show that the RICS Housing Market Survey can help to predict the house prices in the UK. Practical implications Given these findings, the information provided by property market sentiment indicators certainly should be used in a forward-looking early warning system for house prices in the UK. Originality/value To authors’ knowledge, this is the first paper that uses the procedure suggested by Toda and Yamaoto to search for suitable early warning indicators for investors in UK real estate assets.

Modeling the Covid-19 Epidemic Using Time Series Econometrics

The classic ‘logistic’ model has provided a realistic model of the behavior of Covid-19 in China and many East Asian countries. Once these countries passed the peak, the daily case count fell back, mirroring its initial climb in a symmetric way, just as the classic model predicts. However, in Italy and Spain, and now the UK and many other Western countries, the experience has been very different. The daily count has fallen back gradually from the peak but remained stubbornly high. The reason for the divergence from the classical model remain unclear. We take an empirical stance on this issue and develop a model that is based upon the statistical characteristics of the time series. With the possible exception of China, the workhorse logistic model is decisively rejected against more flexible alternatives.

An Empirical Analysis of the Impact of Foreign Direct Investment on Tourism Development: The Mauritian Case

This article investigates the link between foreign direct investment (FDI) and tourism development for the case of the small island economy of Mauritius for the period 1980–2015. The research employs a dynamic time series econometrics framework, namely a vector error correction model (VECM), to account for potential dynamic and endogenous relationship in the FDI–tourism nexus. Analysis of the finding shows that FDI has a positive and significant effect, albeit relatively lower compared to the other classical factors of tourism development, in the long run. Interestingly, a bicausal effect is observed in the long run while an indirect link between FDI and tourism development via the economic growth channel is found.