Testing for Breaks in Cointegrated Panels − with an Application to the Feldstein-Horioka Puzzle

Abstract

Stability tests for cointegrating coefficients are known to have very low power with small to medium sample sizes. In this paper we propose to solve this problem by extending the tests to dependent cointegrated panels through the stationary bootstrap. Simulation evidence shows that the proposed panel tests improve considerably on asymptotic tests applied to individual series. As an empirical illustration we examined investment and saving for a panel of European countries over the 1960-2002 period. While the individual stability tests, contrary to expectations and graphical evidence, in almost all cases do not reject the null of stability, the bootstrap panel tests lead to the more plausible conclusion that the long-run relationship between these two variables is likely to have undergone a break. --cointegration,stationary bootstrap,parameter stability tests,FM-OLS

Regional integration, capital mobility and financial intermediation revisited: Application of general to specific method in panel data

“…The second group of studies investigated the FH puzzle using panel methodologies (Coakley et al, 1999(Coakley et al, , 2001(Coakley et al, , 2004Krol, 1996;Coakley and Kulasi, 1997;Oh et al, 1999;Coiteux and Olivier, 2000;Cadoret, 2001;Corbin, 2001;Ho and Chiu, 2001;Kim, 2001;Tsung-wu, 2002;Pelgrin and Schich, 2004;Kim et al, 2005;Bahmani-Oskooee and Chakrabarti, 2005;Chakrabarti, 2006;Murthy, 2007;Christopoulos, 2007;Di Iorio and Fachin, 2007;Herwartz and Xu, 2009;Fouquau et al, 2009). The results in these studies reinforce the previous results based on a time series framework.…”

“…Analogous inferences were made by Rao et al (2010) using the exogenous structural break tests in Mancini-Griffoli andPauwels, 2006. Di Iorio andFachin (2007) have used panel bootstrap tests to examine the FH puzzle for a sample of 12 EU countries; their results show that the bootstrap panel stability tests allow for cointegration between saving and investment in the long run with at least one break. This paper investigates the stationarity properties of investment and saving series for panels that comprise six regional investment agreements.…”

A Time‐series Approach to the Feldstein–Horioka Puzzle with Panel Data from the OECD Countries

“…Their empirical findings show that b is very close to one (between 0.85 and 0.95), indicating low capital mobility in the sample OECD countries. A number of recent panel data studies on FHP have focused on the OECD countries; for instance, see Cadoret (2001), Coakley et al (2001Coakley et al ( , 2004, Giannone and Lenza (2004), Pelgrin and Schich (2004), Christopoulos (2007), Di Iorio and Fachin (2007), Herwartz and Xu (2009) and Fouquau et al (2009). 1 Other recent panel data studies such as Coakley et al (1999), Bahmani-Oskooee and Chakrabarti (2005), Kim et al (2005), Chakrabarti (2006) and Murthy (2007a) are based on developing countries.…”

“…A brief summary of their findings is as follows. Di Iorio and Fachin (2007) employed the panel bootstrap tests to examine FHP for a panel of 12 EU countries over the period . Their country-specific Fully Modified Ordinary Least Squares (FMOLS) estimates of b range from 0.59 to 1.03.…”

An Investigation of the Feldstein–Horioka Puzzle for the Association of Southeast Asian Nations Economies

“…Recently, the empirical literature has shown several comprehensive studies based on the F–H puzzle (see Di Iorio and Fachin ; Ozmen ; Apergis and Tsoumas ; Fouquau, Harlin and Rabard ; Rao, Tamazian and Kumar ; Bangake and Eggoh ). Feldstein and Horioka () and Feldstein () estimated the β ‐coefficient of national savings to be 0.887, with a standard error of 0.07.…”