Combining non-cointegration tests

Abstract

Preliminary. AbstractThe local asymptotic power of many popular non-cointegration tests has recently been shown to depend on a certain nuisance parameter. Depending on the value of that parameter, different tests perform best. This paper suggests combination procedures with the aim of providing meta tests that maintain high power across the range of the nuisance parameter. The local asymptotic power of the new meta tests is in general almost as high as that of the more powerful of the underlying tests. When the underlying tests have similar power, the meta tests are even more powerful than the best underlying test. At the same time, our new meta tests avoid the arbitrary decision which test to use if single test results conflict. Moreover it avoids the size distortion inherent in separately applying multiple tests for cointegration to the same data set. We apply our test to 161 data sets from published cointegration studies. There, in one third of all cases single tests give conflicting results whereas our meta tests provide an unambiguous test decision.

The role of globalization on the recent evolution of energy demand in India: Implications for sustainable development

“…The cointegration relationship among variables is investigated by applying the combined cointegration test developed by Bayer and Hanck (2013). Engle and Granger (1987) developed the residual based cointegration test which is one of the most widely used tests of cointegration.…”

“…Thirdly, a relatively new approach to cointegration (the combined cointegration approach of Bayer and Hanck, 2013) is employed to investigate the existence of cointegration among the variables. Fourth, the robustness of the cointegration result is investigated by applying the bounds testing approach.…”

Is globalization detrimental to financial development? Further evidence from a very large emerging economy with significant orientation towards policies

“…To enhance the power of the cointegration test, with the aim of generating a joint teststatistic for the null hypothesis of no-cointegration, Bayer and Hanck (2013) propose a cointegration test that is called the Bayer-Hanck combined test which is based on the p-values of the Engle and Granger (1987), Johansen (1991), Boswijk (1994) and Banerjee et al (1998) tests.…”

“…Following Bayer and Hanck (2013), the combination of the computed significance levels (p-values) of individual cointegration tests is derived from the Fisher (1932) formulae as follows: …”

“…First, it explores the relationship between globalization and financial development by endogenising key variables such as economic growth, population density, inflation and institutional quality by using annual data over the period 1971-2013 in the Indian context. Second, it utilizes a more powerful cointegration technique developed by Bayer-Hanck (2013). A unique feature of this newly developed cointegration test is that it allows one to combine the results of different individual cointegration tests to provide a more conclusive result.…”