Additional Tests for a Unit Root Allowing for a Break in the Trend Function at an Unknown Time

Statistically derived contributions of diverse human influences to twentieth-century temperature changes

“…The slope coefficient relating these two variables is the transient climate sensitivity estimated to be Our results have implications for previous work questioning the relevance of anthropogenic factors to explain the observed warming 20 . Their main conclusion is that previous cointegration-based studies 2,21,29 have overlooked the differences in the order of integration arguing that radiative forcings are integrated of order two while temperatures are integrated of order one. Given our findings, these conflicting results can easily be explained.…”

“…A direct implication of this finding is that cointegration techniques are not adequate to investigate the attribution of climate change (i.e., the long-run relationships between temperatures and radiative forcing series) because this technique relies on the assumption of stochastic trends. As shown in the econometric literature, under similar circumstances spurious cointegration is likely to occur and the inferences drawn are not reliable 19,20,21 . As a consequence, a different approach to test for common long-run relationships is required.…”

Non-Linearities and Unit Roots in G7 Macroeconomic Variables

“…It ranges from attempts at alleviating the low power properties of traditional ADF tests (see Elliott et al, 1996 andNg andPerron, 2001) to the impact of structural breaks on inference about unit roots in Perron (1989) and the literature thereafter (e.g. Andrews andPloberger, 1994, Vogelsang andPerron, 1998). 2 To date, there is a consensus view that in the presence of structural breaks the standard linear unit root tests tend to under-reject the null of a unit root.…”

Budget Deficit Sustainability and Revenue Expenditure Linkages in Major South Asian Economies

“…This observation led to the development of breakpoint unit root tests based on modified ADF tests that allow for levels and trends to differ across a break date. Following Perron (1989), Perron and Vogelsang (1992) and Vogelsang and Perron (1998), four models of breakpoint unit root tests are developed. Model 1 supposes a non-trending series with a break in the intercept; Model 2 supposes a trending series with a break in the intercept; Model 3 supposes a trending series with a break in the intercept and trend; and Model 4 supposes a trending series with a break in trend.…”