Reformulating Critical Values for the Bounds F- statistics Approach to Cointegration: An Application to the Tourism Demand Model for Fiji

By Paresh Kumar Narayan. 2004

562 citations recorded by the source corpus.

This paper examines the short-and long-run relationships between visitor arrivals to Fiji, real disposable incomes, and own-hotel price and substitute hotel price for the period 1970-2000, using the bounds testing approach to cointegration and error correction models. The paper's main contribution is that it generates bounds F-statistic critical values specific to the study's sample size (31 observations) and finds that critical values are 35.5% higher than those reported in Pesaran et al. (2001) for 1000 observations and 17.1% higher than those reported in Pesaran and Pesaran (1997) for 500 observations for a model with 4 regressors and an intercept. In the light of this, we tabulate critical values for sample sizes ranging from 30 observations to 80 observations, which will be usefull for future researchers using the bounds testing approach to cointegration.

View Paper: https://www.semanticscholar.org/paper/df6f58edee229fd7bd03dde79335ea942ba43a16

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

The saving and investment nexus for China: evidence from cointegration tests (2005, background): “Narayan (2004a, 2004b) and Narayan (2005) argues that exiting CVs, because they are based on large sample sizes, cannot be used for small sample sizes.”
Determinants of Malaysian Trade Balance: An ARDL Bound Testing Approach (2007, methodology): “As suggested by Pesaran and Shin (1999) and Narayan (2004), since the observations are annual, we choose two as the maximum order of lags in the ARDL and estimate for the period 1974 2003.”
On the Causality Between Tourism Growth and Economic Growth: Empirical Evidence from Turkey (2009, background): “The upper limit of the critical value based on Narayan (2004) is 4.306 for the 5% significance levels, respectively.”
Islamic banking and economic growth: the Indonesian experience (2012, methodology): “The ARDL method does not involve pre-testing variables, which is particularly problematic in the unit root-cointegration literatures where the power of the unit root tests is typically very low and there is a switch in the distribution function of the test statistics, therefore, obviating uncertaint”