Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
The inherent nonstationarity of the variables has led many researchers to use unit root and cointegration methodologies to analyze the PPP hypothesis. The imposition of proportionality and symmetry restrictions has been a common practice yet no explicit hypothesis tests have been conducted to determine the validity of such restrictions. Few of the studies have dealt with the presence of deterministic trends in the data. This study uses a long span of data and explicitly tests the proportionality and symmetry restrictions implied by PPP. A careful treatment of the role of deterministic trends in the data is also included. Copyright 1996 by Blackwell Publishing Ltd.