Abstract
Studies of productivity in the operations and engineering management literature have typically focused on identifying the drivers of productivity and how best to manage resources. To date, the issues of the time-series behavior and the stochastic structure of productivity have largely been overlooked. This article examines the times-series properties of productivity utilizing several unit root and stationarity tests including one that allows for asymmetric adjustments to equilibrium. The findings suggest that productivity is a nonstationary process and first-differencing is necessary to render a stationary series. Moreover, we find some evidence of an asymmetric adjustment process in the productivity growth rates of manufacturing.
ACKNOWLEDGMENTS
The authors thank Phillip Ostwald and an anonymous reviewer for helpful comments on an earlier version of the article. The usual disclaimer applies.
Notes
1More details on the construction of the productivity index measures can be found in United States Department of Labor, Bureau of Labor Statistics publication USDL 05-1820, September 27, 2005, or on their website at http://bls.gov/schedule/archives/all_nr.htm
2See CitationElliot et al. (1996) for further discussion of the detrending procedure.
a (b)denotes significance at the 1% (5%) level. The critical values for DF and PP were obtained from CitationMacKinnon (1996) as follows: 1% (−4.09) and 5% (−3.47). The asymptotic critical values for the KPSS test were obtained from CitationKwiatkowski et al. (1992) as follows: 1% (0.22) and 5% (0.14). The DF-GLS critical values were obtained from CitationElliott et al. (1996) as follows: 1% (−3.68) and 5% (−3.11). The critical values for the TAR and M-TAR unit root tests were obtained from CitationEnders and Granger (1998) as follows: 1% (9.14) and 5% (6.52) for the TAR and 1% (9.77) and 5% (7.07) for the M-TAR.
3 CitationDolmas et al. (1999) and CitationHansen (2001) found evidence of a structural break in labor productivity. Therefore, we conduct an ADF-type test for a unit root when there is an unknown break in both the intercept and slope following the procedure and corresponding critical values in CitationVogelsang and Perron (1998). While there may be evidence of breaks in the productivity series, we fail to reject the null hypothesis of unit root (allowing for such breaks). Results are available upon request by the authors.