Distributions of GDP across versions of the Penn World Tables: A functional data analysis approach

• Published in: Economics letters Vol. 170; pp. 179 - 184
• Main Authors: Chen, Tao, DeJuan, Joseph, Tian, Renfang
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.09.2018; Elsevier Science Ltd
• Subjects: Bootstrap; Data analysis; Data quality; economics; Equality; Functional data analysis; GDP; Gross Domestic Product; Penn World Table; Robustness; Sensitivity analysis; Studies; Penn World Table; GDP; O47; C12; C15; Bootstrap; Data quality; O50; Functional data analysis
• ISSN: 0165-1765; 1873-7374
• DOI: 10.1016/j.econlet.2018.05.038

Data in the Penn World Tables (PWT) have been subject to a series of revisions since its first release in the early 1990s, and the amendments are substantial for many countries. This paper uses functional data analysis to examine the distribution functions of GDP across different versions of the PWT. We find no support for distribution equality hypothesis, indicating that GDP in different versions do not share a common underlying distribution. This suggests, at the least, a need to use caution in drawing conclusions from a particular PWT version, and conduct appropriate sensitivity analysis to check the robustness of results. •Approximate GDP processes using functional data analysis.•Application of functional data analysis to examine the GDP distribution functions.•The distribution equality of GDP processes is tested by verifying the equality of an enlarging set of moment functions of the sample paths at an increasing order of derivatives of the curve fitting functions.•Distributions of GDP are not identical across versions of the Penn World Tables.•The validity of the functional-data based bootstrap test for distribution equality is justified theoretically.