A coding error in excel, among other errors, has seriously weakened the conclusions of an important financial paper (by Harvard economists Carmen Reinhart and Kenneth Rogoff, "Growth in a Time of Debt." ) regarding GDP growth at high debt to GDP levels. Another paper, ("Does High Public Debt Consistently Stifle Economic Growth? A Critique of Reinhart and Rogoff," by Thomas Herndon, Michael Ash, and Robert Pollin) tracked down the flaws - Excel spreadsheet errors, excluded data, and unusual weightings of statistics. With the importance f Excel as a modeling and calculation tool at our company, always be aware of the possibility of errors.
When modeling and examining model results I especially think of three things among many others - 1. Do the final results make sense? 2. If not, is there an error in my calculations or in the original data? Is there an source external to the model I can check against? 3. If the result is unexpected, is this a new insight? The more surprising, the more evidence needed to convince others, especially in business.
Read more at: http://phys.org/news/2013-04-excel-austerity-economics-paper-coding-flawed.html
No comments:
Post a Comment