Statistical construction error

August 20, 2011

Yes, the title is meant to have two readings.

The effect

The Numbers Guy, among other examples, talks about the UK Office for National Statistics needing to revise its estimate for the construction sector output because of an error.

Original: 2.3% growth

Corrected: 0.5% growth

Here is the Telegraph article cited by The Numbers Guy.

The cause

The spreadsheet that is used to calculate the statistic was not updated properly.

Questions

Have they not read “Spreadsheet Addiction”?

Why are they not using R?

Does this scare anybody else?

Epilogue

Who would take the repercussions when the bottle is to blame?

from “Down the Mountain” by Robin E. Contreras

Subscribe to the Portfolio Probe blog by Email

Latest posts

Leave a Reply

Related posts

  • A test of Ledoit-Wolf versus a factor model

    April 28, 2011

    Statistical factor models and Ledoit-Wolf shrinkage are competing methods for estimating variance matrices of returns.  So which is better?  This adds a data point for answering that question. Previously [...]

  • Risk fraction constraints and volatility

    April 21, 2011

    What is the effect on predicted and realized volatility of substituting risk fraction constraints for weight constraints? Previously This post depends on two previous blog posts: "Unproxying weight constraints" [...]

  • Weight compared to risk fraction

    April 18, 2011

    How well do asset weight constraints constrain risk? The setup In "Unproxying weight constraints" I claimed that many constraints on asset weights are really a proxy for constraining risk. [...]