logo
Call us: +44 (0)1865 244727

  • Home
  • Scope
  • News
  • Products
    • RADAR
    • CALL-OFF PROJECTS
  • Clients
  • Contact
  • How we work
    • Independent
      • Common law orthodoxies
      • Sensationalism
      • Expert witness
      • Regulation and Politics
      • Tied services
    • Up-to-date
      • Timely
      • Insurance Scenarios
      • Probabilistic Methods
    • Expert
      • Personal Injury
      • Trends
    • Innovative
  • Database
    • Member’s login
    • Member’s Settings
    • Register
    • RADAR Database
  • Recent projects
    • EMFs
    • STRESS AT WORK
    • WHIPLASH
    • WELDING RODS: MANGANESE EXPOSURE
    • ENVIRONMENTAL TOBACCO SMOKE
    • Other Projects



2001. Epidemiology for insurers. P value.

May 23, 2012
by Andrew@Reliabilityoxford.co.uk
0 Comment
Confidence in epidemiological findings is often expressed by a statistical measure. In 2001 the following view was expressed. We have since updated the criterion based on confidence limits. The difference between the upper and lower 95% confidence limits should be smaller than 3 times the (relative risk, minus 1). 

(upper – lower) < 3× (RR-1)

Understanding the confidence in epidemiology results is essential if the uncertainty in liability exposure estimates is to be usefully expressed. Uncertainty is often greater than the central exposure estimate.

Evidence from:

andrew@reliabilityoxford.co.uk

Epidemiological results are often supported by reference to P values. It has become commonplace to refer with great confidence to results with P values less than 0.05. Such confidence may be misplaced.

For example, a P value of 0.04 tells us that if the null hypothesis were true, an association as strong as the one we observe in that particular experiment would occur with a probability of only 4%. That is, it is not very likely that you would get the reported Risk Ratio, based on the data at hand, if in fact, in that particular experiment, the null hypothesis was the true one.

But this does not mean the true result would ever have been found by the experiment in question, only that in the circumstances of the experiment at hand, the null value would have been unlikely.

Ratio of upper to lower 95% Confidence Interval is a better measure of precision, but still will not tell us if the experiment was ever capable of unearthing the true strength of association.

The editors of this journal are often, more persuaded by epidemiological results when the ratio of upper to lower 95% Confidence Interval is three or less. This is an entirely subjective criterion.

In general, it is useful to plot actual data on a graph including the null hypothesis. The reader can then judge for themselves whether the excellent P value, often enthusiastically quoted by the authors, really means anything. Such graphs are rare.

Leave a Reply Cancel reply

*
*

captcha *

Search Documents


Categories

  • Causation
    • de minimis
    • material contribution
  • Date of knowledge
  • Diagnosis
  • Duty of Care
  • Exposure estimation data
  • Mitigation
  • Motor related injury
  • News
  • Uncategorized

Archives

  • July 2023
  • June 2023
  • November 2020
  • January 2020
  • November 2019
  • May 2019
  • April 2019
  • March 2019
  • January 2019
  • December 2018
  • November 2018
  • September 2018
  • August 2018
  • July 2018
  • June 2018
  • April 2018
  • November 2017
  • July 2017
  • April 2017
  • May 2016
  • April 2016
  • November 2015
  • April 2015
  • March 2015
  • December 2014
  • October 2014
  • July 2014
  • April 2014
  • February 2014
  • December 2013
  • November 2013
  • October 2013
  • September 2013
  • July 2013
  • June 2013
  • April 2013
  • March 2013
  • February 2013
  • January 2013
  • December 2012
  • November 2012
  • October 2012
  • September 2012
  • August 2012
  • July 2012
  • June 2012
  • May 2012

© Re: Liability (Oxford) Ltd. 2012. All rights reserved.
Website Design by The Big Picture