Med P:n som i programpaket. Om datatortyr och signifikansfiskeri
(2002) In Läkartidningen 99(34). p.5-3302- Abstract
For the study of prognostic factors, the medical researchers have access to a number of advanced statistical techniques available in standard program packages. A tradition has developed where survival or time to relapse is analysed on the basis of statistical materials with few patients but a large number of possible explanatory variables. In statistical "fishing expeditions" the p-values are used to sort out potentially useful prognostic variables. Since the number of observations is small, all relevant prognostic factors do not give statistical significance. Since a large number of variables are tested there is a considerable risk for spurious significances. It is not enough to show that a prognostic factor seems to be efficient in... (More)
For the study of prognostic factors, the medical researchers have access to a number of advanced statistical techniques available in standard program packages. A tradition has developed where survival or time to relapse is analysed on the basis of statistical materials with few patients but a large number of possible explanatory variables. In statistical "fishing expeditions" the p-values are used to sort out potentially useful prognostic variables. Since the number of observations is small, all relevant prognostic factors do not give statistical significance. Since a large number of variables are tested there is a considerable risk for spurious significances. It is not enough to show that a prognostic factor seems to be efficient in the patient group where it was first found. The result must be verified in further studies of independent groups of similar patients.
(Less)
- author
- Taube, Adam and Högberg, Thomas LU
- alternative title
- "P" as in Program Package. About torturing data and significant "fishing expeditions"
- publishing date
- 2002-08-22
- type
- Contribution to journal
- publication status
- published
- keywords
- Confidence Intervals, Data Interpretation, Statistical, Humans, Predictive Value of Tests, Prognosis, Reproducibility of Results, Statistics as Topic
- in
- Läkartidningen
- volume
- 99
- issue
- 34
- pages
- 4 pages
- publisher
- Swedish Medical Association
- external identifiers
-
- pmid:12362849
- scopus:0037158811
- ISSN
- 0023-7205
- language
- Swedish
- LU publication?
- no
- id
- d9ab969f-fc79-41ea-bebd-64f720ad6a6d
- alternative location
- http://www.lakartidningen.se/OldArticlePdf/#!/2002/25243
- date added to LUP
- 2019-09-20 07:55:03
- date last changed
- 2024-01-01 20:54:31
@article{d9ab969f-fc79-41ea-bebd-64f720ad6a6d, abstract = {{<p>For the study of prognostic factors, the medical researchers have access to a number of advanced statistical techniques available in standard program packages. A tradition has developed where survival or time to relapse is analysed on the basis of statistical materials with few patients but a large number of possible explanatory variables. In statistical "fishing expeditions" the p-values are used to sort out potentially useful prognostic variables. Since the number of observations is small, all relevant prognostic factors do not give statistical significance. Since a large number of variables are tested there is a considerable risk for spurious significances. It is not enough to show that a prognostic factor seems to be efficient in the patient group where it was first found. The result must be verified in further studies of independent groups of similar patients.</p>}}, author = {{Taube, Adam and Högberg, Thomas}}, issn = {{0023-7205}}, keywords = {{Confidence Intervals; Data Interpretation, Statistical; Humans; Predictive Value of Tests; Prognosis; Reproducibility of Results; Statistics as Topic}}, language = {{swe}}, month = {{08}}, number = {{34}}, pages = {{5--3302}}, publisher = {{Swedish Medical Association}}, series = {{Läkartidningen}}, title = {{Med P:n som i programpaket. Om datatortyr och signifikansfiskeri}}, url = {{http://www.lakartidningen.se/OldArticlePdf/#!/2002/25243}}, volume = {{99}}, year = {{2002}}, }