Observations by a statistical watchdog

  • Adam Taube Department of Statistics, Uppsala University, PO Box 513, SE-75120 Uppsala
Keywords: Selection bias, Data torturing, Statistical cleansing, Multiplicity problems, Clinical trials, Survival analysis

Abstract

During more than five decades, the author has kept a critical eye on how statistical methods are (mis-)used in medical research. Some areas are presented where serious statistical mistakes are prevalent. Two investigations with erroneous conclusions are described in detail. Situations where outside authorities have tried to mute medical researchers are also commented upon. The authors own efforts to improve the use of statistical methods and the current situation with easily accessible statistical program packages are described. Finally, the importance of continued ‘statistical cleansing’ is stressed.

Downloads

Download data is not yet available.

References


  1. Henschen F. Arteriosclersosens correlation till ålder, kön, nutritionstillstånd, hjärtsvikt, diabetes, gallsten, tuberkulos och maligna svulster. Sv Läkartidningen. 1959;56:1674–86.

  2. van der Linden W, Taube A. Arterioscleros och cancer i obduktionsmaterial. Sv Läkartidningen. 1959;56:3536–9.

  3. Berkson J. Limitations of the application of fourfold table analysis to hospital data. Biometric Bull. 1946;2:47–53. doi: 10.2307/3002000

  4. van der Linden W, Taube A. Association of cholelithiasis, hiatus hernia, and diverticulosis coli. JAMA. 1959;180:408. doi: 10.1001/jama.1959.03000210102018

  5. van der Linden W, Taube A. Statistiska selektions-problem i icke-experimentella medicinska material. Nord Med. 1962;67:589–602.

  6. Schwarz D, AngueraG . Une cause de biais dans certaines enquêtes medical: le temps de séjour de maladies à l´hopital. Comm. Inst. Intern. Statis. 30 è Session. Stockholm: Almqvist och Wiksell; 1957.

  7. Tekle Wold F, Sterky G, Taube A. The age of menarche in a group of schoolgirls in Addis Ababa. Ethiop Med J. 1972;10:159–66.

  8. Atwood C, Taube A. Estimating mean time to reach a milestone, using retrospective data. Biometrics. 1976;32:159–71. doi: 10.2307/2529346

  9. Simon B, Altman DG. Statistical aspects of prognostic factors in oncology. Br J Cancer. 1994;69:979–85. doi: 10.1038/bjc.1994.192

  10. Taube A, Högberg T. Med P: n som i progampaket. Läkartidningen. 2002;99:3302–5.

  11. Taube A. Nollhypotesen ‘bevisad’ – vanlig missuppfattning. Läkartidningen. 1993;90:684.

  12. Altman D. Statistical reviewing for medical journals. Stat Med. 1998;17:2661–74. doi: 10.1002/(sici)1097-0258(19981215)17:23<2661::aid-sim33>3.0.co;2-b.

  13. Taube A. Studier i medicinsk statistisk slentrian. I. Att illustrera en åldersfördelning. Läkartidningen. 1985;82:2235–6.

  14. Taube A. Studier i medicinsk statistisk slentrian. II. Att rita diagram. Läkartidningen. 1985;82:2327–30.

  15. Taube A. Studier i medicinsk statistisk slentrian. III. Det borde (inte) vara stjärnor. Läkartidningen. 1985;82:2422–4.

  16. Taube A. Studier i medicinsk statistisk slentrian. IV. Varför bara studera en variabel i taget? Läkartidningen. 1985;82:2520–1.

  17. Taube A. Studier i medicinsk statistisk slentrian. V. Några funderingar. Läkartidningen. 1985;82:2585.

  18. Taube A. Missbruk av registerdata I.: osäkra data om infarkt. Resultaten övertolkade. Läkartidningen. 1996;93:4620–2.

  19. Taube A. Missbruk av registerdata II.: Tretton kirurger gör statistiska snitt. Läkartidningen. 1997;94:61–2.

Published
2021-02-08
How to Cite
Taube, A. (2021). Observations by a statistical watchdog. Upsala Journal of Medical Sciences, 126(1). https://doi.org/10.48101/ujms.v126.5665
Section
Biography