Skip to main content

Advertisement

SpringerLink
Log in

Choice of exposure scores for categorical regression in meta-analysis: a case study of a common problem

  • Published:
Cancer Causes & Control Aims and scope Submit manuscript

Abstract

Objective: Reporting categorical relative risk estimates for a series of exposure levels versus a common reference category is a widespread practice. In meta-analysis, categorical regression estimates a dose–response trend from such results. This method requires the assignment of a single score to each exposure category. We examined how closely meta-analytical categorical regression approximates the results of analysis based on the individual-level continuous exposure.

Methods: The analysis included five studies on tea intake and outcomes related to colorectal cancer. In addition, we derived categorical mean and median values from published distributions of tea consumption in similar populations to assign scores to the categories of tea intake when possible. We examined whether these derived mean and median values well approximate the individual-level results.

Results: In meta-analytical categorical regression, using the midrange scores approximated the individual-level continuous analyses reasonably well, if the value assigned to the uppermost, open-ended category was at least as high as the lower bound plus the width of the second-highest category. Categorical mean values derived from the published distributions of regular tea (in the US) and green tea (in Japan) well approximated the slope obtained from individual-level analysis.

Conclusion: Publication of both the categorical and the continuous estimates of effect in primary studies, with their standard errors, can enhance the quality of meta-analysis, as well as providing intrinsically valuable information on dose–response.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Abbreviations

CLR:

confidence limit ratios

RR:

relative risk

References

  1. S Greenland (1998) Basic methods for sensitivity analysis and external adjustment KJ Rothman S Greenland (Eds) Modern Epidemiology Lippincott-Raven Publishers Philadelphia 343–358

    Google Scholar 

  2. S Greenland MP Longnecker (1992) ArticleTitleMethods for trend estimation from summarized dose–response data, with applications to meta-analysis Am J Epidemiol 135 1301–1309 Occurrence Handle1:STN:280:By2A38fgt1I%3D Occurrence Handle1626547

    CAS  PubMed  Google Scholar 

  3. JA Berlin MP Longnecker S Greenland (1993) ArticleTitleMeta-analysis of epidemiologic dose–response data Epidemiology 4 218–228 Occurrence Handle1:STN:280:ByyB1M7itl0%3D Occurrence Handle8512986

    CAS  PubMed  Google Scholar 

  4. KG Brown (1999) ArticleTitleLung cancer and environmental tobacco smoke: occupational risk to nonsmokers Environ Health Perspect 107 IssueID(Suppl 6 885–890 Occurrence Handle10592148

    PubMed  Google Scholar 

  5. CM Villanueva F Fernandez N Malats JO Grimalt M Kogevinas (2003) ArticleTitleMeta-analysis of studies on individual consumption of chlorinated drinking water and bladder cancer J Epidemiol Community Health 57 166–173 Occurrence Handle1:STN:280:DC%2BD3s7hs1Ciuw%3D%3D Occurrence Handle12594192

    CAS  PubMed  Google Scholar 

  6. ES Ford SJ Smith DF Stroup KK Steinberg PW Mueller SB Thacker (2002) ArticleTitleHomocyst(e)ine and cardiovascular disease: a systematic review of the evidence with special emphasis on case–control studies and nested case-control studies Int J Epidemiol 31 59–70 Occurrence Handle11914295

    PubMed  Google Scholar 

  7. K Reynolds B Lewis JD Nolen GL Kinney B Sathya J He (2003) ArticleTitleAlcohol consumption and risk of stroke: a meta-analysis JAMA 289 579–588 Occurrence Handle12578491

    PubMed  Google Scholar 

  8. T Norat A Lukanova P Ferrari E Riboli (2002) ArticleTitleMeat consumption and colorectal cancer risk: dose–response meta-analysis of epidemiological studies Int J Cancer 98 241–256 Occurrence Handle1:CAS:528:DC%2BD38XhsVSkur0%3D Occurrence Handle11857415

    CAS  PubMed  Google Scholar 

  9. WO Spitzer JM Faith KD MacRae (2002) ArticleTitleMyocardial infarction and third generation oral ontraceptives: aggregation of recent studies Hum Reprod 17 2307–2314 Occurrence Handle12202417

    PubMed  Google Scholar 

  10. A Bergstrom CC Hsieh P Lindblad CM Lu NR Cook A Wolk (2001) ArticleTitleObesity and renal cell cancer – a quantitative review Br J Cancer 85 984–990 Occurrence Handle1:STN:280:DC%2BD3Mrks1Snug%3D%3D Occurrence Handle11592770

    CAS  PubMed  Google Scholar 

  11. JQ Shi JB Copas (2004) ArticleTitleMeta-analysis for trend estimation Stat Med 23 3–19 Occurrence Handle14695636

    PubMed  Google Scholar 

  12. N Mantel (1963) ArticleTitleChi-Square Tests with One Degree of Freedom: Extensions of the Mantel-Haenszel Procedure J Am Stat Assoc 53 690–700

    Google Scholar 

  13. KJ Rothman (1986) Modern epidemiology Little, Brown Boston

    Google Scholar 

  14. U Peters C Poole L Arab (2001) ArticleTitleDoes tea affect cardiovascular disease? A meta-analysis Am J Epidemiol 154 495–503 Occurrence Handle1:STN:280:DC%2BD3MvpvF2jtw%3D%3D Occurrence Handle11549554

    CAS  PubMed  Google Scholar 

  15. JA Baron D Gerhardsson A Ekbom (1994) ArticleTitleCoffee, tea, tobacco, and cancer of the large bowel Cancer Epidemiol Biomarkers Prev 3 565–570 Occurrence Handle1:STN:280:ByqC38fislU%3D Occurrence Handle7827586

    CAS  PubMed  Google Scholar 

  16. JA Baron ER Greenberg R Haile J Mandel RS Sandler L Mott (1997) ArticleTitleCoffee and tea and the risk of recurrent colorectal adenomas Cancer Epidemiol Biomarkers Prev 6 7–10 Occurrence Handle1:STN:280:ByiC2cnptlA%3D Occurrence Handle8993790

    CAS  PubMed  Google Scholar 

  17. D Il’yasova L Arab A Martinchik UM Weisgerber A Sdvizhkov L Urbanovich (2003) ArticleTitleBlack tea consumption and risk of rectal cancer in Moscow population Ann Epidemiol 13 405–411 Occurrence Handle10.1016/S1047-2797(02)00459-3 Occurrence Handle12875797

    Article  PubMed  Google Scholar 

  18. S Kono K Shinchi N Ikeda F Yanai K Imanishi (1991) ArticleTitlePhysical activity, dietary habits and adenomatous polyps of the sigmoid colon: a study of self-defense officials in Japan J Clin Epidemiol 44 1255–1261 Occurrence Handle1:STN:280:By2D2cvmslY%3D Occurrence Handle1941019

    CAS  PubMed  Google Scholar 

  19. LJ Su L Arab (2002) ArticleTitleTea consumption and the reduced risk of colon cancer – results from a national prospective cohort study Public Health Nutr 5 419–425 Occurrence Handle12003653

    PubMed  Google Scholar 

  20. C Poole (2001) ArticleTitleLow P-values or narrow confidence intervals: which are more durable? Epidemiology 12 291–294 Occurrence Handle1:STN:280:DC%2BD3MvpsVOhtA%3D%3D Occurrence Handle11337599

    CAS  PubMed  Google Scholar 

  21. US Department of Health and Human Services (DHHS). Second National Health and Nutrition Examination Survey I Epidemiologic Followup Study, 1982–1984. NCHS. 2001. NCHS.

  22. M Inoue K Tajima K Hirose et al. (1997) ArticleTitleEpidemiological features of first-visit outpatients in Japan: comparison with general population and variation by sex, age, and season J Clin Epidemiol 50 69–77 Occurrence Handle1:STN:280:ByiB3c%2Fos1c%3D Occurrence Handle9048692

    CAS  PubMed  Google Scholar 

  23. InstitutionalAuthorNameU.S. Environmental Protection Agency (1986) ArticleTitleGuidelines for Carcinogen Risk Assessment Fed. Reg. 51 33992–34003

    Google Scholar 

  24. I Hertz-Picciotto (1995) ArticleTitleEpidemiology and quantitative risk assessment: a bridge from science to policy Am J Public Health 85 484–491 Occurrence Handle1:STN:280:ByqB3MnmslA%3D Occurrence Handle7702110

    CAS  PubMed  Google Scholar 

  25. RE Shore (1995) ArticleTitleEpidemiologic data in risk assessment – imperfect but valuable Am J Public Health 85 474–476 Occurrence Handle1:STN:280:ByqB3MnmslQ%3D Occurrence Handle7702106

    CAS  PubMed  Google Scholar 

  26. TE Rohan AJ McMichael (1988) ArticleTitleAlcohol consumption and risk of breast cancer Int J Cancer 41 695–699 Occurrence Handle1:STN:280:BieB3M3mtVE%3D Occurrence Handle3366491

    CAS  PubMed  Google Scholar 

  27. RJ Cook BB Brumback MB Wigg LM Ryan (2001) ArticleTitleSynthesis of evidence from epidemiological studies with interval-censored exposure due to grouping Biometrics 57 671–680 Occurrence Handle1:STN:280:DC%2BD3MrgtFOisg%3D%3D Occurrence Handle11550914 Occurrence HandleMR1859804

    CAS  PubMed  MathSciNet  Google Scholar 

  28. V Bagnardi A Zambon P Quatto G Corrao (2004) ArticleTitleFlexible meta-regression functions for modeling aggregate dose–response data, with an application to alcohol and mortality Am J Epidemiol 159 1077–1086 Occurrence Handle15155292

    PubMed  Google Scholar 

  29. I Hertz-Picciotto AH Smith (1993) ArticleTitleObservations on the dose–response curve for arsenic exposure and lung cancer Scand J Work Environ Health 19 217–226 Occurrence Handle1:CAS:528:DyaK2cXhtFGmurg%3D Occurrence Handle8235510

    CAS  PubMed  Google Scholar 

  30. C Poole S Greenland (1999) ArticleTitleRandom-effects meta-analyses are not always conservative Am J Epidemiol 150 469–475 Occurrence Handle1:STN:280:DyaK1MzpvF2htw%3D%3D Occurrence Handle10472946

    CAS  PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department Epidemiology, School of Public Health, University of North Carolina, Chapel Hill, North Carolina, USA

    Dora Il’yasova, Irva Hertz-Picciotto & Charles Poole

  2. Division of Cancer Epidemiology and Genetics, National Cancer Institute, NIH, DHHS, Bethesda, Maryland, USA

    Ulrike Peters

  3. Center for Clinical Epidemiology and Biostatistics and Department of Biostatistics and Epidemiology, University of Pennsylvania School of Medicine, USA

    Jesse A. Berlin

  4. Medical Center Boulevard, Wake Forest University School of Medicine, Winston-Salem, NC, 27157

    Dora Il’yasova

  5. Department of Epidemiology and Preventive Medicine, University of California, Davis, USA

    Irva Hertz-Picciotto

Authors
  1. Dora Il’yasova
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Irva Hertz-Picciotto
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ulrike Peters
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jesse A. Berlin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Charles Poole
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dora Il’yasova.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Il’yasova, D., Hertz-Picciotto, I., Peters, U. et al. Choice of exposure scores for categorical regression in meta-analysis: a case study of a common problem. Cancer Causes Control 16, 383–388 (2005). https://doi.org/10.1007/s10552-004-5025-x

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10552-004-5025-x

Keywords

Search

Navigation