¿Qué es una variable de confusión?

https://doi.org/10.1016/S0025-7753(01)72121-5Get rights and content

First page preview

First page preview
Click to open first page preview

Referencias Bibliografía (30)

  • L.D. Botto et al.

    Neural-tube defects

    N engl j med

    (1999)
  • G. Axelsson et al.

    Dietary factors and lung cancer among men in west sweden

    Int j epidemiol

    (1996)
  • F. Nyberg et al.

    Dietary factors and risk of lung cancer in never-smokers

    Int j cancer

    (1998)
  • A. Ascherio et al.

    Relation of consumption of vitamin e, vitamin c and carote-noids to risk for stroke among men in the united states

    Ann intern med

    (1999)
  • The heart outcomes prevention evaluation study investigators (hopes). vitamin e supplementation and cardiovascular events in high-risk patients

    N engl j med

    (2000)
  • Cited by (20)

    • Child, family and system variables associated to breakdowns in family foster care

      2020, Children and Youth Services Review
      Citation Excerpt :

      If this was the case, the variable was kept (confounding variable). If not, it was excluded from the model (De Irala, Martinez-Gonzalez, & Grima, 2001). Having taken all these considerations into account, the most parsimonious logistic regression model has been presented in this article.

    • Normalized second and fourth finger lengths in male and female partners and IVF cycle outcomes

      2019, Reproductive BioMedicine Online
      Citation Excerpt :

      The multivariate models were constructed to adjust for variables identified as potential risk markers or confounding factors in the previous bivariate analyses. The strategy was to retain in the final adjusted model only potential confounders that, if they were eliminated, would modify by more than 10% the net value of the principal regression coefficient, according to De Irala et al. (2001). Data were processed using the IBM SPSS-22 Statistics package.

    • Bias in clinical epidemiological study designs

      2013, Allergologia et Immunopathologia
      Citation Excerpt :

      Rothman established three conditions for identifying a potential confounding variable: (I) it must be a predictor of effect even among the subjects not exposed to the study factor; (II) it must be associated to the exposure under study, including the subjects that do not develop the effect; and (III) a confounding variable cannot be the intermediate step in the causal sequence between exposure and the effect or disease under study (e.g., the blood cotinine value in children between a cause such as exposure to tobacco smoke in the home and the development of asthma in childhood).19 Confounding bias is the only one of the three types of bias that can be controlled both in the study design phase and posteriorly in the analytical phase of an epidemiological study.20 In the design phase, the methodological variants aim to prevent the occurrence of such bias, with the adoption of three possible types of strategies:

    • Cannabis use, adolescence and suicide

      2011, Trastornos Adictivos
    • How to apply for research grants in allergology

      2009, Allergologia et Immunopathologia
    View all citing articles on Scopus
    View full text