More on Non Linear Relationships, Splines

  • Ton J. Cleophas
  • Aeilko H. Zwinderman


The general principle of regression analysis is that the best fit line/exponential-curve/curvilinear-curve etc is calculated, i.e., the one with the shortest distances to the data, and it is, subsequently, tested how far the data are from the curve. A significant correlation between the y (outcome data) and the x (exposure data) means that the data are closer to the model than will happen purely by chance. The level of significance is usually tested, simply, with t-tests or analysis of variance. The initial regression model is almost always a linear model.


Polynomial Regression Multinomial Logistic Regression Generalize Additive Model Data Pattern Data Plot 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. Additive regression and transformation using ACE or AVAS. Accessed 15 Dec 2011
  2. Akaike information criterion. Accessed 15 Dec 2011
  3. Birkhof F, De Boor R (1965) Piecewise polynomial interpretation and approximation. In: Proceedings of general motors symposium of 1964, pp 164–190Google Scholar
  4. Box-Cox normality plot. Accessed 15 Dec 2011
  5. Cubic Spline for Excel. Accessed 15 Dec 2011
  6. Ferguson JC (1964) Multi-variable curve interpolation. JACM 11:221–228CrossRefGoogle Scholar
  7. Generalized additive model. Accessed 15 Dec 2011
  8. Hastie and Tibshirani (1990) Generalized additive models. Chapman & Hall, LondonGoogle Scholar
  9. Lambda-calculus. Accessed 15 Dec 2011
  10. Local regression. Accessed 15 Dec 2011
  11. SPSS. Accessed 15 Dec 2011

Copyright information

© Springer Science+Business Media B.V. 2012

Authors and Affiliations

  • Ton J. Cleophas
    • 1
    • 2
  • Aeilko H. Zwinderman
    • 1
    • 3
  1. 1.Applied to Clinical TrialsEuropean Interuniversity College of Pharmaceutical MedicineLyonFrance
  2. 2.Department of MedicineAlbert Schweitzer HospitalDordrechtNetherlands
  3. 3.Department of Biostatistics and EpidemiologyAcademic Medical CenterAmsterdamNetherlands

Personalised recommendations