Modelling continuous risk variables: Introduction to fractional polynomial regression  

Hao Duong1,*, Devin Volding2

1Centers for Disease Control and Prevention (CDC), U.S. Embassy, Hanoi, Vietnam
2Houston Methodist Hospital, Houston, Texas, USA
* To whom correspondence should be addressed: Hao Duong. 02 Ngo Quyen, Hoan Kiem, Hanoi. Tel: 04-39352142. Email: hduong@cdc.gov

Abstract

Linear regression analysisis used to examine the relationship between twocontinuous variableswith the assumption of a linear relationship between these variables. When this assumption is not met, alternative approaches such as data transformation, higher-order polynomial regression, piecewise/spline regression, and fractional polynomial regression are used. Of those, fractional polynomial regression appears to be more flexible and provides abetter fitto the observeddata.

Tóm tắt
Hồi quy tuyến tính được sử dụng để đánh giá mối liên quan giữa hai biến liên tục với điều kiện mối liên quan giữa chúng là một đường thẳng. Khi mối liên quan này không phải là một đường thẳng thì các phương pháp khác được dùng thay thế như là chuyển đổi dữ liệu, hồi quy đa thức bậc cao, hồi quy tuyến tính từng mảnh, hoặc hồi quy đa thức phân đoạn. Trong đó hồi quy đa thức phân đoạn linh động hơn và cho phép mô hình hóa số liệu chính xác hơn.
Publicaton Date (Web): December 30, 2014
Full-text Download: PDF
Editor: Phuc Le, Center for Value-based Care Research, Medicine Institute, Cleveland Clinic, OH

Introduction

Linear regression analysisis used to examine relationships among continuous variables, specifically the relationship between a dependent variableand one or moreindependent variables. Alternative approaches, including higher-order polynomial regression, piecewise/spline regression and fractional polynomial regression, have been developed to be compatible with examining different forms of associations among variables.

Traditional regression models

Continuous risk variables, used in linear regression models, are typically entered into the modelswith the underlying assumption of a linear relationship between risk variables and outcomes of interest. This assumption, unfortunately, is not always met, and therefore various alternative statistical approaches are used. The most common approach is data transformation (logX, sqrt(X), or 1/X – X is the risk variable of interest) which may solve the issueof non-linearity in some cases but in many cases more flexible approaches are needed. Using higher-order polynomial regression (quadratic, cubic) or piecewise models/splines may improve model fit. The morecomplex modelalmost alwaysfitsthe databetter thantheless complex model, i.e. linear model, but testing is needed to determine whether the improvement in model fit is significant (1).

Models and functions:

Linear model: β0 + β1X (straight line)

Other models used to improve the model fit:

Quadratic model: β0 + β1X + β2X2 (parabola curve)

Cubic model: β0 + β1X + β2X2 + β3X3 (S-shaped curve)

Piecewise/spline model: β0 + β1X (if X ϵ [x1, x2]) + β2X (if X ϵ [x2, x3]) +…+ βnX (if X ϵ [xn-1, xn])

where X is the risk variable of interest, and x1<x2<x3<...<xn-1<xn. Commonly, these knots can be predetermined or based on visual data inspection.

Fractional polynomial (FP) models

Transforming data or using higher-order polynomialmodelsmay provide a significantly better fit than a linear regression modelalone, but these options may notprovide for the best fit to the data. Royston and Altman developed modeling frameworks– fractional polynomial (FP) models that aremore flexible on parameterization and offer a variety of curve shapes (2). These frameworks include transformations that are power functions Xp or Xp1 + Xp2 for different values of powers (p, p1 and p2), taking from a predefined set S = {-2, - 1, - 0.5, 0, 0.5, 1, 2, 3}.

They are presented as follows:

FP degree 1 with one power p: FP1 = β01Xp; when p=0, FP1= β01ln(X)

FP degree 2 with one pair of powers (p1, p2):FP2 = β0 + β1Xp1 + β2Xp2; when p1=p2, FP2 = β0 + β1Xp1 + β2Xp2ln(X)

FP1 has 8 models with 8 different power values, and FP2 has 36 different models, including 28 combinations of those 8 values and 8 repeated ones. Table 1 presents FP modelswith degrees 1 and 2. These two sets of models provide a very wide range of curves shapes (Figures 1, 2) and cover many types of continuous functions encountered in the health sciences and elsewhere (2).

Model selection strategy

Simple function, i.e. linear function is preferred over the complex functionexcept when fit of the best-fitting alternative model (power p≠1) is significantly improved compared to that of the linear model (power p=1)(2,3). The best fitting FP degree 1 model is the one with the smallest deviance from among the 8 models with different power values, taking fromthe set {-2, - 1, - 0.5, 0, 0.5, 1, 2, 3} (Table 1). The best fitting FP degree 2 model is the one with the smallest deviance from among the 36 models with different pairs of powers, taking from the set {-2, - 1, - 0.5, 0, 0.5, 1, 2, 3} (Table 1).

Model selection stepsare as follows (2, 3):

Step 1: Test whether there is any effect of X – risk variable of interest on the outcome by comparing the fit of the best fitting FP2 withthat of the null model, using the chi-square test with 4 degrees of freedom. If the test is not significant, stop and conclude that there is no effect of X on the outcome. Otherwise continue.

Step 2: Test whether the relationshipbetween X and the outcome is nonlinear by comparing the fit of the best fitting FP2 with that of the linear model, using the chi-square test with 3 degrees of freedom.If the test is not significant, stop and conclude that there is straight relationship between X and the outcome. Otherwise continue.

Step 3: Test whether the FP 2 fits better than the FP 1 using chi-square test with 2 degrees of freedom. If the test is not significant, the final model is FP1, otherwise the final model is FP2.

Table 2 illustrates one example of model selection.

Conclusion

FP is computationally intensive and complicated when modelling multiple continuous variables. Interpreting FP results is also more difficult than other models. In contrast, FP allows more flexibility for modelling and potentially provides a better fit to the observed data.

 

Fig. 1: Schematic diagram of eight FP1 curve shapes. Numbers indicate the power p

Multivariable model-building. A pragmatic approach to regression analysis based on fractional polynomials for modelling continuous variables. Patrick Royston and Willi Sauerbrei.

Fig. 2: Schematic examples of FP2 curves

Multivariable model-building. A pragmatic approach to regression analysis based on fractional polynomials for modelling continuous variables. Patrick Royston and Willi Sauerbrei

About the authors
Dr. Hao Duong received her MD in Hue Medical School, and DrPH from the University of Texas Health Science Center at Houston, School of Public Health. She pursued her postdoctoral research in the Departmentof Epidemiology investigating risk factors associated with birth defects, and currently works as a statistician at the Centers for Centers for Disease Control and Prevention (CDC), U.S. Embassy, Hanoi, Vietnam.

References

  1. Anonymous (2014) Likelihood-ratio test after estimation (http://www.stata.com/manuals13/rlrtest.pdf).
  2. Patrick Royston and Willi Sauerbrei (2008) Multivariable model-building. A pragmatic approach to regression analysis based on fractional polynomials for modelling continuous variables (John Wiley & Sons).
  3. Royston,P; Ambler,G; Sauerbrei,W (1999) The use of fractional polynomials to model continuous risk variables in epidemiology. Int. J. Epidemiol.28(5): 964-974.

Add new comment

CAPTCHA
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.
Image CAPTCHA
Enter the characters shown in the image.