Detecting an interaction between treatment and a continuous covariate: A comparison of two approaches
Detecting an interaction between treatment and a continuous covariate: A comparison of two approaches
复制标题
DOI：
10.1016/j.csda.2006.12.041
复制
发表时间：
2007-05-01
影响因子：
1.8
通讯作者：
Zapien, Karina
中科院分区：
文献类型：
--
作者：
Sauerbrei, Willi;Royston, Patrick;Zapien, Karina
在临床试验中，研究治疗效果是否在所有患者中相似，或者某些预后变量是否表明对治疗的不同反应，是相当有意义的。为了检验这一点，通常根据一个或多个切割点将连续预测因子分类为组。然后使用乘法项以析因方式分析治疗/协变量相互作用。对分析师来说，使用分割点会带来几个难题。在这样的模型中，最好保持连续变量连续。为了实现这一点，MFP算法的多变量模型建立分数多项式最近扩展到一个新的算法称为多变量分数多项式相互作用（MFPI）。对于后者，协变量可以是二元的、分类的或连续的，并且避免了临界点。MFPI与图形技术，亚群治疗效应模式图或亚群治疗效应模式图（STEPP）进行比较。MFPI和STEPP之间的差异通过对肾癌随机试验的重新分析来说明。利用Bootstrap方法研究了这两种方法的稳定性。通过模拟估计MFPI“检测”虚假相互作用的I型错误概率。发现MFPI和STEPP表现出相似的治疗/协变量相互作用。STEPP的面向尾部的变体被发现比滑动窗口变体提供更稳定和可解释的结果。MFPI的第1类错误概率接近其标称值。(c)2007 Elsevier B. V.保留所有权利。
In clinical trials, there is considerable interest in investigating whether a treatment effect is similar in all patients, or that some prognostic variable indicates a differential response to treatment. To examine this, a continuous predictor is usually categorized into groups according to one or more cutpoints. The treatment/covariate interaction is then analyzed in factorial fashion using multiplicative terms. The use of cutpoints raises several difficult issues for the analyst. It is preferable to keep continuous variables continuous in such a model. To achieve this, the MFP algorithm for multivariable model-building with fractional polynomials was recently extended to a new algorithm called multivariable fractional polynomial interaction (MFPI). With the latter, covariates may be binary, categorical or continuous, and cutpoints are avoided. MFPI is compared with a graphical technique, the subpopulation treatment-effect pattern plot or subpopulation treatment effect pattern plot (STEPP). Differences between MFPI and STEPP are illustrated by re-analysis of a randomized trial in kidney cancer. The stability of the two procedures is investigated by using the bootstrap. The Type I error probability of MFPI to 'detect' spurious interactions is estimated by simulation. MFPI and STEPP are found to exhibit similar treatment/covariate interactions. The tail-oriented variant of STEPP is found to give more stable and interpretable results than the sliding window variant. The type 1 error probabilty of MFPI is found to be close to its nominal value. (c) 2007 Elsevier B.V. All rights reserved.