本人最近一篇文章待发表,涉及Logistic回归的倾向值(Probabilities),审稿人要求用cubic spline的方法重新求一下这个Probabilities。本来通过SPSS的Logistic回归就能简单搞定,现在复杂了,网上说可以用SAS或Matlab做,但太专业了,不会啊,求教名位大神啊!附件中有数据表格,一共26个变量,全部强制纳入回归。感激!!
(reviewer的意见) Re-estimate thepropensity score by using cubic splines (Harrell, F. E., Jr. [2001].Regressionmodeling strategies: with application to linear models, logistic regression,and survival analysis. New York, Springer-Verlag.) with 5 knots foreach of the continuous variables.