求问有大神用过geeglm中的ns函数吗，我想用5个节点的自然立方样条建立一个交互作用模型，模型是这样的：
geeglm(falseteeth~ns(age,knots=c(73,81,87,92,100))*female


出来的结果是每个节点和female的交互项都有一个p值：
ns(age, knots = c(73, 81, 87, 92, 100))1:female 0.163049   
ns(age, knots = c(73, 81, 87, 92, 100))2:female 0.054540 .  
ns(age, knots = c(73, 81, 87, 92, 100))3:female 0.011970 *  
ns(age, knots = c(73, 81, 87, 92, 100))4:female 0.067661 .  
ns(age, knots = c(73, 81, 87, 92, 100))5:female 0.000485 ***
ns(age, knots = c(73, 81, 87, 92, 100))6:female 0.007331 **


我想问一下可不可以求一个总的样条与性别交互项的p值，我在一篇文献中《Trends in Prevalence of Chronic Kidney Disease in the United States》看到作者只求了一个p值，统计方法的部分他只介绍了“To test for interactions of the temporal trends across categories (e.g., age) we tested the combined interaction of the spline terms with the category of interest.”，但是我不知道是怎么求的 combined interaction