非线性问题

Question

我在alr3软件包中使用Length and Age形式的wblake数据在R中运行注册。如何知道长度取决于年龄或年龄的某种力量。

我已经使用Age进行多项式回归。

我的R代码如下：

require(alr3)
require(MASS)
require(lmreg)
data("wblake")
attach(wblake)

mod<-lm(Length~Age)
summary(mod)
mod2 <- lm(Length~poly(Age,3,raw=T)); summary(mod2)

and the output is :
Call:
lm(formula = Length ~ poly(Age, 3, raw = T))

Residuals:
    Min      1Q  Median      3Q     Max 
-81.521 -20.066  -3.612  17.066  93.412 

Coefficients:
                       Estimate Std. Error t value Pr(>|t|)    
(Intercept)             82.4856    11.3401   7.274 1.64e-12 ***
poly(Age, 3, raw = T)1  10.4322    10.0722   1.036   0.3009    
poly(Age, 3, raw = T)2   6.1282     2.6239   2.336   0.0200 *  
poly(Age, 3, raw = T)3  -0.5314     0.2075  -2.560   0.0108 *  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 28.45 on 435 degrees of freedom
Multiple R-squared:  0.8198,    Adjusted R-squared:  0.8185 
F-statistic: 659.6 on 3 and 435 DF,  p-value: < 2.2e-16`Call:
lm(formula = Length ~ poly(Age, 3, raw = T))