Question

我目前正在尝试使用lm()使多项式模型适合测量数据。

fit_poly4 <- lm(y ~ poly(x, degree = 4, raw = T), weights = w)

以x作为独立变量，y作为因变量，并且w = 1 /测量变量。

我想尝试使用给定系数而不是R确定的多项式。具体地说，我希望我的多项式为

y = -3,3583*x^4 + 43*x^3 - 191,14*x^2 + 328,2*x - 137,7

我试图输入为

fit_poly4 <- lm(y ~ 328.2*x-191.14*I(x^2)+43*I(x^3)-3.3583*I(x^4)-137.3, 
                weights = w)

但这只会返回错误：

terms.formula（formula，data = data）中的错误：ExtractVars中的模型公式无效

是否有一种方法可以确定lm()中的系数，并且该怎么做？

Answer 1

我不确定为什么要这样做，但是可以使用偏移量项：

> dput(cpu[,1:6])
structure(list(Datapoints.Timestamp = structure(1L, .Label = "2019-03-05T08:00:00Z", class = "factor"), 
    Datapoints.Maximum = 7.83333333332848, Datapoints.Unit = structure(1L, .Label = "Percent", class = "factor"), 
    Datapoints.Timestamp.1 = structure(1L, .Label = "2019-03-11T22:00:00Z", class = "factor"), 
    Datapoints.Maximum.1 = 24.2500000000048, Datapoints.Unit.1 = structure(1L, .Label = "Percent", class = "factor")), .Names = c("Datapoints.Timestamp", 
"Datapoints.Maximum", "Datapoints.Unit", "Datapoints.Timestamp.1", 
"Datapoints.Maximum.1", "Datapoints.Unit.1"), class = "data.frame", row.names = c(NA, 
-1L))

set.seed(101) dd <- data.frame(x=rnorm(1000),y=rnorm(1000), w = rlnorm(1000)) fit_poly4 <- lm(y ~ -1 + offset(328.2*x-191.14*I(x^2)+43*I(x^3)-3.3583*I(x^4)-137.3), data=dd, weights = w)取消了通常的拦截项。

以lm（）为单位给定系数

1 个答案: