指定回归线截距（R & ggplot2）

背景

我当前的情节如下所示：

PROBLEM

我想强制 station_1 的回归线从 1 开始。

CODE

 library(ggplot2)

 #READ IN DATA
 var_x = c(2001,2002,2003,2004,2005,2006,2007,2008,2009,2010,2011,2001,2002,2003,2004,2005,2006,2007,2008,2009,2010,2011)
 var_y = c(1.000000,1.041355,1.053106,1.085738,1.126375,1.149899,1.210831,1.249480,1.286305,1.367923,1.486978,1.000000,0.9849343,0.9826141,0.9676000,0.9382975,0.9037476,0.8757748,0.8607960,0.8573634,0.8536138,0.8258877)
 var_z = c('Station_1','Station_1','Station_1','Station_1','Station_1','Station_1','Station_1','Station_1','Station_1','Station_1','Station_1','Station_2','Station_2','Station_2','Station_2','Station_2','Station_2','Station_2','Station_2','Station_2','Station_2','Station_2')

 df_data = data.frame(var_x,var_y,var_z)

 out = ggplot(df_data,aes(x=var_x,y=var_y,group=var_z))       
 out = out + geom_line(aes(linetype=var_z),size=1)  
 out = out + theme_classic()

 #SELECT DATA FOR Station_1
 PFI_data=subset(df_data,var_z=="Station_1")

 #PLOT REGRESSION FOR Station_1
 out = out+ stat_smooth(data = PFI_data,
                   method=lm,
                   formula = y~x,
                   se=T,size = 1.4,colour = "blue",linetype=1)

任何帮助将不胜感激 - 这让我发疯太久了！

首先，在将回归线强制到某个固定点时应该小心。这是一个link https://stats.stackexchange.com/questions/12484/constrained-linear-regression-through-a-specified-point来讨论为什么。

现在，从技术角度来看，我严重依赖这些问题和答案：one https://stackoverflow.com/questions/7333203/linear-regression-with-explicit-intercept-in-r, two https://stackoverflow.com/questions/9789871/method-to-extract-stat-smooth-line-fit。我的解决方案的概要如下：预先计算所需的截距，在没有它的情况下运行回归，将截距添加到结果预测中。

我正在使用内部ggplot2:::predictdf.default功能可以节省一些打字。这cbind(df, df)部分可能看起来很奇怪，但这是一个简单的技巧geom_smooth工作正常，因为有两个因素水平var_z.

# Previous code should remain intact, replace the rest with this:
# SELECT DATA FOR Station_1
PFI_data=subset(df_data,var_z=="Station_1")
names(PFI_data) <- c("x", "y", "z")

x0 <- df_data[df_data$var_z == "Station_1", "var_x"][1]
y0 <- df_data[df_data$var_z == "Station_1", "var_y"][1]

model <- lm(I(y-y0) ~ I(x-x0) + 0, data = PFI_data)
xrange <- range(PFI_data$x)
xseq <- seq(from=xrange[1], to=xrange[2])
df <- ggplot2:::predictdf.default(model, xseq, se=T, level=0.95)
df <- rbind(df, df)
df[c("y", "ymin", "ymax")] <- df[c("y", "ymin", "ymax")] + y0
out + geom_smooth(aes_auto(df), data=df, stat="identity")