如何在 R 中创建置信区间图

Question

乙

DF1 = read.csv("Nerlove.3.csv",header=TRUE)

head(DF1, n=5)

split = round(nrow(DF1) * 0.60)


train = (DF1[1:split, ])

test = (DF1[(split + 1):nrow(DF1), ])

model = lm(output ~ ., train)

summary(model)

plot(train$cost, train$output, ylab = "Output", xlab = "Cost",main = "....")


abline(model, col=2)

C

plot(test$cost, test$output, ylab = "Output", xlab = "Cost",main = "....")

model1 = lm(output ~ ., test)

abline(model, col=2)

prediction = predict(model, test)

plot(prediction, main = "....")

abline(model1, col=2)

summary(model1)

d

library(stats)

X_0 = data.frame(cost = test$cost)

FI_mean = predict(model, newdata = X_0, interval="confidence", level = 0.95)

FI_ind =  predict(model,newdata = X_0, interval = "prediction")

plot(test$cost, test$output, ylab = "Output", xlab = "Cost",main = "....")

abline(model, col=2)

min = test$cost

max = test$cost

newx = seq(min,max)

matlines(newx, FI_mean[,2:3], col = "blue", lty=2)

我需要绘制我在回归线周围找到的置信区间结果，但出现错误。 任何人都可以帮我解决这个问题。 谢谢这是我的数据的链接。 我已经对其进行了编辑，并且仅使用了数据框中的成本和输出数据

Answer 1

您做错了，因为您在通过命令model = lm(output ~ ., train)开发线性模型时使用了所有变量。 但是在绘图期间，您使用的是成本与输出绘图（如 b 和 c 的情况），而在 d 的情况下，您试图仅使用一个变量（即成本）进行预测。 应在观察输出与预测输出之间绘制回归图。 为此，您可以使用以下代码

library(lattice)
library(mosaic)
#> Loading required package: dplyr
#> 
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#> 
#>     filter, lag
#> The following objects are masked from 'package:base':
#> 
#>     intersect, setdiff, setequal, union
#> Loading required package: ggformula
#> Loading required package: ggplot2
#> Loading required package: ggstance
#> 
#> Attaching package: 'ggstance'
#> The following objects are masked from 'package:ggplot2':
#> 
#>     geom_errorbarh, GeomErrorbarh
#> 
#> New to ggformula?  Try the tutorials: 
#>  learnr::run_tutorial("introduction", package = "ggformula")
#>  learnr::run_tutorial("refining", package = "ggformula")
#> Loading required package: mosaicData
#> Loading required package: Matrix
#> Registered S3 method overwritten by 'mosaic':
#>   method                           from   
#>   fortify.SpatialPolygonsDataFrame ggplot2
#> 
#> The 'mosaic' package masks several functions from core packages in order to add 
#> additional features.  The original behavior of these functions should not be affected by this.
#> 
#> Note: If you use the Matrix package, be sure to load it BEFORE loading mosaic.
#> 
#> Attaching package: 'mosaic'
#> The following object is masked from 'package:Matrix':
#> 
#>     mean
#> The following object is masked from 'package:ggplot2':
#> 
#>     stat
#> The following objects are masked from 'package:dplyr':
#> 
#>     count, do, tally
#> The following objects are masked from 'package:stats':
#> 
#>     binom.test, cor, cor.test, cov, fivenum, IQR, median, prop.test,
#>     quantile, sd, t.test, var
#> The following objects are masked from 'package:base':
#> 
#>     max, mean, min, prod, range, sample, sum
DF1 = read.csv("Nerlove.csv",header=TRUE)

head(DF1, n=5)
#>    cost output   pl     sl  pk     sk   pf     sf
#> 1 0.082      2 2.09 0.3164 183 0.4521 17.9 0.2315
#> 2 0.661      3 2.05 0.2073 174 0.6676 35.1 0.1251
#> 3 0.990      4 2.05 0.2349 171 0.5799 35.1 0.1852
#> 4 0.315      4 1.83 0.1152 166 0.7857 32.2 0.0990
#> 5 0.197      5 2.12 0.2300 233 0.3841 28.6 0.3859

split = round(nrow(DF1) * 0.60)

train = (DF1[1:split, ])

test = (DF1[(split + 1):nrow(DF1), ])

model = lm(output ~ ., train)

summary(model)
#> 
#> Call:
#> lm(formula = output ~ ., data = train)
#> 
#> Residuals:
#>     Min      1Q  Median      3Q     Max 
#> -409.65 -112.20   -4.61   94.20  430.76 
#> 
#> Coefficients:
#>              Estimate Std. Error t value Pr(>|t|)    
#> (Intercept)  1182.296   1861.876   0.635    0.527    
#> cost          146.231      6.127  23.866  < 2e-16 ***
#> pl             14.897     80.142   0.186    0.853    
#> sl          -2471.312   1930.034  -1.280    0.204    
#> pk              1.477      1.011   1.460    0.148    
#> sk           -869.468   1874.585  -0.464    0.644    
#> pf            -13.701      2.365  -5.794 1.08e-07 ***
#> sf           -947.958   1861.490  -0.509    0.612    
#> ---
#> Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#> 
#> Residual standard error: 169.3 on 87 degrees of freedom
#> Multiple R-squared:  0.9111, Adjusted R-squared:  0.904 
#> F-statistic: 127.4 on 7 and 87 DF,  p-value: < 2.2e-16

#Calibration plotting
pred_cal <- predict(model, newdata=train)
df_cal <- data.frame(Observed=train$output, Predicted=pred_cal)

xyplot(Predicted ~ Observed, data = df_cal, pch = 19,  panel=panel.lmbands,
       band.lty = c(conf =2, pred = 1))

#Validation plottig
pred_val <- predict(model, newdata=test)
df_val <- data.frame(Observed=test$output, Predicted=pred_val)

xyplot(Predicted ~ Observed, data = df_val, pch = 19,  panel=panel.lmbands,
       band.lty = c(conf =2, pred = 1))

^{由reprex 包(v0.3.0) 于 2020 年 1 月 7 日创建}