Plot Residual pada Linear Regresi
Akbar Maulana D
2022-03-11
library(readxl)
dataregresisederhana <- read_excel("D:/Mas/Kuliah/dataregresisederhana.xlsx")
head(dataregresisederhana)## # A tibble: 6 x 14
## A1 A2 A3 A4 A5 A B1 B2 B3 B C1 C2 C3
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 5 5 6 6 6 28 6 6 6 18 6 6 6
## 2 3 2 2 2 3 12 4 4 3 11 2 4 3
## 3 2 2 2 3 3 12 3 4 4 11 5 5 4
## 4 3 3 2 3 3 14 4 3 3 10 3 4 3
## 5 6 6 5 6 6 29 6 6 6 18 6 6 5
## 6 3 3 1 2 4 13 3 3 3 9 3 3 3
## # ... with 1 more variable: C <dbl>library(ggplot2)
ggplot(data=dataregresisederhana, aes(dataregresisederhana$A1)) +
geom_histogram(aes(y =..density..), fill = "blue") +
geom_density()## Warning: Use of `dataregresisederhana$A1` is discouraged. Use `A1` instead.
## Use of `dataregresisederhana$A1` is discouraged. Use `A1` instead.## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
library(psych)##
## Attaching package: 'psych'## The following objects are masked from 'package:ggplot2':
##
## %+%, alphapsych::describe(dataregresisederhana)## vars n mean sd median trimmed mad min max range skew kurtosis se
## A1 1 145 4.28 1.22 4 4.31 1.48 1 6 5 -0.35 -0.36 0.10
## A2 2 145 4.23 1.22 4 4.28 1.48 1 6 5 -0.35 -0.37 0.10
## A3 3 145 4.07 1.28 4 4.14 1.48 1 6 5 -0.48 -0.32 0.11
## A4 4 145 4.08 1.31 4 4.15 1.48 1 6 5 -0.32 -0.46 0.11
## A5 5 145 4.17 1.34 4 4.27 1.48 1 6 5 -0.57 -0.17 0.11
## A 6 145 20.83 5.35 22 21.04 4.45 5 30 25 -0.54 0.31 0.44
## B1 7 145 4.47 1.05 4 4.50 1.48 1 6 5 -0.20 -0.31 0.09
## B2 8 145 4.54 1.07 5 4.57 1.48 1 6 5 -0.37 -0.44 0.09
## B3 9 145 4.53 1.14 5 4.59 1.48 1 6 5 -0.44 -0.51 0.09
## B 10 145 13.54 2.95 14 13.62 2.97 3 18 15 -0.36 -0.02 0.24
## C1 11 145 4.46 1.15 4 4.51 1.48 1 6 5 -0.43 -0.22 0.10
## C2 12 145 4.57 1.17 5 4.65 1.48 1 6 5 -0.44 -0.49 0.10
## C3 13 145 4.57 1.18 5 4.65 1.48 1 6 5 -0.53 -0.30 0.10
## C 14 145 13.60 3.25 14 13.78 2.97 3 18 15 -0.52 -0.13 0.27model <- lm(dataregresisederhana)
res <- resid(model)
plot(fitted(model), res)
abline(0,0)
qqnorm(res)
qqline(res)
plot(density(res))
model##
## Call:
## lm(formula = dataregresisederhana)
##
## Coefficients:
## (Intercept) A2 A3 A4 A5 A
## 3.540e-15 -1.000e+00 -1.000e+00 -1.000e+00 -1.000e+00 1.000e+00
## B1 B2 B3 B C1 C2
## -1.586e-17 1.110e-16 -2.471e-16 NA -6.232e-16 4.496e-17
## C3 C
## 3.549e-16 NAnames(model)## [1] "coefficients" "residuals" "effects" "rank"
## [5] "fitted.values" "assign" "qr" "df.residual"
## [9] "xlevels" "call" "terms" "model"plot(model$model)
model$coef## (Intercept) A2 A3 A4 A5
## 3.540442e-15 -1.000000e+00 -1.000000e+00 -1.000000e+00 -1.000000e+00
## A B1 B2 B3 B
## 1.000000e+00 -1.586419e-17 1.110097e-16 -2.470830e-16 NA
## C1 C2 C3 C
## -6.231552e-16 4.496287e-17 3.548751e-16 NAattributes(model)## $names
## [1] "coefficients" "residuals" "effects" "rank"
## [5] "fitted.values" "assign" "qr" "df.residual"
## [9] "xlevels" "call" "terms" "model"
##
## $class
## [1] "lm"round(summary(model)$coef, 3)## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0 0 1.780000e+00 0.077
## A2 -1 0 -1.127483e+15 0.000
## A3 -1 0 -1.299211e+15 0.000
## A4 -1 0 -1.410790e+15 0.000
## A5 -1 0 -1.576958e+15 0.000
## A 1 0 2.060108e+15 0.000
## B1 0 0 -2.500000e-02 0.980
## B2 0 0 1.730000e-01 0.863
## B3 0 0 -3.940000e-01 0.694
## C1 0 0 -9.950000e-01 0.322
## C2 0 0 6.300000e-02 0.950
## C3 0 0 5.000000e-01 0.618crime.lm.coef <- round(summary(model)$coef, 3)
class(crime.lm.coef)## [1] "matrix" "array"attributes(crime.lm.coef)## $dim
## [1] 12 4
##
## $dimnames
## $dimnames[[1]]
## [1] "(Intercept)" "A2" "A3" "A4" "A5"
## [6] "A" "B1" "B2" "B3" "C1"
## [11] "C2" "C3"
##
## $dimnames[[2]]
## [1] "Estimate" "Std. Error" "t value" "Pr(>|t|)"plot(model)
diamonds.lm <- lm(A ~ A1 + A2 + A3 + A4 + A5, data = dataregresisederhana)
plot(diamonds.lm)
