Chunk : Tempat saya menulis perintah / syntax / function : ctrl+alt+I

ini ada

11^4
## [1] 14641

Read data

data("PlantGrowth")
PlantGrowth
##    weight group
## 1    4.17  ctrl
## 2    5.58  ctrl
## 3    5.18  ctrl
## 4    6.11  ctrl
## 5    4.50  ctrl
## 6    4.61  ctrl
## 7    5.17  ctrl
## 8    4.53  ctrl
## 9    5.33  ctrl
## 10   5.14  ctrl
## 11   4.81  trt1
## 12   4.17  trt1
## 13   4.41  trt1
## 14   3.59  trt1
## 15   5.87  trt1
## 16   3.83  trt1
## 17   6.03  trt1
## 18   4.89  trt1
## 19   4.32  trt1
## 20   4.69  trt1
## 21   6.31  trt2
## 22   5.12  trt2
## 23   5.54  trt2
## 24   5.50  trt2
## 25   5.37  trt2
## 26   5.29  trt2
## 27   4.92  trt2
## 28   6.15  trt2
## 29   5.80  trt2
## 30   5.26  trt2

struktur data

str(PlantGrowth)
## 'data.frame':    30 obs. of  2 variables:
##  $ weight: num  4.17 5.58 5.18 6.11 4.5 4.61 5.17 4.53 5.33 5.14 ...
##  $ group : Factor w/ 3 levels "ctrl","trt1",..: 1 1 1 1 1 1 1 1 1 1 ...

Statistika Deskriptif

mean

mean (PlantGrowth$weight)
## [1] 5.073
summary(PlantGrowth)
##      weight       group   
##  Min.   :3.590   ctrl:10  
##  1st Qu.:4.550   trt1:10  
##  Median :5.155   trt2:10  
##  Mean   :5.073            
##  3rd Qu.:5.530            
##  Max.   :6.310
hist(PlantGrowth$weight)

Data 2 (Regresi)

membaca data dari external

data = read.csv("C:/Users/Hafizah Ilma/OneDrive - apps.ipb.ac.id/UNIVERSITAS MATARAM/WORKSHOP RSTUDIO/study_hours_exam_scores.csv", sep = ";")
head(data)
##   Jam_Belajar Nilai_Ujian
## 1       10.99       86.90
## 2        9.72       86.79
## 3       11.30       93.47
## 4       13.05       98.17
## 5        9.53       87.32
## 6        9.53       90.15
str(data)
## 'data.frame':    100 obs. of  2 variables:
##  $ Jam_Belajar: num  10.99 9.72 11.3 13.05 9.53 ...
##  $ Nilai_Ujian: num  86.9 86.8 93.5 98.2 87.3 ...

korelasi

melihat kekuatan/keeratan hubungan 2 variabel

cor(data$Jam_Belajar, data$Nilai_Ujian)
## [1] 0.8137691

korelasi nilai dan belajar sebersar 81.37% cukup kuat dan bersifat positif

plot(data$Jam_Belajar, data$Nilai_Ujian)
abline(lm(Nilai_Ujian ~ Jam_Belajar, data))

## Regresi Linear Sederhana

y = dipengaruhi = nilai ujian = tak bebas = dependen = target x = mempengaruhi = jam belajar = bebas = independen = prediktor

apakah jam belajar mempengaruhi nilai ujian

model = lm(Nilai_Ujian ~ Jam_Belajar, data)
summary(model)
## 
## Call:
## lm(formula = Nilai_Ujian ~ Jam_Belajar, data = data)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -9.9517 -3.9701  0.2021  2.8410 12.1532 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  53.6281     2.6156   20.50   <2e-16 ***
## Jam_Belajar   3.6410     0.2627   13.86   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 4.748 on 98 degrees of freedom
## Multiple R-squared:  0.6622, Adjusted R-squared:  0.6588 
## F-statistic: 192.1 on 1 and 98 DF,  p-value: < 2.2e-16