price <- c(100, 110, 120, 130, 140, 150, 160, 170, 180, 190)
marketing_cost <- c(20, 25, 22, 30, 35, 40, 42, 45, 50, 55)
stores <- c(50, 52, 55, 58, 60, 62, 65, 67, 70, 72)
income <- c(5000, 5200, 5400, 5600, 5800, 6000, 6200, 6400, 6600, 6800)
sales_volume <- c(200, 220, 210, 230, 240, 250, 260, 270, 280, 290)

# Membuat Data Frame
data <- data.frame(price, marketing_cost, stores, income, sales_volume)
data
##    price marketing_cost stores income sales_volume
## 1    100             20     50   5000          200
## 2    110             25     52   5200          220
## 3    120             22     55   5400          210
## 4    130             30     58   5600          230
## 5    140             35     60   5800          240
## 6    150             40     62   6000          250
## 7    160             42     65   6200          260
## 8    170             45     67   6400          270
## 9    180             50     70   6600          280
## 10   190             55     72   6800          290
# Model Regresi Linear Berganda
model <- lm(sales_volume ~ price + marketing_cost + stores 
+ income, data = data)
# Ringkasan Model
summary(model)
## 
## Call:
## lm(formula = sales_volume ~ price + marketing_cost + stores + 
##     income, data = data)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -3.5778 -1.5081 -0.0229  1.4289  4.4748 
## 
## Coefficients: (1 not defined because of singularities)
##                Estimate Std. Error t value Pr(>|t|)  
## (Intercept)    172.6154    83.1662   2.076   0.0832 .
## price            0.5164     0.9521   0.542   0.6071  
## marketing_cost   1.9689     0.5688   3.462   0.0134 *
## stores          -1.2139     3.4233  -0.355   0.7350  
## income               NA         NA      NA       NA  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 3.059 on 6 degrees of freedom
## Multiple R-squared:  0.9932, Adjusted R-squared:  0.9898 
## F-statistic: 291.8 on 3 and 6 DF,  p-value: 6.882e-07

Visualisasi

# Pair Plot
pairs(data, main = "Scatterplot Matrix", pch = 19)

# Residual Plot
plot(model$residuals, main="Residual Plot", ylab="Residuals"
, xlab="Fitted Values")
abline(h = 0, col="red", lwd=2)

# Data Baru untuk Prediksi
new_data <- data.frame(price=175, marketing_cost=48, stores=68, income=6500)
# Prediksi Volume Penjualan
predicted_sales <- predict(model, newdata = new_data)
print(predicted_sales)
##        1 
## 274.9569