kk匡的日記&學習筆記

/*
Simple linear regression 简单回归分析
假设花红是3250、经过预测月薪将是10060.22元。
图中红色就是预期花红和月薪的关系。
*/

userName <- c("Lam Wei Wei", "Zheng Da Shi", "Lin Da You", "Fei Gu Man", "Chen Kuang", "Wong wei yun")
salary <- c(8500, 9800, 12500, 15000, 8700, 7500)
jobPosition <- c("Staff", "Manger", "BOSS", "CEO", "Staff", "Staff")
bonus <- c(2300, 1350, 3285, 1035, 3285, 1035)

#取得salary和bonus的图表
result <- data.frame(salary, bonus)

#用正态分布计算salary和bonus的方差
totalAmount.lm = lm(salary ~ bonus, data=result)

#系数
coeffs = coefficients(totalAmount.lm); 

#bonus是3250的话、salary会是...？
newdata = data.frame(bonus=3250)

#预测
NewSalary <- predict(totalAmount.lm, newdata)

#画图
plot(result, 
main = "Salary & Bonus Regression",
# lm(bonus ~ salary) bonus和salary要调转
abline(lm(bonus ~ salary), col = "red"),
col = "blue",
cex = 1.2,
pch = 16,
xlab = "Salary",
ylab = "Bonus" )

Call:
lm(formula = salary ~ bonus, data = result)

Residuals:
    1     2     3     4     5     6 
-1776  -692  2448  4436 -1352 -3064 

Coefficients:
              Estimate Std. Error t value Pr(>|t|)  
(Intercept) 10798.8760  3032.0350   3.562   0.0236 *
bonus          -0.2273     1.3374  -0.170   0.8733  
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 3183 on 4 degrees of freedom
Multiple R-squared:  0.007168,	Adjusted R-squared:  -0.241 
F-statistic: 0.02888 on 1 and 4 DF,  p-value: 0.8733

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  10060   10060   10060   10060   10060   10060