Fit a linear model in Mathematica ?

Questions
1

Hi everyone.I need someone to help me derive the wolfram mathematica from this.

salary=c(1000,12000,12500,14000,15000,17000,25000,30000,50000)
experience=c(2,3,4,6,8,10,12,14,15)
lm(salary~experience)

Call:
lm(formula = salary ~ experience)

Coefficients:
(Intercept) experience
-1693 2591

summary(lm(salary~experience))

Call:
lm(formula = salary ~ experience)

Residuals:
Min 1Q Median 3Q Max
-7217 -4399 -2489 3829 12828

Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1692.8 4728.5 -0.358 0.73089
experience 2591.0 503.4 5.147 0.00133 **

Signif. codes: 0 ‘’ 0.001 ‘’ 0.01 ‘’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 6858 on 7 degrees of freedom
Multiple R-squared: 0.791, Adjusted R-squared: 0.7611
F-statistic: 26.49 on 1 and 7 DF, p-value: 0.001329

#y=2591x-1693+u
confint(lm(salary~experience,level=95))
2.5 % 97.5 %
(Intercept) -12873.931 9488.302
experience 1400.609 3781.427
plot(lm(salary~experience))
Hit to see next plot:
Hit to see next plot:
Hit to see next plot:
Hit to see next plot:
plot(salary,experience)

2

I’m assuming that your question is “How do I translate R code that fits a linear model into Mathematica?” If so, the LinearModelFit function is what you need.

3

Thanks for your reply.my professor send a file in java and clearly I dont really understand how to go about.I have really tried but I have not managed.

4

The following will likely give you most of what you show above. The inline documentation has additional options.

salary = {1000, 12000, 12500, 14000, 15000, 17000, 25000, 30000, 50000};
experience = {2, 3, 4, 6, 8, 10, 12, 14, 15};
data = Table[{experience[[i]], salary[[i]]}, {i, Length[salary]}]
lm = LinearModelFit[data, x, x]
lm[{"ParameterTable", "RSquared", "AdjustedRSquared", "ANOVATable"}]

with output

regression.png
regression.png495×205 4.54 KB