Using R studio. a. I need to interpret the Beta Coefficients. I know that Salary
ID: 3337992 • Letter: U
Question
Using R studio.
a. I need to interpret the Beta Coefficients. I know that Salary will increase 1 by experience. But I don't know how Gender fits in there and I'm not sure how to explain the data in the chart
b. What is the value of coefficient of the determination (R-square) for this model, and what does it mean?
summary(ArtsyMLR)$r.squared
[1] 0.4660372
Now would this R squared be large or small?
Code I ran:
ArtsyMLR = lm(Salary~Experience+Gender, data=Artsy)
ArtsyMLR
summary(ArtsyMLR)
summary(ArtsyMLR)$r.squared
anova(ArtsyMLR)
R studio gave me this:
Explanation / Answer
Cool!. I will explain you the interpretation and the Rsquare, but you would also need to check the data in 'Artsy'
a. When you regress Salary against independent variables Experience, Gender you get beta coefficients for each of them: 10.482 and 225.058 respectively.
It means that: for an additional 1 year of 'Experience' salary increases by 10.482.
**Please beware when reporting units of Salary, as I beleive them to be in thousand and not in only 10s
I don't know how Gender means, but if you peek into the data, in most probability it should be a dichotomous variable i.e. 1 for male, 0 for female. If it is so, then a coefficient of 225.058 to this variable can be interprested as ' 'if it were a Male i.e. Gender = 1, then he would earn $225.058 salary more'.
b. The R-square is at .466. It means that 46.6% of variance in Salary is being explained by our independent variables ( gender and experience) in the regression. You need to have more relevant variables to explain Salary.
The higher the Rsquare the better is the predictive power of the model. A .446 is a low Rsquare value, indicating
not-so-good predictive power of the regression equation.
Related Questions
drjack9650@gmail.com
Navigate
Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.