If I have the simple linear model: $y=\alpha+\beta x+\epsilon$, and I know that $\hat{\alpha}= \hat{\overline{y}}-\hat{\beta}\hat{\overline{x}}$.
Then my estimate og the mean is actually: $\hat{\overline{x}}=\frac{\hat{\overline{y}}-\hat{\alpha}}{\hat{\beta}}$
I'm trying to do this in R, with the lm(), but I don't know if this is correct.
Call:
lm(formula = ult ~ vale)
Residuals:
Min 1Q Median 3Q Max
-278701 -34922 -13235 21227 940124
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 4.834e+04 7.337e+02 65.89 <2e-16 ***
vale 2.307e-04 5.874e-06 39.27 <2e-16 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 64480 on 13065 degrees of freedom
Multiple R-squared: 0.1056, Adjusted R-squared: 0.1055
F-statistic: 1542 on 1 and 13065 DF, p-value: < 2.2e-16
