Theory: Consider a linear regression of y on x. It is usually estimated with
which estimation technique (three-letter abbreviation)?
This estimator yields the best linear unbiased estimator (BLUE) under the assumptions
of the Gauss-Markov theorem. Which of the following properties are required for the
errors of the linear regression model under these assumptions?
independent / zero expectation / normally distributed / identically distributed / homoscedastic
Application: Using the data provided in linreg.csv estimate a
linear regression of y on x. What are the estimated parameters?
In terms of significance at 5% level:
x and y are not significantly correlated / y increases significantly with x / y decreases significantly with x
Theory: Linear regression models are typically estimated by ordinary least squares (OLS).
The Gauss-Markov theorem establishes certain optimality properties: Namely, if the errors
have expectation zero, constant variance (homoscedastic), no autocorrelation and the
regressors are exogenous and not linearly dependent, the OLS estimator is the best linear
unbiased estimator (BLUE).
Application: The estimated coefficients along with their significances are reported in the
summary of the fitted regression model, showing that y increases significantly with x (at 5% level).
lm(formula = y ~ x, data = d)
Min 1Q Median 3Q Max
-0.50503 -0.17149 -0.01047 0.13726 0.69840
Estimate Std. Error t value Pr(>|t|)
(Intercept) -0.005094 0.023993 -0.212 0.832
x 0.558063 0.044927 12.421 <2e-16 ***
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.2399 on 98 degrees of freedom
Multiple R-squared: 0.6116, Adjusted R-squared: 0.6076
F-statistic: 154.3 on 1 and 98 DF, p-value: < 2.2e-16
Code: The analysis can be replicated in R using the following code.
d <- read.csv("linreg.csv")
m <- lm(y ~ x, data = d)
plot(y ~ x, data = d)