# Input the data.
> x <- c(10,14,2,10)
> y <- c(82,94,50,70)

# The "lm" command does simple linear regression. The "y~x"
# argument specifies the model "yhat = beta0hat + beta1hat x".
# We store the regression results in the object "study.results".
> study.results <- lm(y~x)

# Lets check out the results.
> summary(study.results)

Call:
lm(formula = y ~ x)

Residuals:
     1      2      3      4 
 4.421  2.105  1.053 -7.579 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)  
(Intercept)  41.7895     7.3684   5.671   0.0297
x             3.5789     0.7368   4.857   0.0399 

Residual standard error: 6.424 on 2 degrees of freedom
Multiple R-squared:  0.9219,	Adjusted R-squared:  0.8828 
F-statistic: 23.59 on 1 and 2 DF,  p-value: 0.03987

# Analysis of Variance (ANOVA) table summarizing regression.
> anova(study.results)
Analysis of Variance Table

Response: y
          Df Sum Sq Mean Sq F value  Pr(>F)  
x          1 973.47  973.47  23.592 0.03987
Residuals  2  82.53   41.26                  

# We want to get predictions and confidence intervals at
# x=4 and 11. The "fit" column specifies the yhat values,
# and the "lwr" and "upr" specify the CI.
> predict(study.results, list(x=c(4,11)), interval="confidence", se.fit=TRUE)
$fit
       fit      lwr      upr
1 56.10526 35.07537 77.13516
2 81.15789 65.95331 96.36248
$se.fit
[1] 4.89 3.53