Using linear regression to predict unknown values

With a fitted regression model, we can apply the model to predict unknown values. For regression models, we can express the precision of prediction with a prediction interval and a confidence interval. In the following recipe, we will introduce how to predict unknown values under these two measurements.

Getting ready

You need to have completed the previous recipe by computing the linear model of the x and y1 variables from the quartet dataset.

How to do it...

Perform the following steps to predict values with linear regression:

1. Fit a linear model with the x and y1 variables:

        > lmfit = lm(y1~x, Quartet)  

2. Assign values to be predicted into newdata:

        > newdata = data.frame(x = c(3,6,15))

3. Compute the prediction result using the confidence interval with level set as 0.95:

        > predict(lmfit, newdata, interval="confidence", level=0.95)
        Output:
            fit lwr upr
        1 4.500364 2.691375 6.309352
        2 6.000636...