Calculation of Prediction Interval

The general formula for prediction interval is,

Sample estimate ± (t-multiplier × standard error)

The formula is

where:

 y^h is the "fitted value" or "predicted value" of the response when the predictor is xh

 t(α/2,n−2) is the "t-multiplier." Note again that the t-multiplier has n-2 (not n-1)

degrees of freedom, because the prediction interval uses the mean square error (MSE) whose

denominator is n-2.

Source : https://onlinecourses.science.psu.edu