# Automating predictions from R

Let's say I have the following lagged data frame and am trying to predict income for 9/10 using data from 9/09.

dat = data.frame(main_date=c("09/01/2013","09/02/2013","09/03/2013","09/04/2013","09/05/2013","09/06/2013",
"09/07/2013","09/08/2013","09/09/2013","09/10/2013"),
lag_date=c(NA,"09/01/2013","09/02/2013","09/03/2013","09/04/2013","09/05/2013","09/06/2013",
"09/07/2013","09/08/2013","09/09/2013"),
income=c(rnorm(10)), status=c(rnorm(10)), avg_temp=c(rnorm(10)))
dat

mod = lm(income ~ status + avg_temp, data=dat)
summary(mod)

(-0.00848) + (0.4272*(0.641)) + (-0.651*(-1.274))


I have my data frame and run a linear model. Then I grab estimates and july data points for my two predictors and calculate for Y manually. However, I was wonder if R had a built in process for generating predictions of this nature or could provide insights into finding an "automated" process for performing this task in R.

If I understand your question, what you're looking for is ?predict, or fitted(mod), depending on whether you have july datapoints or not.