> set.seed(1)
> training_pred <- data.frame(rbind(c(1,0),c(1,0),c(0,0),c(0,0),c(0,1),c(0,1)))
> colnames(training_pred) <- paste0("V",1:2)
> training_obs <- as.vector(cbind(1,as.matrix(training_pred))%*%c(1,-.7,-.8)+
+ rnorm(nrow(training_pred),0,0.2))
> training_obs
[1] 0.17470924 0.33672866 0.83287428 1.31905616 0.26590155 0.03590632

> model <- lm(training_obs~V1+V2,training_pred)
> new_pred <- data.frame(matrix(c(1,1),nrow=1,dimnames=list(NULL,paste0("V",1:2))))
> predict(model,newdata=new_pred)
         1
-0.6693423

> summary(training_pred)
       V1               V2
 Min.   :0.0000   Min.   :0.0000
 1st Qu.:0.0000   1st Qu.:0.0000
 Median :0.0000   Median :0.0000
 Mean   :0.3333   Mean   :0.3333
 3rd Qu.:0.7500   3rd Qu.:0.7500
 Max.   :1.0000   Max.   :1.0000
> summary(new_pred)
       V1          V2
 Min.   :1   Min.   :1
 1st Qu.:1   1st Qu.:1
 Median :1   Median :1
 Mean   :1   Mean   :1
 3rd Qu.:1   3rd Qu.:1
 Max.   :1   Max.   :1

> model

Call:
lm(formula = training_obs ~ V1 + V2, data = training_pred)

Coefficients:
(Intercept)           V1           V2
     1.0760      -0.8202      -0.9251