How to evaluate Regression Model Accuracy using Caret

Question

I am training a regression model using caret in R but I am having a hard time understanding how to validate the model. I am using postResample and it is outputting and RMSE and an R squared. I am honestly just confused as to what this function is doing and how it is getting these numbers. Is this an accurate way to validate a regression model or are there better ways? Below is code similar to what I am doing.

fitControl <- trainControl(## 10-fold CV
                           method = "repeatedcv",
                           number = 10,
                           ## repeated ten times
                           repeats = 3)

car_t_index <- createDataPartition(mtcars$mpg, p = .8, list = FALSE, times = 1)
car_train <- mtcars[car_t_index,]
car_test <- mtcars[-car_t_index,]


model <- train(mpg ~ ., data = car_train,method = "rf", trControl = fitControl)

pred <- predict(model,car_test)

model
pred
postResample(pred = pred, obs = car_test$mpg)

```

Answer 1

The question is pretty vague, both algorithms operate differently, the results of training for both algorithms for RMSE,Rsquared and MAE.

library(tidyverse)
library(caret)

fitControl <- trainControl(## 10-fold CV
  method = "repeatedcv",
  number = 10,
  ## repeated ten times
  repeats = 3)

car_t_index <- createDataPartition(mtcars$mpg, p = .8, list = FALSE, times = 1)
car_train <- mtcars[car_t_index,]
car_test <- mtcars[-car_t_index,]


model <- train(mpg ~ ., data = car_train,method = "rf", trControl = fitControl)
model2 <- train(mpg ~ ., data = car_train,method = "lm", trControl = fitControl)


resamp <- resamples(list(Random_Forest = model, Linear_model = model2))
summary(resamp)

I hope this helps