extract predicted values from Partial least square regression in R

Question

I have following:

library(pls)
pcr(price ~ X, 6, data=cars, validation="CV")

it works, but because I have a small dataset, I cannot divide in into training and test and therefore I want to perform cross-validation and then extract predicted data for AUC and accuracy. But I could not find how I can extract the predicted data.Which parameter is it?

Sorry, it should be per and it gives a lot as an output for help(pcr). What should I search for? — Alina, Apr 28 '15 at 16:45
Where does `price` come from? I don't see that in the built-in `cars` data. — Christopher Bottoms, Apr 28 '15 at 17:00
After `?pcr` look for information under "Values" to find out what the function returns. It will suggest you look at `?mvrCv` for more information on the `validation` result. — Christopher Bottoms, Apr 28 '15 at 17:15
@AlexA. Thanks! You explained that better than I would have. — Christopher Bottoms, Apr 28 '15 at 17:23
@Tonja I also recommend this [explanation of how to find help using R](http://stackoverflow.com/questions/15289995/how-to-get-help-in-r/15290370#15290370). — Christopher Bottoms, Apr 28 '15 at 17:30

Alex A. · Accepted Answer · 2015-04-28T17:27:47.743

When you fit a cross-validated principal component regression model with pcr() and the validation= argument, one of the components of the output list is called validation. This contains the results of the cross validation. This in turn is a list and it has a component called pred, which contains the cross-validated predictions.

An example adapted from example("pcr"):

sens.pcr <- pcr(sensory ~ chemical, data = oliveoil, validation = "CV")

sens.pcr$validation$pred

As an aside, it's generally a good idea to set your random seed immediately prior to performing cross validation to ensure reproducibility of your results.

extract predicted values from Partial least square regression in R

1 Answers1