-3

Does anybody know of a way to create a new data frame that contains the information of specific columns from a master data frame that has multiple columns? I have a master dataframe and I'm trying to run various tests (regression, ANOVA...etc.,) on specific columns in the data frame. Any suggestions would be greatly appreciated.

Roman Luštrik
  • 69,533
  • 24
  • 154
  • 197
almega
  • 1
  • 2
  • Please check this [URL](http://stackoverflow.com/help) it will be useful to lift your content quality up – Willie Cheng Jun 15 '16 at 02:05
  • Welcome to SO! Your question is unfortunately unlikely to be answered in its current state, as @willie implied. The question is very vague, and lacking any context or examples, it sounds like you are asking all of us to "teach you R". I strongly suggest you read [SO help on minimal/complete questions](http://stackoverflow.com/help/mcve) as well as a great answer on [reproducible examples](http://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example). – r2evans Jun 15 '16 at 03:26
  • Why would you need to create a new data frame for running linear models in the first place? Here's how you run ANOVA with iris dataset: `aov(Petal.Length ~ Species, data=iris)`. Here's how you run a linear regression: `lm(Petal.Length ~ Sepal.Length, data=iris)`. Refer to http://www.statmethods.net/stats/regression.html to understand the linear model syntax for R. – Adam Quek Jun 15 '16 at 04:39

1 Answers1

1

if you want to choose columns 3,12 and 15 from the old DF:

newDF <- oldDF[,c(3,12,15)]

if you want to remove columns 3,12 and 15 from the old DF:

newDF <- oldDF[,-c(3,12,15)]
Zahiro Mor
  • 1,708
  • 1
  • 16
  • 30