Multiple Regression - imported data and NA values error

[emmikays]

Hi all,

I'm brand new to R, attempting to use it for a paper for admission to J-school. I have a data set on city budgets with several different variables, a few of which are blank when I couldn't find reported numbers or no such numbers existed. Some variables are dollar amounts, some are numbers, some are percents. My code is:

mydata <- read.csv('C:\Users\Me\Documents\Research.csv', header = TRUE)
model <- lm(Y ~ X1 + X2 + X3 + X4 + X5 + X6 + X7, data = mydata, na.action = na.omit)

And my error message relates to the NA values, which I just want the model to ignore:

Error in lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
NA/NaN/Inf in 'y'
In addition: Warning message:
In storage.mode(v) <- "double" : NAs introduced by coercion

Cool, okay so turns out all my data is character instead of numeric values, and google searching the issue tells me I need to convert them all. So I used as.numeric as such:

mydata$X1 <- as.numeric(mydata$X1)

And then the values in my table display as all NA instead of numbers?? What am I missing?

[FJCC]

Please post the result of

dput(head(mydata))

I suspect you have things like thousands separators and currency signs in the data but seeing the actual content of a few rows will allow specific advice about how to clean up the data.

[emmikays]

That was it! I went back to the file and cleaned it up, and re-imported it. All my data is now int and num values and my regression works!! Thank you for the tip!