Regression on data frame does not work in R

Question

I have a data frame called df with 2 variables and 71 observations. The variables are dead and duration. Now I want to do a regression with lm(formula = dead ~ ., data = df). The dependend variable is dead, but I get this error

Error in model.frame.default(formula = dead ~ ., data = df, drop.unused.levels = TRUE) : object is not a matrix

I have tried to convert the data frame to a matrix and then do the lm(), but then i get this error

Error in model.frame.default(formula = dead ~ ., data = df2, drop.unused.levels = TRUE) : 'data' must be a data.frame, not a matrix or an array

dput(df)
structure(list(DEAD = c(26L, 229L, 43L, 21L, 19L, 2L, 4L, 10L, 
7L, 2L, 4L, 0L, 0L, 0L, 32L, 1L, 0L, 0L, 2L, 2L, 2L, 64L, 25L, 
7L, 6L, 0L, 98L, 95L, 275L, 2L, 3L, 2L, 0L, 340L, 0L, 200L, 15L, 
0L, 3L, 12L, 3L, 283L, 12L, 0L, 147L, 0L, 4L, 11L, 26L, 30L, 
0L, 34L, 0L, 557L, 12L, 0L, 0L, 99L, 1L, 78L, 18L, 49L, 3L, 3L, 
31L, 0L, 54L, 7L, 24L, 0L, 0L), DAYS = c(5, 19, 2, 15, 3, 13, 
2, 5, 8, 4, 6, 2, 2, 2, 16, 2, 9, 2, 2, 2, 2, 12, 3, 20, 2, 2, 
9, 5, 13, 2, 2, 2, 4, 13, 4, 45, 28, 2, 2, 2, 2, 4, 2, 3, 5, 
10, 7, 2, 4, 6, 4, 9, 4, 33, 2, 3, 2, 3, 4, 19, 6, 3, 3, 3, 2, 
5, 9, 4, 4, 3, 2)), .Names = c("DEAD", "DAYS"), row.names = 0:70, class = "data.frame")

If you data is saved as an actual data.frame there is no reason why it shouldn't work. For example: `a <- c(1,2,3,4,5) b <- c(1,2,3,4,5) df <- as.data.frame(cbind(a,b)) lm(b ~., data = df)` Can you please output your data or provide some reproducible example? — An economist, May 12 '16 at 12:17
http://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example — Bulat, May 12 '16 at 12:27
(head(df) DEAD DAYS 0 26 5 1 229 19 2 43 2 3 21 15 4 19 3 5 2 13) > This are the first observations. Do you need more? I am quite new in R and stackoverflow, so I do not have many experience. — EteB, May 12 '16 at 12:29
@EteB : Instead of `head(df)`, run `dput(df)` and post the output here — vasanthcullen, May 12 '16 at 12:39
@EteB it does not work because you use `dead` instead of `DEAD`. So this should work: `lm(formula = DEAD ~ ., data = df)` — An economist, May 12 '16 at 12:51

score 2 · Accepted Answer · answered May 12 '16 at 12:54

Answer is really simple you used wrong dependent variable name dead instead of DEAD in your formula. Therefore, next time just remember to insert correct variable names and it should work just fine.

Here is your regression, with correct dependent variable name.

lm(formula = DEAD ~ ., data = df)

Regression on data frame does not work in R

1 Answers1