0

I'm trying to match a stepwise DFA output from SPSS (which gives a % classification) in R, which I believe uses glm or lda, but it seems so convoluted.

Basically, I want to predict who failed an exam (dataframe=examscores, passedfail is the classification DV) from about 20 vars in the DF, lets call them A, B, C, etc.

Any suggestions would be appreciated.

passedfail        A         B    C       D         E     F     G
    0             1         3     1      5         6     1      6
    0             1         2     6      1         1     1      1
    1             4         6     1      3         5     5      6

So, as per the first comment, I want to predict who will pass/fail using the DV passedfail which has two levels, 0 and 1.

I want to predict this from 20 score variables which are too long to type here, so just use A, B, C, etc. All these 20 variables contain numeric scores.

As I stated, I am trying to match a stepwise DFA output from SPSS in R, but it seems very convoluted.

user15950867
  • 33
  • 5
  • 1
    Hi there and welcome to SO. Please give us some context to your question. Take a look at [How to Ask](https://stackoverflow.com/help/how-to-ask) for hints. It's a good start to give some data, make a [great reproducible example](https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example) and give an example of your desired output. – Martin Gal Jul 25 '21 at 21:42
  • I want to predict who will pass/fail using the DV passedfail which has two levels, 0 and 1. I want to predict this from 20 score variables which are too long to type here, so just use A, B, C, etc. All these 20 variables contain numeric scores. All the vars are in the DF examscores. As I stated, I am trying to match a stepwise DFA output from SPSS in R, but it seems very convoluted. I can't give the actual data as it is real. – user15950867 Jul 25 '21 at 21:53

0 Answers0