## Plot Graph for 2 group Linear Discriminant Function

Solved
Occasional Contributor
Posts: 5

# Plot Graph for 2 group Linear Discriminant Function

Hi,

I've run a discriminant analysis for a binary category group & the code I used is the following:

proc discrim data=discrim;

class group;

var var1 var2 var3 var4 var5;

run;

Now, I want to plot the each groups discriminant scores across the 1st linear discriminant function. Can anybody please tell me the code to do it?

Regards,

Ari14

Accepted Solutions
Solution
‎08-24-2011 03:50 AM
Super User
Posts: 10,787

## Re: Plot Graph for 2 group Linear Discriminant Function

You can use the following code to get linearDisdinctFunction ,then use proc gplot

```ods output LinearDiscFunc=line;
proc discrim data=sashelp.iris method=normal pool=yes;
class Species;
var PetalWidth;
title2 ’Using Normal Density Estimates with Equal Variance’;
run;

```

Ksharp

All Replies
Posts: 1,318

## Plot Graph for 2 group Linear Discriminant Function

Not really certain what it is you are attempting to accomplish here but you might find this helpful:

ods output LinearDiscFunc=discrim_results;

proc discrim data=discrim;

class=group;

var var1-var5;

run;

Occasional Contributor
Posts: 5

## Re: Plot Graph for 2 group Linear Discriminant Function

Hi,

I R software, one can visualy examine how well the discriminant function demarcate the 2 groups. Please find the snap below. But in SAS I just can't able to do it. I was just looking for SAS code to get a plot like the one below.

Solution
‎08-24-2011 03:50 AM
Super User
Posts: 10,787

## Re: Plot Graph for 2 group Linear Discriminant Function

You can use the following code to get linearDisdinctFunction ,then use proc gplot

```ods output LinearDiscFunc=line;
proc discrim data=sashelp.iris method=normal pool=yes;
class Species;
var PetalWidth;
title2 ’Using Normal Density Estimates with Equal Variance’;
run;

```

Ksharp

Occasional Contributor
Posts: 5

## Re: Plot Graph for 2 group Linear Discriminant Function

Thanks Ksharp!

🔒 This topic is solved and locked.