turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

Find a Community

- Home
- /
- SAS Programming
- /
- SAS Procedures
- /
- Predictive Model based on Logistic Regression Mode...

Topic Options

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

07-29-2017 05:56 PM

Hello All,

Need small help!

I am new to SAS and do not have SAS software. I need to run Logistic regression on the below data sets. Having variables

**Customer account , Credit Rating, Annual Income, & Net Worth.**

I need to predict the probabality of customer paying the loan amount.

Accepted Solutions

Solution

07-29-2017
07:31 PM

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

Posted in reply to mnkjoshi5

07-29-2017 07:05 PM - edited 07-29-2017 07:06 PM

SAS is available for free if you're a student and using it for non commerical purposes. Education/research is allowed.

https://www.sas.com/en_sg/learn/analytics-u.html

You can also access a cloud version if you want via SAS Academics on Demand.

mnkjoshi5 wrote:

Hello All,

Need small help!

I am new to SAS and do not have SAS software. I need to run Logistic regression on the below data sets. Having variables

Customer account , Credit Rating, Annual Income, & Net Worth.I need to predict the probabality of customer paying the loan amount.

All Replies

Solution

07-29-2017
07:31 PM

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

Posted in reply to mnkjoshi5

07-29-2017 07:05 PM - edited 07-29-2017 07:06 PM

SAS is available for free if you're a student and using it for non commerical purposes. Education/research is allowed.

https://www.sas.com/en_sg/learn/analytics-u.html

You can also access a cloud version if you want via SAS Academics on Demand.

mnkjoshi5 wrote:

Hello All,

Need small help!

I am new to SAS and do not have SAS software. I need to run Logistic regression on the below data sets. Having variables

Customer account , Credit Rating, Annual Income, & Net Worth.I need to predict the probabality of customer paying the loan amount.

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

Posted in reply to mnkjoshi5

07-29-2017 07:07 PM

Also, you don't have enough information to build a logistic regression model here. You need to have a 0/1 outcome for logistic regression and there's no variable indicated in your dataset that would work.

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

Posted in reply to Reeza

07-29-2017 07:49 PM

Hi Reeza,

Thanks a lot for your guidance and your reply. I have updated my Excel file. Here using the independent variables such as income, wealth and credit rating ,and age ... i need to identify the probablity that the person was miss sold PPI with the loan or not. 1 means customer is telling truth and it was missold and 0 means it was not. It is hypothetical data for learning purpose.

Thanks & Regards

Mayank

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

Posted in reply to mnkjoshi5

07-29-2017 08:19 PM

I don't have time to work through something like that right now, but I highly suggest reading both the SAS documentation examples and the UCLA example.

Both have the source data available and you can follow along with their output. Additionally, the SAS course on how to do statistics with SAS covers logistic regression and is free here: support.sas.com/training/tutorial

UCLA link:

https://stats.idre.ucla.edu/sas/dae/logit-regression/

SAS Documentation:

Note that I've linked to a specific example in the SAS Logistic Regression but you can check the remaining examples if desired.