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
- /
- What kind of transformation procedure need to appl...

- 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

09-01-2016 03:17 AM

Hi All ~ I'm dealing with a contienous variable whose distrubution looks as shown in the two figures. Which tranformation procedure would you recommnend for this kind of distrubution?

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

09-01-2016 04:46 AM

Why are you transforming?

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

09-01-2016 04:50 AM

I'm using this as the dependent variable for my GLM analysis ~ which assumes the normal distrubution of outcome!

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

09-01-2016 05:13 AM

mantubiradar19 wrote:

Logistic regression falls under GLM and a binary response is definitely not normal.

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

09-01-2016 06:50 AM

Your data is right bias. Try Log Normal distribution.

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

09-01-2016 09:27 AM

Box cox transformation using proc transreg may be an option

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

09-12-2016 01:09 AM

Can you please educate me more about this transformation with an example? Thanks

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

09-12-2016 01:09 AM

The distrubution shown here is the log tranformed values of orifinal values!

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

09-01-2016 12:47 PM

How did you create that panel of histogram + box plot + Q-Q plot? Is that something you wrote with GTL or was it generated by a SAS procedure?

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

09-04-2016 05:03 PM

@Rick_SAS that looks like the output from proc univariate.

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

09-12-2016 01:10 AM

This is the output from PROC UNIVARIATE!

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

09-02-2016 02:43 PM

That is an interesting plot. Even the log10 values show an extreme skew. Is there a possibility that these are maximum values for something? If so, you may want to look at a Weibull distribution or some other generalized extreme value distribution. a ln(ln (x)) transformation might be useful. I don't know if TRANSREG will hande this, though.

Steve Denham

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

09-12-2016 01:11 AM

I tried the ln(ln(x)) ~ The distribution almost looks the same with the reduced SD!

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

09-12-2016 01:13 AM

Here are the log(x) and log(log(x)) distrubution!

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

09-12-2016 02:02 AM

It's hard to see what your doing now, since the forum doesn't sort the responses. So no way to tell which reply goes with which post. In the future please just do one response. This isn't your fault - limitation of the forum.

Did you post your original distribution? Also, what is the variable, in laymans terms. Context can help with deciding what type of transformation to use, and there are certain standard transformation in diff industries.