turn on suggestions

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

Showing results for

- JMP User Community
- :
- Discussions
- :
- Discussions
- :
- Re: goodness of fit - include in a script

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
- Permalink
- Email to a Friend
- Report Inappropriate Content

Nov 13, 2017 6:23 AM
(789 views)

Dear all,

I'm triyng to add a goodness of fit after a distribution, using a script. There is a loop. The analysis is performed for n columns.

this is the part of the code:

disti = dt << Distribution( stack( 0 ), Continuous Distribution( Column( listName[i] )), Normal Quantile Plot( 1 ), Fit Distribution( Normal(Goodness of Fit( 1 ) )), Capability Analysis( 1 ), Invisible( 1 ) );

But no goodness of fit appears... and I don't konw why..

Do you have an idea?

What does it mean the "1" parameter of this function?

Thank you

Maïna

Solved! Go to Solution.

1 ACCEPTED SOLUTION

Accepted Solutions

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

Nov 13, 2017 6:36 AM
(1136 views)

Solution

I have expanded your script slightly, to make it a functioning script. Your code works well using the Semiconductor Capability data table. I suggest that you look at the makeup of your data or the list, "listName".

```
Names Default To Here( 1 );
dt = Open( "$SAMPLE_DATA\semiconductor capability.jmp" );
listName = dt << get column names( numeric, continuous );
For( i = 1, i <= 2, i++,
disti = dt << Distribution(
stack( 0 ),
Continuous Distribution( Column( listName[i] ) ),
Normal Quantile Plot( 1 ),
Fit Distribution( Normal( Goodness of Fit( 1 ) ) ),
Capability Analysis( 1 ),
Invisible( 1 )
)
);
```

Jim

8 REPLIES

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

Nov 13, 2017 6:36 AM
(1137 views)

I have expanded your script slightly, to make it a functioning script. Your code works well using the Semiconductor Capability data table. I suggest that you look at the makeup of your data or the list, "listName".

```
Names Default To Here( 1 );
dt = Open( "$SAMPLE_DATA\semiconductor capability.jmp" );
listName = dt << get column names( numeric, continuous );
For( i = 1, i <= 2, i++,
disti = dt << Distribution(
stack( 0 ),
Continuous Distribution( Column( listName[i] ) ),
Normal Quantile Plot( 1 ),
Fit Distribution( Normal( Goodness of Fit( 1 ) ) ),
Capability Analysis( 1 ),
Invisible( 1 )
)
);
```

Jim

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

Nov 13, 2017 6:41 AM
(781 views)

Thank you Jim,

I have already do this loop :) IThe script is bigger !

My first script was like that:

The distribution appears, the capability analysis too, but not the goodness of fit test...

I don't understand why ;(

```
disti = dt << Distribution(
stack( 0 ),
Continuous Distribution( Column( listName[i] ) ),
Normal Quantile Plot( 1 ),
Capability Analysis( 1 ),
Invisible( 1 )
```

But I want to add a goodness of fit analysis below the histogram of the distribution.

Tks

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

Nov 13, 2017 6:53 AM
(779 views)

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

Nov 13, 2017 6:58 AM
(774 views)

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

Nov 13, 2017 7:18 AM
(764 views)

I used your script, and just attached a different data table, so that is why I suggested that you need to look elsewhere.

Jim

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

Nov 13, 2017 7:32 AM
(758 views)

Or do I have no place to display the result?

Would that be possible?

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

Nov 13, 2017 7:38 AM
(754 views)

Are the columns you are analyzing of Modeling Type Continuous? If they are Ordinal or Nominal, they will not provide a goodness of fit

Jim

Highlighted

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

Nov 13, 2017 7:43 AM
(752 views)