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

- JMP User Community
- :
- Discussions
- :
- DSD question on Blocking at 4 blocks vs 3 blocks

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

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

DSD question on Blocking at 4 blocks vs 3 blocks

Jul 22, 2020 5:02 PM
(293 views)

Hi,

Designed a DSD experiment with 5 factors in JMP15. __ Can only run 4 conditions at a time__. So added 4 blocks with center runs to estimate quadratic effects. Expected a design with 4 conditions per block and a total of 16 conditions. Instead, block 1 & 2 have 5 conditions, and block 3 & 4 have three conditions. Tried to repeat or play around the setting still cannot get 4 conditions per block. Not feeling comfortable in manually change the block #, which will change the power of the model as well as the correlation map.

Then, I tried using 3 blocks and the design gave 15 conditions == 5 conditions per block. The design looks good to move forward with but I can only run 4 conditions at a time. Is selecting a 4 blocks setting become an issue due to the algorithm of the program? Or I missed something in setting up this design. Greatly appreciate for any suggestion or a round about way to get a DSD design 5 factors, total 16 conditions-- in 4 conditions per block.

Thanks,

Maria

2 REPLIES 2

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: DSD question on Blocking at 4 blocks vs 3 blocks

I suggest you abandon the definitive screening design in this situation. The generator is somewhat inflexible and not appropriate for every screening case.

You can achieve what you want with the flexible custom design. You can add a **Blocking** factor defined as 4 runs per block. You can add all the interactions and all the quadratic terms. That model is the same as implied by the DSD. Select these higher order terms and change their **Estimability** to **If Possible**. Click the red triangle at the top and select **Optimality Criterion > Make Alias Optimal Design**. The DSD is an alias optimal design. I would use the same number of runs as created by the default DSD. That is 21 runs for your 5 factors with blocking.

Here is a script that will launch the Custom Design platform and set it up as I described so that you can try it for yourself.

```
DOE(
Custom Design,
{Add Response( Maximize, "Y", ., ., . ),
Add Factor( Continuous, -1, 1, "X1", 0 ),
Add Factor( Continuous, -1, 1, "X2", 0 ),
Add Factor( Continuous, -1, 1, "X3", 0 ),
Add Factor( Continuous, -1, 1, "X4", 0 ),
Add Factor( Continuous, -1, 1, "X5", 0 ), Add Factor( Blocking, 4, "Block" ),
Set Random Seed( 968796745 ), Number of Starts( 13195 ), Add Term( {1, 0} ),
Add Term( {1, 1} ), Add Term( {2, 1} ), Add Term( {3, 1} ), Add Term( {4, 1} ),
Add Term( {5, 1} ), Add Term( {6, 1} ), Add Potential Term( {1, 1}, {2, 1} ),
Add Potential Term( {1, 1}, {3, 1} ), Add Potential Term( {1, 1}, {4, 1} ),
Add Potential Term( {1, 1}, {5, 1} ), Add Potential Term( {2, 1}, {3, 1} ),
Add Potential Term( {2, 1}, {4, 1} ), Add Potential Term( {2, 1}, {5, 1} ),
Add Potential Term( {3, 1}, {4, 1} ), Add Potential Term( {3, 1}, {5, 1} ),
Add Potential Term( {4, 1}, {5, 1} ), Add Potential Term( {1, 2} ),
Add Potential Term( {2, 2} ), Add Potential Term( {3, 2} ),
Add Potential Term( {4, 2} ), Add Potential Term( {5, 2} ),
Set Sample Size( 21 ), Optimality Criterion( Make Alias Optimal Design ),
Simulate Responses( 0 ), Save X Matrix( 0 )}
);
```

Learn it once, use it forever!

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: DSD question on Blocking at 4 blocks vs 3 blocks

Thanks Mark! Might look into another option then. Thanks for the scripts.