Changes

Jump to navigation Jump to search
*Run and add in chosen layers!
==Analysis and Exploration==
Choose LHS variable:
As a consequence we can't use nohull, as it is always 1. It also turns out that tothullcount and tothulldensity don't matter, likely because we already include numstartupsl (removing it makes tothullcount significant). avgdisthm, however, does work.
 
===Levels===
 
We tried the following 'levels' (See Levels.xlsx):
{| class="wikitable"
! Name
! Tgt. Avg. Hull Size
! Act. Avg. Hull Size
! Act. Avg. Hull Count
! Coef.
! Sig
! Act. Density
|-
| HCLLayerLevel1
| 2
| 1.390169
| 3.31986
| 0.031994
|
| 0.418743
|-
| HCLLayerLevel2
| 5
| 3.828996
| 4.213987
| -0.00471
|
| 0.90864
|-
| HCLLayerLevel3
| 10
| 7.921853
| 4.949919
| -0.04308
|
| 1.600401
|-
| HCLLayerLevel4
| 15
| 12.38832
| 5.483262
| -0.00495
|
| 2.259297
|-
| HCLLayerLevel5
| 20
| 16.82407
| 5.879045
| 0.057642
|
| 2.861701
|-
| HCLLayerLevel6
| 25
| 21.07783
| 6.218925
| 0.13614
| *
| 3.389304
|-
| HCLLayerLevel7
| 30
| 25.40073
| 6.512421
| 0.174672
| **
| 3.900351
|-
| HCLLayerLevel8
| 35
| 29.48548
| 6.788268
| 0.155578
| **
| 4.343594
|-
| HCLLayerLevel9
| 40
| 33.6133
| 7.02369
| 0.158089
| *
| 4.785704
|-
| HCLLayerLevel10
| 50
| 41.93593
| 7.452783
| 0.163425
| *
| 5.626882
|-
| HCLLayerLevel11
| 35000
| 5080.886
| 37.30932
| 0.3621
|
| 136.1828
|}
 
===Elbow===
Using the first method, the PCA yields 3 or maybe 4 components. We'll use 4.
 
 
===Instrumental Variable(s)===

Navigation menu