Also, we might want to pull a Scott Stern and try:
*Science -- H-Index: 1124 [https://www.scimagojr.com/journalsearch.php?q=23571&tip=sid&clean=0]; Times: 2.0 months to 1st round and 5.3 months to completion based on 54 reviews[https://scirev.org/journal/science/]; Homepage: https://science.sciencemag.org/; Other: up to ~4500 words. Can have additional supplementary materials.
===Changes to methodology===
We changed the PCA to use just 8 variables and we then took just 3 components:
pca nosinglemulti nopair nohull totsinglemulticount totpaircount tothullcount tothullarea totpairlength
Principal components/correlation Number of obs = 216,242
Number of comp. = 8
Trace = 8
Rotation: (unrotated = principal) Rho = 1.0000
--------------------------------------------------------------------------
Component | Eigenvalue Difference Proportion Cumulative
-------------+------------------------------------------------------------
Comp1 | 3.22169 1.09811 0.4027 0.4027
Comp2 | 2.12359 1.11652 0.2654 0.6682
Comp3 | 1.00707 .147009 0.1259 0.7940
Comp4 | .860061 .199002 0.1075 0.9016
Comp5 | .661058 .550229 0.0826 0.9842
Comp6 | .110829 .101626 0.0139 0.9980
Comp7 | .00920377 .00270352 0.0012 0.9992
Comp8 | .00650025 . 0.0008 1.0000
--------------------------------------------------------------------------
Principal components (eigenvectors)
------------------------------------------------------------------------------------------------------------
Variable | Comp1 Comp2 Comp3 Comp4 Comp5 Comp6 Comp7 Comp8 | Unexplained
-------------+--------------------------------------------------------------------------------+-------------
nosinglemu~i | 0.1763 0.6213 0.1362 -0.2153 0.1628 -0.0441 0.4473 0.5380 | 0
nopair | 0.4968 0.0588 -0.1088 0.4258 -0.1916 0.0992 0.5652 -0.4366 | 0
nohull | 0.4613 -0.2494 0.1004 -0.3290 -0.1480 -0.7638 -0.0352 -0.0087 | 0
totsinglem~t | 0.1948 0.6196 0.1305 -0.1813 0.1416 0.0103 -0.4529 -0.5504 | 0
totpaircount | 0.4932 0.0711 -0.0971 0.4262 -0.2260 0.1408 -0.5224 0.4656 | 0
tothullcount | 0.3642 -0.2913 0.2530 -0.5627 -0.1425 0.6171 0.0259 -0.0001 | 0
tothullarea | -0.0543 -0.0905 0.9248 0.3532 0.0797 -0.0494 0.0035 -0.0016 | 0
totpairlen~h | 0.3041 -0.2575 -0.1175 0.0902 0.9039 0.0391 -0.0224 0.0119 | 0
------------------------------------------------------------------------------------------------------------
From the eigenvectors, we can see that (give or take):
*Component 1 is driven by the '''number of lines and hulls''', as well as the '''number of startups in lines and hulls'''
*Component 2 is driven by the '''number of points''' and the '''number of startups in points'''
*Component 3 is driven by the '''total hull area'''
=Previous Version=