Table 5.
Listwise
|
Log
|
CART
|
RF
|
MI
|
||||||
---|---|---|---|---|---|---|---|---|---|---|
30% | 50% | 30% | 50% | 30% | 50% | 30% | 50% | 30% | 50% | |
BX2Y1 | ||||||||||
Linear | .869 | .907 | .898 | 1.101 | 1.007 | 1.104 | 1.027 | 1.500 | .880 | .922 |
One split | .695 | .837 | 1.198 | 1.011 | 1.006 | .968 | 1.945 | 1.738 | .682 | .863 |
Two splits | .803 | .781 | .958 | 1.132 | 1.087 | 1.071 | 1.660 | 2.203 | .762 | .832 |
Three splits | .752 | .777 | .831 | .816 | 1.081 | 1.021 | 1.124 | 1.574 | .754 | .810 |
BY2X1 | ||||||||||
Linear | .999 | .944 | .975 | .979 | 1.015 | .998 | .95 | 1.228 | 1.012 | .860 |
One split | 1.054 | 1.043 | 1.021 | .953 | .994 | 1.034 | 1.162 | 1.250 | .897 | .939 |
Two splits | 1.201 | 1.232 | 1.249 | 1.234 | 1.063 | 1.023 | 1.120 | 1.236 | .936 | .932 |
Three splits | 1.117 | .992 | 1.009 | .986 | 1.039 | 1.002 | 1.096 | 1.372 | .985 | .892 |
BX2X1 | ||||||||||
Linear | 1.004 | .971 | 1.006 | .996 | 1.013 | 1.019 | 1.004 | 1.276 | 1.020 | .985 |
One split | 1.004 | .977 | 1.036 | .967 | 1.012 | 1.008 | 1.287 | 1.100 | .933 | 1.003 |
Two splits | 1.108 | 1.065 | 1.129 | 1.077 | 1.062 | 1.028 | .989 | 1.266 | 1.007 | .973 |
Three splits | 1.039 | .972 | .986 | .968 | .993 | .981 | 1.012 | 1.070 | .956 | .994 |
BY2Y1 | ||||||||||
Linear | 1.009 | 1.022 | .994 | 1.013 | 1.002 | 1.008 | 1.001 | 1.096 | .984 | .957 |
One split | 1.076 | .987 | 1.035 | .972 | .995 | 1.020 | 1.070 | 1.116 | .938 | .947 |
Two splits | 1.151 | 1.202 | 1.156 | 1.198 | .996 | 1.020 | .969 | 1.243 | .969 | .966 |
Three splits | 1.090 | 1.014 | 1.018 | .967 | 1.018 | .999 | 1.017 | 1.225 | .989 | .971 |
rY2X2 | ||||||||||
Linear | .983 | .963 | .997 | 1.042 | .993 | 1.059 | 1.017 | 1.340 | .961 | .987 |
One split | .861 | .984 | .951 | 1.056 | 1.039 | 1.007 | 1.209 | 1.295 | .899 | .995 |
Two splits | .904 | .869 | .926 | 1.002 | 1.042 | .986 | 1.138 | 1.266 | .937 | .924 |
Three splits | .926 | .898 | .977 | .943 | 1.013 | .991 | 1.084 | 1.185 | .936 | .902 |
Resid (X2) | ||||||||||
Linear | .902 | .901 | .917 | 1.047 | 1.025 | 1.043 | 1.016 | 1.538 | .944 | .843 |
One split | .733 | .921 | .930 | 1.092 | 1.060 | 1.019 | 1.847 | 1.470 | .697 | .855 |
Two splits | .850 | .697 | .946 | .961 | 1.062 | 1.034 | 1.332 | 2.128 | .807 | .684 |
Three splits | .840 | .754 | .890 | .751 | 1.051 | 1.068 | 1.131 | 1.367 | .788 | .746 |
Resid (Y2) | ||||||||||
Linear | 1.004 | .998 | 1.006 | 1.009 | 1.001 | 1.010 | 1.014 | 1.005 | 1.018 | 1.059 |
One split | .962 | .979 | .965 | 1.018 | .999 | 1.001 | 1.008 | .963 | .994 | 1.035 |
Two splits | 1.018 | .959 | .996 | .963 | 1.005 | .996 | .975 | 1.044 | 1.054 | 1.030 |
Three splits | .985 | .964 | .990 | .970 | .99 | .999 | 1.000 | 1.030 | 1.004 | 1.022 |
Note. αX = αY = .9, N = 500. MSE ratio is computed as MSEMeasureX/MSEPrune. MSE = mean squared error; Log = logistic regression; CART = classification and regression trees; RF = random forests; MI = multiple imputation.