## [1] 0.9052671
## Hospital.Ownership Emergency.Services Hospital
## Government : 449 Min. :0.0000 Min. : 10001
## Physician : 15 1st Qu.:1.0000 1st Qu.:110044
## Proprietary : 576 Median :1.0000 Median :250095
## Voluntary Non-Profit:1819 Mean :0.9762 Mean :258835
## 3rd Qu.:1.0000 3rd Qu.:390112
## Max. :1.0000 Max. :670098
##
## Cleanliness Nurses Doctors HelpWhenNeeded
## Min. :50.00 Min. :56.00 Min. : 60.00 Min. :37.00
## 1st Qu.:67.00 1st Qu.:76.00 1st Qu.: 78.00 1st Qu.:60.00
## Median :72.00 Median :79.00 Median : 80.00 Median :65.00
## Mean :71.65 Mean :78.49 Mean : 80.29 Mean :65.17
## 3rd Qu.:76.00 3rd Qu.:81.00 3rd Qu.: 83.00 3rd Qu.:70.00
## Max. :98.00 Max. :99.00 Max. :100.00 Max. :96.00
##
## PainControl ExplainMeds RecoveryInfo UnderstandCare
## Min. : 51.00 Min. :23.00 Min. : 66.0 Min. :11.0
## 1st Qu.: 67.00 1st Qu.:60.00 1st Qu.: 85.0 1st Qu.:47.0
## Median : 70.00 Median :63.00 Median : 87.0 Median :51.0
## Mean : 69.84 Mean :63.27 Mean : 86.7 Mean :50.6
## 3rd Qu.: 72.00 3rd Qu.:66.00 3rd Qu.: 89.0 3rd Qu.:54.0
## Max. :100.00 Max. :97.00 Max. :100.0 Max. :98.0
##
## Quiet Recommend HAI2 HAI3
## Min. :32.00 Min. :24.00 Min. :0.0000 Min. : 0.00
## 1st Qu.:54.00 1st Qu.:65.00 1st Qu.:0.0000 1st Qu.: 0.00
## Median :60.00 Median :71.00 Median :0.6485 Median : 15.62
## Mean :59.65 Mean :70.32 Mean :0.7988 Mean : 23.54
## 3rd Qu.:65.00 3rd Qu.:77.00 3rd Qu.:1.1963 3rd Qu.: 34.48
## Max. :93.00 Max. :96.00 Max. :8.9820 Max. :1000.00
## NA's :25 NA's :167
## HAI4 HAI5 HAI6 Aggregate_Inf
## Min. : 0.000 Min. :0.00000 Min. : 0.0000 Min. :0.0000
## 1st Qu.: 0.000 1st Qu.:0.00000 1st Qu.: 0.3215 1st Qu.:0.2290
## Median : 0.000 Median :0.02690 Median : 0.5662 Median :0.3634
## Mean : 9.380 Mean :0.04367 Mean : 1.0074 Mean :0.3714
## 3rd Qu.: 9.434 3rd Qu.:0.06692 3rd Qu.: 0.8181 3rd Qu.:0.4971
## Max. :1000.000 Max. :2.70270 Max. :1000.0000 Max. :7.4906
## NA's :272 NA's :2 NA's :3
## PAYM_30_AMI PAYM_30_HF PAYM_30_PN PayPerBenAvg
## Min. :17887 Min. :12199 Min. :10204 Min. :10415
## 1st Qu.:21930 1st Qu.:15107 1st Qu.:13954 1st Qu.:16523
## Median :22956 Median :15986 Median :14748 Median :17670
## Mean :23023 Mean :16096 Mean :14787 Mean :17395
## 3rd Qu.:24071 3rd Qu.:16955 3rd Qu.:15546 3rd Qu.:18589
## Max. :30334 Max. :22416 Max. :20802 Max. :23347
## NA's :652 NA's :107 NA's :93 NA's :69
## COMP_HIP_KNEE PSI_12_POSTOP_PULMEMB_DVT PSI_13_POST_SEPSIS
## Min. :1.500 Min. : 1.390 Min. : 4.50
## 1st Qu.:2.700 1st Qu.: 3.880 1st Qu.: 9.04
## Median :3.000 Median : 4.770 Median : 9.79
## Mean :3.058 Mean : 5.071 Mean :10.28
## 3rd Qu.:3.400 3rd Qu.: 5.800 3rd Qu.:11.29
## Max. :6.000 Max. :20.880 Max. :27.96
## NA's :574 NA's :106 NA's :684
## PSI_14_POSTOP_DEHIS PSI_15_ACC_LAC PSI_3_ULCER PSI_4_SURG_COMP
## Min. :1.180 Min. :0.320 Min. : 0.0300 Min. : 70.79
## 1st Qu.:2.130 1st Qu.:1.120 1st Qu.: 0.2000 1st Qu.:124.39
## Median :2.230 Median :1.370 Median : 0.3400 Median :135.69
## Mean :2.321 Mean :1.442 Mean : 0.4509 Mean :136.82
## 3rd Qu.:2.480 3rd Qu.:1.690 3rd Qu.: 0.4600 3rd Qu.:148.33
## Max. :4.980 Max. :6.180 Max. :10.3500 Max. :212.16
## NA's :418 NA's :2 NA's :8 NA's :1107
## PSI_6_IAT_PTX PSI_7_CVCBI PSI_8_POST_HIP PSI_90_SAFETY
## Min. :0.1900 Min. :0.0300 Min. :0.06 Min. :0.440
## 1st Qu.:0.3600 1st Qu.:0.1300 1st Qu.:0.06 1st Qu.:0.780
## Median :0.3900 Median :0.1500 Median :0.06 Median :0.870
## Mean :0.4066 Mean :0.1691 Mean :0.06 Mean :0.892
## 3rd Qu.:0.4400 3rd Qu.:0.1700 3rd Qu.:0.06 3rd Qu.:0.970
## Max. :0.8800 Max. :1.2300 Max. :0.06 Max. :2.140
## NA's :2 NA's :4 NA's :141 NA's :2
## MORT_30_AMI MORT_30_COPD MORT_30_HF MORT_30_PN
## Min. : 9.40 Min. : 4.600 Min. : 6.60 Min. : 8.70
## 1st Qu.:13.20 1st Qu.: 7.300 1st Qu.:11.10 1st Qu.:14.90
## Median :14.00 Median : 7.900 Median :12.00 Median :16.20
## Mean :14.06 Mean : 8.073 Mean :12.05 Mean :16.35
## 3rd Qu.:14.90 3rd Qu.: 8.750 3rd Qu.:13.00 3rd Qu.:17.70
## Max. :20.00 Max. :14.100 Max. :17.80 Max. :26.80
## NA's :618 NA's :120 NA's :93 NA's :62
## MORT_30_STK READM_30_AMI READM_30_COPD READM_30_HF
## Min. : 9.3 Min. :13.10 Min. :15.90 Min. :16.30
## 1st Qu.:13.8 1st Qu.:16.30 1st Qu.:19.10 1st Qu.:20.90
## Median :14.8 Median :16.90 Median :19.90 Median :21.90
## Mean :14.9 Mean :16.89 Mean :20.01 Mean :21.99
## 3rd Qu.:15.9 3rd Qu.:17.50 3rd Qu.:20.80 3rd Qu.:23.00
## Max. :23.3 Max. :20.60 Max. :26.10 Max. :31.30
## NA's :443 NA's :804 NA's :103 NA's :89
## READM_30_HIP_KNEE READM_30_HOSP_WIDE READM_30_PN READM_30_STK
## Min. :2.900 Min. :10.80 Min. :12.90 Min. : 9.10
## 1st Qu.:4.300 1st Qu.:15.00 1st Qu.:16.10 1st Qu.:11.90
## Median :4.600 Median :15.50 Median :17.10 Median :12.50
## Mean :4.624 Mean :15.61 Mean :17.22 Mean :12.58
## 3rd Qu.:5.000 3rd Qu.:16.10 3rd Qu.:18.20 3rd Qu.:13.20
## Max. :7.800 Max. :19.90 Max. :24.70 Max. :17.70
## NA's :565 NA's :1 NA's :56 NA's :484
## OP_12.eLab_Rec OP_17_TrackMedInfo OP_25_CHECK_OP SM_PART_GEN_SURG
## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
## 1st Qu.:1.0000 1st Qu.:1.0000 1st Qu.:1.0000 1st Qu.:0.0000
## Median :1.0000 Median :1.0000 Median :1.0000 Median :0.0000
## Mean :0.9157 Mean :0.8779 Mean :0.9713 Mean :0.2648
## 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:1.0000
## Max. :1.0000 Max. :1.0000 Max. :1.0000 Max. :1.0000
##
## SM_PART_NURSE SM_SS_CHECK_IP SumStruct ED_IP_Throughput
## Min. :0.0000 Min. :0.000 Min. :0.000 Min. : 76.0
## 1st Qu.:0.0000 1st Qu.:1.000 1st Qu.:4.000 1st Qu.: 228.0
## Median :1.0000 Median :1.000 Median :5.000 Median : 270.0
## Mean :0.5498 Mean :0.979 Mean :4.559 Mean : 289.2
## 3rd Qu.:1.0000 3rd Qu.:1.000 3rd Qu.:5.000 3rd Qu.: 330.0
## Max. :1.0000 Max. :1.000 Max. :6.000 Max. :1030.0
## NA's :29
## EDV IMM__PT IMM_Workers ED_OP_Throughput
## Min. :1.00 Min. : 5.00 Min. : 18.00 Min. : 55.0
## 1st Qu.:2.00 1st Qu.: 94.00 1st Qu.: 78.00 1st Qu.:123.0
## Median :2.00 Median : 97.00 Median : 89.00 Median :145.0
## Mean :2.43 Mean : 94.93 Mean : 84.57 Mean :150.7
## 3rd Qu.:3.00 3rd Qu.: 99.00 3rd Qu.: 96.00 3rd Qu.:172.0
## Max. :4.00 Max. :100.00 Max. :100.00 Max. :436.0
## NA's :71 NA's :66
## TimeToEval TimeToPainMed LeftBeforeTreat AspirinCP
## Min. : 0.00 Min. : 12.0 Min. : 0.00 Min. : 36.00
## 1st Qu.: 16.00 1st Qu.: 41.0 1st Qu.: 1.00 1st Qu.: 94.00
## Median : 24.00 Median : 52.0 Median : 1.00 Median : 97.00
## Mean : 27.02 Mean : 53.8 Mean : 1.95 Mean : 95.74
## 3rd Qu.: 34.00 3rd Qu.: 65.0 3rd Qu.: 3.00 3rd Qu.:100.00
## Max. :140.00 Max. :172.0 Max. :29.00 Max. :100.00
## NA's :68 NA's :105 NA's :71 NA's :1265
## TimeToECG ElectiveEarlyDelivery AppropStrokeCare HospVTE
## Min. : 0.00 Min. : 0.000 Min. : 0.00 Min. : 0.000
## 1st Qu.: 5.00 1st Qu.: 0.000 1st Qu.: 90.00 1st Qu.: 0.000
## Median : 7.00 Median : 1.000 Median : 96.00 Median : 0.000
## Mean : 8.19 Mean : 2.044 Mean : 91.59 Mean : 1.889
## 3rd Qu.:10.00 3rd Qu.: 3.000 3rd Qu.:100.00 3rd Qu.: 2.000
## Max. :65.00 Max. :85.000 Max. :100.00 Max. :87.000
## NA's :1240 NA's :584 NA's :1940 NA's :1687
## MeaningfulUse MedImage Endosc
## Min. :0.000 Above the national average : 345 Min. : 0
## 1st Qu.:1.000 Below the national average : 323 1st Qu.: 72
## Median :1.000 Not Available : 443 Median : 90
## Mean :0.958 Same as the national average:1748 Mean : 80
## 3rd Qu.:1.000 3rd Qu.: 97
## Max. :1.000 Max. :100
## NA's :334
## Warning in `[<-.factor`(`*tmp*`, iseq, value = c(1390, 1390, 1390, 1390, :
## invalid factor level, NA generated
## Warning in `[<-.factor`(`*tmp*`, iseq, value = c(1390, 1390, 1390, 1390, :
## invalid factor level, NA generated
## Warning in `[<-.factor`(`*tmp*`, iseq, value = c(1390, 1390, 1390, 1390, :
## invalid factor level, NA generated
Now Check Correlations and Perform Groupings
##Numeric Factors
DClean<-DClean[-37]
NF<-data.frame(DClean[6:70],"Endosc"=DClean$Endosc)
Binary<-data.frame("Own"=DClean$Hospital.Ownership,NF[c(1,18,45,46,47,48,49,50,60,61,62,63,64,65)])
NF<-NF[-c(1,18,45,46,47,48,49,50,60,61,62,63,64,65)]
NF<-NF[-1]
NF<-NF[-10]
###################################
#Add Data Transforms here
#Sqrt HAI2
NF$HAI2<-sqrt(NF$HAI2)
#Log Transform HIPKNEWW
NF$COMP_HIP_KNEE<-log(NF$COMP_HIP_KNEE)
NF$PSI_12_POSTOP_PULMEMB_DVT<-log(NF$PSI_12_POSTOP_PULMEMB_DVT)
NF$PSI_13_POST_SEPSIS<-log(NF$PSI_13_POST_SEPSIS)
NF$PSI_14_POSTOP_DEHIS<-log(NF$PSI_14_POSTOP_DEHIS)
NF$PSI_3_ULCER<-log(NF$PSI_3_ULCER)
NF$PSI_4_SURG_COMP<-log(NF$PSI_4_SURG_COMP)
NF$PSI_6_IAT_PTX<-log(NF$PSI_6_IAT_PTX)
NF$PSI_7_CVCBI<-log(NF$PSI_7_CVCBI)
NF$PSI_90_SAFETY<-log(NF$PSI_90_SAFETY)
Binary1<-data.frame(Binary,"PSI90"=NF$PSI_90_SAFETY)
NF<-NF[-28]
NF<-NF[-29] ### COPD Mort is not at all associated.
########################
cormat<-as.matrix(cor(NF))
library(corrplot)
corrplot(as.matrix(cor(NF)),method="shade",order="FPC")
###Scale Columns to reduce heteroscleradicity
NF<-as.data.frame(scale(as.matrix(NF)))
NFeigen<-eigen(cormat)
Nfact<-sum(as.numeric(NFeigen$values >=1))
###13 Eigenvalues above Zero, let's run factor analysis on these Numeric Data to reduce our dimensions
library(nFactors)
## Loading required package: MASS
## Loading required package: psych
## Loading required package: boot
##
## Attaching package: 'boot'
## The following object is masked from 'package:psych':
##
## logit
## Loading required package: lattice
##
## Attaching package: 'lattice'
## The following object is masked from 'package:boot':
##
## melanoma
##
## Attaching package: 'nFactors'
## The following object is masked from 'package:lattice':
##
## parallel
ev <- NFeigen # get eigenvalues
ap <- parallel(subject=nrow(NF),var=ncol(NF),
rep=100,cent=.05)
nS <- nScree(x=ev$values, aparallel=ap$eigen$qevpea)
plotnScree(nS)
componentAxis(cor(NF,use = "pairwise.complete.obs"), nFactors=13)
## $values
## [1] 7.756174 3.069090 2.985654 2.705625 1.924192 1.615359 1.454684
## [8] 1.371761 1.102204 1.063253 1.041435 1.022941 1.009412
##
## $varExplained
## [1] 16.16 6.39 6.22 5.64 4.01 3.37 3.03 2.86 2.30 2.22 2.17
## [12] 2.13 2.10
##
## $cumVarExplained
## [1] 16.16 22.55 28.77 34.41 38.42 41.79 44.82 47.68 49.98 52.20 54.37
## [12] 56.50 58.60
##
## $loadings
## [,1] [,2] [,3] [,4] [,5]
## [1,] -0.691879279 0.059261854 0.1926766303 0.0961407573 -0.056046800
## [2,] -0.817398212 0.040272432 0.3472392439 0.2725983966 0.075094249
## [3,] -0.756448238 0.215313581 0.1192010878 0.2667582232 -0.037315917
## [4,] -0.831106823 0.127661585 0.2144707897 0.1524373919 -0.008116201
## [5,] -0.761081590 0.056709773 0.3281968966 0.2355706235 0.011938782
## [6,] -0.761527462 0.085577884 0.2573711694 0.2637096666 0.049006122
## [7,] -0.614419200 -0.236034479 0.1861196438 0.1290786782 0.268329002
## [8,] -0.674600360 -0.171211236 0.3422927642 0.3163498572 0.114734756
## [9,] -0.601195347 0.310815018 0.1081541539 0.1356690315 -0.114093867
## [10,] 0.319365187 -0.252946182 0.0986198223 0.3131601150 0.258714488
## [11,] 0.034964262 -0.005237802 -0.0413573625 0.1067726765 0.080563348
## [12,] 0.042925070 -0.006288396 -0.0239639582 0.0098774019 -0.009231313
## [13,] 0.184133207 0.025853305 0.0350414931 0.1115966071 0.019584021
## [14,] -0.009501296 0.010617007 -0.0004217437 0.0227193570 -0.041312948
## [15,] 0.221463149 -0.070602047 0.4537461097 -0.2530351841 -0.045354777
## [16,] 0.395383151 -0.253202479 0.5667010294 -0.2697439328 -0.034054508
## [17,] 0.398037805 -0.192348606 0.4472699948 -0.2269909167 0.012754736
## [18,] 0.519491281 -0.366281061 0.5382177507 -0.1782904023 0.152516056
## [19,] 0.066824529 0.272724024 0.0325372584 -0.0689334163 0.152382470
## [20,] 0.220461453 0.154611014 0.1055889410 0.1806838333 0.013292027
## [21,] 0.117211877 0.058042660 0.0858815669 -0.0109314679 0.122327503
## [22,] 0.056215076 0.064131840 -0.0839290238 -0.0379660230 0.099008333
## [23,] -0.009612491 -0.082078008 -0.2440349833 0.0563745713 0.174826193
## [24,] -0.021926356 0.135391089 -0.1461889717 0.0185088128 0.013584641
## [25,] 0.089547392 0.175740024 -0.2046743609 0.1272895376 0.249962350
## [26,] -0.008443935 0.030473273 -0.1184611043 0.0755034023 0.175866631
## [27,] 0.048877766 0.161678983 -0.0139890968 0.0707455010 0.021631722
## [28,] -0.010304598 0.142179089 -0.2864310533 -0.0335586331 0.439404977
## [29,] -0.271818253 0.002818635 -0.4330422312 -0.0721834640 0.421013602
## [30,] -0.070790932 0.132437053 -0.3550946533 0.0007286761 0.486277807
## [31,] -0.075146161 -0.079692324 -0.3805930678 0.0109221851 0.455533902
## [32,] 0.252944815 0.465938292 0.2418628578 0.0205759387 0.148042838
## [33,] 0.275674957 0.467167008 0.2077334557 0.0353643400 0.221745051
## [34,] 0.350819685 0.600306400 0.1994888413 0.0085038532 0.039496848
## [35,] 0.140253220 0.349344199 0.1215037188 -0.0401398314 0.197886849
## [36,] 0.453456057 0.629869011 0.2551673663 0.0820154572 0.154255199
## [37,] 0.361190953 0.532909515 0.2451615010 0.0837478867 0.143371713
## [38,] 0.322298607 0.427862178 0.3046091377 0.1306485911 0.043324441
## [39,] 0.166201515 -0.383307264 0.2780025317 0.2437373931 0.324345916
## [40,] 0.628642657 -0.126507100 0.0438038934 0.4714694001 0.002688336
## [41,] 0.498183010 -0.309731607 0.2483578955 0.3160319730 0.291344174
## [42,] -0.071253235 -0.176187551 0.2820999069 -0.1981558593 0.358110641
## [43,] -0.175166091 -0.255036764 0.0899158865 0.0902565444 0.291191694
## [44,] 0.520435746 -0.276882518 0.0664971484 0.6279594838 0.006484134
## [45,] 0.353816609 -0.072323767 -0.1378132756 0.6398808035 -0.157673094
## [46,] 0.344456850 0.049834861 -0.1710034643 0.5408709534 -0.229628383
## [47,] 0.322591644 0.034223060 -0.2017012669 0.5376717046 -0.177687587
## [48,] -0.081135542 -0.221583820 0.0020756439 -0.0212611611 0.231358518
## [,6] [,7] [,8] [,9] [,10]
## [1,] -0.082001581 0.033987130 -0.042762197 0.120468153 0.0320952315
## [2,] -0.057798710 0.012209956 -0.007816889 0.001212295 0.0393080399
## [3,] -0.083718970 0.066710107 0.003791567 -0.120254338 0.0341369875
## [4,] -0.069844251 0.034483928 -0.010169600 0.055154203 0.0071443546
## [5,] -0.104475794 0.054784577 -0.033405242 -0.038603711 0.0371015223
## [6,] -0.066566439 0.041299407 -0.003537965 -0.010431577 0.0087386065
## [7,] 0.131986554 -0.039565684 0.023393188 0.107952725 -0.0252115578
## [8,] 0.011548085 0.012393580 0.045862346 -0.002354365 0.0134669290
## [9,] -0.182563998 0.091040506 -0.140947686 -0.141880470 0.0341012495
## [10,] 0.117398131 0.028154999 0.140403200 -0.320281540 0.0933128234
## [11,] 0.122566146 0.121285560 0.181786469 0.098707440 0.3643046624
## [12,] -0.032462683 0.068079379 -0.042493774 0.318080426 0.5164375447
## [13,] 0.017830686 0.022313901 0.137017635 -0.626355288 0.1513591906
## [14,] -0.035062488 0.022881396 -0.114035670 0.164611360 -0.4019058116
## [15,] -0.251567350 0.339425437 -0.007339500 0.083984336 -0.0450436599
## [16,] -0.295392955 0.210986007 -0.084345691 0.011543078 0.0204750611
## [17,] -0.357866604 0.180231804 -0.216680933 -0.002126935 0.0541346573
## [18,] -0.258705054 0.126557582 -0.100833775 -0.013473491 0.0166554810
## [19,] 0.447164237 0.215259181 -0.593907359 -0.059370275 0.0600675938
## [20,] 0.335026308 0.374396462 -0.009277442 -0.062329208 0.0693500440
## [21,] 0.246793624 0.218498476 -0.030288699 0.112146121 0.0957048878
## [22,] 0.003791967 0.163726226 -0.016492076 0.323330278 0.2661404382
## [23,] 0.120381940 0.330566231 0.247726778 0.198141733 0.0332787669
## [24,] 0.009237293 0.428433285 0.219374592 0.063500558 -0.2254287139
## [25,] -0.176330932 0.236498350 -0.048221861 -0.139220295 -0.1541606617
## [26,] 0.061505491 0.382231791 0.124352945 0.048437390 -0.1219178183
## [27,] 0.001323685 0.479556767 0.296759497 -0.090067607 -0.2208470573
## [28,] -0.335072632 0.005236990 -0.151368180 -0.088606347 0.0246630876
## [29,] -0.300619822 -0.002402494 -0.062972991 0.043755640 0.0712091270
## [30,] -0.369662866 -0.065854474 -0.115503801 -0.006284413 0.0594067887
## [31,] -0.161774216 0.083934734 0.009644929 -0.060328858 0.0250183323
## [32,] -0.022896450 -0.010083705 0.040144272 0.128123776 -0.0586688120
## [33,] -0.028838027 -0.220267110 0.184092705 0.124414449 0.0245051005
## [34,] -0.085110170 -0.121248935 0.143414422 0.126007909 -0.0481529476
## [35,] 0.345124721 0.091964973 -0.556390220 -0.121295262 0.0380130938
## [36,] 0.034655199 -0.136774105 0.111563002 0.042954919 0.0141622822
## [37,] -0.039264420 -0.174719445 0.123026977 0.060498330 0.0007646301
## [38,] -0.012668886 -0.045967882 0.112032011 -0.088107608 -0.0673950512
## [39,] 0.177097078 -0.078241615 0.134409086 0.104727490 0.0511292630
## [40,] -0.023019221 0.012245576 0.011594135 0.049487010 -0.0267034233
## [41,] 0.027007561 -0.120430087 0.065166307 -0.133423478 0.1041100896
## [42,] 0.056991467 -0.181473385 -0.126297535 0.049508290 -0.2768494771
## [43,] 0.235026574 -0.095923999 -0.039541358 0.179048273 -0.2034483789
## [44,] -0.006920718 -0.031431770 -0.036640503 0.060185285 -0.0191394333
## [45,] -0.139958328 -0.004511188 -0.190323287 0.106470642 -0.0603242878
## [46,] -0.203607340 0.037211307 -0.207074827 0.100800134 -0.0149253406
## [47,] -0.166106494 0.037354020 -0.243877021 0.096817037 -0.1170511571
## [48,] 0.227560565 -0.128495437 -0.012688928 0.097102987 -0.2398954028
## [,11] [,12] [,13]
## [1,] -0.033452773 4.433051e-02 0.029750965
## [2,] 0.005008073 1.097665e-02 0.027098867
## [3,] -0.006102608 -5.881030e-02 -0.033386090
## [4,] -0.011226881 1.197461e-02 0.023978834
## [5,] -0.020795180 -1.742452e-02 0.029858263
## [6,] -0.025821619 -2.366975e-02 -0.021508759
## [7,] 0.013910371 9.804168e-03 0.095283739
## [8,] 0.010736741 4.438123e-03 0.022111500
## [9,] 0.011207108 -8.872394e-02 -0.096339402
## [10,] -0.059824378 -5.123700e-02 -0.105608502
## [11,] -0.029922197 -3.404953e-01 -0.318524057
## [12,] -0.007788177 2.162743e-01 -0.510166186
## [13,] -0.233047143 -1.985640e-01 -0.065360319
## [14,] -0.177600721 -1.222067e-01 -0.415743492
## [15,] 0.054671665 -1.580389e-01 0.019856703
## [16,] 0.038154655 -1.015786e-02 0.018315372
## [17,] 0.006322166 -8.530183e-03 0.010775019
## [18,] 0.026492231 -5.996293e-02 0.009387962
## [19,] 0.083418625 2.891721e-02 0.016772520
## [20,] 0.086257127 2.490252e-01 0.060149328
## [21,] -0.326050055 -7.464966e-02 0.446516736
## [22,] -0.502228988 -1.025504e-01 0.146394756
## [23,] 0.178188177 -3.525719e-01 0.153396815
## [24,] -0.252453100 3.945625e-01 -0.159716488
## [25,] -0.342363471 -7.497839e-03 -0.157971189
## [26,] 0.483858181 -2.274047e-01 -0.156084422
## [27,] 0.047337585 1.139663e-01 0.068403060
## [28,] -0.045704261 2.692823e-02 -0.080016616
## [29,] 0.046396969 2.814546e-02 0.150556864
## [30,] 0.066045753 4.839927e-02 0.111016698
## [31,] 0.122597695 1.044628e-01 -0.002980044
## [32,] -0.065328753 -7.417154e-02 0.036373164
## [33,] 0.035160748 -5.176107e-02 0.042503172
## [34,] 0.051199796 -8.416935e-03 0.008033385
## [35,] 0.081065210 -4.073227e-02 -0.066826405
## [36,] 0.070937786 3.744019e-05 -0.013620424
## [37,] 0.064652089 -3.986012e-02 0.019907847
## [38,] -0.045053658 7.265130e-02 -0.067113282
## [39,] 0.051447058 2.220870e-01 0.013192224
## [40,] -0.102306513 7.614907e-02 0.025469614
## [41,] 0.024963151 5.510919e-02 -0.034438860
## [42,] -0.117934857 3.303808e-02 -0.092734549
## [43,] 0.037701668 1.373879e-01 -0.092197235
## [44,] 0.007368148 3.423013e-02 0.027129317
## [45,] 0.070014690 -5.339542e-02 0.088744512
## [46,] 0.052233327 -5.233922e-02 0.111993548
## [47,] -0.044845295 -1.180711e-01 -0.050480710
## [48,] -0.180794485 -4.537557e-01 -0.101321245
##
## $communalities
## [1] 0.5609375 0.8762632 0.7370456 0.7864450 0.7653372 0.7334560 0.5977167
## [8] 0.7180057 0.6012187 0.5036372 0.4443812 0.6851212 0.5814695 0.4251275
## [15] 0.5419915 0.7568441 0.6578366 0.8467170 0.7221023 0.4507477 0.4821274
## [22] 0.5122090 0.5052152 0.5722474 0.4341998 0.5444146 0.4290341 0.4494562
## [29] 0.5708227 0.5620363 0.4280053 0.3951048 0.4928572 0.5883366 0.6632386
## [36] 0.7376068 0.5591547 0.4376172 0.5377174 0.6562953 0.6435257 0.4380366
## [43] 0.3649998 0.7546433 0.6701530 0.6097611 0.5966211 0.4939470
#f<-factanal(NF
# , factors = 13,
# scores = "Bartlett",rotation = "varimax")
#write.csv(f$loadings,"out_load.csv")
FinalNumeric<-data.frame("HAI4"=NF$HAI4,"HAI6"=NF$HAI6,"IPThroughput"=NF$ED_IP_Throughput,"PAYAMI"=NF$PAYM_30_AMI,"PSI14"=NF$PSI_14_POSTOP_DEHIS,"IMMPT"=NF$IMM__PT,"IMMWork"=NF$IMM_Workers,"PSI4"=NF$PSI_4_SURG_COMP,"HipKnee"=(NF$COMP_HIP_KNEE+NF$READM_30_HIP_KNEE)/2,"Payment"=(NF$PAYM_30_HF+NF$PAYM_30_PN+NF$PayPerBenAvg)/3,"EDTimes"=(NF$ED_OP_Throughput+NF$TimeToEval+NF$TimeToPainMed+NF$LeftBeforeTreat)/4,NF$READM_30_HOSP_WIDE,NF$RecoveryInfo,NF$Quiet,NF$HAI2,NF$HAI5,NF$SumStruct,NF$EDV,"HCAHPSStaff"=(NF$Cleanliness+NF$Nurses+NF$Doctors+NF$HelpWhenNeeded+NF$PainControl+NF$ExplainMeds+NF$UnderstandCare)/6)
Predictors<-data.frame(FinalNumeric,data.frame(Binary1[c(1,2,3,4,5,6,10,11,12,13,14,15,16)]))
Model Building: Recommend
##Weight by the model
library(caret)
## Loading required package: ggplot2
##
## Attaching package: 'ggplot2'
## The following objects are masked from 'package:psych':
##
## %+%, alpha
library(pROC)
## Type 'citation("pROC")' for a citation.
##
## Attaching package: 'pROC'
## The following objects are masked from 'package:stats':
##
## cov, smooth, var
library(car)
##
## Attaching package: 'car'
## The following object is masked from 'package:boot':
##
## logit
## The following object is masked from 'package:psych':
##
## logit
All<-data.frame("Recommend"=DClean$Recommend,"ScoreBin"=DClean$ScoreBin,"Score"=DClean$Score,Predictors)
Recmod<-lm(data=All,Recommend~.-PSI14-ScoreBin-Score-IMMWork-NF.HAI5-ElectiveEarlyDelivery-PAYAMI-TimeToECG-EDTimes-HAI6-NF.HAI2-PSI90-Aggregate_Inf -IPThroughput -HospVTE-AppropStrokeCare)
#summary(mod1a)
wts1 <- 1/fitted(lm(abs(residuals(Recmod)) ~ fitted(Recmod)))^2
Recmodw<-lm(data=All,Recommend~.-PSI14-ScoreBin-Score-IMMWork-NF.HAI5-ElectiveEarlyDelivery-PAYAMI-TimeToECG-EDTimes-HAI6-NF.HAI2 -PSI90-Aggregate_Inf -IPThroughput-HospVTE-AppropStrokeCare,weights = wts1)
summary(Recmodw)
##
## Call:
## lm(formula = Recommend ~ . - PSI14 - ScoreBin - Score - IMMWork -
## NF.HAI5 - ElectiveEarlyDelivery - PAYAMI - TimeToECG - EDTimes -
## HAI6 - NF.HAI2 - PSI90 - Aggregate_Inf - IPThroughput - HospVTE -
## AppropStrokeCare, data = All, weights = wts1)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -5.4966 -0.7942 0.0663 0.8798 4.6464
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 79.8883 1.0948 72.971 < 2e-16 ***
## HAI4 -0.2584 0.1064 -2.430 0.015174 *
## IMMPT 0.4299 0.1099 3.912 9.36e-05 ***
## PSI4 -0.3516 0.1012 -3.474 0.000521 ***
## HipKnee -0.4099 0.1213 -3.378 0.000740 ***
## Payment 0.6367 0.1337 4.762 2.02e-06 ***
## NF.READM_30_HOSP_WIDE -0.8192 0.1117 -7.332 2.95e-13 ***
## NF.RecoveryInfo 1.5523 0.1373 11.306 < 2e-16 ***
## NF.Quiet 0.6221 0.1407 4.422 1.01e-05 ***
## NF.SumStruct 1.8239 0.1639 11.127 < 2e-16 ***
## NF.EDV 1.5835 0.1258 12.591 < 2e-16 ***
## HCAHPSStaff 5.1425 0.1691 30.409 < 2e-16 ***
## OwnPhysician 4.0758 1.3771 2.960 0.003106 **
## OwnProprietary 1.1562 0.3631 3.185 0.001466 **
## OwnVoluntary Non-Profit 0.9650 0.2972 3.247 0.001181 **
## Emergency.Services -1.4507 0.6537 -2.219 0.026550 *
## OP_12.eLab_Rec -1.8686 0.5394 -3.464 0.000540 ***
## OP_17_TrackMedInfo -1.5702 0.4501 -3.488 0.000494 ***
## OP_25_CHECK_OP -2.9570 0.6891 -4.291 1.84e-05 ***
## AspirinCP -3.3568 0.2202 -15.247 < 2e-16 ***
## MeaningfulUse -1.2418 0.5110 -2.430 0.015159 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.269 on 2838 degrees of freedom
## Multiple R-squared: 0.6227, Adjusted R-squared: 0.62
## F-statistic: 234.2 on 20 and 2838 DF, p-value: < 2.2e-16
vif(Recmodw)
## GVIF Df GVIF^(1/(2*Df))
## HAI4 1.018895 1 1.009403
## IMMPT 1.128876 1 1.062486
## PSI4 1.035428 1 1.017560
## HipKnee 1.092609 1 1.045279
## Payment 1.344788 1 1.159650
## NF.READM_30_HOSP_WIDE 1.228767 1 1.108498
## NF.RecoveryInfo 1.746815 1 1.321671
## NF.Quiet 1.966968 1 1.402486
## NF.SumStruct 2.671536 1 1.634483
## NF.EDV 1.572384 1 1.253947
## HCAHPSStaff 2.716860 1 1.648290
## Own 1.381398 3 1.055326
## Emergency.Services 1.027947 1 1.013877
## OP_12.eLab_Rec 2.195739 1 1.481803
## OP_17_TrackMedInfo 2.120606 1 1.456230
## OP_25_CHECK_OP 1.331616 1 1.153957
## AspirinCP 1.189877 1 1.090815
## MeaningfulUse 1.039363 1 1.019491
library(ppcor)
mod1<-pcor(data.frame(All$Recommend,All$HAI4,All$IMMPT,All$PSI4,All$HipKnee,All$Payment,All$NF.READM_30_HOSP_WIDE,All$NF.RecoveryInfo,All$NF.Quiet,All$NF.SumStruct,All$NF.EDV,All$HCAHPSStaff,as.numeric(All$Own=='Physician'),All$Emergency.Services,All$OP_12.eLab_Rec,All$OP_17_TrackMedInfo,All$OP_25_CHECK_OP,All$AspirinCP,All$MeaningfulUse))
est<-data.frame(mod1$estimate)
est[1]
## All.Recommend
## All.Recommend 1.00000000
## All.HAI4 -0.04887691
## All.IMMPT 0.07893775
## All.PSI4 -0.06835207
## All.HipKnee -0.06107802
## All.Payment 0.10517770
## All.NF.READM_30_HOSP_WIDE -0.13421261
## All.NF.RecoveryInfo 0.21459159
## All.NF.Quiet 0.07807329
## All.NF.SumStruct 0.20382147
## All.NF.EDV 0.22694804
## All.HCAHPSStaff 0.50138588
## as.numeric.All.Own.....Physician.. 0.04215514
## All.Emergency.Services -0.04155511
## All.OP_12.eLab_Rec -0.06728329
## All.OP_17_TrackMedInfo -0.06489254
## All.OP_25_CHECK_OP -0.07519691
## All.AspirinCP -0.27595251
## All.MeaningfulUse -0.04650161
##Compare with true values.
hist(Recmodw$residuals)
Binary Logistic
### Now Build 5 or not binary logistic
gmod2a<-glm(data=All,ScoreBin~.-Recommend-Score-PAYAMI-PSI14-IMMWork-TimeToECG-HAI6-EDTimes-OP_17_TrackMedInfo-ElectiveEarlyDelivery-OP_25_CHECK_OP-NF.RecoveryInfo-NF.EDV -AppropStrokeCare-OP_12.eLab_Rec-Emergency.Services -MeaningfulUse-HAI4-IMMPT-HospVTE-Aggregate_Inf-NF.HAI2-Payment-IPThroughput)
summary(gmod2a)
##
## Call:
## glm(formula = ScoreBin ~ . - Recommend - Score - PAYAMI - PSI14 -
## IMMWork - TimeToECG - HAI6 - EDTimes - OP_17_TrackMedInfo -
## ElectiveEarlyDelivery - OP_25_CHECK_OP - NF.RecoveryInfo -
## NF.EDV - AppropStrokeCare - OP_12.eLab_Rec - Emergency.Services -
## MeaningfulUse - HAI4 - IMMPT - HospVTE - Aggregate_Inf -
## NF.HAI2 - Payment - IPThroughput, data = All)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.27736 -0.05979 -0.02259 0.01682 0.93446
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.010976 0.008174 1.343 0.179448
## PSI4 -0.007261 0.002847 -2.550 0.010820 *
## HipKnee -0.008292 0.003414 -2.429 0.015214 *
## NF.READM_30_HOSP_WIDE -0.033375 0.003024 -11.038 < 2e-16 ***
## NF.Quiet 0.007752 0.003766 2.059 0.039630 *
## NF.HAI5 0.013085 0.002851 4.590 4.62e-06 ***
## NF.SumStruct 0.015388 0.003007 5.117 3.31e-07 ***
## HCAHPSStaff 0.018622 0.003887 4.791 1.74e-06 ***
## OwnPhysician 0.192420 0.039751 4.841 1.36e-06 ***
## OwnProprietary 0.013652 0.009702 1.407 0.159514
## OwnVoluntary Non-Profit 0.010166 0.008106 1.254 0.209875
## AspirinCP -0.020671 0.005845 -3.537 0.000412 ***
## PSI90 -0.129973 0.015155 -8.576 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 0.02256087)
##
## Null deviance: 74.926 on 2858 degrees of freedom
## Residual deviance: 64.208 on 2846 degrees of freedom
## AIC: -2711.5
##
## Number of Fisher Scoring iterations: 2
roc(All$ScoreBin,gmod2a$fitted.values,plot=TRUE)
##
## Call:
## roc.default(response = All$ScoreBin, predictor = gmod2a$fitted.values, plot = TRUE)
##
## Data: gmod2a$fitted.values in 2782 controls (All$ScoreBin 0) < 77 cases (All$ScoreBin 1).
## Area under the curve: 0.9777
vif(gmod2a)
## GVIF Df GVIF^(1/(2*Df))
## PSI4 1.027001 1 1.013411
## HipKnee 1.084154 1 1.041227
## NF.READM_30_HOSP_WIDE 1.158238 1 1.076215
## NF.Quiet 1.796300 1 1.340261
## NF.HAI5 1.029360 1 1.014574
## NF.SumStruct 1.145765 1 1.070404
## HCAHPSStaff 1.851994 1 1.360880
## Own 1.228389 3 1.034878
## AspirinCP 1.068003 1 1.033442
## PSI90 1.046802 1 1.023133
sen1<-sensitivity(as.factor(round(gmod2a$fitted.values)),as.factor(All$ScoreBin))
sen1
## [1] 1
specificity(as.factor(round(gmod2a$fitted.values)),as.factor(All$ScoreBin))
## [1] 0.01298701
ppv1<-posPredValue(as.factor(round(gmod2a$fitted.values)),as.factor(All$ScoreBin))
ppv1
## [1] 0.973408
negPredValue(as.factor(round(gmod2a$fitted.values)),as.factor(All$ScoreBin))
## [1] 1
f11<-(2*sen1*ppv1)/(sen1+ppv1)
f11
## [1] 0.9865248
confusionMatrix(All$ScoreBin,round(gmod2a$fitted.values))
## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 2782 0
## 1 76 1
##
## Accuracy : 0.9734
## 95% CI : (0.9668, 0.979)
## No Information Rate : 0.9997
## P-Value [Acc > NIR] : 1
##
## Kappa : 0.025
## Mcnemar's Test P-Value : <2e-16
##
## Sensitivity : 0.97341
## Specificity : 1.00000
## Pos Pred Value : 1.00000
## Neg Pred Value : 0.01299
## Prevalence : 0.99965
## Detection Rate : 0.97307
## Detection Prevalence : 0.97307
## Balanced Accuracy : 0.98670
##
## 'Positive' Class : 0
##
MultiNomial Model for Hospital Score
require(VGAM)
## Loading required package: VGAM
## Loading required package: stats4
## Loading required package: splines
##
## Attaching package: 'VGAM'
## The following object is masked from 'package:car':
##
## logit
## The following object is masked from 'package:caret':
##
## predictors
## The following objects are masked from 'package:boot':
##
## logit, simplex
## The following objects are masked from 'package:psych':
##
## fisherz, logistic, logit
multimod<-vglm(data=All,Score~.-ScoreBin-Recommend-MeaningfulUse-HAI6-ElectiveEarlyDelivery-NF.EDV-OP_25_CHECK_OP-Aggregate_Inf-Emergency.Services-AppropStrokeCare-HospVTE-NF.HAI5-IMMWork-PAYAMI-HAI4-Payment,family=multinomial(refLevel=1))
## Warning in checkwz(wz, M = M, trace = trace, wzepsilon = control
## $wzepsilon): 10 diagonal elements of the working weights variable 'wz' have
## been replaced by 1.819e-12
## Warning in checkwz(wz, M = M, trace = trace, wzepsilon = control
## $wzepsilon): 85 diagonal elements of the working weights variable 'wz' have
## been replaced by 1.819e-12
## Warning in checkwz(wz, M = M, trace = trace, wzepsilon = control
## $wzepsilon): 163 diagonal elements of the working weights variable 'wz'
## have been replaced by 1.819e-12
## Warning in checkwz(wz, M = M, trace = trace, wzepsilon = control
## $wzepsilon): 230 diagonal elements of the working weights variable 'wz'
## have been replaced by 1.819e-12
## Warning in checkwz(wz, M = M, trace = trace, wzepsilon = control
## $wzepsilon): 266 diagonal elements of the working weights variable 'wz'
## have been replaced by 1.819e-12
## Warning in checkwz(wz, M = M, trace = trace, wzepsilon = control
## $wzepsilon): 276 diagonal elements of the working weights variable 'wz'
## have been replaced by 1.819e-12
## Warning in checkwz(wz, M = M, trace = trace, wzepsilon = control
## $wzepsilon): 276 diagonal elements of the working weights variable 'wz'
## have been replaced by 1.819e-12
## Warning in checkwz(wz, M = M, trace = trace, wzepsilon = control
## $wzepsilon): 276 diagonal elements of the working weights variable 'wz'
## have been replaced by 1.819e-12
## Warning in checkwz(wz, M = M, trace = trace, wzepsilon = control
## $wzepsilon): 276 diagonal elements of the working weights variable 'wz'
## have been replaced by 1.819e-12
## Warning in checkwz(wz, M = M, trace = trace, wzepsilon = control
## $wzepsilon): 276 diagonal elements of the working weights variable 'wz'
## have been replaced by 1.819e-12
## Warning in checkwz(wz, M = M, trace = trace, wzepsilon = control
## $wzepsilon): 276 diagonal elements of the working weights variable 'wz'
## have been replaced by 1.819e-12
## Warning in checkwz(wz, M = M, trace = trace, wzepsilon = control
## $wzepsilon): 276 diagonal elements of the working weights variable 'wz'
## have been replaced by 1.819e-12
summary(multimod)
##
## Call:
## vglm(formula = Score ~ . - ScoreBin - Recommend - MeaningfulUse -
## HAI6 - ElectiveEarlyDelivery - NF.EDV - OP_25_CHECK_OP -
## Aggregate_Inf - Emergency.Services - AppropStrokeCare - HospVTE -
## NF.HAI5 - IMMWork - PAYAMI - HAI4 - Payment, family = multinomial(refLevel = 1),
## data = All)
##
##
## Pearson residuals:
## Min 1Q Median 3Q Max
## log(mu[,2]/mu[,1]) -12.215 -0.1624 -0.0355960 -3.284e-04 15.97
## log(mu[,3]/mu[,1]) -10.717 -0.3499 -0.0046272 4.100e-01 11.51
## log(mu[,4]/mu[,1]) -7.004 -0.2237 -0.0424332 -3.433e-10 196.54
## log(mu[,5]/mu[,1]) -5.282 -0.0169 -0.0006646 -2.702e-07 14.41
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept):1 9.07413 1.32563 6.845 7.64e-12 ***
## (Intercept):2 11.33990 1.38333 8.198 2.45e-16 ***
## (Intercept):3 8.16291 1.43108 5.704 1.17e-08 ***
## (Intercept):4 -1.79332 2.01241 -0.891 0.372861
## IPThroughput:1 -0.28157 0.14966 -1.881 0.059914 .
## IPThroughput:2 -0.46283 0.17917 -2.583 0.009788 **
## IPThroughput:3 -0.44888 0.20833 -2.155 0.031189 *
## IPThroughput:4 -0.01047 0.37999 -0.028 0.978029
## PSI14:1 -0.03672 0.14559 -0.252 0.800873
## PSI14:2 -0.23370 0.16143 -1.448 0.147717
## PSI14:3 -0.35355 0.17537 -2.016 0.043798 *
## PSI14:4 -0.15359 0.25294 -0.607 0.543707
## IMMPT:1 0.30445 0.14759 2.063 0.039125 *
## IMMPT:2 0.29326 0.16788 1.747 0.080667 .
## IMMPT:3 0.57036 0.18571 3.071 0.002131 **
## IMMPT:4 0.99312 0.43407 2.288 0.022142 *
## PSI4:1 -0.42437 0.16425 -2.584 0.009773 **
## PSI4:2 -0.84533 0.18156 -4.656 3.23e-06 ***
## PSI4:3 -1.30501 0.19479 -6.699 2.09e-11 ***
## PSI4:4 -1.78075 0.25529 -6.975 3.05e-12 ***
## HipKnee:1 0.49131 0.26578 1.849 0.064519 .
## HipKnee:2 0.55930 0.27941 2.002 0.045318 *
## HipKnee:3 0.55221 0.29016 1.903 0.057027 .
## HipKnee:4 0.67054 0.34398 1.949 0.051250 .
## EDTimes:1 -0.14107 0.21629 -0.652 0.514251
## EDTimes:2 -0.32545 0.24521 -1.327 0.184447
## EDTimes:3 -0.53863 0.27188 -1.981 0.047577 *
## EDTimes:4 -0.52713 0.42708 -1.234 0.217099
## NF.READM_30_HOSP_WIDE:1 -2.01402 0.23934 -8.415 < 2e-16 ***
## NF.READM_30_HOSP_WIDE:2 -4.20376 0.27088 -15.519 < 2e-16 ***
## NF.READM_30_HOSP_WIDE:3 -6.22503 0.29504 -21.099 < 2e-16 ***
## NF.READM_30_HOSP_WIDE:4 -8.98751 0.45143 -19.909 < 2e-16 ***
## NF.RecoveryInfo:1 0.12094 0.24704 0.490 0.624433
## NF.RecoveryInfo:2 0.12248 0.26437 0.463 0.643150
## NF.RecoveryInfo:3 0.58661 0.27989 2.096 0.036097 *
## NF.RecoveryInfo:4 0.83322 0.40660 2.049 0.040439 *
## NF.Quiet:1 0.28936 0.27362 1.058 0.290269
## NF.Quiet:2 0.34946 0.29017 1.204 0.228460
## NF.Quiet:3 0.34158 0.30353 1.125 0.260432
## NF.Quiet:4 0.90689 0.40297 2.251 0.024416 *
## NF.HAI2:1 -0.49815 0.24275 -2.052 0.040154 *
## NF.HAI2:2 -0.62386 0.25659 -2.431 0.015043 *
## NF.HAI2:3 -0.51823 0.26490 -1.956 0.050429 .
## NF.HAI2:4 -0.55834 0.33775 -1.653 0.098307 .
## NF.SumStruct:1 0.52156 0.28354 1.839 0.065854 .
## NF.SumStruct:2 1.02371 0.30532 3.353 0.000800 ***
## NF.SumStruct:3 1.36594 0.32000 4.269 1.97e-05 ***
## NF.SumStruct:4 2.45177 0.44561 5.502 3.76e-08 ***
## HCAHPSStaff:1 1.48642 0.39171 3.795 0.000148 ***
## HCAHPSStaff:2 3.59313 0.42414 8.472 < 2e-16 ***
## HCAHPSStaff:3 5.13392 0.44124 11.635 < 2e-16 ***
## HCAHPSStaff:4 6.82137 0.55601 12.268 < 2e-16 ***
## OwnPhysician:1 7.55050 476.98564 0.016 0.987370
## OwnPhysician:2 7.81915 476.98629 0.016 0.986921
## OwnPhysician:3 9.56794 476.98731 0.020 0.983996
## OwnPhysician:4 10.94579 476.99128 0.023 0.981692
## OwnProprietary:1 -1.13209 0.64794 -1.747 0.080600 .
## OwnProprietary:2 -0.52890 0.69246 -0.764 0.444990
## OwnProprietary:3 -0.01929 0.73305 -0.026 0.979003
## OwnProprietary:4 1.15033 1.13962 1.009 0.312786
## OwnVoluntary Non-Profit:1 0.25687 0.52156 0.492 0.622371
## OwnVoluntary Non-Profit:2 0.91997 0.56298 1.634 0.102236
## OwnVoluntary Non-Profit:3 1.49156 0.59539 2.505 0.012238 *
## OwnVoluntary Non-Profit:4 3.15736 0.88922 3.551 0.000384 ***
## OP_12.eLab_Rec:1 0.82646 1.13672 0.727 0.467193
## OP_12.eLab_Rec:2 -0.43892 1.19199 -0.368 0.712708
## OP_12.eLab_Rec:3 -1.42571 1.23824 -1.151 0.249567
## OP_12.eLab_Rec:4 -3.49605 1.74299 -2.006 0.044879 *
## OP_17_TrackMedInfo:1 -2.15432 1.00419 -2.145 0.031926 *
## OP_17_TrackMedInfo:2 -2.43134 1.04971 -2.316 0.020547 *
## OP_17_TrackMedInfo:3 -2.48228 1.08673 -2.284 0.022361 *
## OP_17_TrackMedInfo:4 -1.92089 1.53375 -1.252 0.210418
## AspirinCP:1 -2.66722 1.25222 -2.130 0.033172 *
## AspirinCP:2 -3.25378 1.38779 -2.345 0.019049 *
## AspirinCP:3 -3.31811 1.53743 -2.158 0.030910 *
## AspirinCP:4 -2.89310 1.96657 -1.471 0.141253
## TimeToECG:1 1.71177 1.21288 1.411 0.158150
## TimeToECG:2 2.15477 1.35306 1.593 0.111268
## TimeToECG:3 2.01262 1.50616 1.336 0.181465
## TimeToECG:4 0.50943 1.95285 0.261 0.794196
## PSI90:1 -11.36413 1.29826 -8.753 < 2e-16 ***
## PSI90:2 -21.93507 1.44874 -15.141 < 2e-16 ***
## PSI90:3 -30.91783 1.54319 -20.035 < 2e-16 ***
## PSI90:4 -41.75321 2.12841 -19.617 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Number of linear predictors: 4
##
## Names of linear predictors:
## log(mu[,2]/mu[,1]), log(mu[,3]/mu[,1]), log(mu[,4]/mu[,1]), log(mu[,5]/mu[,1])
##
## Residual deviance: 3198.767 on 11352 degrees of freedom
##
## Log-likelihood: -1599.383 on 11352 degrees of freedom
##
## Number of iterations: 15
##
## Reference group is level 1 of the response
class<-predict(multimod, type="response")
categHat <- levels(as.factor(All$Score))[max.col(class)]
head(categHat)
## [1] "4" "4" "4" "5" "4" "5"
facHat <- factor(categHat, levels=levels(as.factor(All$Score)))
logLik(multimod)
## [1] -1599.383
AIC(multimod)
## [1] 3366.767
### Compare to zero model
vglm0 <- vglm(Score ~ 1, family=multinomial(refLevel=1), data=All)
LLf <- logLik(multimod)
LL0 <- logLik(vglm0)
##McFadden
McF<-as.vector(1 - (LLf / LL0))
#Cox & Snell
CS<-as.vector(1 - exp((2/nrow(All)) * (LL0 - LLf)))
#Nagelkerke
Nagel<-as.vector((1 - exp((2/nrow(All)) * (LL0 - LLf))) / (1 - exp(LL0)^(2/nrow(All))))
McF
## [1] 0.5530888
CS
## [1] 0.7495903
Nagel
## [1] 0.7495903