Read data from SPSS
library(foreign)
DataSPSS <- read.spss("Fs36mix.sav", to.data.frame=T, use.value.labels=FALSE)
#names(DataSPSS)
#summary(DataSPSS)
# get column names
#colnames(DataSPSS)
# Rename variable to Uppercase from col 17:49
#names(DataSPSS)[90:114] <- toupper(names(DataSPSS)[90:114])
#fix(DataSPSS)
#str(DataSPSS)
#levels(DataSPSS$Timept_gr)
Xóa dữ liệu NA
DataSPSS <- na.omit(DataSPSS)
Biến đổi thành biến Factor
# Etiology to Factor Etiology.F
DataSPSS$Etiology.F[DataSPSS$Timept_gr==1]<-"Glomerulonephritis"
DataSPSS$Etiology.F[DataSPSS$Timept_gr==2]<-"Tang huyet ap"
DataSPSS$Etiology.F[DataSPSS$Timept_gr==3]<-"Dai thao duong"
DataSPSS$Etiology.F[DataSPSS$Timept_gr==4]<-"Khac"
DataSPSS$Etiology.F<-as.factor(DataSPSS$Etiology.F)
# Group to Factor GroupST
DataSPSS$GroupST[DataSPSS$Group=="10"]<-"Suy than co loc mau"
DataSPSS$GroupST[DataSPSS$Group=="21"]<-"Sau ghep"
DataSPSS$GroupST[DataSPSS$Group=="10"]<-"Sau ghep 3 thang"
DataSPSS$GroupST<-as.factor(DataSPSS$GroupST)
# Male to Factor Gender
DataSPSS$Gender[DataSPSS$Male==1]<-"Nam"
DataSPSS$Gender[DataSPSS$Male==2]<-"Nu"
DataSPSS$Gender<-as.factor(DataSPSS$Gender)
# Timept_gr to Factor GroupTimePt
DataSPSS$GroupTimePt[DataSPSS$Timept_gr==1]<-"0 - 3 thang"
DataSPSS$GroupTimePt[DataSPSS$Timept_gr==2]<-"3 - 12 thang"
DataSPSS$GroupTimePt[DataSPSS$Timept_gr==3]<-"1 - 5 nam"
DataSPSS$GroupTimePt[DataSPSS$Timept_gr==4]<-"> 5 nam"
DataSPSS$GroupTimePt<-as.factor(DataSPSS$GroupTimePt)
Lấy các trường dữ liệu cần thiết
# Get column by name
Data_New <-
DataSPSS[, c(
90:113,
55,
which(
colnames(DataSPSS) == "c2score" |
colnames(DataSPSS) == "Male" |
colnames(DataSPSS) == "Group" |
colnames(DataSPSS) == "Etiology.F" |
colnames(DataSPSS) == "GroupST" |
colnames(DataSPSS) == "Gender" |
colnames(DataSPSS) == "GroupTimePt"
)
)]
names(Data_New)
## [1] "phy_function" "phy_health" "emotional" "fatigue"
## [5] "wellbeing" "social_fun" "pain" "general"
## [9] "PostPT" "age" "BMI" "Weight"
## [13] "Height" "Ure" "Cre" "Chol"
## [17] "trig" "Alb" "protein" "Hb"
## [21] "RCB" "Canxi" "PCS" "MCS"
## [25] "c2score" "Male" "Group" "c2score.1"
## [29] "Etiology.F" "GroupST" "Gender" "GroupTimePt"
nameCol <- c("c2score", "phy_function", "phy_health" , "emotional" , "fatigue" , "wellbeing" , "social_fun" , "pain" , "general" , "PostPT" , "age" , "BMI" , "Weight" , "Height" , "Ure" , "Cre" , "Chol" , "trig" , "Alb" , "protein" , "Hb" , "RCB" , "Canxi" , "PCS" , "MCS" , "Male","Gender","Group","GroupST","Etiology.F","GroupTimePt")
# Sắp xếp lại thứ tự các cột
Data_New <- Data_New[, nameCol]
Xem xét độ tương quan giữa các biến độc lập
pairs(Data_New[11:20])
Chạy hồi quy tuyến tính cho từng Outcome và các biến phụ thuộc
# names(Data_New)
for (i in 1:10) {
outcome <- names(Data_New[i])
variables <- names(Data_New[11:20])
f <- as.formula(paste(outcome,
paste(variables, collapse = " + "),
sep = " ~ "))
print(paste(i,'---',outcome, "###########"))
# Exec fucntion lm()
result = summary(assign(paste0('lm1.mod', i), lm(formula = f, data = Data_New)))
print(result)
}
## [1] "1 --- c2score ###########"
##
## Call:
## lm(formula = f, data = Data_New)
##
## Residuals:
## Min 1Q Median 3Q Max
## -44.206 -12.424 0.424 12.042 42.809
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -719.58607 684.25575 -1.052 0.29913
## age -0.72109 0.26568 -2.714 0.00968 **
## BMI 22.34996 15.86722 1.409 0.16650
## Weight -6.85274 5.81765 -1.178 0.24562
## Height 4.09112 4.12757 0.991 0.32742
## Ure 3.27113 1.62288 2.016 0.05042 .
## Cre 0.06656 0.12401 0.537 0.59431
## Chol 6.06705 3.04757 1.991 0.05320 .
## trig -7.03356 2.25303 -3.122 0.00329 **
## Alb 0.64328 1.70765 0.377 0.70834
## protein -0.09294 0.83240 -0.112 0.91164
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 23.16 on 41 degrees of freedom
## Multiple R-squared: 0.4874, Adjusted R-squared: 0.3624
## F-statistic: 3.899 on 10 and 41 DF, p-value: 0.0009009
##
## [1] "2 --- phy_function ###########"
##
## Call:
## lm(formula = f, data = Data_New)
##
## Residuals:
## Min 1Q Median 3Q Max
## -60.499 -10.346 3.842 9.422 27.734
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.956e+02 5.176e+02 -0.378 0.7075
## age -3.263e-01 2.010e-01 -1.624 0.1121
## BMI 6.157e+00 1.200e+01 0.513 0.6107
## Weight -1.891e+00 4.401e+00 -0.430 0.6696
## Height 1.354e+00 3.122e+00 0.433 0.6669
## Ure 1.061e+00 1.228e+00 0.864 0.3926
## Cre 9.857e-03 9.380e-02 0.105 0.9168
## Chol -1.397e+00 2.305e+00 -0.606 0.5480
## trig -3.359e+00 1.704e+00 -1.971 0.0555 .
## Alb 1.835e+00 1.292e+00 1.421 0.1630
## protein -4.532e-01 6.297e-01 -0.720 0.4758
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 17.52 on 41 degrees of freedom
## Multiple R-squared: 0.1982, Adjusted R-squared: 0.002589
## F-statistic: 1.013 on 10 and 41 DF, p-value: 0.4491
##
## [1] "3 --- phy_health ###########"
##
## Call:
## lm(formula = f, data = Data_New)
##
## Residuals:
## Min 1Q Median 3Q Max
## -71.058 -32.682 1.205 26.236 64.190
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1020.3875 1187.0435 -0.860 0.3950
## age -0.1292 0.4609 -0.280 0.7806
## BMI 24.4288 27.5264 0.887 0.3800
## Weight -9.0445 10.0924 -0.896 0.3754
## Height 6.3697 7.1605 0.890 0.3789
## Ure 2.1456 2.8154 0.762 0.4504
## Cre -0.2234 0.2151 -1.039 0.3050
## Chol 12.1061 5.2869 2.290 0.0272 *
## trig -5.0653 3.9086 -1.296 0.2022
## Alb 1.5915 2.9624 0.537 0.5940
## protein -1.1388 1.4440 -0.789 0.4349
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 40.19 on 41 degrees of freedom
## Multiple R-squared: 0.1803, Adjusted R-squared: -0.01967
## F-statistic: 0.9016 on 10 and 41 DF, p-value: 0.5403
##
## [1] "4 --- emotional ###########"
##
## Call:
## lm(formula = f, data = Data_New)
##
## Residuals:
## Min 1Q Median 3Q Max
## -68.482 -25.001 -6.592 31.705 71.469
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.512e+03 1.182e+03 -1.279 0.208
## age 9.027e-02 4.591e-01 0.197 0.845
## BMI 2.691e+01 2.742e+01 0.981 0.332
## Weight -1.062e+01 1.005e+01 -1.056 0.297
## Height 9.172e+00 7.133e+00 1.286 0.206
## Ure 1.920e+00 2.804e+00 0.685 0.497
## Cre -3.436e-01 2.143e-01 -1.604 0.116
## Chol 7.651e+00 5.266e+00 1.453 0.154
## trig -8.588e-01 3.893e+00 -0.221 0.827
## Alb -3.502e-01 2.951e+00 -0.119 0.906
## protein 1.220e+00 1.438e+00 0.848 0.401
##
## Residual standard error: 40.03 on 41 degrees of freedom
## Multiple R-squared: 0.1591, Adjusted R-squared: -0.04604
## F-statistic: 0.7755 on 10 and 41 DF, p-value: 0.6512
##
## [1] "5 --- fatigue ###########"
##
## Call:
## lm(formula = f, data = Data_New)
##
## Residuals:
## Min 1Q Median 3Q Max
## -58.074 -8.357 0.415 10.412 34.988
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -761.49159 559.82236 -1.360 0.1812
## age -0.14919 0.21737 -0.686 0.4964
## BMI 20.62132 12.98173 1.588 0.1199
## Weight -6.96791 4.75970 -1.464 0.1508
## Height 4.10147 3.37696 1.215 0.2315
## Ure 1.74881 1.32775 1.317 0.1951
## Cre 0.07326 0.10145 0.722 0.4743
## Chol 0.20680 2.49336 0.083 0.9343
## trig -3.26282 1.84332 -1.770 0.0841 .
## Alb 2.22642 1.39711 1.594 0.1187
## protein 0.16198 0.68103 0.238 0.8132
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 18.95 on 41 degrees of freedom
## Multiple R-squared: 0.269, Adjusted R-squared: 0.09067
## F-statistic: 1.509 on 10 and 41 DF, p-value: 0.1713
##
## [1] "6 --- wellbeing ###########"
##
## Call:
## lm(formula = f, data = Data_New)
##
## Residuals:
## Min 1Q Median 3Q Max
## -38.536 -10.186 0.812 10.034 23.687
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -742.42055 481.68398 -1.541 0.1309
## age 0.07090 0.18703 0.379 0.7066
## BMI 20.65498 11.16978 1.849 0.0716 .
## Weight -7.04388 4.09536 -1.720 0.0930 .
## Height 4.19570 2.90561 1.444 0.1563
## Ure 1.49641 1.14243 1.310 0.1975
## Cre 0.07114 0.08729 0.815 0.4198
## Chol -1.59855 2.14535 -0.745 0.4604
## trig -1.71757 1.58603 -1.083 0.2852
## Alb 2.01324 1.20211 1.675 0.1016
## protein -0.06206 0.58597 -0.106 0.9162
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 16.31 on 41 degrees of freedom
## Multiple R-squared: 0.2775, Adjusted R-squared: 0.1013
## F-statistic: 1.575 on 10 and 41 DF, p-value: 0.1489
##
## [1] "7 --- social_fun ###########"
##
## Call:
## lm(formula = f, data = Data_New)
##
## Residuals:
## Min 1Q Median 3Q Max
## -54.107 -9.627 0.969 10.044 38.797
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -960.19002 575.13544 -1.670 0.1026
## age -0.03303 0.22331 -0.148 0.8831
## BMI 26.92374 13.33682 2.019 0.0501 .
## Weight -9.30569 4.88990 -1.903 0.0641 .
## Height 5.80725 3.46933 1.674 0.1018
## Ure 2.00777 1.36407 1.472 0.1487
## Cre -0.05526 0.10423 -0.530 0.5988
## Chol 3.89973 2.56157 1.522 0.1356
## trig -3.45094 1.89374 -1.822 0.0757 .
## Alb 1.33933 1.43533 0.933 0.3562
## protein -0.56566 0.69966 -0.808 0.4235
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 19.47 on 41 degrees of freedom
## Multiple R-squared: 0.2303, Adjusted R-squared: 0.04252
## F-statistic: 1.227 on 10 and 41 DF, p-value: 0.3035
##
## [1] "8 --- pain ###########"
##
## Call:
## lm(formula = f, data = Data_New)
##
## Residuals:
## Min 1Q Median 3Q Max
## -65.619 -13.419 -1.326 17.206 44.074
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1456.1539 752.0344 -1.936 0.0597 .
## age -0.1971 0.2920 -0.675 0.5034
## BMI 35.8017 17.4389 2.053 0.0465 *
## Weight -12.4480 6.3939 -1.947 0.0584 .
## Height 8.4089 4.5364 1.854 0.0710 .
## Ure 3.0093 1.7836 1.687 0.0992 .
## Cre -0.1680 0.1363 -1.233 0.2247
## Chol 3.0177 3.3494 0.901 0.3729
## trig -4.3158 2.4762 -1.743 0.0888 .
## Alb 2.7569 1.8768 1.469 0.1495
## protein -0.2663 0.9149 -0.291 0.7724
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 25.46 on 41 degrees of freedom
## Multiple R-squared: 0.2505, Adjusted R-squared: 0.06769
## F-statistic: 1.37 on 10 and 41 DF, p-value: 0.2281
##
## [1] "9 --- general ###########"
##
## Call:
## lm(formula = f, data = Data_New)
##
## Residuals:
## Min 1Q Median 3Q Max
## -34.957 -9.612 1.446 11.467 25.940
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 71.48251 488.24128 0.146 0.8843
## age -0.24797 0.18957 -1.308 0.1982
## BMI -0.94492 11.32183 -0.083 0.9339
## Weight 0.76613 4.15111 0.185 0.8545
## Height -0.54177 2.94517 -0.184 0.8550
## Ure 0.96087 1.15798 0.830 0.4115
## Cre 0.02817 0.08848 0.318 0.7519
## Chol 0.93186 2.17455 0.429 0.6705
## trig -3.20632 1.60762 -1.994 0.0528 .
## Alb 1.54772 1.21847 1.270 0.2112
## protein -0.35167 0.59395 -0.592 0.5570
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 16.53 on 41 degrees of freedom
## Multiple R-squared: 0.1895, Adjusted R-squared: -0.008227
## F-statistic: 0.9584 on 10 and 41 DF, p-value: 0.4928
##
## [1] "10 --- PostPT ###########"
##
## Call:
## lm(formula = f, data = Data_New)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.84476 -0.36749 0.03496 0.26322 0.82930
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.271532 13.009758 0.482 0.63232
## age -0.007056 0.005051 -1.397 0.16996
## BMI -0.107337 0.301683 -0.356 0.72382
## Weight 0.036661 0.110611 0.331 0.74200
## Height -0.010430 0.078477 -0.133 0.89491
## Ure -0.012167 0.030856 -0.394 0.69539
## Cre 0.003048 0.002358 1.293 0.20336
## Chol -0.064062 0.057943 -1.106 0.27535
## trig -0.095034 0.042837 -2.218 0.03212 *
## Alb -0.093536 0.032468 -2.881 0.00628 **
## protein 0.023418 0.015826 1.480 0.14660
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4404 on 41 degrees of freedom
## Multiple R-squared: 0.3734, Adjusted R-squared: 0.2206
## F-statistic: 2.443 on 10 and 41 DF, p-value: 0.02165
# Tìm ra 2 hàm hồi quy
# summary(lm(c2score ~ age + trig, data = Data_New))
# summary(lm(PostPT ~ age + trig + Ure + Cre + trig + Alb, data = Data_New))
Chạy Stepwise
# names(Data_New)
for (i in 1:10) {
outcome <- names(Data_New[i])
variables <- names(Data_New[11:20])
f <- as.formula(paste(outcome,
paste(variables, collapse = " + "),
sep = " ~ "))
print(paste(i,'---',outcome, "###########"))
# Exec fucntion lm()
step(lm(formula = f, data = Data_New), direction = "backward")
}
## [1] "1 --- c2score ###########"
## Start: AIC=336.47
## c2score ~ age + BMI + Weight + Height + Ure + Cre + Chol + trig +
## Alb + protein
##
## Df Sum of Sq RSS AIC
## - protein 1 6.7 22007 334.49
## - Alb 1 76.1 22076 334.65
## - Cre 1 154.6 22155 334.84
## - Height 1 527.2 22527 335.70
## - Weight 1 744.5 22745 336.20
## <none> 22000 336.47
## - BMI 1 1064.6 23065 336.93
## - Chol 1 2126.6 24127 339.27
## - Ure 1 2180.0 24180 339.39
## - age 1 3952.7 25953 343.06
## - trig 1 5229.4 27230 345.56
##
## Step: AIC=334.49
## c2score ~ age + BMI + Weight + Height + Ure + Cre + Chol + trig +
## Alb
##
## Df Sum of Sq RSS AIC
## - Alb 1 71.4 22078 332.66
## - Cre 1 178.4 22185 332.91
## - Height 1 541.8 22549 333.75
## - Weight 1 750.4 22757 334.23
## <none> 22007 334.49
## - BMI 1 1074.0 23081 334.97
## - Chol 1 2120.4 24127 337.27
## - Ure 1 2178.0 24185 337.40
## - age 1 4135.5 26142 341.44
## - trig 1 5338.2 27345 343.78
##
## Step: AIC=332.66
## c2score ~ age + BMI + Weight + Height + Ure + Cre + Chol + trig
##
## Df Sum of Sq RSS AIC
## - Cre 1 287.3 22365 331.33
## - Height 1 565.3 22643 331.97
## - Weight 1 778.8 22857 332.46
## <none> 22078 332.66
## - BMI 1 1115.5 23194 333.22
## - Chol 1 2084.7 24163 335.35
## - Ure 1 2173.2 24251 335.54
## - age 1 4064.9 26143 339.44
## - trig 1 5289.7 27368 341.83
##
## Step: AIC=331.33
## c2score ~ age + BMI + Weight + Height + Ure + Chol + trig
##
## Df Sum of Sq RSS AIC
## <none> 22365 331.33
## - Height 1 958.7 23324 331.51
## - Weight 1 1171.5 23537 331.98
## - BMI 1 1543.6 23909 332.80
## - Chol 1 2244.9 24610 334.30
## - Ure 1 3358.0 25723 336.60
## - age 1 4080.6 26446 338.04
## - trig 1 5023.0 27388 339.86
## [1] "2 --- phy_function ###########"
## Start: AIC=307.44
## phy_function ~ age + BMI + Weight + Height + Ure + Cre + Chol +
## trig + Alb + protein
##
## Df Sum of Sq RSS AIC
## - Cre 1 3.39 12592 305.46
## - Weight 1 56.70 12646 305.68
## - Height 1 57.70 12647 305.68
## - BMI 1 80.79 12670 305.78
## - Chol 1 112.68 12702 305.91
## - protein 1 159.04 12748 306.10
## - Ure 1 229.17 12818 306.38
## <none> 12589 307.44
## - Alb 1 619.58 13208 307.94
## - age 1 809.41 13398 308.69
## - trig 1 1192.45 13781 310.15
##
## Step: AIC=305.46
## phy_function ~ age + BMI + Weight + Height + Ure + Chol + trig +
## Alb + protein
##
## Df Sum of Sq RSS AIC
## - Weight 1 67.42 12660 303.74
## - Height 1 70.04 12662 303.75
## - BMI 1 92.21 12684 303.84
## - Chol 1 109.76 12702 303.91
## - protein 1 178.70 12771 304.19
## - Ure 1 328.12 12920 304.80
## <none> 12592 305.46
## - Alb 1 764.40 13357 306.52
## - age 1 830.18 13422 306.78
## - trig 1 1191.59 13784 308.16
##
## Step: AIC=303.74
## phy_function ~ age + BMI + Height + Ure + Chol + trig + Alb +
## protein
##
## Df Sum of Sq RSS AIC
## - Height 1 2.63 12662 301.75
## - Chol 1 128.39 12788 302.26
## - protein 1 201.73 12861 302.56
## - Ure 1 291.51 12951 302.92
## - BMI 1 336.36 12996 303.10
## <none> 12660 303.74
## - Alb 1 871.70 13531 305.20
## - age 1 1000.16 13660 305.69
## - trig 1 1152.08 13812 306.27
##
## Step: AIC=301.75
## phy_function ~ age + BMI + Ure + Chol + trig + Alb + protein
##
## Df Sum of Sq RSS AIC
## - Chol 1 125.77 12788 300.26
## - protein 1 249.04 12911 300.76
## - Ure 1 304.00 12966 300.98
## - BMI 1 389.64 13052 301.32
## <none> 12662 301.75
## - Alb 1 934.45 13597 303.45
## - age 1 1029.83 13692 303.81
## - trig 1 1151.09 13813 304.27
##
## Step: AIC=300.26
## phy_function ~ age + BMI + Ure + trig + Alb + protein
##
## Df Sum of Sq RSS AIC
## - protein 1 238.71 13027 299.22
## - Ure 1 328.74 13117 299.58
## - BMI 1 375.37 13164 299.77
## <none> 12788 300.26
## - age 1 906.20 13694 301.82
## - Alb 1 943.44 13732 301.96
## - trig 1 1198.16 13986 302.92
##
## Step: AIC=299.22
## phy_function ~ age + BMI + Ure + trig + Alb
##
## Df Sum of Sq RSS AIC
## - Ure 1 350.71 13378 298.61
## - BMI 1 482.00 13509 299.11
## <none> 13027 299.22
## - Alb 1 733.65 13760 300.07
## - age 1 765.57 13792 300.19
## - trig 1 999.33 14026 301.07
##
## Step: AIC=298.6
## phy_function ~ age + BMI + trig + Alb
##
## Df Sum of Sq RSS AIC
## - BMI 1 297.79 13675 297.75
## <none> 13378 298.61
## - Alb 1 532.88 13910 298.64
## - age 1 744.71 14122 299.42
## - trig 1 818.21 14196 299.69
##
## Step: AIC=297.75
## phy_function ~ age + trig + Alb
##
## Df Sum of Sq RSS AIC
## <none> 13675 297.75
## - Alb 1 663.24 14339 298.21
## - age 1 669.84 14345 298.24
## - trig 1 850.30 14526 298.89
## [1] "3 --- phy_health ###########"
## Start: AIC=393.77
## phy_health ~ age + BMI + Weight + Height + Ure + Cre + Chol +
## trig + Alb + protein
##
## Df Sum of Sq RSS AIC
## - age 1 127.0 66336 391.87
## - Alb 1 466.1 66676 392.13
## - Ure 1 937.9 67147 392.50
## - protein 1 1004.3 67214 392.55
## - BMI 1 1271.9 67481 392.75
## - Height 1 1277.9 67487 392.76
## - Weight 1 1296.9 67506 392.77
## - Cre 1 1742.2 67952 393.12
## <none> 66209 393.77
## - trig 1 2712.1 68922 393.85
## - Chol 1 8467.2 74677 398.02
##
## Step: AIC=391.87
## phy_health ~ BMI + Weight + Height + Ure + Cre + Chol + trig +
## Alb + protein
##
## Df Sum of Sq RSS AIC
## - Alb 1 379.1 66716 390.16
## - protein 1 888.6 67225 390.56
## - Ure 1 919.1 67256 390.58
## - BMI 1 1493.5 67830 391.02
## - Weight 1 1526.9 67863 391.05
## - Height 1 1527.8 67864 391.05
## - Cre 1 1662.0 67998 391.15
## <none> 66336 391.87
## - trig 1 2813.8 69150 392.03
## - Chol 1 9821.2 76158 397.04
##
## Step: AIC=390.16
## phy_health ~ BMI + Weight + Height + Ure + Cre + Chol + trig +
## protein
##
## Df Sum of Sq RSS AIC
## - protein 1 575.8 67291 388.61
## - Ure 1 625.9 67342 388.65
## - Cre 1 1306.9 68022 389.17
## - BMI 1 1545.0 68261 389.35
## - Weight 1 1555.9 68271 389.36
## - Height 1 1589.3 68305 389.39
## - trig 1 2574.9 69290 390.13
## <none> 66716 390.16
## - Chol 1 9471.7 76187 395.06
##
## Step: AIC=388.61
## phy_health ~ BMI + Weight + Height + Ure + Cre + Chol + trig
##
## Df Sum of Sq RSS AIC
## - Ure 1 695.2 67986 387.14
## - Cre 1 1196.7 68488 387.52
## - BMI 1 1504.3 68796 387.76
## - Weight 1 1507.4 68799 387.76
## - Height 1 1632.1 68923 387.85
## - trig 1 2251.2 69543 388.32
## <none> 67291 388.61
## - Chol 1 9195.8 76487 393.27
##
## Step: AIC=387.14
## phy_health ~ BMI + Weight + Height + Cre + Chol + trig
##
## Df Sum of Sq RSS AIC
## - Cre 1 693.5 68680 385.67
## - BMI 1 1054.6 69041 385.94
## - Weight 1 1073.8 69060 385.96
## - Height 1 1192.8 69179 386.05
## - trig 1 2094.2 70081 386.72
## <none> 67986 387.14
## - Chol 1 8765.1 76752 391.45
##
## Step: AIC=385.67
## phy_health ~ BMI + Weight + Height + Chol + trig
##
## Df Sum of Sq RSS AIC
## - Weight 1 777.3 69457 384.26
## - BMI 1 799.2 69479 384.27
## - Height 1 827.8 69508 384.29
## <none> 68680 385.67
## - trig 1 2780.2 71460 385.73
## - Chol 1 8500.3 77180 389.74
##
## Step: AIC=384.26
## phy_health ~ BMI + Height + Chol + trig
##
## Df Sum of Sq RSS AIC
## - BMI 1 38.1 69495 382.28
## - Height 1 56.2 69514 382.30
## - trig 1 2577.3 72035 384.15
## <none> 69457 384.26
## - Chol 1 8353.6 77811 388.16
##
## Step: AIC=382.28
## phy_health ~ Height + Chol + trig
##
## Df Sum of Sq RSS AIC
## - Height 1 98.6 69594 380.36
## - trig 1 2637.7 72133 382.22
## <none> 69495 382.28
## - Chol 1 8326.2 77822 386.17
##
## Step: AIC=380.36
## phy_health ~ Chol + trig
##
## Df Sum of Sq RSS AIC
## - trig 1 2539.1 72133 380.22
## <none> 69594 380.36
## - Chol 1 8870.3 78464 384.60
##
## Step: AIC=380.22
## phy_health ~ Chol
##
## Df Sum of Sq RSS AIC
## <none> 72133 380.22
## - Chol 1 8636.1 80769 384.10
## [1] "4 --- emotional ###########"
## Start: AIC=393.36
## emotional ~ age + BMI + Weight + Height + Ure + Cre + Chol +
## trig + Alb + protein
##
## Df Sum of Sq RSS AIC
## - Alb 1 22.6 65716 391.38
## - age 1 62.0 65755 391.41
## - trig 1 78.0 65771 391.42
## - Ure 1 751.4 66445 391.95
## - protein 1 1152.3 66846 392.26
## - BMI 1 1543.0 67236 392.57
## - Weight 1 1786.7 67480 392.75
## <none> 65693 393.36
## - Height 1 2649.4 68343 393.41
## - Chol 1 3382.2 69076 393.97
## - Cre 1 4120.7 69814 394.52
##
## Step: AIC=391.38
## emotional ~ age + BMI + Weight + Height + Ure + Cre + Chol +
## trig + protein
##
## Df Sum of Sq RSS AIC
## - age 1 48.2 65764 389.41
## - trig 1 90.1 65806 389.45
## - Ure 1 966.6 66683 390.14
## - protein 1 1257.5 66973 390.36
## - BMI 1 1523.3 67239 390.57
## - Weight 1 1768.1 67484 390.76
## <none> 65716 391.38
## - Height 1 2626.9 68343 391.41
## - Chol 1 3434.0 69150 392.03
## - Cre 1 5084.0 70800 393.25
##
## Step: AIC=389.41
## emotional ~ BMI + Weight + Height + Ure + Cre + Chol + trig +
## protein
##
## Df Sum of Sq RSS AIC
## - trig 1 77.5 65842 387.48
## - Ure 1 944.0 66708 388.16
## - protein 1 1210.2 66974 388.36
## - BMI 1 1475.2 67239 388.57
## - Weight 1 1721.2 67485 388.76
## <none> 65764 389.41
## - Height 1 2590.4 68355 389.42
## - Chol 1 3516.5 69281 390.12
## - Cre 1 5104.7 70869 391.30
##
## Step: AIC=387.48
## emotional ~ BMI + Weight + Height + Ure + Cre + Chol + protein
##
## Df Sum of Sq RSS AIC
## - Ure 1 916.0 66758 386.19
## - protein 1 1349.3 67191 386.53
## - BMI 1 1445.0 67287 386.60
## - Weight 1 1690.0 67532 386.79
## - Height 1 2545.2 68387 387.45
## <none> 65842 387.48
## - Chol 1 3518.1 69360 388.18
## - Cre 1 5441.7 71283 389.61
##
## Step: AIC=386.19
## emotional ~ BMI + Weight + Height + Cre + Chol + protein
##
## Df Sum of Sq RSS AIC
## - BMI 1 933.4 67691 384.92
## - Weight 1 1162.8 67920 385.09
## - protein 1 1213.8 67971 385.13
## - Height 1 1928.5 68686 385.68
## <none> 66758 386.19
## - Chol 1 3193.4 69951 386.62
## - Cre 1 4526.0 71284 387.61
##
## Step: AIC=384.92
## emotional ~ Weight + Height + Cre + Chol + protein
##
## Df Sum of Sq RSS AIC
## - protein 1 1289.7 68981 383.90
## - Weight 1 1977.5 69669 384.41
## <none> 67691 384.92
## - Chol 1 3043.9 70735 385.20
## - Height 1 3853.0 71544 385.79
## - Cre 1 3920.0 71611 385.84
##
## Step: AIC=383.9
## emotional ~ Weight + Height + Cre + Chol
##
## Df Sum of Sq RSS AIC
## - Weight 1 2136.0 71117 383.48
## <none> 68981 383.90
## - Height 1 3097.9 72079 384.18
## - Chol 1 3372.0 72353 384.38
## - Cre 1 4608.3 73589 385.26
##
## Step: AIC=383.48
## emotional ~ Height + Cre + Chol
##
## Df Sum of Sq RSS AIC
## - Height 1 1096.9 72214 382.28
## <none> 71117 383.48
## - Cre 1 2863.3 73980 383.54
## - Chol 1 3399.9 74517 383.91
##
## Step: AIC=382.28
## emotional ~ Cre + Chol
##
## Df Sum of Sq RSS AIC
## - Cre 1 2303.3 74517 381.91
## <none> 72214 382.28
## - Chol 1 4108.6 76322 383.16
##
## Step: AIC=381.91
## emotional ~ Chol
##
## Df Sum of Sq RSS AIC
## <none> 74517 381.91
## - Chol 1 3602.7 78120 382.37
## [1] "5 --- fatigue ###########"
## Start: AIC=315.6
## fatigue ~ age + BMI + Weight + Height + Ure + Cre + Chol + trig +
## Alb + protein
##
## Df Sum of Sq RSS AIC
## - Chol 1 2.47 14729 313.61
## - protein 1 20.32 14746 313.67
## - age 1 169.20 14895 314.19
## - Cre 1 187.30 14913 314.26
## - Height 1 529.82 15256 315.44
## <none> 14726 315.60
## - Ure 1 623.10 15349 315.75
## - Weight 1 769.75 15496 316.25
## - BMI 1 906.30 15632 316.70
## - Alb 1 912.12 15638 316.72
## - trig 1 1125.36 15851 317.43
##
## Step: AIC=313.61
## fatigue ~ age + BMI + Weight + Height + Ure + Cre + trig + Alb +
## protein
##
## Df Sum of Sq RSS AIC
## - protein 1 20.94 14750 311.68
## - Cre 1 194.33 14923 312.29
## - age 1 196.09 14925 312.30
## - Height 1 527.70 15256 313.44
## <none> 14729 313.61
## - Ure 1 623.60 15352 313.76
## - Weight 1 770.43 15499 314.26
## - BMI 1 907.89 15636 314.72
## - Alb 1 909.84 15638 314.73
## - trig 1 1122.96 15852 315.43
##
## Step: AIC=311.68
## fatigue ~ age + BMI + Weight + Height + Ure + Cre + trig + Alb
##
## Df Sum of Sq RSS AIC
## - Cre 1 175.70 14925 310.30
## - age 1 252.12 15002 310.56
## - Height 1 512.85 15262 311.46
## <none> 14750 311.68
## - Ure 1 652.02 15402 311.93
## - Weight 1 761.46 15511 312.30
## - BMI 1 896.67 15646 312.75
## - trig 1 1218.75 15968 313.81
## - Alb 1 1279.94 16029 314.01
##
## Step: AIC=310.3
## fatigue ~ age + BMI + Weight + Height + Ure + trig + Alb
##
## Df Sum of Sq RSS AIC
## - age 1 293.00 15218 309.31
## <none> 14925 310.30
## - Height 1 757.08 15682 310.87
## - Weight 1 1011.71 15937 311.71
## - trig 1 1108.62 16034 312.02
## - BMI 1 1134.21 16059 312.11
## - Ure 1 1251.44 16177 312.48
## - Alb 1 1775.25 16700 314.14
##
## Step: AIC=309.31
## fatigue ~ BMI + Weight + Height + Ure + trig + Alb
##
## Df Sum of Sq RSS AIC
## <none> 15218 309.31
## - Height 1 1019.4 16238 310.68
## - Ure 1 1246.6 16465 311.40
## - trig 1 1252.3 16470 311.42
## - Weight 1 1292.6 16511 311.55
## - BMI 1 1415.2 16633 311.93
## - Alb 1 1601.7 16820 312.51
## [1] "6 --- wellbeing ###########"
## Start: AIC=299.96
## wellbeing ~ age + BMI + Weight + Height + Ure + Cre + Chol +
## trig + Alb + protein
##
## Df Sum of Sq RSS AIC
## - protein 1 2.98 10905 297.98
## - age 1 38.21 10940 298.15
## - Chol 1 147.63 11050 298.66
## - Cre 1 176.58 11079 298.80
## - trig 1 311.84 11214 299.43
## <none> 10902 299.96
## - Ure 1 456.21 11358 300.10
## - Height 1 554.45 11457 300.54
## - Alb 1 745.82 11648 301.40
## - Weight 1 786.62 11689 301.59
## - BMI 1 909.26 11811 302.13
##
## Step: AIC=297.98
## wellbeing ~ age + BMI + Weight + Height + Ure + Cre + Chol +
## trig + Alb
##
## Df Sum of Sq RSS AIC
## - age 1 46.80 10952 296.20
## - Chol 1 149.60 11055 296.69
## - Cre 1 197.02 11102 296.91
## - trig 1 311.14 11216 297.44
## <none> 10905 297.98
## - Ure 1 453.42 11358 298.10
## - Height 1 566.00 11471 298.61
## - Weight 1 791.00 11696 299.62
## - Alb 1 873.38 11778 299.99
## - BMI 1 915.49 11821 300.17
##
## Step: AIC=296.2
## wellbeing ~ BMI + Weight + Height + Ure + Cre + Chol + trig +
## Alb
##
## Df Sum of Sq RSS AIC
## - Cre 1 187.47 11139 295.08
## - Chol 1 223.98 11176 295.25
## - trig 1 286.12 11238 295.54
## <none> 10952 296.20
## - Ure 1 454.27 11406 296.31
## - Height 1 523.71 11476 296.63
## - Weight 1 745.83 11698 297.63
## - BMI 1 869.75 11822 298.18
## - Alb 1 953.29 11905 298.54
##
## Step: AIC=295.08
## wellbeing ~ BMI + Weight + Height + Ure + Chol + trig + Alb
##
## Df Sum of Sq RSS AIC
## - Chol 1 178.67 11318 293.91
## - trig 1 229.15 11368 294.14
## <none> 11139 295.08
## - Height 1 810.32 11950 296.74
## - Ure 1 968.08 12108 297.42
## - Weight 1 1037.84 12177 297.72
## - BMI 1 1146.88 12286 298.18
## - Alb 1 1376.32 12516 299.14
##
## Step: AIC=293.91
## wellbeing ~ BMI + Weight + Height + Ure + trig + Alb
##
## Df Sum of Sq RSS AIC
## - trig 1 234.06 11552 292.98
## <none> 11318 293.91
## - Height 1 812.24 12130 295.51
## - Ure 1 1051.23 12369 296.53
## - Weight 1 1069.03 12387 296.61
## - BMI 1 1183.57 12502 297.08
## - Alb 1 1451.28 12769 298.19
##
## Step: AIC=292.98
## wellbeing ~ BMI + Weight + Height + Ure + Alb
##
## Df Sum of Sq RSS AIC
## <none> 11552 292.98
## - Height 1 725.39 12278 294.14
## - Ure 1 913.75 12466 294.93
## - Weight 1 993.47 12546 295.27
## - BMI 1 1106.48 12659 295.73
## - Alb 1 1333.10 12885 296.65
## [1] "7 --- social_fun ###########"
## Start: AIC=318.41
## social_fun ~ age + BMI + Weight + Height + Ure + Cre + Chol +
## trig + Alb + protein
##
## Df Sum of Sq RSS AIC
## - age 1 8.29 15551 316.43
## - Cre 1 106.56 15649 316.76
## - protein 1 247.79 15790 317.23
## - Alb 1 330.08 15873 317.50
## <none> 15543 318.41
## - Ure 1 821.29 16364 319.08
## - Chol 1 878.62 16421 319.26
## - Height 1 1062.17 16605 319.84
## - trig 1 1258.87 16802 320.46
## - Weight 1 1372.91 16916 320.81
## - BMI 1 1544.93 17088 321.33
##
## Step: AIC=316.43
## social_fun ~ BMI + Weight + Height + Ure + Cre + Chol + trig +
## Alb + protein
##
## Df Sum of Sq RSS AIC
## - Cre 1 101.46 15652 314.77
## - protein 1 240.80 15792 315.23
## - Alb 1 323.96 15875 315.51
## <none> 15551 316.43
## - Ure 1 817.27 16368 317.10
## - Chol 1 1005.25 16556 317.69
## - Height 1 1156.44 16708 318.16
## - trig 1 1280.74 16832 318.55
## - Weight 1 1475.78 17027 319.15
## - BMI 1 1654.29 17205 319.69
##
## Step: AIC=314.77
## social_fun ~ BMI + Weight + Height + Ure + Chol + trig + Alb +
## protein
##
## Df Sum of Sq RSS AIC
## - protein 1 188.78 15841 313.39
## - Alb 1 236.56 15889 313.55
## <none> 15652 314.77
## - Ure 1 729.94 16382 315.14
## - Chol 1 934.25 16587 315.79
## - Height 1 1055.00 16708 316.16
## - trig 1 1359.54 17012 317.10
## - Weight 1 1374.38 17027 317.15
## - BMI 1 1552.92 17205 317.69
##
## Step: AIC=313.39
## social_fun ~ BMI + Weight + Height + Ure + Chol + trig + Alb
##
## Df Sum of Sq RSS AIC
## - Alb 1 125.03 15966 311.80
## <none> 15841 313.39
## - Ure 1 729.20 16570 313.73
## - Chol 1 865.31 16707 314.16
## - Height 1 1160.48 17002 315.07
## - trig 1 1198.96 17040 315.19
## - Weight 1 1418.68 17260 315.85
## - BMI 1 1605.03 17446 316.41
##
## Step: AIC=311.8
## social_fun ~ BMI + Weight + Height + Ure + Chol + trig
##
## Df Sum of Sq RSS AIC
## <none> 15966 311.80
## - Ure 1 627.34 16594 311.81
## - Chol 1 824.98 16791 312.42
## - trig 1 1123.24 17090 313.34
## - Height 1 1291.15 17257 313.85
## - Weight 1 1548.67 17515 314.62
## - BMI 1 1747.96 17714 315.21
## [1] "8 --- pain ###########"
## Start: AIC=346.3
## pain ~ age + BMI + Weight + Height + Ure + Cre + Chol + trig +
## Alb + protein
##
## Df Sum of Sq RSS AIC
## - protein 1 54.93 26629 344.40
## - age 1 295.44 26870 344.87
## - Chol 1 526.12 27100 345.32
## - Cre 1 984.97 27559 346.19
## <none> 26574 346.30
## - Alb 1 1398.52 27973 346.96
## - Ure 1 1845.02 28419 347.79
## - trig 1 1968.94 28543 348.01
## - Height 1 2227.03 28801 348.48
## - Weight 1 2456.64 29031 348.89
## - BMI 1 2731.79 29306 349.38
##
## Step: AIC=344.4
## pain ~ age + BMI + Weight + Height + Ure + Cre + Chol + trig +
## Alb
##
## Df Sum of Sq RSS AIC
## - age 1 250.53 26880 342.89
## - Chol 1 513.20 27142 343.40
## - Cre 1 930.16 27559 344.19
## <none> 26629 344.40
## - Alb 1 1444.15 28073 345.15
## - Ure 1 1799.57 28429 345.80
## - trig 1 1914.45 28544 346.01
## - Height 1 2306.80 28936 346.72
## - Weight 1 2485.54 29115 347.04
## - BMI 1 2770.65 29400 347.55
##
## Step: AIC=342.89
## pain ~ BMI + Weight + Height + Ure + Cre + Chol + trig + Alb
##
## Df Sum of Sq RSS AIC
## - Chol 1 824.3 27704 342.46
## - Cre 1 882.0 27762 342.57
## <none> 26880 342.89
## - Alb 1 1302.1 28182 343.35
## - Ure 1 1795.7 28676 344.25
## - trig 1 2125.3 29005 344.85
## - Height 1 2730.5 29610 345.92
## - Weight 1 2924.6 29804 346.26
## - BMI 1 3220.8 30101 346.77
##
## Step: AIC=342.46
## pain ~ BMI + Weight + Height + Ure + Cre + trig + Alb
##
## Df Sum of Sq RSS AIC
## - Cre 1 693.39 28398 341.75
## <none> 27704 342.46
## - Alb 1 1108.69 28813 342.50
## - Ure 1 1509.49 29214 343.22
## - trig 1 2140.62 29845 344.33
## - Height 1 2614.40 30318 345.15
## - Weight 1 2733.59 30438 345.35
## - BMI 1 3019.01 30723 345.84
##
## Step: AIC=341.75
## pain ~ BMI + Weight + Height + Ure + trig + Alb
##
## Df Sum of Sq RSS AIC
## - Alb 1 701.84 29099 341.02
## - Ure 1 913.31 29311 341.39
## <none> 28398 341.75
## - Height 1 2048.45 30446 343.37
## - Weight 1 2207.77 30605 343.64
## - BMI 1 2511.21 30909 344.15
## - trig 1 2549.44 30947 344.22
##
## Step: AIC=341.02
## pain ~ BMI + Weight + Height + Ure + trig
##
## Df Sum of Sq RSS AIC
## - Ure 1 607.83 29707 340.09
## <none> 29099 341.02
## - trig 1 2269.00 31368 342.92
## - Height 1 2436.68 31536 343.20
## - Weight 1 2575.34 31675 343.43
## - BMI 1 2914.73 32014 343.98
##
## Step: AIC=340.09
## pain ~ BMI + Weight + Height + trig
##
## Df Sum of Sq RSS AIC
## <none> 29707 340.09
## - trig 1 1974.8 31682 341.44
## - Height 1 2114.3 31822 341.67
## - Weight 1 2211.7 31919 341.82
## - BMI 1 2494.4 32202 342.28
## [1] "9 --- general ###########"
## Start: AIC=301.37
## general ~ age + BMI + Weight + Height + Ure + Cre + Chol + trig +
## Alb + protein
##
## Df Sum of Sq RSS AIC
## - BMI 1 1.90 11203 299.38
## - Height 1 9.24 11210 299.41
## - Weight 1 9.31 11210 299.41
## - Cre 1 27.68 11229 299.50
## - Chol 1 50.17 11251 299.60
## - protein 1 95.77 11297 299.81
## - Ure 1 188.11 11389 300.24
## <none> 11201 301.37
## - Alb 1 440.78 11642 301.38
## - age 1 467.41 11668 301.50
## - trig 1 1086.72 12288 304.19
##
## Step: AIC=299.38
## general ~ age + Weight + Height + Ure + Cre + Chol + trig + Alb +
## protein
##
## Df Sum of Sq RSS AIC
## - Cre 1 25.85 11229 297.50
## - Chol 1 53.27 11256 297.63
## - Height 1 61.37 11264 297.66
## - protein 1 94.78 11298 297.82
## - Ure 1 210.87 11414 298.35
## - Alb 1 438.95 11642 299.38
## <none> 11203 299.38
## - Weight 1 440.12 11643 299.38
## - age 1 474.17 11677 299.54
## - trig 1 1095.76 12299 302.23
##
## Step: AIC=297.5
## general ~ age + Weight + Height + Ure + Chol + trig + Alb + protein
##
## Df Sum of Sq RSS AIC
## - Height 1 45.86 11275 295.71
## - Chol 1 60.31 11289 295.78
## - protein 1 127.35 11356 296.09
## - Ure 1 347.71 11576 297.08
## - Weight 1 419.50 11648 297.41
## <none> 11229 297.50
## - age 1 521.94 11751 297.86
## - Alb 1 634.19 11863 298.36
## - trig 1 1071.61 12300 300.24
##
## Step: AIC=295.71
## general ~ age + Weight + Ure + Chol + trig + Alb + protein
##
## Df Sum of Sq RSS AIC
## - Chol 1 48.29 11323 293.93
## - protein 1 94.92 11370 294.15
## - Ure 1 310.12 11585 295.12
## - Weight 1 421.74 11696 295.62
## <none> 11275 295.71
## - age 1 487.20 11762 295.91
## - Alb 1 594.08 11869 296.38
## - trig 1 1121.38 12396 298.64
##
## Step: AIC=293.93
## general ~ age + Weight + Ure + trig + Alb + protein
##
## Df Sum of Sq RSS AIC
## - protein 1 96.51 11419 292.38
## - Ure 1 298.75 11622 293.29
## <none> 11323 293.93
## - Weight 1 451.20 11774 293.96
## - Alb 1 586.52 11909 294.56
## - age 1 646.39 11969 294.82
## - trig 1 1099.24 12422 296.75
##
## Step: AIC=292.37
## general ~ age + Weight + Ure + trig + Alb
##
## Df Sum of Sq RSS AIC
## - Ure 1 317.65 11737 291.80
## <none> 11419 292.38
## - Alb 1 491.84 11911 292.57
## - age 1 574.96 11994 292.93
## - Weight 1 604.21 12024 293.06
## - trig 1 1004.33 12424 294.76
##
## Step: AIC=291.8
## general ~ age + Weight + trig + Alb
##
## Df Sum of Sq RSS AIC
## - Alb 1 330.61 12068 291.25
## - Weight 1 446.61 12184 291.74
## <none> 11737 291.80
## - age 1 568.38 12305 292.26
## - trig 1 822.84 12560 293.32
##
## Step: AIC=291.25
## general ~ age + Weight + trig
##
## Df Sum of Sq RSS AIC
## <none> 12068 291.25
## - age 1 477.20 12545 291.26
## - Weight 1 570.14 12638 291.65
## - trig 1 740.55 12808 292.34
## [1] "10 --- PostPT ###########"
## Start: AIC=-75.64
## PostPT ~ age + BMI + Weight + Height + Ure + Cre + Chol + trig +
## Alb + protein
##
## Df Sum of Sq RSS AIC
## - Height 1 0.00343 7.9563 -77.618
## - Weight 1 0.02131 7.9742 -77.502
## - BMI 1 0.02455 7.9775 -77.480
## - Ure 1 0.03016 7.9831 -77.444
## - Chol 1 0.23710 8.1900 -76.113
## <none> 7.9529 -75.641
## - Cre 1 0.32414 8.2770 -75.563
## - age 1 0.37850 8.3314 -75.223
## - protein 1 0.42470 8.3776 -74.935
## - trig 1 0.95468 8.9076 -71.746
## - Alb 1 1.60990 9.5628 -68.055
##
## Step: AIC=-77.62
## PostPT ~ age + BMI + Weight + Ure + Cre + Chol + trig + Alb +
## protein
##
## Df Sum of Sq RSS AIC
## - Ure 1 0.02711 7.9834 -79.442
## - BMI 1 0.21202 8.1683 -78.251
## - Chol 1 0.23384 8.1902 -78.112
## - Weight 1 0.24846 8.2048 -78.019
## <none> 7.9563 -77.618
## - Cre 1 0.32948 8.2858 -77.508
## - age 1 0.38079 8.3371 -77.187
## - protein 1 0.43480 8.3911 -76.852
## - trig 1 0.96733 8.9237 -73.652
## - Alb 1 1.63550 9.5918 -69.897
##
## Step: AIC=-79.44
## PostPT ~ age + BMI + Weight + Cre + Chol + trig + Alb + protein
##
## Df Sum of Sq RSS AIC
## - BMI 1 0.19631 8.1797 -80.178
## - Chol 1 0.21894 8.2024 -80.035
## - Weight 1 0.23533 8.2188 -79.931
## - Cre 1 0.31131 8.2947 -79.452
## <none> 7.9834 -79.442
## - age 1 0.40021 8.3836 -78.898
## - protein 1 0.41455 8.3980 -78.809
## - trig 1 1.00482 8.9883 -75.277
## - Alb 1 1.73409 9.7175 -71.220
##
## Step: AIC=-80.18
## PostPT ~ age + Weight + Cre + Chol + trig + Alb + protein
##
## Df Sum of Sq RSS AIC
## - Weight 1 0.04009 8.2198 -81.924
## - Chol 1 0.17680 8.3565 -81.066
## <none> 8.1797 -80.178
## - protein 1 0.32709 8.5068 -80.139
## - age 1 0.43019 8.6099 -79.513
## - Cre 1 0.51178 8.6915 -79.023
## - trig 1 0.95832 9.1381 -76.417
## - Alb 1 1.75305 9.9328 -72.081
##
## Step: AIC=-81.92
## PostPT ~ age + Cre + Chol + trig + Alb + protein
##
## Df Sum of Sq RSS AIC
## - Chol 1 0.15911 8.3789 -82.927
## - protein 1 0.28731 8.5071 -82.138
## <none> 8.2198 -81.924
## - age 1 0.43565 8.6555 -81.239
## - Cre 1 0.47266 8.6925 -81.017
## - trig 1 0.94690 9.1667 -78.254
## - Alb 1 1.75336 9.9732 -73.870
##
## Step: AIC=-82.93
## PostPT ~ age + Cre + trig + Alb + protein
##
## Df Sum of Sq RSS AIC
## - protein 1 0.29865 8.6776 -83.106
## - age 1 0.32328 8.7022 -82.959
## <none> 8.3789 -82.927
## - Cre 1 0.45045 8.8294 -82.204
## - trig 1 0.97415 9.3531 -79.208
## - Alb 1 1.75335 10.1323 -75.047
##
## Step: AIC=-83.11
## PostPT ~ age + Cre + trig + Alb
##
## Df Sum of Sq RSS AIC
## - Cre 1 0.31949 8.9971 -83.226
## <none> 8.6776 -83.106
## - age 1 0.51594 9.1935 -82.103
## - trig 1 1.28243 9.9600 -77.939
## - Alb 1 1.45788 10.1355 -77.031
##
## Step: AIC=-83.23
## PostPT ~ age + trig + Alb
##
## Df Sum of Sq RSS AIC
## <none> 8.9971 -83.226
## - age 1 0.66688 9.6640 -81.508
## - trig 1 1.03706 10.0341 -79.553
## - Alb 1 1.27007 10.2672 -78.359
Tìm ra Best Subset Regression sử dụng olsrr
library(olsrr)
##
## Attaching package: 'olsrr'
## The following object is masked from 'package:datasets':
##
## rivers
# names(Data_New)
for (i in 1:10) {
outcome <- names(Data_New[i])
variables <- names(Data_New[11:20])
f <- as.formula(paste(outcome,
paste(variables, collapse = " + "),
sep = " ~ "))
print(paste(i,'---',outcome, "###########"))
# Exec fucntion lm()
print(ols_step_best_subset(lm(formula = f, data = Data_New)))
}
## [1] "1 --- c2score ###########"
## Best Subsets Regression
## ------------------------------------------------------------------
## Model Index Predictors
## ------------------------------------------------------------------
## 1 age
## 2 age trig
## 3 age BMI trig
## 4 age BMI Ure trig
## 5 age BMI Ure Chol trig
## 6 age BMI Weight Ure Chol trig
## 7 age BMI Weight Height Ure Chol trig
## 8 age BMI Weight Height Ure Cre Chol trig
## 9 age BMI Weight Height Ure Cre Chol trig Alb
## 10 age BMI Weight Height Ure Cre Chol trig Alb protein
## ------------------------------------------------------------------
##
## Subsets Regression Summary
## -------------------------------------------------------------------------------------------------------------------------------------
## Adj. Pred
## Model R-Square R-Square R-Square C(p) AIC SBIC SBC MSEP FPE HSP APC
## -------------------------------------------------------------------------------------------------------------------------------------
## 1 0.1909 0.1747 0.1252 16.7215 491.7817 343.3486 497.6354 722.3791 721.2887 14.1750 0.8739
## 2 0.2831 0.2538 0.2208 11.3435 487.4879 339.3418 495.2929 666.6986 664.1827 13.0824 0.8047
## 3 0.3493 0.3087 0.2172 8.0469 484.4484 336.8716 494.2046 630.8681 626.5830 12.3793 0.7591
## 4 0.4044 0.3537 0.2826 5.6400 481.8478 335.1766 493.5552 602.5573 596.1906 11.8238 0.7223
## 5 0.4458 0.3856 0.3003 4.3289 480.1019 334.5490 493.7607 585.5977 576.7585 11.4910 0.6988
## 6 0.4566 0.3841 0.2793 5.4675 481.0815 336.1830 496.6915 600.3190 588.0860 11.7798 0.7125
## 7 0.4789 0.3960 0.3036 5.6809 480.8991 337.1680 498.4603 602.4190 586.5060 11.8211 0.7106
## 8 0.4856 0.3899 0.2372 7.1455 482.2268 339.2665 501.7392 622.9985 602.3103 12.2249 0.7297
## 9 0.4873 0.3774 0.2014 9.0125 484.0584 341.7034 505.5220 651.2763 624.7337 12.7798 0.7569
## 10 0.4874 0.3624 0.1631 11.0000 486.0426 344.2314 509.4575 683.6323 650.0956 13.4147 0.7876
## -------------------------------------------------------------------------------------------------------------------------------------
## AIC: Akaike Information Criteria
## SBIC: Sawa's Bayesian Information Criteria
## SBC: Schwarz Bayesian Criteria
## MSEP: Estimated error of prediction, assuming multivariate normality
## FPE: Final Prediction Error
## HSP: Hocking's Sp
## APC: Amemiya Prediction Criteria
##
## [1] "2 --- phy_function ###########"
## Best Subsets Regression
## ------------------------------------------------------------------
## Model Index Predictors
## ------------------------------------------------------------------
## 1 trig
## 2 age trig
## 3 age trig Alb
## 4 age trig Alb protein
## 5 age BMI Ure trig Alb
## 6 age BMI Ure trig Alb protein
## 7 age BMI Ure Chol trig Alb protein
## 8 age BMI Ure Cre Chol trig Alb protein
## 9 age BMI Weight Height Ure Chol trig Alb protein
## 10 age BMI Weight Height Ure Cre Chol trig Alb protein
## ------------------------------------------------------------------
##
## Subsets Regression Summary
## ------------------------------------------------------------------------------------------------------------------------------------
## Adj. Pred
## Model R-Square R-Square R-Square C(p) AIC SBIC SBC MSEP FPE HSP APC
## ------------------------------------------------------------------------------------------------------------------------------------
## 1 0.0537 0.0348 -0.0204 0.3878 447.6297 300.3475 453.4834 309.0407 308.5742 6.0642 1.0220
## 2 0.0867 0.0494 -0.1487 0.6984 447.7817 300.8675 455.5867 310.6780 309.5057 6.0963 1.0251
## 3 0.1290 0.0745 -0.0692 0.5383 447.3190 301.0335 457.0752 308.9162 306.8179 6.0618 1.0162
## 4 0.1507 0.0785 -0.0722 1.4242 448.0017 302.3290 459.7092 314.2842 310.9634 6.1671 1.0299
## 5 0.1703 0.0801 -0.1 2.4262 448.7927 303.8291 462.4514 320.7084 315.8675 6.2931 1.0462
## 6 0.1855 0.0769 -0.1207 3.6488 449.8310 305.6174 465.4409 329.1421 322.4350 6.4586 1.0679
## 7 0.1935 0.0652 -0.2072 5.2392 451.3171 307.7863 468.8783 341.0635 332.0542 6.6926 1.0998
## 8 0.1945 0.0446 -0.2333 7.1882 453.2528 310.2703 472.7652 356.8631 345.0125 7.0026 1.1427
## 9 0.1979 0.0261 -0.4102 9.0110 455.0286 312.6744 476.4923 372.6610 357.4733 7.3126 1.1840
## 10 0.1982 0.0026 -0.4558 11.0000 457.0146 315.2035 480.4295 391.1887 371.9983 7.6762 1.2321
## ------------------------------------------------------------------------------------------------------------------------------------
## AIC: Akaike Information Criteria
## SBIC: Sawa's Bayesian Information Criteria
## SBC: Schwarz Bayesian Criteria
## MSEP: Estimated error of prediction, assuming multivariate normality
## FPE: Final Prediction Error
## HSP: Hocking's Sp
## APC: Amemiya Prediction Criteria
##
## [1] "3 --- phy_health ###########"
## Best Subsets Regression
## ------------------------------------------------------------------
## Model Index Predictors
## ------------------------------------------------------------------
## 1 Chol
## 2 Chol trig
## 3 Chol trig protein
## 4 Cre Chol trig protein
## 5 Ure Cre Chol trig protein
## 6 Ure Cre Chol trig Alb protein
## 7 BMI Weight Height Ure Cre Chol trig
## 8 BMI Weight Height Ure Cre Chol trig protein
## 9 BMI Weight Height Ure Cre Chol trig Alb protein
## 10 age BMI Weight Height Ure Cre Chol trig Alb protein
## ------------------------------------------------------------------
##
## Subsets Regression Summary
## ---------------------------------------------------------------------------------------------------------------------------------------
## Adj. Pred
## Model R-Square R-Square R-Square C(p) AIC SBIC SBC MSEP FPE HSP APC
## ---------------------------------------------------------------------------------------------------------------------------------------
## 1 0.1069 0.0891 0.0444 -3.3318 529.7909 382.8240 535.6446 1500.4145 1498.1498 29.4421 0.9645
## 2 0.1384 0.1032 0.0554 -2.9041 529.9275 383.5122 537.7325 1507.9161 1502.2258 29.5893 0.9671
## 3 0.1455 0.0921 0.027 -1.2637 531.4919 385.5624 541.2481 1558.9671 1548.3779 30.5911 0.9969
## 4 0.1516 0.0794 -0.037 0.4327 533.1211 387.7045 544.8285 1615.1901 1598.1240 31.6943 1.0289
## 5 0.1542 0.0623 -0.0842 2.3012 534.9598 390.0363 548.6185 1681.7509 1656.3660 33.0004 1.0664
## 6 0.1595 0.0475 -0.1216 4.0366 536.6335 392.2697 552.2434 1747.1960 1711.5928 34.2846 1.1019
## 7 0.1669 0.0343 -0.3163 5.6699 538.1779 394.4518 555.7390 1812.5107 1764.6331 35.5662 1.1361
## 8 0.1740 0.0203 -0.369 7.3134 539.7310 396.6837 559.2434 1882.5735 1820.0578 36.9411 1.1718
## 9 0.1787 0.0027 -0.417 9.0786 541.4347 399.0410 562.8984 1963.1873 1883.1782 38.5229 1.2124
## 10 0.1803 -0.0197 -0.5332 11.0000 543.3350 401.5239 566.7500 2057.4008 1956.4717 40.3716 1.2596
## ---------------------------------------------------------------------------------------------------------------------------------------
## AIC: Akaike Information Criteria
## SBIC: Sawa's Bayesian Information Criteria
## SBC: Schwarz Bayesian Criteria
## MSEP: Estimated error of prediction, assuming multivariate normality
## FPE: Final Prediction Error
## HSP: Hocking's Sp
## APC: Amemiya Prediction Criteria
##
## [1] "4 --- emotional ###########"
## Best Subsets Regression
## ------------------------------------------------------------------
## Model Index Predictors
## ------------------------------------------------------------------
## 1 Chol
## 2 Cre Chol
## 3 Height Cre Chol
## 4 Weight Height Cre Chol
## 5 Weight Height Cre Chol protein
## 6 BMI Weight Height Cre Chol protein
## 7 BMI Weight Height Ure Cre Chol protein
## 8 BMI Weight Height Ure Cre Chol trig protein
## 9 age BMI Weight Height Ure Cre Chol trig protein
## 10 age BMI Weight Height Ure Cre Chol trig Alb protein
## ------------------------------------------------------------------
##
## Subsets Regression Summary
## ---------------------------------------------------------------------------------------------------------------------------------------
## Adj. Pred
## Model R-Square R-Square R-Square C(p) AIC SBIC SBC MSEP FPE HSP APC
## ---------------------------------------------------------------------------------------------------------------------------------------
## 1 0.0461 0.0270 -0.0195 -1.4931 531.4816 384.3565 537.3353 1549.9990 1547.6594 30.4151 1.0302
## 2 0.0756 0.0379 -0.0352 -0.9306 531.8489 385.1547 539.6539 1564.6758 1558.7713 30.7031 1.0376
## 3 0.0896 0.0327 -0.0745 0.3848 533.0530 386.7971 542.8092 1606.4794 1595.5674 31.5234 1.0621
## 4 0.1170 0.0418 -0.0967 1.0517 533.4672 387.8897 545.1747 1625.9776 1608.7975 31.9060 1.0709
## 5 0.1335 0.0393 -0.1349 2.2468 534.4858 389.5800 548.1445 1666.4927 1641.3381 32.7010 1.0925
## 6 0.1454 0.0315 -0.2583 3.6642 535.7638 391.5441 551.3737 1718.2181 1683.2054 33.7160 1.1204
## 7 0.1572 0.0231 -0.3627 5.0925 537.0453 393.5818 554.6065 1773.4630 1726.6168 34.8000 1.1493
## 8 0.1582 0.0015 -0.4454 7.0442 538.9841 396.0767 558.4965 1855.7264 1794.1023 36.4143 1.1942
## 9 0.1588 -0.0215 -0.5086 9.0141 540.9460 398.5900 562.4097 1944.8237 1865.5629 38.1626 1.2418
## 10 0.1591 -0.0460 -0.6103 11.0000 542.9281 401.1170 566.3430 2041.3636 1941.2212 40.0569 1.2922
## ---------------------------------------------------------------------------------------------------------------------------------------
## AIC: Akaike Information Criteria
## SBIC: Sawa's Bayesian Information Criteria
## SBC: Schwarz Bayesian Criteria
## MSEP: Estimated error of prediction, assuming multivariate normality
## FPE: Final Prediction Error
## HSP: Hocking's Sp
## APC: Amemiya Prediction Criteria
##
## [1] "5 --- fatigue ###########"
## Best Subsets Regression
## ------------------------------------------------------------------
## Model Index Predictors
## ------------------------------------------------------------------
## 1 Alb
## 2 trig Alb
## 3 Ure trig Alb
## 4 age Ure trig Alb
## 5 BMI Weight Cre trig Alb
## 6 BMI Weight Height Ure trig Alb
## 7 age BMI Weight Height Ure trig Alb
## 8 age BMI Weight Height Ure Cre trig Alb
## 9 age BMI Weight Height Ure Cre trig Alb protein
## 10 age BMI Weight Height Ure Cre Chol trig Alb protein
## ------------------------------------------------------------------
##
## Subsets Regression Summary
## ------------------------------------------------------------------------------------------------------------------------------------
## Adj. Pred
## Model R-Square R-Square R-Square C(p) AIC SBIC SBC MSEP FPE HSP APC
## ------------------------------------------------------------------------------------------------------------------------------------
## 1 0.0658 0.0471 -0.0062 4.3966 459.9225 312.3225 465.7763 391.4563 390.8654 7.6814 1.0090
## 2 0.1170 0.0810 -0.0226 3.5233 458.9898 311.7153 466.7948 385.4063 383.9519 7.5627 0.9911
## 3 0.1461 0.0928 -0.007 3.8886 459.2443 312.3468 469.0006 388.5428 385.9037 7.6242 0.9962
## 4 0.1662 0.0953 0.0211 4.7622 460.0066 313.5320 471.7141 395.8996 391.7166 7.7686 1.0112
## 5 0.2037 0.1171 -0.122 4.6604 459.6153 313.9638 473.2740 394.9101 388.9492 7.7492 1.0040
## 6 0.2445 0.1438 -0.0203 4.3701 458.8778 314.3868 474.4877 391.6883 383.7067 7.6860 0.9905
## 7 0.2591 0.1412 0.0071 5.5543 459.8668 316.1928 477.4280 402.0142 391.3949 7.8886 1.0103
## 8 0.2678 0.1316 -0.0341 7.0652 461.2511 318.3327 480.7635 416.1999 402.3789 8.1669 1.0387
## 9 0.2688 0.1122 -0.0684 9.0069 463.1772 320.8255 484.6409 435.8828 418.1185 8.5532 1.0793
## 10 0.2690 0.0907 -0.1427 11.0000 465.1685 323.3574 488.5834 457.6001 435.1518 8.9793 1.1233
## ------------------------------------------------------------------------------------------------------------------------------------
## AIC: Akaike Information Criteria
## SBIC: Sawa's Bayesian Information Criteria
## SBC: Schwarz Bayesian Criteria
## MSEP: Estimated error of prediction, assuming multivariate normality
## FPE: Final Prediction Error
## HSP: Hocking's Sp
## APC: Amemiya Prediction Criteria
##
## [1] "6 --- wellbeing ###########"
## Best Subsets Regression
## ------------------------------------------------------------------
## Model Index Predictors
## ------------------------------------------------------------------
## 1 Alb
## 2 Chol Alb
## 3 BMI Weight Alb
## 4 BMI Weight Cre Alb
## 5 BMI Weight Height Ure Alb
## 6 BMI Weight Height Ure trig Alb
## 7 BMI Weight Height Ure Chol trig Alb
## 8 BMI Weight Height Ure Cre Chol trig Alb
## 9 age BMI Weight Height Ure Cre Chol trig Alb
## 10 age BMI Weight Height Ure Cre Chol trig Alb protein
## ------------------------------------------------------------------
##
## Subsets Regression Summary
## ------------------------------------------------------------------------------------------------------------------------------------
## Adj. Pred
## Model R-Square R-Square R-Square C(p) AIC SBIC SBC MSEP FPE HSP APC
## ------------------------------------------------------------------------------------------------------------------------------------
## 1 0.0893 0.0711 0.0186 3.6810 443.5730 296.0280 449.4267 285.8477 285.4163 5.6091 0.9836
## 2 0.1149 0.0787 -0.0069 4.2282 444.0903 296.7299 451.8953 289.3881 288.2960 5.6786 0.9935
## 3 0.1361 0.0821 -0.0188 5.0241 444.8285 297.7371 454.5847 294.4695 292.4693 5.7783 1.0079
## 4 0.1873 0.1181 0.0044 4.1182 443.6511 297.3243 455.3586 289.0592 286.0050 5.6721 0.9856
## 5 0.2344 0.1512 0.0581 3.4444 442.5454 297.2614 456.2041 284.4027 280.1098 5.5807 0.9653
## 6 0.2499 0.1499 0.0281 4.5642 443.4810 298.9167 459.0909 291.3058 285.3698 5.7162 0.9834
## 7 0.2618 0.1443 -0.0327 5.8922 444.6535 300.8280 462.2147 300.0423 292.1166 5.8876 1.0067
## 8 0.2742 0.1392 -0.1098 7.1872 445.7709 302.7890 465.2834 309.0400 298.7775 6.0642 1.0296
## 9 0.2773 0.1224 -0.2119 9.0112 447.5483 305.1940 469.0119 322.7302 309.5774 6.3328 1.0669
## 10 0.2775 0.1013 -0.249 11.0000 449.5340 307.7229 472.9490 338.7740 322.1549 6.6476 1.1102
## ------------------------------------------------------------------------------------------------------------------------------------
## AIC: Akaike Information Criteria
## SBIC: Sawa's Bayesian Information Criteria
## SBC: Schwarz Bayesian Criteria
## MSEP: Estimated error of prediction, assuming multivariate normality
## FPE: Final Prediction Error
## HSP: Hocking's Sp
## APC: Amemiya Prediction Criteria
##
## [1] "7 --- social_fun ###########"
## Best Subsets Regression
## ------------------------------------------------------------------
## Model Index Predictors
## ------------------------------------------------------------------
## 1 trig
## 2 BMI trig
## 3 BMI Chol trig
## 4 BMI Weight Height trig
## 5 BMI Weight Height Chol trig
## 6 BMI Weight Height Ure Chol trig
## 7 BMI Weight Height Ure Chol trig Alb
## 8 BMI Weight Height Ure Chol trig Alb protein
## 9 BMI Weight Height Ure Cre Chol trig Alb protein
## 10 age BMI Weight Height Ure Cre Chol trig Alb protein
## ------------------------------------------------------------------
##
## Subsets Regression Summary
## ------------------------------------------------------------------------------------------------------------------------------------
## Adj. Pred
## Model R-Square R-Square R-Square C(p) AIC SBIC SBC MSEP FPE HSP APC
## ------------------------------------------------------------------------------------------------------------------------------------
## 1 0.0465 0.0274 -0.0032 2.7878 461.1074 313.6322 466.9612 400.4787 399.8742 7.8585 1.0298
## 2 0.0788 0.0412 -0.0139 3.0694 461.3176 314.0992 469.1225 403.0505 401.5295 7.9089 1.0340
## 3 0.1071 0.0513 -0.0289 3.5590 461.6918 314.8518 471.4480 407.2672 404.5009 7.9917 1.0417
## 4 0.1423 0.0693 -0.0223 3.6858 461.6022 315.3765 473.3097 408.2362 403.9227 8.0107 1.0402
## 5 0.1782 0.0889 -0.0434 3.7722 461.3772 315.9925 475.0359 408.5201 402.3538 8.0162 1.0362
## 6 0.2093 0.1039 -0.0363 4.1173 461.3731 316.9785 476.9831 410.9427 402.5688 8.0638 1.0367
## 7 0.2155 0.0907 -0.0827 5.7875 462.9643 319.1855 480.5255 426.6886 415.4176 8.3728 1.0698
## 8 0.2248 0.0806 -0.1491 7.2895 464.3409 321.3059 483.8534 441.6802 427.0130 8.6669 1.0997
## 9 0.2299 0.0648 -0.1854 9.0219 466.0028 323.6423 487.4665 460.2230 441.4667 9.0308 1.1369
## 10 0.2303 0.0425 -0.251 11.0000 467.9750 326.1639 491.3900 482.9764 459.2832 9.4773 1.1828
## ------------------------------------------------------------------------------------------------------------------------------------
## AIC: Akaike Information Criteria
## SBIC: Sawa's Bayesian Information Criteria
## SBC: Schwarz Bayesian Criteria
## MSEP: Estimated error of prediction, assuming multivariate normality
## FPE: Final Prediction Error
## HSP: Hocking's Sp
## APC: Amemiya Prediction Criteria
##
## [1] "8 --- pain ###########"
## Best Subsets Regression
## ------------------------------------------------------------------
## Model Index Predictors
## ------------------------------------------------------------------
## 1 trig
## 2 BMI trig
## 3 BMI trig Alb
## 4 BMI Weight Height trig
## 5 BMI Weight Height Ure trig
## 6 BMI Weight Height Ure trig Alb
## 7 BMI Weight Height Ure Cre trig Alb
## 8 BMI Weight Height Ure Cre Chol trig Alb
## 9 age BMI Weight Height Ure Cre Chol trig Alb
## 10 age BMI Weight Height Ure Cre Chol trig Alb protein
## ------------------------------------------------------------------
##
## Subsets Regression Summary
## -------------------------------------------------------------------------------------------------------------------------------------
## Adj. Pred
## Model R-Square R-Square R-Square C(p) AIC SBIC SBC MSEP FPE HSP APC
## -------------------------------------------------------------------------------------------------------------------------------------
## 1 0.0513 0.0323 -0.0422 3.8959 490.1202 342.5586 495.9739 699.6621 698.6061 13.7292 1.0246
## 2 0.0997 0.0629 -0.0059 3.2507 489.3996 342.1587 497.2046 691.6649 689.0549 13.5723 1.0106
## 3 0.1209 0.0659 -0.0165 4.0912 490.1608 343.2282 499.9170 704.1214 699.3387 13.8167 1.0257
## 4 0.1621 0.0908 -0.0044 3.8335 489.6604 343.4000 501.3679 700.2419 692.8431 13.7406 1.0161
## 5 0.1793 0.0901 -0.0158 4.8957 490.5854 344.8646 504.2441 716.3995 705.5860 14.0577 1.0348
## 6 0.1991 0.0923 3e-04 5.8129 491.3159 346.2925 506.9258 730.8990 716.0052 14.3422 1.0501
## 7 0.2186 0.0943 -0.0143 6.7431 492.0304 347.8321 509.5916 746.2178 726.5064 14.6428 1.0655
## 8 0.2419 0.1008 -0.0919 7.4713 492.4597 349.3310 511.9721 758.4917 733.3040 14.8836 1.0755
## 9 0.2489 0.0880 -0.2388 9.0848 493.9728 351.5755 515.4365 788.0769 755.9590 15.4641 1.1087
## 10 0.2505 0.0677 -0.2831 11.0000 495.8654 354.0543 519.2803 825.7737 785.2640 16.2039 1.1517
## -------------------------------------------------------------------------------------------------------------------------------------
## AIC: Akaike Information Criteria
## SBIC: Sawa's Bayesian Information Criteria
## SBC: Schwarz Bayesian Criteria
## MSEP: Estimated error of prediction, assuming multivariate normality
## FPE: Final Prediction Error
## HSP: Hocking's Sp
## APC: Amemiya Prediction Criteria
##
## [1] "9 --- general ###########"
## Best Subsets Regression
## ------------------------------------------------------------------
## Model Index Predictors
## ------------------------------------------------------------------
## 1 trig
## 2 Weight trig
## 3 age Weight trig
## 4 age Weight trig Alb
## 5 age Weight Ure trig Alb
## 6 age BMI Ure trig Alb protein
## 7 age BMI Ure Chol trig Alb protein
## 8 age BMI Ure Cre Chol trig Alb protein
## 9 age Weight Height Ure Cre Chol trig Alb protein
## 10 age BMI Weight Height Ure Cre Chol trig Alb protein
## ------------------------------------------------------------------
##
## Subsets Regression Summary
## ------------------------------------------------------------------------------------------------------------------------------------
## Adj. Pred
## Model R-Square R-Square R-Square C(p) AIC SBIC SBC MSEP FPE HSP APC
## ------------------------------------------------------------------------------------------------------------------------------------
## 1 0.0564 0.0375 -0.0281 -0.2670 440.8469 293.6189 446.7006 271.2484 270.8390 5.3226 1.0191
## 2 0.0922 0.0552 -0.0031 -0.0809 440.8323 294.0222 448.6373 271.8130 270.7873 5.3337 1.0189
## 3 0.1268 0.0722 -0.0624 0.1723 440.8156 294.6009 450.5719 272.6000 270.7484 5.3491 1.0188
## 4 0.1507 0.0784 -0.0435 0.9622 441.3712 295.8167 453.0786 276.6592 273.7360 5.4288 1.0300
## 5 0.1737 0.0838 -0.0463 1.7994 441.9444 297.1841 455.6031 281.1349 276.8914 5.5166 1.0419
## 6 0.1825 0.0735 -0.0955 3.3542 443.3876 299.2895 458.9976 290.7834 284.8580 5.7059 1.0719
## 7 0.1872 0.0579 -0.1487 5.1146 445.0855 301.6118 462.6467 302.5450 294.5532 5.9367 1.1084
## 8 0.1888 0.0379 -0.2057 7.0342 446.9837 304.0815 466.4961 316.3321 305.8274 6.2073 1.1508
## 9 0.1893 0.0156 -0.2505 9.0070 448.9491 306.5973 470.4128 331.5424 318.0305 6.5057 1.1967
## 10 0.1895 -0.0082 -0.3572 11.0000 450.9403 309.1291 474.3552 348.0604 330.9858 6.8299 1.2455
## ------------------------------------------------------------------------------------------------------------------------------------
## AIC: Akaike Information Criteria
## SBIC: Sawa's Bayesian Information Criteria
## SBC: Schwarz Bayesian Criteria
## MSEP: Estimated error of prediction, assuming multivariate normality
## FPE: Final Prediction Error
## HSP: Hocking's Sp
## APC: Amemiya Prediction Criteria
##
## [1] "10 --- PostPT ###########"
## Best Subsets Regression
## ------------------------------------------------------------------
## Model Index Predictors
## ------------------------------------------------------------------
## 1 Alb
## 2 trig Alb
## 3 age trig Alb
## 4 age Cre trig Alb
## 5 age Cre trig Alb protein
## 6 age Cre Chol trig Alb protein
## 7 age Height Cre Chol trig Alb protein
## 8 age BMI Weight Cre Chol trig Alb protein
## 9 age BMI Weight Ure Cre Chol trig Alb protein
## 10 age BMI Weight Height Ure Cre Chol trig Alb protein
## ------------------------------------------------------------------
##
## Subsets Regression Summary
## ------------------------------------------------------------------------------------------------------------------------------
## Adj. Pred
## Model R-Square R-Square R-Square C(p) AIC SBIC SBC MSEP FPE HSP APC
## ------------------------------------------------------------------------------------------------------------------------------
## 1 0.1461 0.1290 0.0824 7.8764 72.0264 -75.8303 77.8802 0.2254 0.2251 0.0044 0.9223
## 2 0.2386 0.2075 0.0456 3.8211 68.0619 -79.2491 75.8669 0.2094 0.2086 0.0041 0.8546
## 3 0.2911 0.2468 0.1413 2.3831 66.3437 -80.2864 76.1000 0.2032 0.2019 0.0040 0.8270
## 4 0.3163 0.2581 0.1478 2.7360 66.4636 -79.5350 78.1711 0.2045 0.2024 0.0040 0.8292
## 5 0.3398 0.2681 0.142 3.1964 66.6425 -78.5646 80.3012 0.2063 0.2032 0.0040 0.8324
## 6 0.3524 0.2660 0.1028 4.3762 67.6455 -76.8477 83.2555 0.2116 0.2073 0.0042 0.8491
## 7 0.3689 0.2685 0.0892 5.2933 68.2995 -75.2560 85.8607 0.2157 0.2100 0.0042 0.8606
## 8 0.3710 0.2540 0.0437 7.1574 70.1281 -72.8384 89.6405 0.2253 0.2178 0.0044 0.8923
## 9 0.3731 0.2388 0.0109 9.0177 71.9512 -70.4068 93.4149 0.2355 0.2259 0.0046 0.9254
## 10 0.3734 0.2206 -0.0492 11.0000 73.9288 -67.8823 97.3437 0.2471 0.2350 0.0048 0.9628
## ------------------------------------------------------------------------------------------------------------------------------
## AIC: Akaike Information Criteria
## SBIC: Sawa's Bayesian Information Criteria
## SBC: Schwarz Bayesian Criteria
## MSEP: Estimated error of prediction, assuming multivariate normality
## FPE: Final Prediction Error
## HSP: Hocking's Sp
## APC: Amemiya Prediction Criteria
Tìm các biến được chọn sử dụng stepwise forward regression
Chọn các biến có có ý nghĩa
for (i in 1:10) {
outcome <- names(Data_New[i])
variables <- names(Data_New[11:20])
f <- as.formula(paste(outcome,
paste(variables, collapse = " + "),
sep = " ~ "))
print(paste("--------------------------------------------------------"))
print(paste("BIEN - ",i,"---",outcome))
print(paste("--------------------------------------------------------"))
# Exec fucntion lm()
print(ols_step_forward_p(lm(formula = f, data = Data_New)))
}
## [1] "--------------------------------------------------------"
## [1] "BIEN - 1 --- c2score"
## [1] "--------------------------------------------------------"
## Forward Selection Method
## ---------------------------
##
## Candidate Terms:
##
## 1. age
## 2. BMI
## 3. Weight
## 4. Height
## 5. Ure
## 6. Cre
## 7. Chol
## 8. trig
## 9. Alb
## 10. protein
##
## We are selecting variables based on p value...
##
## Variables Entered:
##
## - age
## - trig
## - BMI
## - Ure
## - Chol
##
## No more variables to be added.
##
## Final Model Output
## ------------------
##
## Model Summary
## ---------------------------------------------------------------
## R 0.668 RMSE 22.740
## R-Squared 0.446 Coef. Var 32.620
## Adj. R-Squared 0.386 MSE 517.094
## Pred R-Squared 0.300 MAE 17.529
## ---------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 19134.358 5 3826.872 7.401 0.0000
## Residual 23786.315 46 517.094
## Total 42920.673 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## -----------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## -----------------------------------------------------------------------------------------
## (Intercept) -0.143 34.074 -0.004 0.997 -68.730 68.444
## age -0.770 0.244 -0.368 -3.154 0.003 -1.262 -0.279
## trig -6.547 2.084 -0.352 -3.142 0.003 -10.741 -2.353
## BMI 3.130 1.106 0.329 2.829 0.007 0.903 5.357
## Ure 2.978 1.333 0.262 2.235 0.030 0.296 5.661
## Chol 5.417 2.922 0.214 1.854 0.070 -0.465 11.299
## -----------------------------------------------------------------------------------------
##
## Selection Summary
## --------------------------------------------------------------------------
## Variable Adj.
## Step Entered R-Square R-Square C(p) AIC RMSE
## --------------------------------------------------------------------------
## 1 age 0.1909 0.1747 16.7215 491.7817 26.3548
## 2 trig 0.2831 0.2538 11.3435 487.4879 25.0590
## 3 BMI 0.3493 0.3087 8.0469 484.4484 24.1211
## 4 Ure 0.4044 0.3537 5.6400 481.8478 23.3215
## 5 Chol 0.4458 0.3856 4.3289 480.1019 22.7397
## --------------------------------------------------------------------------
## [1] "--------------------------------------------------------"
## [1] "BIEN - 2 --- phy_function"
## [1] "--------------------------------------------------------"
## Forward Selection Method
## ---------------------------
##
## Candidate Terms:
##
## 1. age
## 2. BMI
## 3. Weight
## 4. Height
## 5. Ure
## 6. Cre
## 7. Chol
## 8. trig
## 9. Alb
## 10. protein
##
## We are selecting variables based on p value...
##
## Variables Entered:
##
## - trig
## - age
## - Alb
## - protein
##
## No more variables to be added.
##
## Final Model Output
## ------------------
##
## Model Summary
## ----------------------------------------------------------------
## R 0.388 RMSE 16.843
## R-Squared 0.151 Coef. Var 22.457
## Adj. R-Squared 0.078 MSE 283.686
## Pred R-Squared -0.072 MAE 12.091
## ----------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 2366.761 4 591.690 2.086 0.0976
## Residual 13333.239 47 283.686
## Total 15700.000 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## ------------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## ------------------------------------------------------------------------------------------
## (Intercept) 56.690 49.190 1.152 0.255 -42.269 155.648
## trig -3.123 1.588 -0.277 -1.966 0.055 -6.317 0.072
## age -0.304 0.176 -0.240 -1.727 0.091 -0.658 0.050
## Alb 1.918 1.059 0.262 1.811 0.077 -0.213 4.049
## protein -0.596 0.543 -0.164 -1.098 0.278 -1.689 0.496
## ------------------------------------------------------------------------------------------
##
## Selection Summary
## -------------------------------------------------------------------------
## Variable Adj.
## Step Entered R-Square R-Square C(p) AIC RMSE
## -------------------------------------------------------------------------
## 1 trig 0.0537 0.0348 0.3878 447.6297 17.2379
## 2 age 0.0867 0.0494 0.6984 447.7817 17.1062
## 3 Alb 0.1290 0.0745 0.5383 447.3190 16.8790
## 4 protein 0.1507 0.0785 1.4242 448.0017 16.8430
## -------------------------------------------------------------------------
## [1] "--------------------------------------------------------"
## [1] "BIEN - 3 --- phy_health"
## [1] "--------------------------------------------------------"
## Forward Selection Method
## ---------------------------
##
## Candidate Terms:
##
## 1. age
## 2. BMI
## 3. Weight
## 4. Height
## 5. Ure
## 6. Cre
## 7. Chol
## 8. trig
## 9. Alb
## 10. protein
##
## We are selecting variables based on p value...
##
## Variables Entered:
##
## - Chol
## - trig
##
## No more variables to be added.
##
## Final Model Output
## ------------------
##
## Model Summary
## ----------------------------------------------------------------
## R 0.372 RMSE 37.687
## R-Squared 0.138 Coef. Var 85.205
## Adj. R-Squared 0.103 MSE 1420.286
## Pred R-Squared 0.055 MAE 30.381
## ----------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 11175.205 2 5587.603 3.934 0.0260
## Residual 69594.025 49 1420.286
## Total 80769.231 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## -----------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## -----------------------------------------------------------------------------------------
## (Intercept) -2.461 23.723 -0.104 0.918 -50.135 45.213
## Chol 11.490 4.598 0.332 2.499 0.016 2.251 20.730
## trig -4.532 3.389 -0.177 -1.337 0.187 -11.343 2.279
## -----------------------------------------------------------------------------------------
##
## Selection Summary
## --------------------------------------------------------------------------
## Variable Adj.
## Step Entered R-Square R-Square C(p) AIC RMSE
## --------------------------------------------------------------------------
## 1 Chol 0.1069 0.0891 -3.3318 529.7909 37.9824
## 2 trig 0.1384 0.1032 -2.9041 529.9275 37.6867
## --------------------------------------------------------------------------
## [1] "--------------------------------------------------------"
## [1] "BIEN - 4 --- emotional"
## [1] "--------------------------------------------------------"
## Forward Selection Method
## ---------------------------
##
## Candidate Terms:
##
## 1. age
## 2. BMI
## 3. Weight
## 4. Height
## 5. Ure
## 6. Cre
## 7. Chol
## 8. trig
## 9. Alb
## 10. protein
##
## We are selecting variables based on p value...
##
## Variables Entered:
##
## - Chol
## - Cre
##
## No more variables to be added.
##
## Final Model Output
## ------------------
##
## Model Summary
## -----------------------------------------------------------------
## R 0.275 RMSE 38.389
## R-Squared 0.076 Coef. Var 83.177
## Adj. R-Squared 0.038 MSE 1473.747
## Pred R-Squared -0.035 MAE 32.644
## -----------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 5906.034 2 2953.017 2.004 0.1457
## Residual 72213.625 49 1473.747
## Total 78119.658 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## -----------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## -----------------------------------------------------------------------------------------
## (Intercept) 27.532 26.955 1.021 0.312 -26.637 81.700
## Chol 7.849 4.701 0.230 1.670 0.101 -1.598 17.296
## Cre -0.186 0.149 -0.172 -1.250 0.217 -0.486 0.113
## -----------------------------------------------------------------------------------------
##
## Selection Summary
## --------------------------------------------------------------------------
## Variable Adj.
## Step Entered R-Square R-Square C(p) AIC RMSE
## --------------------------------------------------------------------------
## 1 Chol 0.0461 0.0270 -1.4931 531.4816 38.6049
## 2 Cre 0.0756 0.0379 -0.9306 531.8489 38.3894
## --------------------------------------------------------------------------
## [1] "--------------------------------------------------------"
## [1] "BIEN - 5 --- fatigue"
## [1] "--------------------------------------------------------"
## Forward Selection Method
## ---------------------------
##
## Candidate Terms:
##
## 1. age
## 2. BMI
## 3. Weight
## 4. Height
## 5. Ure
## 6. Cre
## 7. Chol
## 8. trig
## 9. Alb
## 10. protein
##
## We are selecting variables based on p value...
##
## Variables Entered:
##
## - Alb
## - trig
## - Ure
## - age
##
## No more variables to be added.
##
## Final Model Output
## ------------------
##
## Model Summary
## ---------------------------------------------------------------
## R 0.408 RMSE 18.904
## R-Squared 0.166 Coef. Var 29.878
## Adj. R-Squared 0.095 MSE 357.355
## Pred R-Squared 0.021 MAE 13.675
## ---------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 3348.524 4 837.131 2.343 0.0685
## Residual 16795.706 47 357.355
## Total 20144.231 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## -------------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## -------------------------------------------------------------------------------------------
## (Intercept) -53.173 51.092 -1.041 0.303 -155.958 49.611
## Alb 2.894 1.166 0.349 2.482 0.017 0.548 5.240
## trig -3.184 1.745 -0.250 -1.825 0.074 -6.695 0.327
## Ure 1.396 1.094 0.179 1.276 0.208 -0.806 3.598
## age -0.206 0.193 -0.143 -1.064 0.293 -0.595 0.183
## -------------------------------------------------------------------------------------------
##
## Selection Summary
## -------------------------------------------------------------------------
## Variable Adj.
## Step Entered R-Square R-Square C(p) AIC RMSE
## -------------------------------------------------------------------------
## 1 Alb 0.0658 0.0471 4.3966 459.9225 19.4007
## 2 trig 0.1170 0.0810 3.5233 458.9898 19.0528
## 3 Ure 0.1461 0.0928 3.8886 459.2443 18.9298
## 4 age 0.1662 0.0953 4.7622 460.0066 18.9038
## -------------------------------------------------------------------------
## [1] "--------------------------------------------------------"
## [1] "BIEN - 6 --- wellbeing"
## [1] "--------------------------------------------------------"
## Forward Selection Method
## ---------------------------
##
## Candidate Terms:
##
## 1. age
## 2. BMI
## 3. Weight
## 4. Height
## 5. Ure
## 6. Cre
## 7. Chol
## 8. trig
## 9. Alb
## 10. protein
##
## We are selecting variables based on p value...
##
## Variables Entered:
##
## - Alb
## - Chol
## - Ure
##
## No more variables to be added.
##
## Final Model Output
## ------------------
##
## Model Summary
## ----------------------------------------------------------------
## R 0.368 RMSE 16.485
## R-Squared 0.136 Coef. Var 23.294
## Adj. R-Squared 0.081 MSE 271.760
## Pred R-Squared -0.016 MAE 13.207
## ----------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 2044.738 3 681.579 2.508 0.0700
## Residual 13044.493 48 271.760
## Total 15089.231 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## -------------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## -------------------------------------------------------------------------------------------
## (Intercept) -25.669 45.967 -0.558 0.579 -118.092 66.755
## Alb 2.384 0.999 0.333 2.386 0.021 0.375 4.393
## Chol -2.269 2.016 -0.151 -1.126 0.266 -6.321 1.784
## Ure 1.005 0.939 0.149 1.071 0.290 -0.883 2.893
## -------------------------------------------------------------------------------------------
##
## Selection Summary
## -------------------------------------------------------------------------
## Variable Adj.
## Step Entered R-Square R-Square C(p) AIC RMSE
## -------------------------------------------------------------------------
## 1 Alb 0.0893 0.0711 3.6810 443.5730 16.5785
## 2 Chol 0.1149 0.0787 4.2282 444.0903 16.5097
## 3 Ure 0.1355 0.0815 5.0569 444.8632 16.4852
## -------------------------------------------------------------------------
## [1] "--------------------------------------------------------"
## [1] "BIEN - 7 --- social_fun"
## [1] "--------------------------------------------------------"
## Forward Selection Method
## ---------------------------
##
## Candidate Terms:
##
## 1. age
## 2. BMI
## 3. Weight
## 4. Height
## 5. Ure
## 6. Cre
## 7. Chol
## 8. trig
## 9. Alb
## 10. protein
##
## We are selecting variables based on p value...
##
## Variables Entered:
##
## - trig
## - BMI
## - Chol
##
## No more variables to be added.
##
## Final Model Output
## ------------------
##
## Model Summary
## ----------------------------------------------------------------
## R 0.327 RMSE 19.381
## R-Squared 0.107 Coef. Var 29.641
## Adj. R-Squared 0.051 MSE 375.608
## Pred R-Squared -0.029 MAE 14.697
## ----------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 2163.125 3 721.042 1.92 0.1390
## Residual 18029.183 48 375.608
## Total 20192.308 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## -----------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## -----------------------------------------------------------------------------------------
## (Intercept) 31.631 22.823 1.386 0.172 -14.258 77.520
## trig -2.790 1.743 -0.218 -1.601 0.116 -6.295 0.714
## BMI 1.147 0.889 0.176 1.290 0.203 -0.641 2.935
## Chol 2.920 2.365 0.168 1.235 0.223 -1.835 7.675
## -----------------------------------------------------------------------------------------
##
## Selection Summary
## -------------------------------------------------------------------------
## Variable Adj.
## Step Entered R-Square R-Square C(p) AIC RMSE
## -------------------------------------------------------------------------
## 1 trig 0.0465 0.0274 2.7878 461.1074 19.6230
## 2 BMI 0.0788 0.0412 3.0694 461.3176 19.4840
## 3 Chol 0.1071 0.0513 3.5590 461.6918 19.3806
## -------------------------------------------------------------------------
## [1] "--------------------------------------------------------"
## [1] "BIEN - 8 --- pain"
## [1] "--------------------------------------------------------"
## Forward Selection Method
## ---------------------------
##
## Candidate Terms:
##
## 1. age
## 2. BMI
## 3. Weight
## 4. Height
## 5. Ure
## 6. Cre
## 7. Chol
## 8. trig
## 9. Alb
## 10. protein
##
## We are selecting variables based on p value...
##
## Variables Entered:
##
## - trig
## - BMI
## - Alb
## - age
##
## No more variables to be added.
##
## Final Model Output
## ------------------
##
## Model Summary
## ----------------------------------------------------------------
## R 0.380 RMSE 25.403
## R-Squared 0.145 Coef. Var 37.002
## Adj. R-Squared 0.072 MSE 645.336
## Pred R-Squared -0.080 MAE 19.945
## ----------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 5124.954 4 1281.239 1.985 0.1121
## Residual 30330.815 47 645.336
## Total 35455.769 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## --------------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## --------------------------------------------------------------------------------------------
## (Intercept) -27.549 64.602 -0.426 0.672 -157.512 102.414
## trig -3.859 2.304 -0.228 -1.675 0.101 -8.494 0.776
## BMI 1.825 1.184 0.211 1.542 0.130 -0.556 4.206
## Alb 1.824 1.518 0.166 1.202 0.235 -1.229 4.878
## age -0.298 0.261 -0.156 -1.141 0.260 -0.823 0.227
## --------------------------------------------------------------------------------------------
##
## Selection Summary
## -------------------------------------------------------------------------
## Variable Adj.
## Step Entered R-Square R-Square C(p) AIC RMSE
## -------------------------------------------------------------------------
## 1 trig 0.0513 0.0323 3.8959 490.1202 25.9371
## 2 BMI 0.0997 0.0629 3.2507 489.3996 25.5239
## 3 Alb 0.1209 0.0659 4.0912 490.1608 25.4831
## 4 age 0.1445 0.0717 4.7957 490.7407 25.4035
## -------------------------------------------------------------------------
## [1] "--------------------------------------------------------"
## [1] "BIEN - 9 --- general"
## [1] "--------------------------------------------------------"
## Forward Selection Method
## ---------------------------
##
## Candidate Terms:
##
## 1. age
## 2. BMI
## 3. Weight
## 4. Height
## 5. Ure
## 6. Cre
## 7. Chol
## 8. trig
## 9. Alb
## 10. protein
##
## We are selecting variables based on p value...
##
## Variables Entered:
##
## - trig
## - Weight
## - age
## - Alb
## - Ure
##
## No more variables to be added.
##
## Final Model Output
## ------------------
##
## Model Summary
## ----------------------------------------------------------------
## R 0.417 RMSE 15.756
## R-Squared 0.174 Coef. Var 35.622
## Adj. R-Squared 0.084 MSE 248.247
## Pred R-Squared -0.046 MAE 12.356
## ----------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 2399.850 5 479.970 1.933 0.1070
## Residual 11419.381 46 248.247
## Total 13819.231 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## -------------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## -------------------------------------------------------------------------------------------
## (Intercept) -25.923 44.130 -0.587 0.560 -114.752 62.905
## trig -2.936 1.459 -0.278 -2.011 0.050 -5.873 0.002
## Weight 0.356 0.228 0.218 1.560 0.126 -0.103 0.815
## age -0.246 0.162 -0.207 -1.522 0.135 -0.571 0.079
## Alb 1.372 0.974 0.200 1.408 0.166 -0.590 3.333
## Ure 1.059 0.936 0.164 1.131 0.264 -0.825 2.942
## -------------------------------------------------------------------------------------------
##
## Selection Summary
## --------------------------------------------------------------------------
## Variable Adj.
## Step Entered R-Square R-Square C(p) AIC RMSE
## --------------------------------------------------------------------------
## 1 trig 0.0564 0.0375 -0.2670 440.8469 16.1495
## 2 Weight 0.0922 0.0552 -0.0809 440.8323 16.0005
## 3 age 0.1268 0.0722 0.1723 440.8156 15.8559
## 4 Alb 0.1507 0.0784 0.9622 441.3712 15.8027
## 5 Ure 0.1737 0.0838 1.7994 441.9444 15.7559
## --------------------------------------------------------------------------
## [1] "--------------------------------------------------------"
## [1] "BIEN - 10 --- PostPT"
## [1] "--------------------------------------------------------"
## Forward Selection Method
## ---------------------------
##
## Candidate Terms:
##
## 1. age
## 2. BMI
## 3. Weight
## 4. Height
## 5. Ure
## 6. Cre
## 7. Chol
## 8. trig
## 9. Alb
## 10. protein
##
## We are selecting variables based on p value...
##
## Variables Entered:
##
## - Alb
## - trig
## - age
## - Cre
## - protein
##
## No more variables to be added.
##
## Final Model Output
## ------------------
##
## Model Summary
## --------------------------------------------------------------
## R 0.583 RMSE 0.427
## R-Squared 0.340 Coef. Var 27.065
## Adj. R-Squared 0.268 MSE 0.182
## Pred R-Squared 0.142 MAE 0.344
## --------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## ------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## ------------------------------------------------------------------
## Regression 4.313 5 0.863 4.736 0.0014
## Residual 8.379 46 0.182
## Total 12.692 51
## ------------------------------------------------------------------
##
## Parameter Estimates
## ----------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## ----------------------------------------------------------------------------------------
## (Intercept) 4.036 1.256 3.213 0.002 1.508 6.565
## Alb -0.086 0.028 -0.412 -3.103 0.003 -0.141 -0.030
## trig -0.095 0.041 -0.297 -2.313 0.025 -0.178 -0.012
## age -0.006 0.005 -0.168 -1.332 0.189 -0.015 0.003
## Cre 0.003 0.002 0.205 1.573 0.123 -0.001 0.006
## protein 0.018 0.014 0.174 1.280 0.207 -0.010 0.046
## ----------------------------------------------------------------------------------------
##
## Selection Summary
## -----------------------------------------------------------------------
## Variable Adj.
## Step Entered R-Square R-Square C(p) AIC RMSE
## -----------------------------------------------------------------------
## 1 Alb 0.1461 0.1290 7.8764 72.0264 0.4656
## 2 trig 0.2386 0.2075 3.8211 68.0619 0.4441
## 3 age 0.2911 0.2468 2.3831 66.3437 0.4329
## 4 Cre 0.3163 0.2581 2.7360 66.4636 0.4297
## 5 protein 0.3398 0.2681 3.1964 66.6425 0.4268
## -----------------------------------------------------------------------
Tìm các biến được chọn sử dụng stepwise backward regression
Loại bỏ các biến không có ý nghĩa
for (i in 1:10) {
outcome <- names(Data_New[i])
variables <- names(Data_New[11:20])
f <- as.formula(paste(outcome,
paste(variables, collapse = " + "),
sep = " ~ "))
print(paste(i,'---',outcome, "###########"))
# Exec fucntion lm()
print(ols_step_backward_p(lm(formula = f, data = Data_New)))
}
## [1] "1 --- c2score ###########"
## Backward Elimination Method
## ---------------------------
##
## Candidate Terms:
##
## 1 . age
## 2 . BMI
## 3 . Weight
## 4 . Height
## 5 . Ure
## 6 . Cre
## 7 . Chol
## 8 . trig
## 9 . Alb
## 10 . protein
##
## We are eliminating variables based on p value...
##
## Variables Removed:
##
## - protein
## - Alb
## - Cre
##
## No more variables satisfy the condition of p value = 0.3
##
##
## Final Model Output
## ------------------
##
## Model Summary
## ---------------------------------------------------------------
## R 0.692 RMSE 22.546
## R-Squared 0.479 Coef. Var 32.341
## Adj. R-Squared 0.396 MSE 508.305
## Pred R-Squared 0.304 MAE 16.528
## ---------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 20555.244 7 2936.463 5.777 1e-04
## Residual 22365.429 44 508.305
## Total 42920.673 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## ----------------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## ----------------------------------------------------------------------------------------------
## (Intercept) -872.906 627.688 -1.391 0.171 -2137.927 392.116
## age -0.701 0.248 -0.335 -2.833 0.007 -1.200 -0.202
## BMI 25.872 14.846 2.722 1.743 0.088 -4.049 55.792
## Weight -8.215 5.411 -2.849 -1.518 0.136 -19.121 2.691
## Height 5.190 3.779 0.944 1.373 0.177 -2.426 12.806
## Ure 3.485 1.356 0.307 2.570 0.014 0.752 6.218
## Chol 6.194 2.947 0.245 2.102 0.041 0.254 12.134
## trig -6.670 2.122 -0.358 -3.144 0.003 -10.945 -2.394
## ----------------------------------------------------------------------------------------------
##
##
## Elimination Summary
## -------------------------------------------------------------------------
## Variable Adj.
## Step Removed R-Square R-Square C(p) AIC RMSE
## -------------------------------------------------------------------------
## 1 protein 0.4873 0.3774 9.0125 484.0584 22.8904
## 2 Alb 0.4856 0.3899 7.1455 482.2268 22.6593
## 3 Cre 0.4789 0.396 5.6809 480.8991 22.5456
## -------------------------------------------------------------------------
## [1] "2 --- phy_function ###########"
## Backward Elimination Method
## ---------------------------
##
## Candidate Terms:
##
## 1 . age
## 2 . BMI
## 3 . Weight
## 4 . Height
## 5 . Ure
## 6 . Cre
## 7 . Chol
## 8 . trig
## 9 . Alb
## 10 . protein
##
## We are eliminating variables based on p value...
##
## Variables Removed:
##
## - Cre
## - Weight
## - Height
## - Chol
## - protein
##
## No more variables satisfy the condition of p value = 0.3
##
##
## Final Model Output
## ------------------
##
## Model Summary
## ----------------------------------------------------------------
## R 0.413 RMSE 16.828
## R-Squared 0.170 Coef. Var 22.438
## Adj. R-Squared 0.080 MSE 283.192
## Pred R-Squared -0.100 MAE 11.883
## ----------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 2673.190 5 534.638 1.888 0.1149
## Residual 13026.810 46 283.192
## Total 15700.000 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## ------------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## ------------------------------------------------------------------------------------------
## (Intercept) -8.811 48.522 -0.182 0.857 -106.482 88.859
## age -0.284 0.173 -0.224 -1.644 0.107 -0.632 0.064
## BMI 1.069 0.819 0.186 1.305 0.199 -0.580 2.719
## Ure 1.133 1.018 0.165 1.113 0.272 -0.916 3.183
## trig -2.919 1.554 -0.259 -1.879 0.067 -6.047 0.209
## Alb 1.673 1.040 0.229 1.610 0.114 -0.419 3.766
## ------------------------------------------------------------------------------------------
##
##
## Elimination Summary
## -------------------------------------------------------------------------
## Variable Adj.
## Step Removed R-Square R-Square C(p) AIC RMSE
## -------------------------------------------------------------------------
## 1 Cre 0.1979 0.0261 9.0110 455.0286 17.3152
## 2 Weight 0.1936 0.0436 7.2306 453.3062 17.1584
## 3 Height 0.1935 0.0652 5.2392 451.3171 16.9641
## 4 Chol 0.1855 0.0769 3.6488 449.8310 16.8576
## 5 protein 0.1703 0.0801 2.4262 448.7927 16.8283
## -------------------------------------------------------------------------
## [1] "3 --- phy_health ###########"
## Backward Elimination Method
## ---------------------------
##
## Candidate Terms:
##
## 1 . age
## 2 . BMI
## 3 . Weight
## 4 . Height
## 5 . Ure
## 6 . Cre
## 7 . Chol
## 8 . trig
## 9 . Alb
## 10 . protein
##
## We are eliminating variables based on p value...
##
## Variables Removed:
##
## - age
## - Alb
## - protein
## - Ure
## - Cre
## - Weight
## - BMI
## - Height
##
## No more variables satisfy the condition of p value = 0.3
##
##
## Final Model Output
## ------------------
##
## Model Summary
## ----------------------------------------------------------------
## R 0.372 RMSE 37.687
## R-Squared 0.138 Coef. Var 85.205
## Adj. R-Squared 0.103 MSE 1420.286
## Pred R-Squared 0.055 MAE 30.381
## ----------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 11175.205 2 5587.603 3.934 0.0260
## Residual 69594.025 49 1420.286
## Total 80769.231 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## -----------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## -----------------------------------------------------------------------------------------
## (Intercept) -2.461 23.723 -0.104 0.918 -50.135 45.213
## Chol 11.490 4.598 0.332 2.499 0.016 2.251 20.730
## trig -4.532 3.389 -0.177 -1.337 0.187 -11.343 2.279
## -----------------------------------------------------------------------------------------
##
##
## Elimination Summary
## --------------------------------------------------------------------------
## Variable Adj.
## Step Removed R-Square R-Square C(p) AIC RMSE
## --------------------------------------------------------------------------
## 1 age 0.1787 0.0027 9.0786 541.4347 39.7422
## 2 Alb 0.174 0.0203 7.3134 539.7310 39.3894
## 3 protein 0.1669 0.0343 5.6699 538.1779 39.1069
## 4 Ure 0.1583 0.046 4.1004 536.7123 38.8692
## 5 Cre 0.1497 0.0572 2.5299 535.2400 38.6399
## 6 Weight 0.1401 0.0669 1.0112 533.8252 38.4424
## 7 BMI 0.1396 0.0858 -0.9652 531.8538 38.0502
## 8 Height 0.1384 0.1032 -2.9041 529.9275 37.6867
## --------------------------------------------------------------------------
## [1] "4 --- emotional ###########"
## Backward Elimination Method
## ---------------------------
##
## Candidate Terms:
##
## 1 . age
## 2 . BMI
## 3 . Weight
## 4 . Height
## 5 . Ure
## 6 . Cre
## 7 . Chol
## 8 . trig
## 9 . Alb
## 10 . protein
##
## We are eliminating variables based on p value...
##
## Variables Removed:
##
## - Alb
## - age
## - trig
## - Ure
## - BMI
## - protein
##
## No more variables satisfy the condition of p value = 0.3
##
##
## Final Model Output
## ------------------
##
## Model Summary
## -----------------------------------------------------------------
## R 0.342 RMSE 38.310
## R-Squared 0.117 Coef. Var 83.006
## Adj. R-Squared 0.042 MSE 1467.675
## Pred R-Squared -0.097 MAE 32.267
## -----------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 9138.938 4 2284.735 1.557 0.2015
## Residual 68980.720 47 1467.675
## Total 78119.658 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## ---------------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## ---------------------------------------------------------------------------------------------
## (Intercept) -246.722 200.532 -1.230 0.225 -650.140 156.695
## Weight -0.895 0.742 -0.230 -1.206 0.234 -2.388 0.598
## Height 2.074 1.427 0.280 1.453 0.153 -0.798 4.946
## Cre -0.296 0.167 -0.273 -1.772 0.083 -0.631 0.040
## Chol 7.195 4.747 0.211 1.516 0.136 -2.354 16.744
## ---------------------------------------------------------------------------------------------
##
##
## Elimination Summary
## -------------------------------------------------------------------------
## Variable Adj.
## Step Removed R-Square R-Square C(p) AIC RMSE
## -------------------------------------------------------------------------
## 1 Alb 0.1588 -0.0215 9.0141 540.9460 39.5559
## 2 age 0.1582 0.0015 7.0442 538.9841 39.1075
## 3 trig 0.1572 0.0231 5.0925 537.0453 38.6833
## 4 Ure 0.1454 0.0315 3.6642 535.7638 38.5163
## 5 BMI 0.1335 0.0393 2.2468 534.4858 38.3607
## 6 protein 0.117 0.0418 1.0517 533.4672 38.3102
## -------------------------------------------------------------------------
## [1] "5 --- fatigue ###########"
## Backward Elimination Method
## ---------------------------
##
## Candidate Terms:
##
## 1 . age
## 2 . BMI
## 3 . Weight
## 4 . Height
## 5 . Ure
## 6 . Cre
## 7 . Chol
## 8 . trig
## 9 . Alb
## 10 . protein
##
## We are eliminating variables based on p value...
##
## Variables Removed:
##
## - Chol
## - protein
## - Cre
## - age
##
## No more variables satisfy the condition of p value = 0.3
##
##
## Final Model Output
## ------------------
##
## Model Summary
## ----------------------------------------------------------------
## R 0.495 RMSE 18.390
## R-Squared 0.245 Coef. Var 29.066
## Adj. R-Squared 0.144 MSE 338.182
## Pred R-Squared -0.020 MAE 13.034
## ----------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 4926.034 6 821.006 2.428 0.0406
## Residual 15218.197 45 338.182
## Total 20144.231 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## ---------------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## ---------------------------------------------------------------------------------------------
## (Intercept) -948.671 498.739 -1.902 0.064 -1953.183 55.841
## BMI 24.477 11.965 3.759 2.046 0.047 0.378 48.577
## Weight -8.509 4.352 -4.308 -1.955 0.057 -17.275 0.257
## Height 5.284 3.043 1.403 1.736 0.089 -0.846 11.414
## Ure 2.176 1.133 0.280 1.920 0.061 -0.107 4.459
## trig -3.324 1.727 -0.261 -1.924 0.061 -6.803 0.155
## Alb 2.482 1.141 0.300 2.176 0.035 0.185 4.780
## ---------------------------------------------------------------------------------------------
##
##
## Elimination Summary
## -------------------------------------------------------------------------
## Variable Adj.
## Step Removed R-Square R-Square C(p) AIC RMSE
## -------------------------------------------------------------------------
## 1 Chol 0.2688 0.1122 9.0069 463.1772 18.7265
## 2 protein 0.2678 0.1316 7.0652 461.2511 18.5206
## 3 Cre 0.2591 0.1412 5.5543 459.8668 18.4176
## 4 age 0.2445 0.1438 4.3701 458.8778 18.3897
## -------------------------------------------------------------------------
## [1] "6 --- wellbeing ###########"
## Backward Elimination Method
## ---------------------------
##
## Candidate Terms:
##
## 1 . age
## 2 . BMI
## 3 . Weight
## 4 . Height
## 5 . Ure
## 6 . Cre
## 7 . Chol
## 8 . trig
## 9 . Alb
## 10 . protein
##
## We are eliminating variables based on p value...
##
## Variables Removed:
##
## - protein
## - age
## - Cre
## - Chol
## - trig
##
## No more variables satisfy the condition of p value = 0.3
##
##
## Final Model Output
## ------------------
##
## Model Summary
## ---------------------------------------------------------------
## R 0.484 RMSE 15.847
## R-Squared 0.234 Coef. Var 22.393
## Adj. R-Squared 0.151 MSE 251.133
## Pred R-Squared 0.058 MAE 12.108
## ---------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 3537.117 5 707.423 2.817 0.0266
## Residual 11552.114 46 251.133
## Total 15089.231 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## ---------------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## ---------------------------------------------------------------------------------------------
## (Intercept) -795.034 426.616 -1.864 0.069 -1653.768 63.700
## BMI 21.571 10.277 3.828 2.099 0.041 0.885 42.257
## Weight -7.433 3.737 -4.348 -1.989 0.053 -14.956 0.089
## Height 4.428 2.606 1.359 1.700 0.096 -0.816 9.673
## Ure 1.835 0.962 0.272 1.907 0.063 -0.101 3.771
## Alb 2.248 0.976 0.314 2.304 0.026 0.284 4.212
## ---------------------------------------------------------------------------------------------
##
##
## Elimination Summary
## -------------------------------------------------------------------------
## Variable Adj.
## Step Removed R-Square R-Square C(p) AIC RMSE
## -------------------------------------------------------------------------
## 1 protein 0.2773 0.1224 9.0112 447.5483 16.1135
## 2 age 0.2742 0.1392 7.1872 445.7709 15.9592
## 3 Cre 0.2618 0.1443 5.8922 444.6535 15.9112
## 4 Chol 0.2499 0.1499 4.5642 443.4810 15.8591
## 5 trig 0.2344 0.1512 3.4444 442.5454 15.8472
## -------------------------------------------------------------------------
## [1] "7 --- social_fun ###########"
## Backward Elimination Method
## ---------------------------
##
## Candidate Terms:
##
## 1 . age
## 2 . BMI
## 3 . Weight
## 4 . Height
## 5 . Ure
## 6 . Cre
## 7 . Chol
## 8 . trig
## 9 . Alb
## 10 . protein
##
## We are eliminating variables based on p value...
##
## Variables Removed:
##
## - age
## - Cre
## - protein
## - Alb
##
## No more variables satisfy the condition of p value = 0.3
##
##
## Final Model Output
## ------------------
##
## Model Summary
## ----------------------------------------------------------------
## R 0.457 RMSE 18.836
## R-Squared 0.209 Coef. Var 28.808
## Adj. R-Squared 0.104 MSE 354.806
## Pred R-Squared -0.036 MAE 13.752
## ----------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 4226.021 6 704.337 1.985 0.0877
## Residual 15966.287 45 354.806
## Total 20192.308 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## ---------------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## ---------------------------------------------------------------------------------------------
## (Intercept) -966.376 510.784 -1.892 0.065 -1995.147 62.395
## BMI 27.005 12.167 4.142 2.220 0.032 2.500 51.511
## Weight -9.248 4.426 -4.676 -2.089 0.042 -18.163 -0.332
## Height 5.891 3.088 1.562 1.908 0.063 -0.329 12.111
## Ure 1.504 1.131 0.193 1.330 0.190 -0.774 3.782
## Chol 3.566 2.339 0.206 1.525 0.134 -1.144 8.277
## trig -3.125 1.756 -0.245 -1.779 0.082 -6.663 0.412
## ---------------------------------------------------------------------------------------------
##
##
## Elimination Summary
## -------------------------------------------------------------------------
## Variable Adj.
## Step Removed R-Square R-Square C(p) AIC RMSE
## -------------------------------------------------------------------------
## 1 age 0.2299 0.0648 9.0219 466.0028 19.2422
## 2 Cre 0.2248 0.0806 7.2895 464.3409 19.0791
## 3 protein 0.2155 0.0907 5.7875 462.9643 18.9744
## 4 Alb 0.2093 0.1039 4.1173 461.3731 18.8363
## -------------------------------------------------------------------------
## [1] "8 --- pain ###########"
## Backward Elimination Method
## ---------------------------
##
## Candidate Terms:
##
## 1 . age
## 2 . BMI
## 3 . Weight
## 4 . Height
## 5 . Ure
## 6 . Cre
## 7 . Chol
## 8 . trig
## 9 . Alb
## 10 . protein
##
## We are eliminating variables based on p value...
##
## Variables Removed:
##
## - protein
## - age
##
## No more variables satisfy the condition of p value = 0.3
##
##
## Final Model Output
## ------------------
##
## Model Summary
## ----------------------------------------------------------------
## R 0.492 RMSE 25.002
## R-Squared 0.242 Coef. Var 36.418
## Adj. R-Squared 0.101 MSE 625.112
## Pred R-Squared -0.092 MAE 17.743
## ----------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 8575.970 8 1071.996 1.715 0.1225
## Residual 26879.800 43 625.112
## Total 35455.769 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## ------------------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## ------------------------------------------------------------------------------------------------
## (Intercept) -1582.404 715.495 -2.212 0.032 -3025.338 -139.470
## BMI 38.110 16.789 4.411 2.270 0.028 4.251 71.968
## Weight -13.303 6.150 -5.076 -2.163 0.036 -25.706 -0.900
## Height 9.087 4.348 1.819 2.090 0.043 0.319 17.856
## Ure 2.954 1.743 0.286 1.695 0.097 -0.561 6.468
## Cre -0.155 0.130 -0.212 -1.188 0.241 -0.417 0.108
## Chol 3.601 3.136 0.157 1.148 0.257 -2.723 9.925
## trig -4.374 2.372 -0.258 -1.844 0.072 -9.159 0.410
## Alb 2.365 1.638 0.215 1.443 0.156 -0.939 5.669
## ------------------------------------------------------------------------------------------------
##
##
## Elimination Summary
## -------------------------------------------------------------------------
## Variable Adj.
## Step Removed R-Square R-Square C(p) AIC RMSE
## -------------------------------------------------------------------------
## 1 protein 0.2489 0.088 9.0848 493.9728 25.1800
## 2 age 0.2419 0.1008 7.4713 492.4597 25.0022
## -------------------------------------------------------------------------
## [1] "9 --- general ###########"
## Backward Elimination Method
## ---------------------------
##
## Candidate Terms:
##
## 1 . age
## 2 . BMI
## 3 . Weight
## 4 . Height
## 5 . Ure
## 6 . Cre
## 7 . Chol
## 8 . trig
## 9 . Alb
## 10 . protein
##
## We are eliminating variables based on p value...
##
## Variables Removed:
##
## - BMI
## - Cre
## - Height
## - Chol
## - protein
##
## No more variables satisfy the condition of p value = 0.3
##
##
## Final Model Output
## ------------------
##
## Model Summary
## ----------------------------------------------------------------
## R 0.417 RMSE 15.756
## R-Squared 0.174 Coef. Var 35.622
## Adj. R-Squared 0.084 MSE 248.247
## Pred R-Squared -0.046 MAE 12.356
## ----------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## --------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## --------------------------------------------------------------------
## Regression 2399.850 5 479.970 1.933 0.1070
## Residual 11419.381 46 248.247
## Total 13819.231 51
## --------------------------------------------------------------------
##
## Parameter Estimates
## -------------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## -------------------------------------------------------------------------------------------
## (Intercept) -25.923 44.130 -0.587 0.560 -114.752 62.905
## age -0.246 0.162 -0.207 -1.522 0.135 -0.571 0.079
## Weight 0.356 0.228 0.218 1.560 0.126 -0.103 0.815
## Ure 1.059 0.936 0.164 1.131 0.264 -0.825 2.942
## trig -2.936 1.459 -0.278 -2.011 0.050 -5.873 0.002
## Alb 1.372 0.974 0.200 1.408 0.166 -0.590 3.333
## -------------------------------------------------------------------------------------------
##
##
## Elimination Summary
## -------------------------------------------------------------------------
## Variable Adj.
## Step Removed R-Square R-Square C(p) AIC RMSE
## -------------------------------------------------------------------------
## 1 BMI 0.1893 0.0156 9.0070 448.9491 16.3320
## 2 Cre 0.1875 0.0363 7.1016 447.0689 16.1596
## 3 Height 0.1841 0.0543 5.2694 445.2809 16.0075
## 4 Chol 0.1806 0.0714 3.4462 443.5031 15.8625
## 5 protein 0.1737 0.0838 1.7994 441.9444 15.7559
## -------------------------------------------------------------------------
## [1] "10 --- PostPT ###########"
## Backward Elimination Method
## ---------------------------
##
## Candidate Terms:
##
## 1 . age
## 2 . BMI
## 3 . Weight
## 4 . Height
## 5 . Ure
## 6 . Cre
## 7 . Chol
## 8 . trig
## 9 . Alb
## 10 . protein
##
## We are eliminating variables based on p value...
##
## Variables Removed:
##
## - Height
## - Ure
## - BMI
## - Weight
## - Chol
##
## No more variables satisfy the condition of p value = 0.3
##
##
## Final Model Output
## ------------------
##
## Model Summary
## --------------------------------------------------------------
## R 0.583 RMSE 0.427
## R-Squared 0.340 Coef. Var 27.065
## Adj. R-Squared 0.268 MSE 0.182
## Pred R-Squared 0.142 MAE 0.344
## --------------------------------------------------------------
## RMSE: Root Mean Square Error
## MSE: Mean Square Error
## MAE: Mean Absolute Error
##
## ANOVA
## ------------------------------------------------------------------
## Sum of
## Squares DF Mean Square F Sig.
## ------------------------------------------------------------------
## Regression 4.313 5 0.863 4.736 0.0014
## Residual 8.379 46 0.182
## Total 12.692 51
## ------------------------------------------------------------------
##
## Parameter Estimates
## ----------------------------------------------------------------------------------------
## model Beta Std. Error Std. Beta t Sig lower upper
## ----------------------------------------------------------------------------------------
## (Intercept) 4.036 1.256 3.213 0.002 1.508 6.565
## age -0.006 0.005 -0.168 -1.332 0.189 -0.015 0.003
## Cre 0.003 0.002 0.205 1.573 0.123 -0.001 0.006
## trig -0.095 0.041 -0.297 -2.313 0.025 -0.178 -0.012
## Alb -0.086 0.028 -0.412 -3.103 0.003 -0.141 -0.030
## protein 0.018 0.014 0.174 1.280 0.207 -0.010 0.046
## ----------------------------------------------------------------------------------------
##
##
## Elimination Summary
## -----------------------------------------------------------------------
## Variable Adj.
## Step Removed R-Square R-Square C(p) AIC RMSE
## -----------------------------------------------------------------------
## 1 Height 0.3731 0.2388 9.0177 71.9512 0.4352
## 2 Ure 0.371 0.254 7.1574 70.1281 0.4309
## 3 BMI 0.3555 0.253 6.1695 69.3913 0.4312
## 4 Weight 0.3524 0.266 4.3762 67.6455 0.4274
## 5 Chol 0.3398 0.2681 3.1964 66.6425 0.4268
## -----------------------------------------------------------------------
# Viết hàm chèn dữ liệu thiếu bằng mean:
chen_na <- function(x) {
x[is.na(x)] <- mean(x, na.rm = TRUE)
return(x)
}
plot(Data_New$Alb, Data_New$PostPT)
