setwd("~/Google Drive/PhD/Projects/NS QoL survey/Data")
load("qol_cleaned_v1_Sept7.RData")
library(readr)
library(GGally)
library(ggplot2)
library(PerformanceAnalytics)
library(corrplot)
library(plyr)
library(dplyr)
library(psych)
library(Hmisc)
library(rmarkdown)
library(jmv)
library(stats)
library(rsq)
library(plotly)
library(sjPlot)
library(car)
library(tidyverse)
library(MASS)
#truncating social support variables
qol<- filter(qol, NEIGHBRS < 100)
qol<- filter(qol, FRIENDS < 100)
qol<- filter(qol, RELATVS < 100)
### Correlations
#looking at correlations of numeric variables identified as relevant to our first pass
qol.plot<- qol[,c("LIFESAT", "RELATVS", "FRIENDS", "ENV", "NEIGHBRS", "PHYSHLTH", "MNTLHLTH", "HB_EXERCISE", "POLICY_R",
"AGE", "OVERALL_SOC", "TIME_ADEQ_R", "FINANCIAL_INSECURITY")]
#Calculating correlations and CIs
cor1 <- cor.mtest(qol.plot, use="pairwise.complete.obs", conf.level = 0.95)
cor1
## $p
## [,1] [,2] [,3] [,4] [,5]
## [1,] 0.000000e+00 1.000684e-50 3.671487e-84 0.000000e+00 5.793919e-92
## [2,] 1.000684e-50 0.000000e+00 7.069533e-296 8.115520e-27 1.334546e-214
## [3,] 3.671487e-84 7.069533e-296 0.000000e+00 3.697630e-39 9.082378e-270
## [4,] 0.000000e+00 8.115520e-27 3.697630e-39 0.000000e+00 1.164020e-100
## [5,] 5.793919e-92 1.334546e-214 9.082378e-270 1.164020e-100 0.000000e+00
## [6,] 0.000000e+00 3.667847e-19 1.026701e-34 1.507863e-146 5.337166e-49
## [7,] 0.000000e+00 4.702364e-35 3.896097e-57 3.748877e-317 1.100156e-70
## [8,] 1.847924e-188 3.965434e-11 3.148131e-34 5.544733e-73 8.200064e-34
## [9,] 1.967960e-129 1.173935e-11 4.716317e-29 1.781366e-189 8.212826e-31
## [10,] 7.269967e-127 8.143447e-01 6.013021e-08 1.539305e-145 4.564393e-10
## [11,] 0.000000e+00 5.468869e-99 7.111568e-185 0.000000e+00 0.000000e+00
## [12,] 0.000000e+00 5.533916e-10 1.593264e-27 0.000000e+00 4.990736e-26
## [13,] 0.000000e+00 4.839760e-09 2.918186e-21 2.800348e-245 7.976672e-26
## [,6] [,7] [,8] [,9] [,10]
## [1,] 0.000000e+00 0.000000e+00 1.847924e-188 1.967960e-129 7.269967e-127
## [2,] 3.667847e-19 4.702364e-35 3.965434e-11 1.173935e-11 8.143447e-01
## [3,] 1.026701e-34 3.896097e-57 3.148131e-34 4.716317e-29 6.013021e-08
## [4,] 1.507863e-146 3.748877e-317 5.544733e-73 1.781366e-189 1.539305e-145
## [5,] 5.337166e-49 1.100156e-70 8.200064e-34 8.212826e-31 4.564393e-10
## [6,] 0.000000e+00 0.000000e+00 0.000000e+00 5.782106e-77 1.757129e-15
## [7,] 0.000000e+00 0.000000e+00 4.577083e-182 9.043695e-65 2.170968e-114
## [8,] 0.000000e+00 4.577083e-182 0.000000e+00 2.585603e-59 4.197618e-01
## [9,] 5.782106e-77 9.043695e-65 2.585603e-59 0.000000e+00 6.726556e-20
## [10,] 1.757129e-15 2.170968e-114 4.197618e-01 6.726556e-20 0.000000e+00
## [11,] 5.280251e-191 0.000000e+00 1.335750e-131 1.186848e-312 1.679939e-67
## [12,] 2.850380e-56 1.820671e-288 9.853761e-74 1.548059e-90 0.000000e+00
## [13,] 4.796370e-124 1.827803e-235 5.312595e-59 5.440807e-89 1.124694e-281
## [,11] [,12] [,13]
## [1,] 0.000000e+00 0.000000e+00 0.000000e+00
## [2,] 5.468869e-99 5.533916e-10 4.839760e-09
## [3,] 7.111568e-185 1.593264e-27 2.918186e-21
## [4,] 0.000000e+00 0.000000e+00 2.800348e-245
## [5,] 0.000000e+00 4.990736e-26 7.976672e-26
## [6,] 5.280251e-191 2.850380e-56 4.796370e-124
## [7,] 0.000000e+00 1.820671e-288 1.827803e-235
## [8,] 1.335750e-131 9.853761e-74 5.312595e-59
## [9,] 1.186848e-312 1.548059e-90 5.440807e-89
## [10,] 1.679939e-67 0.000000e+00 1.124694e-281
## [11,] 0.000000e+00 5.122835e-240 2.518500e-199
## [12,] 5.122835e-240 0.000000e+00 0.000000e+00
## [13,] 2.518500e-199 0.000000e+00 0.000000e+00
##
## $lowCI
## [,1] [,2] [,3] [,4] [,5] [,6]
## [1,] 1.0000000 0.11969268 0.16024946 0.46611815 0.16840095 0.35188732
## [2,] 0.1196927 1.00000000 0.31270501 0.08082155 0.26520865 0.06433815
## [3,] 0.1602495 0.31270501 1.00000000 0.10259415 0.29837094 0.09502247
## [4,] 0.4661182 0.08082155 0.10259415 1.00000000 0.17735531 0.21784541
## [5,] 0.1684010 0.26520865 0.29837094 0.17735531 1.00000000 0.11718277
## [6,] 0.3518873 0.06433815 0.09502247 0.21784541 0.11718277 1.00000000
## [7,] 0.5319441 0.09562356 0.12832191 0.32539402 0.14510813 0.47841229
## [8,] 0.2488773 0.04285751 0.09431740 0.14838732 0.09359986 0.43313332
## [9,] 0.2151177 0.04705733 0.08990572 0.26375350 0.09333913 0.16132422
## [10,] 0.2010254 -0.01587923 0.03183478 0.21683153 0.03933266 -0.09118631
## [11,] 0.4218775 0.17600797 0.24656134 0.47177240 0.34169122 0.25113572
## [12,] 0.4553687 0.03931693 0.08247109 0.42565000 0.07952856 0.12801766
## [13,] -0.4339644 -0.07303107 -0.10662679 -0.32288872 -0.11628163 -0.23675589
## [,7] [,8] [,9] [,10] [,11] [,12]
## [1,] 0.53194405 0.24887733 0.21511767 0.20102541 0.4218775 0.45536873
## [2,] 0.09562356 0.04285751 0.04705733 -0.01587923 0.1760080 0.03931693
## [3,] 0.12832191 0.09431740 0.08990572 0.03183478 0.2465613 0.08247109
## [4,] 0.32539402 0.14838732 0.26375350 0.21683153 0.4717724 0.42565000
## [5,] 0.14510813 0.09359986 0.09333913 0.03933266 0.3416912 0.07952856
## [6,] 0.47841229 0.43313332 0.16132422 -0.09118631 0.2511357 0.12801766
## [7,] 1.00000000 0.24422725 0.14623842 0.18993345 0.3325496 0.31117367
## [8,] 0.24422725 1.00000000 0.13913090 -0.01064268 0.2060284 0.14975644
## [9,] 0.14623842 0.13913090 1.00000000 0.06994408 0.3414783 0.17754957
## [10,] 0.18993345 -0.01064268 0.06994408 1.00000000 0.1418787 0.44583208
## [11,] 0.33254956 0.20602844 0.34147825 0.14187873 1.0000000 0.28422685
## [12,] 0.31117367 0.14975644 0.17754957 0.44583208 0.2842269 1.00000000
## [13,] -0.31674080 -0.16901208 -0.21497985 -0.34288869 -0.2947376 -0.40785580
## [,13]
## [1,] -0.43396435
## [2,] -0.07303107
## [3,] -0.10662679
## [4,] -0.32288872
## [5,] -0.11628163
## [6,] -0.23675589
## [7,] -0.31674080
## [8,] -0.16901208
## [9,] -0.21497985
## [10,] -0.34288869
## [11,] -0.29473763
## [12,] -0.40785580
## [13,] 1.00000000
##
## $uppCI
## [,1] [,2] [,3] [,4] [,5] [,6]
## [1,] 1.0000000 0.15515164 0.19524892 0.4939999 0.20329396 0.3831828
## [2,] 0.1551516 1.00000000 0.34487706 0.1166702 0.29841574 0.1002123
## [3,] 0.1952489 0.34487706 1.00000000 0.1382707 0.33087195 0.1306810
## [4,] 0.4939999 0.11667021 0.13827068 1.0000000 0.21218333 0.2520888
## [5,] 0.2032940 0.29841574 0.33087195 0.2121833 1.00000000 0.1526438
## [6,] 0.3831828 0.10021226 0.13068102 0.2520888 0.15264383 1.0000000
## [7,] 0.5573981 0.13128626 0.16367944 0.3574214 0.18027944 0.5058063
## [8,] 0.2825525 0.07889129 0.13003000 0.1836647 0.12931825 0.4620765
## [9,] 0.2513432 0.08513826 0.12770087 0.2990743 0.13110536 0.1983753
## [10,] 0.2354525 0.02020102 0.06782558 0.2510587 0.07529452 -0.0552537
## [11,] 0.4512815 0.21091249 0.28030620 0.4995637 0.37331738 0.2848361
## [12,] 0.4837155 0.07551994 0.11842726 0.4549866 0.11550582 0.1636107
## [13,] -0.4036558 -0.03644296 -0.07021570 -0.2895554 -0.07993688 -0.2017813
## [,7] [,8] [,9] [,10] [,11] [,12]
## [1,] 0.5573981 0.28255249 0.25134316 0.23545254 0.4512815 0.48371547
## [2,] 0.1312863 0.07889129 0.08513826 0.02020102 0.2109125 0.07551994
## [3,] 0.1636794 0.13003000 0.12770087 0.06782558 0.2803062 0.11842726
## [4,] 0.3574214 0.18366467 0.29907427 0.25105865 0.4995637 0.45498663
## [5,] 0.1802794 0.12931825 0.13110536 0.07529452 0.3733174 0.11550582
## [6,] 0.5058063 0.46207646 0.19837530 -0.05525370 0.2848361 0.16361073
## [7,] 1.0000000 0.27796609 0.18349797 0.22451679 0.3644554 0.34364763
## [8,] 0.2779661 1.00000000 0.17651861 0.02553086 0.2405412 0.18513650
## [9,] 0.1834980 0.17651861 1.00000000 0.10789687 0.3749859 0.21454081
## [10,] 0.2245168 0.02553086 0.10789687 1.00000000 0.1772250 0.47446810
## [11,] 0.3644554 0.24054123 0.37498589 0.17722501 1.0000000 0.31742303
## [12,] 0.3436476 0.18513650 0.21454081 0.47446810 0.3174230 1.00000000
## [13,] -0.2832986 -0.13307582 -0.17761628 -0.31009795 -0.2607050 -0.37665648
## [,13]
## [1,] -0.40365577
## [2,] -0.03644296
## [3,] -0.07021570
## [4,] -0.28955541
## [5,] -0.07993688
## [6,] -0.20178134
## [7,] -0.28329857
## [8,] -0.13307582
## [9,] -0.17761628
## [10,] -0.31009795
## [11,] -0.26070496
## [12,] -0.37665648
## [13,] 1.00000000
#Correlation Matrix
corrplot(cor(qol.plot, use="pairwise.complete.obs"), method="number", type="upper",
addCoef.col = "black", tl.col="black", tl.srt=40, p.mat = cor1$p, tl.cex = .5,
sig.level = 0.05, insig = "blank", diag=FALSE, number.cex= 10/ncol(qol.plot))
## Descriptives
#descriptives of numeric variables
descriptives(qol, vars = vars("RELATVS", "FRIENDS", "ENV", "NEIGHBRS", "PHYSHLTH", "MNTLHLTH", "FINANCIAL_INSECURITY"), missing=TRUE, box=FALSE)
##
## DESCRIPTIVES
##
## Descriptives
## ───────────────────────────────────────────────────────────────────────────────────────────────────────────
## RELATVS FRIENDS ENV NEIGHBRS PHYSHLTH MNTLHLTH FINANCIAL_INSECURITY
## ───────────────────────────────────────────────────────────────────────────────────────────────────────────
## N 11809 11809 11725 11809 11779 11773 11410
## Missing 0 0 84 0 30 36 399
## Mean 6.292531 5.029342 5.476077 4.584258 3.290093 3.542682 1.416995
## Median 4.000000 4.000000 6.000000 3.000000 3.000000 4.000000 1.000000
## Minimum 0.000000 0.000000 1.000000 0.000000 1.000000 1.000000 1.000000
## Maximum 96.00000 85.00000 7.000000 80.00000 5.000000 5.000000 5.000000
## ───────────────────────────────────────────────────────────────────────────────────────────────────────────
descriptives(qol, vars = vars("HB_EXERCISE", "POLICY_R", "AGE", "OVERALL_SOC","TIME_ADEQ_R"), missing=TRUE, box=FALSE)
##
## DESCRIPTIVES
##
## Descriptives
## ────────────────────────────────────────────────────────────────────────────────
## HB_EXERCISE POLICY_R AGE OVERALL_SOC TIME_ADEQ_R
## ────────────────────────────────────────────────────────────────────────────────
## N 11747 10504 11804 11686 11647
## Missing 62 1305 5 123 162
## Mean 4.661786 4.457254 59.75479 4.805503 7.701547
## Median 5.000000 4.000000 62.00000 4.833333 8.363636
## Minimum 1.000000 1.000000 14.00000 1.000000 1.000000
## Maximum 7.000000 7.000000 101.0000 7.000000 10.00000
## ────────────────────────────────────────────────────────────────────────────────
#OLS Regression model to do diagnostics
summary(ols <- lm(LIFESAT ~ RELATVS + FRIENDS + ENV + NEIGHBRS + PHYSHLTH + MNTLHLTH + FINANCIAL_INSECURITY + HB_EXERCISE
+ POLICY_R + AGE + OVERALL_SOC + TIME_ADEQ_R + TIME_CAN, data = qol))
##
## Call:
## lm(formula = LIFESAT ~ RELATVS + FRIENDS + ENV + NEIGHBRS + PHYSHLTH +
## MNTLHLTH + FINANCIAL_INSECURITY + HB_EXERCISE + POLICY_R +
## AGE + OVERALL_SOC + TIME_ADEQ_R + TIME_CAN, data = qol)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.0369 -0.7181 0.1246 0.9131 6.4653
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.224955 0.183303 6.683 2.48e-11 ***
## RELATVS 0.007155 0.002118 3.379 0.000731 ***
## FRIENDS 0.011465 0.002902 3.950 7.86e-05 ***
## ENV 0.272883 0.014539 18.769 < 2e-16 ***
## NEIGHBRS -0.001464 0.003065 -0.478 0.632927
## PHYSHLTH 0.115706 0.020150 5.742 9.62e-09 ***
## MNTLHLTH 0.647247 0.020134 32.147 < 2e-16 ***
## FINANCIAL_INSECURITY -0.394340 0.021595 -18.261 < 2e-16 ***
## HB_EXERCISE 0.065969 0.010686 6.174 6.95e-10 ***
## POLICY_R 0.016724 0.013177 1.269 0.204416
## AGE -0.007865 0.001281 -6.138 8.69e-10 ***
## OVERALL_SOC 0.273265 0.021785 12.544 < 2e-16 ***
## TIME_ADEQ_R 0.189212 0.008227 23.000 < 2e-16 ***
## TIME_CAN 0.351690 0.120362 2.922 0.003487 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.455 on 9677 degrees of freedom
## (2118 observations deleted due to missingness)
## Multiple R-squared: 0.4943, Adjusted R-squared: 0.4937
## F-statistic: 727.7 on 13 and 9677 DF, p-value: < 2.2e-16
# need help with next steps (e.g., cooks distance)
write.csv(qol, file = "qol_cleaned_v1_sept8")
save.image(file="qol_cleaned_v1_Sept8.RData")