Nutrition and DD
Vu Thien
2023-12-04
1. Import data set
library(haven)
df <- read_sas("/Users/thien/Desktop/R-dir/Depressive Disorder project/nhanes.sas7bdat")2. Dependent variables
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.4.0 ✔ purrr 0.3.4
## ✔ tibble 3.1.8 ✔ dplyr 1.0.10
## ✔ tidyr 1.2.1 ✔ stringr 1.5.0
## ✔ readr 2.1.4 ✔ forcats 1.0.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()# Filter the dataframe
df21 <- df %>%
filter(DPQ010 != 7 & DPQ010 != 9 & !is.na(DPQ010))
df22 <- df21 %>%
filter(DPQ020 != 7 & DPQ020 != 9 & !is.na(DPQ020))
df23 <- df22 %>%
filter(DPQ030 != 7 & DPQ030 != 9 & !is.na(DPQ030))
df24 <- df23 %>%
filter(DPQ040 != 7 & DPQ040 != 9 & !is.na(DPQ040))
df25 <- df24 %>%
filter(DPQ050 != 7 & DPQ050 != 9 & !is.na(DPQ050))
df26 <- df25 %>%
filter(DPQ060 != 7 & DPQ060 != 9 & !is.na(DPQ060))
df27 <- df26 %>%
filter(DPQ070 != 7 & DPQ070 != 9 & !is.na(DPQ070))
df28 <- df27 %>%
filter(DPQ080 != 7 & DPQ080 != 9 & !is.na(DPQ080))
df29 <- df28 %>%
filter(DPQ090 != 7 & DPQ090 != 9 & !is.na(DPQ090))
# Create depression variable:
depress <- df29
depress$dp = depress$DPQ010 + depress$DPQ020 + depress$DPQ030 + depress$DPQ040 + depress$DPQ050 + depress$DPQ060 + depress$DPQ070 + depress$DPQ080 + depress$DPQ090
# Create the new variable 'dp10'
depress <- depress %>%
mutate(dp10 = ifelse(dp <= 9, 0, 1))3. Some potential covariates
# 3.1 Create SBP and DBP
depress$SBP = (depress$BPXSY1 + depress$BPXSY2) / 2
depress$DBP =(depress$BPXDI1 + depress$BPXDI2) / 2
# 3.2 Create the variable ‘hyper’
hypertension <- depress %>%
mutate(hyper = case_when(
SBP >= 140 | DBP >= 90 | BPQ040A == 1 | BPQ050A == 1 ~ 1,
TRUE ~ 0))
# 3.3 Create the variable ‘dyslip’ using case_when
lipid <- hypertension %>%
mutate(dyslip = case_when(
LBXTC >= 200 | LBXTR >= 150 | LBDLDL >= 100 | LBDHDD <= 40 | BPQ090D == 1 ~ 1,
TRUE ~ 0
))
# 3.4 Create the ‘db’ variable using case_when
diab <- lipid %>%
mutate(db = case_when(
LBXGLU >= 126 | LBXGLT >= 200 | LBXGH >= 6.5 | DIQ070 == 1 ~ 1,
TRUE ~ 0
))4. Select variables (with nutrition variables) for analysis from original one
df3 <- subset(diab, select = c( RIDAGEYR, RIAGENDR, RIDRETH3, DMDEDUC2, DMDMARTL,
SBP, DBP, BMXBMI, INDFMIN2, INDFMPIR, LBXSBU, LBXSCR,
LBXSASSI, LBXSATSI, LBXAPB, LBDHDD,
LBDLDL, LBXTR, LBXTC, LBXGLU, LBXGLT,
ALQ101, SMQ020, PAQ665, PAQ650,
LBXCOT, LBXHCT, URXCOTT, URXHCTT,
DBD100, DR1TKCAL, DR1TPROT,
DR1TCARB, DR1TSUGR, DR1TFIBE,
DR1TTFAT, DR1TSFAT, DR1TMFAT,
DR1TPFAT, DR1TCHOL, DR1TATOC,
DR1TATOA, DR1TRET, DR1TVARA,
DR1TACAR, DR1TBCAR, DR1TCRYP,
DR1TLYCO, DR1TLZ, DR1TVB1, DR1TVB2,
DR1TNIAC, DR1TVB6, DR1TFOLA, DR1TFA,
DR1TFF, DR1TFDFE, DR1TCHL, DR1TVB12,
DR1TB12A, DR1TVC, DR1TVD, DR1TVK,
DR1TCALC, DR1TPHOS, DR1TMAGN, DR1TIRON,
DR1TZINC, DR1TCOPP, DR1TSODI, DR1TPOTA,
DR1TSELE, DR1TCAFF, DR1TTHEO, DR1TALCO,
DR1TMOIS, DR1TS040, DR1TS060, DR1TS080,
DR1TS100, DR1TS120, DR1TS140, DR1TS160,
DR1TS180, DR1TM161, DR1TM181, DR1TM201,
DR1TM221, DR1TP182, DR1TP183, DR1TP184,
DR1TP204, DR1TP205, DR1TP225, DR1TP226, hyper, db, dyslip, dp10))4. Rename variables
# Rename all variables in one code
df4 <- df3 %>% rename(age = RIDAGEYR, sex = RIAGENDR, ethnic = RIDRETH3,
educ = DMDEDUC2, masts = DMDMARTL, BMI = BMXBMI,
finc = INDFMIN2, PIR = INDFMPIR,
BUN = LBXSBU, crea = LBXSCR, AST = LBXSASSI, ALT = LBXSATSI,
apoB = LBXAPB, HDL = LBDHDD, LDL = LBDLDL,
TG = LBXTR, TC = LBXTC, Glu = LBXGLU, tolGlu = LBXGLT,
sCOT = LBXCOT, sHCOT = LBXHCT, uCOT = URXCOTT, uHCOT = URXHCTT)# Filter out values ‘7, 77’ and ‘9, 99’ from categorical variables column
## Those values are unknown and confused values
df5 <- df4 %>%
filter(educ %in% c('1', '2', '3', '4', '5'),
masts %in% c('1', '2', '3', '4', '5', '6'),
ALQ101 %in% c('1', '2'),
SMQ020 %in% c('1', '2')
)# Change to factor
df_new = df5
df_new$dp10 = as.factor(df_new$dp10)
df_new$sex = as.factor(df_new$sex)
df_new$ethnic = as.factor(df_new$ethnic)
df_new$educ = as.factor(df_new$educ)
df_new$masts = as.factor(df_new$masts)
df_new$DBD100 = as.factor(df_new$DBD100)
df_new$ALQ101 = as.factor(df_new$ALQ101)
df_new$SMQ020 = as.factor(df_new$SMQ020)
df_new$PAQ650 = as.factor(df_new$PAQ650)
df_new$PAQ665 = as.factor(df_new$PAQ665)
df_new$hyper = as.factor(df_new$hyper)
df_new$db = as.factor(df_new$db)
df_new$dyslip = as.factor(df_new$dyslip)5. Descriptive analysis
5.1 Table 1
library(table1)##
## Attaching package: 'table1'## The following objects are masked from 'package:base':
##
## units, units<-table1(~ .| dp10, data = df_new)| 0 (N=4553) |
1 (N=487) |
Overall (N=5040) |
|
|---|---|---|---|
| Age in years at screening | |||
| Mean (SD) | 48.9 (17.6) | 51.6 (16.4) | 49.2 (17.5) |
| Median [Min, Max] | 48.0 [20.0, 80.0] | 54.0 [20.0, 80.0] | 49.0 [20.0, 80.0] |
| sex | |||
| 1 | 2275 (50.0%) | 158 (32.4%) | 2433 (48.3%) |
| 2 | 2278 (50.0%) | 329 (67.6%) | 2607 (51.7%) |
| ethnic | |||
| 1 | 607 (13.3%) | 67 (13.8%) | 674 (13.4%) |
| 2 | 392 (8.6%) | 57 (11.7%) | 449 (8.9%) |
| 3 | 2006 (44.1%) | 216 (44.4%) | 2222 (44.1%) |
| 4 | 905 (19.9%) | 105 (21.6%) | 1010 (20.0%) |
| 6 | 509 (11.2%) | 17 (3.5%) | 526 (10.4%) |
| 7 | 134 (2.9%) | 25 (5.1%) | 159 (3.2%) |
| educ | |||
| 1 | 292 (6.4%) | 64 (13.1%) | 356 (7.1%) |
| 2 | 575 (12.6%) | 103 (21.1%) | 678 (13.5%) |
| 3 | 1009 (22.2%) | 117 (24.0%) | 1126 (22.3%) |
| 4 | 1442 (31.7%) | 148 (30.4%) | 1590 (31.5%) |
| 5 | 1235 (27.1%) | 55 (11.3%) | 1290 (25.6%) |
| masts | |||
| 1 | 2443 (53.7%) | 187 (38.4%) | 2630 (52.2%) |
| 2 | 309 (6.8%) | 57 (11.7%) | 366 (7.3%) |
| 3 | 484 (10.6%) | 98 (20.1%) | 582 (11.5%) |
| 4 | 123 (2.7%) | 27 (5.5%) | 150 (3.0%) |
| 5 | 872 (19.2%) | 82 (16.8%) | 954 (18.9%) |
| 6 | 322 (7.1%) | 36 (7.4%) | 358 (7.1%) |
| Systolic: Blood pres (1st rdg) mm Hg | |||
| Mean (SD) | 123 (17.2) | 125 (19.1) | 123 (17.4) |
| Median [Min, Max] | 120 [70.0, 229] | 122 [66.0, 216] | 120 [66.0, 229] |
| Missing | 412 (9.0%) | 55 (11.3%) | 467 (9.3%) |
| Diastolic: Blood pres (1st rdg) mm Hg | |||
| Mean (SD) | 69.4 (12.5) | 69.7 (12.4) | 69.4 (12.5) |
| Median [Min, Max] | 70.0 [0, 119] | 71.0 [0, 104] | 70.0 [0, 119] |
| Missing | 412 (9.0%) | 55 (11.3%) | 467 (9.3%) |
| Body Mass Index (kg/m**2) | |||
| Mean (SD) | 28.9 (6.87) | 31.9 (9.32) | 29.2 (7.19) |
| Median [Min, Max] | 27.7 [14.1, 70.1] | 30.8 [15.2, 82.9] | 27.9 [14.1, 82.9] |
| Missing | 41 (0.9%) | 5 (1.0%) | 46 (0.9%) |
| Annual family income | |||
| Mean (SD) | 10.8 (13.4) | 8.97 (15.0) | 10.6 (13.6) |
| Median [Min, Max] | 8.00 [1.00, 99.0] | 6.00 [1.00, 99.0] | 8.00 [1.00, 99.0] |
| Missing | 41 (0.9%) | 8 (1.6%) | 49 (1.0%) |
| Ratio of family income to poverty | |||
| Mean (SD) | 2.62 (1.66) | 1.74 (1.33) | 2.53 (1.65) |
| Median [Min, Max] | 2.26 [0, 5.00] | 1.27 [0, 5.00] | 2.15 [0, 5.00] |
| Missing | 322 (7.1%) | 42 (8.6%) | 364 (7.2%) |
| Blood urea nitrogen (mg/dL) | |||
| Mean (SD) | 13.4 (5.73) | 13.6 (9.17) | 13.4 (6.15) |
| Median [Min, Max] | 12.0 [1.00, 73.0] | 12.0 [2.00, 95.0] | 12.0 [1.00, 95.0] |
| Missing | 170 (3.7%) | 20 (4.1%) | 190 (3.8%) |
| Creatinine (mg/dL) | |||
| Mean (SD) | 0.912 (0.441) | 0.995 (1.09) | 0.920 (0.539) |
| Median [Min, Max] | 0.860 [0.300, 16.6] | 0.820 [0.360, 17.4] | 0.860 [0.300, 17.4] |
| Missing | 170 (3.7%) | 20 (4.1%) | 190 (3.8%) |
| Aspartate aminotransferase AST (U/L) | |||
| Mean (SD) | 25.3 (18.6) | 26.6 (21.7) | 25.4 (18.9) |
| Median [Min, Max] | 22.0 [9.00, 882] | 22.0 [11.0, 294] | 22.0 [9.00, 882] |
| Missing | 172 (3.8%) | 20 (4.1%) | 192 (3.8%) |
| Alanine aminotransferase ALT (U/L) | |||
| Mean (SD) | 25.0 (18.9) | 25.7 (21.5) | 25.1 (19.1) |
| Median [Min, Max] | 20.0 [6.00, 536] | 20.0 [7.00, 300] | 20.0 [6.00, 536] |
| Missing | 172 (3.8%) | 20 (4.1%) | 192 (3.8%) |
| Apolipoprotein (B) (mg/dL) | |||
| Mean (SD) | 89.8 (24.6) | 95.3 (26.5) | 90.3 (24.8) |
| Median [Min, Max] | 88.0 [24.0, 228] | 94.0 [20.0, 234] | 89.0 [20.0, 234] |
| Missing | 2447 (53.7%) | 273 (56.1%) | 2720 (54.0%) |
| Direct HDL-Cholesterol (mg/dL) | |||
| Mean (SD) | 52.9 (16.2) | 51.2 (15.5) | 52.8 (16.1) |
| Median [Min, Max] | 50.0 [10.0, 173] | 48.0 [22.0, 117] | 50.0 [10.0, 173] |
| Missing | 159 (3.5%) | 17 (3.5%) | 176 (3.5%) |
| LDL-cholesterol (mg/dL) | |||
| Mean (SD) | 111 (34.6) | 113 (37.1) | 111 (34.9) |
| Median [Min, Max] | 108 [14.0, 375] | 112 [24.0, 288] | 108 [14.0, 375] |
| Missing | 2480 (54.5%) | 276 (56.7%) | 2756 (54.7%) |
| Triglyceride (mg/dL) | |||
| Mean (SD) | 120 (130) | 142 (98.7) | 122 (128) |
| Median [Min, Max] | 94.0 [14.0, 4230] | 121 [21.0, 1000] | 96.0 [14.0, 4230] |
| Missing | 2446 (53.7%) | 273 (56.1%) | 2719 (53.9%) |
| Total Cholesterol( mg/dL) | |||
| Mean (SD) | 189 (41.9) | 192 (41.3) | 189 (41.9) |
| Median [Min, Max] | 185 [82.0, 813] | 189 [85.0, 380] | 186 [82.0, 813] |
| Missing | 159 (3.5%) | 17 (3.5%) | 176 (3.5%) |
| Fasting Glucose (mg/dL) | |||
| Mean (SD) | 107 (32.6) | 117 (43.8) | 107 (33.9) |
| Median [Min, Max] | 99.0 [51.0, 405] | 102 [67.0, 375] | 99.0 [51.0, 405] |
| Missing | 2436 (53.5%) | 269 (55.2%) | 2705 (53.7%) |
| Two Hour Glucose(OGTT) (mg/dL) | |||
| Mean (SD) | 118 (50.1) | 129 (52.3) | 119 (50.3) |
| Median [Min, Max] | 107 [40.0, 604] | 121 [48.0, 352] | 108 [40.0, 604] |
| Missing | 2900 (63.7%) | 336 (69.0%) | 3236 (64.2%) |
| ALQ101 | |||
| 1 | 3293 (72.3%) | 350 (71.9%) | 3643 (72.3%) |
| 2 | 1260 (27.7%) | 137 (28.1%) | 1397 (27.7%) |
| SMQ020 | |||
| 1 | 1924 (42.3%) | 280 (57.5%) | 2204 (43.7%) |
| 2 | 2629 (57.7%) | 207 (42.5%) | 2836 (56.3%) |
| PAQ665 | |||
| 1 | 2009 (44.1%) | 123 (25.3%) | 2132 (42.3%) |
| 2 | 2544 (55.9%) | 364 (74.7%) | 2908 (57.7%) |
| PAQ650 | |||
| 1 | 1090 (23.9%) | 48 (9.9%) | 1138 (22.6%) |
| 2 | 3463 (76.1%) | 439 (90.1%) | 3902 (77.4%) |
| Cotinine, Serum (ng/mL) | |||
| Mean (SD) | 56.7 (131) | 104 (163) | 61.3 (135) |
| Median [Min, Max] | 0.0330 [0.0110, 1820] | 0.233 [0.0110, 1030] | 0.0360 [0.0110, 1820] |
| Missing | 157 (3.4%) | 18 (3.7%) | 175 (3.5%) |
| Hematocrit (%) | |||
| Mean (SD) | 22.6 (60.9) | 45.4 (78.0) | 24.8 (63.1) |
| Median [Min, Max] | 0.0110 [0.0110, 1150] | 0.0840 [0.0110, 540] | 0.0110 [0.0110, 1150] |
| Missing | 157 (3.4%) | 18 (3.7%) | 175 (3.5%) |
| Total Cotinine, urine (ng/mL) | |||
| Mean (SD) | 686 (1830) | 1570 (3240) | 759 (2000) |
| Median [Min, Max] | 0.411 [0.0210, 26800] | 13.8 [0.0210, 24200] | 0.451 [0.0210, 26800] |
| Missing | 3076 (67.6%) | 354 (72.7%) | 3430 (68.1%) |
| Total Hydroxycotinine, urine (ng/mL) | |||
| Mean (SD) | 1350 (4210) | 3140 (6200) | 1500 (4430) |
| Median [Min, Max] | 0.739 [0.0210, 70600] | 20.1 [0.0210, 40400] | 0.829 [0.0210, 70600] |
| Missing | 3076 (67.6%) | 354 (72.7%) | 3430 (68.1%) |
| DBD100 | |||
| 1 | 1442 (31.7%) | 128 (26.3%) | 1570 (31.2%) |
| 2 | 944 (20.7%) | 86 (17.7%) | 1030 (20.4%) |
| 3 | 637 (14.0%) | 96 (19.7%) | 733 (14.5%) |
| 9 | 5 (0.1%) | 0 (0%) | 5 (0.1%) |
| Missing | 1525 (33.5%) | 177 (36.3%) | 1702 (33.8%) |
| Energy (kcal) | |||
| Mean (SD) | 2130 (1030) | 2000 (1050) | 2120 (1030) |
| Median [Min, Max] | 1950 [193, 12100] | 1790 [117, 7420] | 1940 [117, 12100] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Protein (gm) | |||
| Mean (SD) | 84.0 (46.2) | 69.5 (42.8) | 82.6 (46.1) |
| Median [Min, Max] | 75.4 [0.850, 558] | 60.9 [0, 396] | 74.1 [0, 558] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Carbohydrate (gm) | |||
| Mean (SD) | 253 (129) | 253 (142) | 253 (130) |
| Median [Min, Max] | 230 [8.67, 1420] | 224 [11.5, 844] | 229 [8.67, 1420] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Total sugars (gm) | |||
| Mean (SD) | 109 (78.0) | 123 (98.2) | 111 (80.2) |
| Median [Min, Max] | 92.8 [0.130, 1120] | 97.8 [0.610, 836] | 93.1 [0.130, 1120] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Dietary fiber (gm) | |||
| Mean (SD) | 17.3 (10.9) | 14.6 (10.0) | 17.0 (10.9) |
| Median [Min, Max] | 14.9 [0, 136] | 12.3 [0, 66.2] | 14.6 [0, 136] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Total fat (gm) | |||
| Mean (SD) | 82.3 (48.5) | 74.1 (46.6) | 81.5 (48.4) |
| Median [Min, Max] | 73.5 [0.330, 548] | 66.5 [0, 344] | 72.8 [0, 548] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Total saturated fatty acids (gm) | |||
| Mean (SD) | 26.2 (16.7) | 24.4 (16.7) | 26.0 (16.7) |
| Median [Min, Max] | 23.0 [0.0910, 177] | 20.5 [0, 94.2] | 22.7 [0, 177] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Total monounsaturated fatty acids (gm) | |||
| Mean (SD) | 28.9 (18.1) | 25.2 (16.8) | 28.5 (18.0) |
| Median [Min, Max] | 25.4 [0.0430, 222] | 22.1 [0, 131] | 25.0 [0, 222] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Total polyunsaturated fatty acids (gm) | |||
| Mean (SD) | 19.4 (13.6) | 17.4 (12.7) | 19.2 (13.6) |
| Median [Min, Max] | 16.3 [0.0440, 182] | 14.7 [0, 123] | 16.2 [0, 182] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Cholesterol (mg) | |||
| Mean (SD) | 305 (251) | 248 (219) | 300 (249) |
| Median [Min, Max] | 233 [0, 2580] | 185 [0, 1590] | 229 [0, 2580] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Vitamin E as alpha-tocopherol (mg) | |||
| Mean (SD) | 9.19 (7.88) | 7.76 (6.44) | 9.05 (7.76) |
| Median [Min, Max] | 7.34 [0.0100, 158] | 6.01 [0, 55.8] | 7.19 [0, 158] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Added alpha-tocopherol (Vitamin E) (mg) | |||
| Mean (SD) | 0.819 (3.82) | 0.638 (2.73) | 0.802 (3.73) |
| Median [Min, Max] | 0 [0, 99.9] | 0 [0, 20.7] | 0 [0, 99.9] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Retinol (mcg) | |||
| Mean (SD) | 410 (414) | 353 (351) | 404 (409) |
| Median [Min, Max] | 308 [0, 7340] | 253 [0, 3070] | 305 [0, 7340] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Vitamin A, RAE (mcg) | |||
| Mean (SD) | 624 (618) | 486 (427) | 612 (604) |
| Median [Min, Max] | 474 [0, 8550] | 382 [0, 3090] | 465 [0, 8550] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Alpha-carotene (mcg) | |||
| Mean (SD) | 401 (1240) | 284 (758) | 390 (1200) |
| Median [Min, Max] | 45.0 [0, 35100] | 30.0 [0, 6840] | 43.0 [0, 35100] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Beta-carotene (mcg) | |||
| Mean (SD) | 2340 (4840) | 1430 (2500) | 2250 (4680) |
| Median [Min, Max] | 777 [0, 78800] | 495 [0, 19700] | 738 [0, 78800] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Beta-cryptoxanthin (mcg) | |||
| Mean (SD) | 95.6 (433) | 61.9 (127) | 92.4 (414) |
| Median [Min, Max] | 29.0 [0, 24300] | 20.0 [0, 1700] | 28.0 [0, 24300] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Lycopene (mcg) | |||
| Mean (SD) | 5030 (8770) | 4070 (7250) | 4940 (8640) |
| Median [Min, Max] | 1590 [0, 87900] | 1160 [0, 50800] | 1550 [0, 87900] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Lutein + zeaxanthin (mcg) | |||
| Mean (SD) | 1660 (3770) | 1080 (2090) | 1610 (3650) |
| Median [Min, Max] | 747 [0, 103000] | 542 [0, 19800] | 719 [0, 103000] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Thiamin (Vitamin B1) (mg) | |||
| Mean (SD) | 1.61 (0.920) | 1.38 (0.790) | 1.59 (0.911) |
| Median [Min, Max] | 1.43 [0.0220, 8.56] | 1.23 [0.0990, 4.26] | 1.41 [0.0220, 8.56] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Riboflavin (Vitamin B2) (mg) | |||
| Mean (SD) | 2.09 (1.31) | 1.87 (1.32) | 2.07 (1.31) |
| Median [Min, Max] | 1.84 [0.0240, 17.6] | 1.60 [0, 16.3] | 1.82 [0, 17.6] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Niacin (mg) | |||
| Mean (SD) | 26.4 (16.9) | 22.2 (16.1) | 26.0 (16.9) |
| Median [Min, Max] | 22.7 [0.215, 260] | 19.2 [1.90, 168] | 22.3 [0.215, 260] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Vitamin B6 (mg) | |||
| Mean (SD) | 2.17 (1.74) | 1.84 (2.16) | 2.14 (1.79) |
| Median [Min, Max] | 1.81 [0.0230, 48.3] | 1.47 [0.0160, 34.9] | 1.78 [0.0160, 48.3] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Total folate (mcg) | |||
| Mean (SD) | 402 (259) | 337 (209) | 396 (256) |
| Median [Min, Max] | 349 [0, 3170] | 301 [0, 1330] | 344 [0, 3170] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Folic acid (mcg) | |||
| Mean (SD) | 174 (182) | 152 (146) | 172 (179) |
| Median [Min, Max] | 128 [0, 2830] | 108 [0, 1300] | 126 [0, 2830] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Food folate (mcg) | |||
| Mean (SD) | 228 (157) | 186 (128) | 224 (155) |
| Median [Min, Max] | 192 [0, 2360] | 158 [0, 1010] | 189 [0, 2360] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Folate, DFE (mcg) | |||
| Mean (SD) | 524 (369) | 443 (297) | 516 (364) |
| Median [Min, Max] | 439 [0, 5150] | 383 [0, 2240] | 436 [0, 5150] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Total choline (mg) | |||
| Mean (SD) | 346 (215) | 282 (191) | 340 (213) |
| Median [Min, Max] | 299 [7.90, 2910] | 244 [0, 1590] | 293 [0, 2910] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Vitamin B12 (mcg) | |||
| Mean (SD) | 4.94 (5.12) | 4.16 (5.19) | 4.86 (5.13) |
| Median [Min, Max] | 3.64 [0, 78.8] | 3.02 [0, 68.0] | 3.59 [0, 78.8] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Added vitamin B12 (mcg) | |||
| Mean (SD) | 1.01 (2.84) | 0.871 (2.87) | 1.00 (2.85) |
| Median [Min, Max] | 0 [0, 44.9] | 0 [0, 37.4] | 0 [0, 44.9] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Vitamin C (mg) | |||
| Mean (SD) | 82.6 (93.8) | 64.9 (76.4) | 81.0 (92.5) |
| Median [Min, Max] | 53.4 [0, 2010] | 36.1 [0, 553] | 51.5 [0, 2010] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Vitamin D (D2 + D3) (mcg) | |||
| Mean (SD) | 4.71 (6.02) | 3.53 (3.69) | 4.60 (5.85) |
| Median [Min, Max] | 3.00 [0, 68.8] | 2.55 [0, 26.6] | 3.00 [0, 68.8] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Vitamin K (mcg) | |||
| Mean (SD) | 122 (180) | 89.7 (112) | 119 (175) |
| Median [Min, Max] | 73.1 [0, 4080] | 59.9 [0, 941] | 71.7 [0, 4080] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Calcium (mg) | |||
| Mean (SD) | 938 (602) | 838 (552) | 928 (599) |
| Median [Min, Max] | 817 [18.0, 7340] | 704 [6.00, 3460] | 808 [6.00, 7340] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Phosphorus (mg) | |||
| Mean (SD) | 1390 (728) | 1190 (671) | 1370 (725) |
| Median [Min, Max] | 1260 [56.0, 11500] | 1110 [0, 4570] | 1240 [0, 11500] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Magnesium (mg) | |||
| Mean (SD) | 304 (163) | 262 (143) | 300 (161) |
| Median [Min, Max] | 273 [20.0, 2730] | 231 [0, 929] | 269 [0, 2730] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Iron (mg) | |||
| Mean (SD) | 14.5 (8.59) | 12.8 (8.21) | 14.3 (8.57) |
| Median [Min, Max] | 12.5 [0.220, 99.7] | 10.4 [0.130, 49.1] | 12.4 [0.130, 99.7] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Zinc (mg) | |||
| Mean (SD) | 11.1 (6.93) | 9.42 (6.42) | 11.0 (6.90) |
| Median [Min, Max] | 9.68 [0.160, 73.9] | 7.82 [0.280, 75.2] | 9.53 [0.160, 75.2] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Copper (mg) | |||
| Mean (SD) | 1.24 (0.785) | 1.06 (0.649) | 1.22 (0.775) |
| Median [Min, Max] | 1.09 [0.0220, 14.2] | 0.892 [0.0280, 6.74] | 1.07 [0.0220, 14.2] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Sodium (mg) | |||
| Mean (SD) | 3540 (1850) | 3050 (1790) | 3490 (1850) |
| Median [Min, Max] | 3210 [45.0, 21400] | 2710 [29.0, 13200] | 3160 [29.0, 21400] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Potassium (mg) | |||
| Mean (SD) | 2650 (1300) | 2250 (1160) | 2610 (1290) |
| Median [Min, Max] | 2440 [110, 15900] | 2090 [200, 7990] | 2420 [110, 15900] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Selenium (mcg) | |||
| Mean (SD) | 119 (71.7) | 99.3 (64.3) | 117 (71.2) |
| Median [Min, Max] | 105 [0.700, 987] | 84.8 [0, 551] | 103 [0, 987] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Caffeine (mg) | |||
| Mean (SD) | 142 (177) | 176 (244) | 146 (185) |
| Median [Min, Max] | 95.0 [0, 2450] | 102 [0, 2020] | 96.0 [0, 2450] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Theobromine (mg) | |||
| Mean (SD) | 35.7 (79.0) | 45.5 (146) | 36.6 (87.5) |
| Median [Min, Max] | 0 [0, 1150] | 0 [0, 2040] | 0 [0, 2040] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Alcohol (gm) | |||
| Mean (SD) | 10.4 (29.0) | 9.22 (26.8) | 10.3 (28.8) |
| Median [Min, Max] | 0 [0, 591] | 0 [0, 225] | 0 [0, 591] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| Moisture (gm) | |||
| Mean (SD) | 2890 (1510) | 2860 (1580) | 2890 (1520) |
| Median [Min, Max] | 2590 [339, 17400] | 2560 [379, 13900] | 2590 [339, 17400] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| SFA 4:0 (Butanoic) (gm) | |||
| Mean (SD) | 0.472 (0.485) | 0.467 (0.508) | 0.472 (0.487) |
| Median [Min, Max] | 0.332 [0, 5.38] | 0.309 [0, 3.09] | 0.328 [0, 5.38] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| SFA 6:0 (Hexanoic) (gm) | |||
| Mean (SD) | 0.297 (0.306) | 0.289 (0.312) | 0.296 (0.307) |
| Median [Min, Max] | 0.213 [0, 3.01] | 0.177 [0, 1.65] | 0.210 [0, 3.01] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| SFA 8:0 (Octanoic) (gm) | |||
| Mean (SD) | 0.252 (0.275) | 0.244 (0.243) | 0.251 (0.272) |
| Median [Min, Max] | 0.182 [0, 4.31] | 0.159 [0, 1.12] | 0.180 [0, 4.31] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| SFA 10:0 (Decanoic) (gm) | |||
| Mean (SD) | 0.486 (0.453) | 0.468 (0.454) | 0.485 (0.453) |
| Median [Min, Max] | 0.367 [0, 3.90] | 0.308 [0, 2.55] | 0.363 [0, 3.90] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| SFA 12:0 (Dodecanoic) (gm) | |||
| Mean (SD) | 0.824 (1.33) | 0.803 (0.990) | 0.822 (1.30) |
| Median [Min, Max] | 0.487 [0, 26.4] | 0.444 [0, 6.15] | 0.484 [0, 26.4] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| SFA 14:0 (Tetradecanoic) (gm) | |||
| Mean (SD) | 2.14 (1.85) | 2.06 (1.91) | 2.13 (1.85) |
| Median [Min, Max] | 1.68 [0.00200, 18.8] | 1.52 [0, 11.7] | 1.66 [0, 18.8] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| SFA 16:0 (Hexadecanoic) (gm) | |||
| Mean (SD) | 14.3 (8.86) | 13.2 (8.78) | 14.2 (8.86) |
| Median [Min, Max] | 12.6 [0.0570, 91.7] | 11.0 [0, 49.3] | 12.5 [0, 91.7] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| SFA 18:0 (Octadecanoic) (gm) | |||
| Mean (SD) | 6.36 (4.13) | 5.94 (4.11) | 6.32 (4.13) |
| Median [Min, Max] | 5.56 [0.0160, 40.3] | 4.99 [0, 22.8] | 5.51 [0, 40.3] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| MFA 16:1 (Hexadecenoic) (gm) | |||
| Mean (SD) | 1.08 (0.827) | 0.925 (0.739) | 1.07 (0.821) |
| Median [Min, Max] | 0.915 [0, 13.9] | 0.756 [0, 6.62] | 0.896 [0, 13.9] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| MFA 18:1 (Octadecenoic) (gm) | |||
| Mean (SD) | 26.1 (16.8) | 22.8 (15.5) | 25.8 (16.7) |
| Median [Min, Max] | 22.9 [0.0330, 205] | 19.9 [0, 126] | 22.6 [0, 205] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| MFA 20:1 (Eicosenoic) (gm) | |||
| Mean (SD) | 0.331 (0.329) | 0.280 (0.266) | 0.327 (0.324) |
| Median [Min, Max] | 0.246 [0, 5.76] | 0.214 [0, 2.49] | 0.243 [0, 5.76] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| MFA 22:1 (Docosenoic) (gm) | |||
| Mean (SD) | 0.0315 (0.112) | 0.0210 (0.0414) | 0.0305 (0.108) |
| Median [Min, Max] | 0.00900 [0, 3.62] | 0.00800 [0, 0.347] | 0.00900 [0, 3.62] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| PFA 18:2 (Octadecadienoic) (gm) | |||
| Mean (SD) | 17.1 (12.2) | 15.3 (11.4) | 17.0 (12.1) |
| Median [Min, Max] | 14.4 [0.0390, 170] | 12.8 [0, 111] | 14.3 [0, 170] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| PFA 18:3 (Octadecatrienoic) (gm) | |||
| Mean (SD) | 1.81 (1.42) | 1.64 (1.40) | 1.80 (1.42) |
| Median [Min, Max] | 1.46 [0.00200, 16.6] | 1.27 [0, 12.1] | 1.45 [0, 16.6] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| PFA 18:4 (Octadecatetraenoic) (gm) | |||
| Mean (SD) | 0.0110 (0.0376) | 0.00706 (0.0225) | 0.0106 (0.0365) |
| Median [Min, Max] | 0.00100 [0, 0.635] | 0.00100 [0, 0.190] | 0.00100 [0, 0.635] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| PFA 20:4 (Eicosatetraenoic) (gm) | |||
| Mean (SD) | 0.166 (0.144) | 0.134 (0.122) | 0.163 (0.143) |
| Median [Min, Max] | 0.125 [0, 1.22] | 0.101 [0, 0.868] | 0.122 [0, 1.22] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| PFA 20:5 (Eicosapentaenoic) (gm) | |||
| Mean (SD) | 0.0358 (0.117) | 0.0199 (0.0690) | 0.0343 (0.114) |
| Median [Min, Max] | 0.00800 [0, 2.69] | 0.00600 [0, 1.22] | 0.00800 [0, 2.69] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| PFA 22:5 (Docosapentaenoic) (gm) | |||
| Mean (SD) | 0.0262 (0.0422) | 0.0188 (0.0219) | 0.0255 (0.0408) |
| Median [Min, Max] | 0.0160 [0, 1.07] | 0.0130 [0, 0.181] | 0.0160 [0, 1.07] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| PFA 22:6 (Docosahexaenoic) (gm) | |||
| Mean (SD) | 0.0756 (0.211) | 0.0450 (0.114) | 0.0727 (0.204) |
| Median [Min, Max] | 0.0130 [0, 4.34] | 0.00800 [0, 1.62] | 0.0130 [0, 4.34] |
| Missing | 233 (5.1%) | 39 (8.0%) | 272 (5.4%) |
| hyper | |||
| 0 | 2915 (64.0%) | 225 (46.2%) | 3140 (62.3%) |
| 1 | 1638 (36.0%) | 262 (53.8%) | 1900 (37.7%) |
| db | |||
| 0 | 3849 (84.5%) | 364 (74.7%) | 4213 (83.6%) |
| 1 | 704 (15.5%) | 123 (25.3%) | 827 (16.4%) |
| dyslip | |||
| 0 | 1354 (29.7%) | 118 (24.2%) | 1472 (29.2%) |
| 1 | 3199 (70.3%) | 369 (75.8%) | 3568 (70.8%) |
5.2 Exploratory data analysis
# About the DD variable
ggplot(data = df_new, mapping = aes(dp10, fill = dp10)) + geom_bar(width = 0.5) +
xlab("Depressive Disorder") +
scale_x_discrete(labels = c ("No", "Yes")) +
ylab("Count") +
theme(plot.title = element_text(hjust = 0.5)) +
theme(legend.position = "none") +
geom_text(stat='count', aes(label=..count..), vjust=-0.5) +
geom_text(stat='count', aes(label=paste0(round(after_stat(count/sum(count)*100),1),'%')), vjust=2, color = "black") ## Warning: The dot-dot notation (`..count..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(count)` instead.
5.3 CompareGroup
library(compareGroups)
med_iqr <- compareGroups(dp10 ~ . , data = df_new, method = c(age = 2, finc = 2, PIR = 2, crea = 2, AST = 2, ALT = 2, TG = 2, Glu = 2))## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredcreateTable(med_iqr)##
## --------Summary descriptives table by 'dp10'---------
##
## ___________________________________________________________________________________
## 0 1 p.overall
## N=4553 N=487
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
## Age in years at screening 48.0 [34.0;63.0] 54.0 [38.0;63.0] 0.001
## sex: <0.001
## 1 2275 (50.0%) 158 (32.4%)
## 2 2278 (50.0%) 329 (67.6%)
## ethnic: <0.001
## 1 607 (13.3%) 67 (13.8%)
## 2 392 (8.61%) 57 (11.7%)
## 3 2006 (44.1%) 216 (44.4%)
## 4 905 (19.9%) 105 (21.6%)
## 6 509 (11.2%) 17 (3.49%)
## 7 134 (2.94%) 25 (5.13%)
## educ: <0.001
## 1 292 (6.41%) 64 (13.1%)
## 2 575 (12.6%) 103 (21.1%)
## 3 1009 (22.2%) 117 (24.0%)
## 4 1442 (31.7%) 148 (30.4%)
## 5 1235 (27.1%) 55 (11.3%)
## masts: <0.001
## 1 2443 (53.7%) 187 (38.4%)
## 2 309 (6.79%) 57 (11.7%)
## 3 484 (10.6%) 98 (20.1%)
## 4 123 (2.70%) 27 (5.54%)
## 5 872 (19.2%) 82 (16.8%)
## 6 322 (7.07%) 36 (7.39%)
## Systolic: Blood pres (1st rdg) mm Hg 123 (17.2) 125 (19.1) 0.003
## Diastolic: Blood pres (1st rdg) mm Hg 69.4 (12.5) 69.7 (12.4) 0.656
## Body Mass Index (kg/m**2) 28.9 (6.87) 31.9 (9.32) <0.001
## Annual family income 8.00 [5.00;14.0] 6.00 [3.00;8.00] <0.001
## Ratio of family income to poverty 2.26 [1.13;4.28] 1.27 [0.78;2.35] <0.001
## Blood urea nitrogen (mg/dL) 13.4 (5.73) 13.6 (9.17) 0.597
## Creatinine (mg/dL) 0.86 [0.72;1.02] 0.82 [0.71;1.01] 0.052
## Aspartate aminotransferase AST (U/L) 22.0 [19.0;27.0] 22.0 [18.5;28.0] 0.467
## Alanine aminotransferase ALT (U/L) 20.0 [16.0;28.0] 20.0 [15.0;28.0] 0.369
## Apolipoprotein (B) (mg/dL) 89.8 (24.6) 95.3 (26.5) 0.004
## Direct HDL-Cholesterol (mg/dL) 52.9 (16.2) 51.2 (15.5) 0.019
## LDL-cholesterol (mg/dL) 111 (34.6) 113 (37.1) 0.359
## Triglyceride (mg/dL) 94.0 [64.0;139] 120 [80.0;183] <0.001
## Total Cholesterol( mg/dL) 189 (41.9) 192 (41.3) 0.090
## Fasting Glucose (mg/dL) 99.0 [92.0;108] 102 [95.0;117] <0.001
## Two Hour Glucose(OGTT) (mg/dL) 118 (50.1) 129 (52.3) 0.016
## ALQ101: 0.872
## 1 3293 (72.3%) 350 (71.9%)
## 2 1260 (27.7%) 137 (28.1%)
## SMQ020: <0.001
## 1 1924 (42.3%) 280 (57.5%)
## 2 2629 (57.7%) 207 (42.5%)
## PAQ665: <0.001
## 1 2009 (44.1%) 123 (25.3%)
## 2 2544 (55.9%) 364 (74.7%)
## PAQ650: <0.001
## 1 1090 (23.9%) 48 (9.86%)
## 2 3463 (76.1%) 439 (90.1%)
## Cotinine, Serum (ng/mL) 56.7 (131) 104 (163) <0.001
## Hematocrit (%) 22.6 (60.9) 45.4 (78.0) <0.001
## Total Cotinine, urine (ng/mL) 686 (1833) 1573 (3242) 0.002
## Total Hydroxycotinine, urine (ng/mL) 1348 (4209) 3143 (6196) 0.001
## DBD100: 0.002
## 1 1442 (47.6%) 128 (41.3%)
## 2 944 (31.2%) 86 (27.7%)
## 3 637 (21.0%) 96 (31.0%)
## 9 5 (0.17%) 0 (0.00%)
## Energy (kcal) 2135 (1032) 1998 (1046) 0.009
## Protein (gm) 84.0 (46.2) 69.5 (42.8) <0.001
## Carbohydrate (gm) 253 (129) 253 (142) 0.969
## Total sugars (gm) 109 (78.0) 123 (98.2) 0.006
## Dietary fiber (gm) 17.3 (10.9) 14.6 (10.0) <0.001
## Total fat (gm) 82.3 (48.5) 74.1 (46.6) <0.001
## Total saturated fatty acids (gm) 26.2 (16.7) 24.4 (16.7) 0.029
## Total monounsaturated fatty acids (gm) 28.9 (18.1) 25.2 (16.8) <0.001
## Total polyunsaturated fatty acids (gm) 19.4 (13.6) 17.4 (12.7) 0.001
## Cholesterol (mg) 305 (251) 248 (219) <0.001
## Vitamin E as alpha-tocopherol (mg) 9.19 (7.88) 7.76 (6.44) <0.001
## Added alpha-tocopherol (Vitamin E) (mg) 0.82 (3.82) 0.64 (2.73) 0.200
## Retinol (mcg) 410 (414) 353 (351) 0.002
## Vitamin A, RAE (mcg) 624 (618) 486 (427) <0.001
## Alpha-carotene (mcg) 401 (1235) 284 (758) 0.004
## Beta-carotene (mcg) 2339 (4841) 1433 (2495) <0.001
## Beta-cryptoxanthin (mcg) 95.6 (433) 61.9 (127) <0.001
## Lycopene (mcg) 5027 (8770) 4068 (7255) 0.009
## Lutein + zeaxanthin (mcg) 1664 (3770) 1082 (2089) <0.001
## Thiamin (Vitamin B1) (mg) 1.61 (0.92) 1.38 (0.79) <0.001
## Riboflavin (Vitamin B2) (mg) 2.09 (1.31) 1.87 (1.32) 0.001
## Niacin (mg) 26.4 (16.9) 22.2 (16.1) <0.001
## Vitamin B6 (mg) 2.17 (1.74) 1.84 (2.16) 0.002
## Total folate (mcg) 402 (259) 337 (209) <0.001
## Folic acid (mcg) 174 (182) 152 (146) 0.003
## Food folate (mcg) 228 (157) 186 (128) <0.001
## Folate, DFE (mcg) 524 (369) 443 (297) <0.001
## Total choline (mg) 346 (215) 282 (191) <0.001
## Vitamin B12 (mcg) 4.94 (5.12) 4.16 (5.19) 0.003
## Added vitamin B12 (mcg) 1.01 (2.84) 0.87 (2.87) 0.316
## Vitamin C (mg) 82.6 (93.8) 64.9 (76.4) <0.001
## Vitamin D (D2 + D3) (mcg) 4.71 (6.02) 3.53 (3.69) <0.001
## Vitamin K (mcg) 122 (180) 89.7 (112) <0.001
## Calcium (mg) 938 (602) 838 (552) <0.001
## Phosphorus (mg) 1385 (728) 1194 (671) <0.001
## Magnesium (mg) 304 (163) 262 (143) <0.001
## Iron (mg) 14.5 (8.59) 12.8 (8.21) <0.001
## Zinc (mg) 11.1 (6.93) 9.42 (6.42) <0.001
## Copper (mg) 1.24 (0.79) 1.06 (0.65) <0.001
## Sodium (mg) 3538 (1846) 3053 (1787) <0.001
## Potassium (mg) 2646 (1300) 2250 (1161) <0.001
## Selenium (mcg) 119 (71.7) 99.3 (64.3) <0.001
## Caffeine (mg) 142 (177) 176 (244) 0.005
## Theobromine (mg) 35.7 (79.0) 45.5 (146) 0.162
## Alcohol (gm) 10.4 (29.0) 9.22 (26.8) 0.383
## Moisture (gm) 2892 (1509) 2858 (1579) 0.659
## SFA 4:0 (Butanoic) (gm) 0.47 (0.49) 0.47 (0.51) 0.852
## SFA 6:0 (Hexanoic) (gm) 0.30 (0.31) 0.29 (0.31) 0.600
## SFA 8:0 (Octanoic) (gm) 0.25 (0.28) 0.24 (0.24) 0.509
## SFA 10:0 (Decanoic) (gm) 0.49 (0.45) 0.47 (0.45) 0.414
## SFA 12:0 (Dodecanoic) (gm) 0.82 (1.33) 0.80 (0.99) 0.693
## SFA 14:0 (Tetradecanoic) (gm) 2.14 (1.85) 2.06 (1.91) 0.370
## SFA 16:0 (Hexadecanoic) (gm) 14.3 (8.86) 13.2 (8.78) 0.008
## SFA 18:0 (Octadecanoic) (gm) 6.36 (4.13) 5.94 (4.11) 0.039
## MFA 16:1 (Hexadecenoic) (gm) 1.08 (0.83) 0.92 (0.74) <0.001
## MFA 18:1 (Octadecenoic) (gm) 26.1 (16.8) 22.8 (15.5) <0.001
## MFA 20:1 (Eicosenoic) (gm) 0.33 (0.33) 0.28 (0.27) <0.001
## MFA 22:1 (Docosenoic) (gm) 0.03 (0.11) 0.02 (0.04) <0.001
## PFA 18:2 (Octadecadienoic) (gm) 17.1 (12.2) 15.3 (11.4) 0.002
## PFA 18:3 (Octadecatrienoic) (gm) 1.81 (1.42) 1.64 (1.40) 0.012
## PFA 18:4 (Octadecatetraenoic) (gm) 0.01 (0.04) 0.01 (0.02) 0.001
## PFA 20:4 (Eicosatetraenoic) (gm) 0.17 (0.14) 0.13 (0.12) <0.001
## PFA 20:5 (Eicosapentaenoic) (gm) 0.04 (0.12) 0.02 (0.07) <0.001
## PFA 22:5 (Docosapentaenoic) (gm) 0.03 (0.04) 0.02 (0.02) <0.001
## PFA 22:6 (Docosahexaenoic) (gm) 0.08 (0.21) 0.05 (0.11) <0.001
## hyper: <0.001
## 0 2915 (64.0%) 225 (46.2%)
## 1 1638 (36.0%) 262 (53.8%)
## db: <0.001
## 0 3849 (84.5%) 364 (74.7%)
## 1 704 (15.5%) 123 (25.3%)
## dyslip: 0.013
## 0 1354 (29.7%) 118 (24.2%)
## 1 3199 (70.3%) 369 (75.8%)
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯# We can export this table by the following codes:
table_result <- createTable(med_iqr)
export2word(table_result, file = "tab1 with nutrition.docx")6. Logistic regression model
# Change the reference category to 'No = 2'
# Those variables are categorical variables with 1: Yes, 2: No
df_new$SMQ020 <- relevel(df_new$SMQ020, ref = 2)
df_new$ALQ101 <- relevel(df_new$ALQ101, ref = 2)
df_new$PAQ665 <- relevel(df_new$PAQ665, ref = 2)# Calculate OR(95% CI) for nutrition variables of having DD
library(epiDisplay)## Loading required package: foreign## Loading required package: survival## Loading required package: MASS##
## Attaching package: 'MASS'## The following object is masked from 'package:dplyr':
##
## select## Loading required package: nnet##
## Attaching package: 'epiDisplay'## The following object is masked from 'package:ggplot2':
##
## alphamodel1 = glm(dp10 ~ age + sex + educ + masts + PIR + SMQ020 + ALQ101 + PAQ665 + BMI + SBP + DBP + DR1TKCAL + DR1TPROT + DR1TCARB + DR1TSUGR + DR1TFIBE + DR1TTFAT + DR1TSFAT + DR1TMFAT + DR1TPFAT + DR1TCHOL, family = binomial, data = df_new)
logistic.display(model1)##
## Logistic regression predicting dp10 : 1 vs 0
##
## crude OR(95%CI) adj. OR(95%CI)
## age (cont. var.) 1.0093 (1.0032,1.0154) 1.0076 (0.9985,1.0167)
##
## sex: 2 vs 1 1.95 (1.56,2.44) 1.81 (1.4,2.35)
##
## educ: ref.=1
## 2 0.83 (0.55,1.24) 0.87 (0.56,1.34)
## 3 0.5 (0.34,0.74) 0.57 (0.37,0.87)
## 4 0.47 (0.32,0.68) 0.61 (0.4,0.93)
## 5 0.21 (0.13,0.32) 0.48 (0.29,0.79)
##
## masts: ref.=1
## 2 2.46 (1.67,3.61) 1.32 (0.85,2.06)
## 3 3.1 (2.32,4.15) 2.09 (1.52,2.87)
## 4 2.81 (1.69,4.67) 1.55 (0.9,2.67)
## 5 1.27 (0.93,1.72) 1.1 (0.78,1.55)
## 6 1.52 (1,2.31) 1.04 (0.66,1.65)
##
## PIR (cont. var.) 0.69 (0.64,0.75) 0.8 (0.73,0.88)
##
## SMQ020: 1 vs 2 1.84 (1.49,2.28) 1.45 (1.13,1.85)
##
## ALQ101: 1 vs 2 1.04 (0.81,1.32) 1.31 (0.99,1.74)
##
## PAQ665: 1 vs 2 0.44 (0.35,0.56) 0.57 (0.44,0.73)
##
## BMI (cont. var.) 1.05 (1.03,1.06) 1.04 (1.02,1.05)
##
## SBP (cont. var.) 1.0073 (1.0014,1.0133) 0.9996 (0.9922,1.0071)
##
## DBP (cont. var.) 1.0035 (0.9948,1.0123) 1.0042 (0.9943,1.0141)
##
## DR1TKCAL (cont. var.) 0.9999 (0.9998,1) 1.0002 (0.9997,1.0008)
##
## DR1TPROT (cont. var.) 0.9912 (0.9882,0.9942) 0.9927 (0.9869,0.9986)
##
## DR1TCARB (cont. var.) 1.0001 (0.9992,1.0009) 1.0003 (0.9964,1.0042)
##
## DR1TSUGR (cont. var.) 1.0017 (1.0006,1.0029) 1.0013 (0.9982,1.0045)
##
## DR1TFIBE (cont. var.) 0.974 (0.9627,0.9855) 0.9931 (0.9762,1.0104)
##
## DR1TTFAT (cont. var.) 0.9964 (0.9939,0.9989) 0.9986 (0.948,1.0519)
##
## DR1TSFAT (cont. var.) 0.99 (0.99,1) 1.01 (0.95,1.07)
##
## DR1TMFAT (cont. var.) 0.9883 (0.9814,0.9951) 0.9917 (0.9361,1.0505)
##
## DR1TPFAT (cont. var.) 0.9864 (0.9773,0.9956) 0.9982 (0.9441,1.0555)
##
## DR1TCHOL (cont. var.) 0.999 (0.9985,0.9995) 0.9996 (0.9989,1.0004)
##
## P(Wald's test) P(LR-test)
## age (cont. var.) 0.101 0.101
##
## sex: 2 vs 1 < 0.001 < 0.001
##
## educ: ref.=1 0.009
## 2 0.521
## 3 0.009
## 4 0.022
## 5 0.004
##
## masts: ref.=1 < 0.001
## 2 0.21
## 3 < 0.001
## 4 0.113
## 5 0.599
## 6 0.855
##
## PIR (cont. var.) < 0.001 < 0.001
##
## SMQ020: 1 vs 2 0.003 0.003
##
## ALQ101: 1 vs 2 0.059 0.057
##
## PAQ665: 1 vs 2 < 0.001 < 0.001
##
## BMI (cont. var.) < 0.001 < 0.001
##
## SBP (cont. var.) 0.919 0.919
##
## DBP (cont. var.) 0.409 0.405
##
## DR1TKCAL (cont. var.) 0.436 0.448
##
## DR1TPROT (cont. var.) 0.015 0.013
##
## DR1TCARB (cont. var.) 0.889 0.889
##
## DR1TSUGR (cont. var.) 0.4 0.4
##
## DR1TFIBE (cont. var.) 0.432 0.429
##
## DR1TTFAT (cont. var.) 0.957 0.957
##
## DR1TSFAT (cont. var.) 0.702 0.701
##
## DR1TMFAT (cont. var.) 0.776 0.777
##
## DR1TPFAT (cont. var.) 0.95 0.95
##
## DR1TCHOL (cont. var.) 0.325 0.319
##
## Log-likelihood = -1097.9949
## No. of observations = 4041
## AIC value = 2253.9897summary_model <- summary(model1)
# Extracting p-values
p_values <- summary_model$coefficients[, "Pr(>|z|)"]
# Sorting p-values and names in ascending order
sorted_p_values <- sort(p_values)
sorted_names <- names(p_values)[order(p_values)]
# Creating a bar plot in ascending order of -log(p-values)
barplot(-log(sorted_p_values), names.arg = sorted_names, horiz = TRUE, col = "blue", las = 1, main = "Important variables - based on p-value")
# Calculate OR(95% CI) for micro-nutrient variables of having DD
library(epiDisplay)
model2 = glm(dp10 ~ age + sex + educ + masts + PIR + SMQ020 + ALQ101 + PAQ665 + BMI + SBP + DBP + DR1TATOC + DR1TATOA + DR1TRET + DR1TVARA + DR1TACAR + DR1TBCAR + DR1TCRYP + DR1TLYCO + DR1TLZ + DR1TVB1 + DR1TVB2 + DR1TNIAC + DR1TVB6 + DR1TFOLA + DR1TFA + DR1TFF + DR1TFDFE + DR1TCHL + DR1TVB12 + DR1TB12A + DR1TVC + DR1TVD + DR1TVK, family = binomial, data = df_new)
logistic.display(model2)## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred##
## Logistic regression predicting dp10 : 1 vs 0
##
## crude OR(95%CI) adj. OR(95%CI)
## age (cont. var.) 1.0093 (1.0032,1.0154) 1.0065 (0.9975,1.0155)
##
## sex: 2 vs 1 1.95 (1.56,2.44) 1.7 (1.31,2.21)
##
## educ: ref.=1
## 2 0.83 (0.55,1.24) 0.93 (0.6,1.44)
## 3 0.5 (0.34,0.74) 0.62 (0.4,0.95)
## 4 0.47 (0.32,0.68) 0.63 (0.42,0.97)
## 5 0.21 (0.13,0.32) 0.49 (0.29,0.81)
##
## masts: ref.=1
## 2 2.46 (1.67,3.61) 1.3 (0.83,2.01)
## 3 3.1 (2.32,4.15) 2.25 (1.64,3.09)
## 4 2.81 (1.69,4.67) 1.65 (0.96,2.84)
## 5 1.27 (0.93,1.72) 1.16 (0.82,1.65)
## 6 1.52 (1,2.31) 1.12 (0.7,1.77)
##
## PIR (cont. var.) 0.69 (0.64,0.75) 0.79 (0.72,0.87)
##
## SMQ020: 1 vs 2 1.84 (1.49,2.28) 1.46 (1.14,1.87)
##
## ALQ101: 1 vs 2 1.04 (0.81,1.32) 1.27 (0.96,1.69)
##
## PAQ665: 1 vs 2 0.44 (0.35,0.56) 0.56 (0.43,0.72)
##
## BMI (cont. var.) 1.05 (1.03,1.06) 1.03 (1.02,1.05)
##
## SBP (cont. var.) 1.0073 (1.0014,1.0133) 1 (0.9926,1.0075)
##
## DBP (cont. var.) 1.0035 (0.9948,1.0123) 1.0049 (0.9951,1.0148)
##
## DR1TATOC (cont. var.) 0.97 (0.95,0.99) 1.02 (0.99,1.04)
##
## DR1TATOA (cont. var.) 0.9864 (0.953,1.021) 0.9955 (0.9515,1.0415)
##
## DR1TRET (cont. var.) 0.9995 (0.9992,0.9998) 0.9945 (0.939,1.0533)
##
## DR1TVARA (cont. var.) 0.9994 (0.9991,0.9996) 1.0054 (0.9492,1.0649)
##
## DR1TACAR (cont. var.) 0.9998 (0.9997,1) 0.9998 (0.9974,1.0022)
##
## DR1TBCAR (cont. var.) 0.9999 (0.9999,1) 0.9995 (0.9947,1.0043)
##
## DR1TCRYP (cont. var.) 0.9986 (0.9976,0.9996) 0.9993 (0.9968,1.0018)
##
## DR1TLYCO (cont. var.) 1 (1,1) 1 (1,1)
##
## DR1TLZ (cont. var.) 0.9999 (0.9998,1) 1 (0.9999,1.0001)
##
## DR1TVB1 (cont. var.) 0.71 (0.62,0.82) 0.88 (0.68,1.15)
##
## DR1TVB2 (cont. var.) 0.86 (0.78,0.95) 1.24 (1.06,1.45)
##
## DR1TNIAC (cont. var.) 0.98 (0.97,0.99) 0.98 (0.96,0.99)
##
## DR1TVB6 (cont. var.) 0.85 (0.78,0.93) 1.2 (1.04,1.38)
##
## DR1TFOLA (cont. var.) 1 (1,1) 1.02 (0.9,1.15)
##
## DR1TFA (cont. var.) 1 (1,1) 0.93 (0.81,1.06)
##
## DR1TFF (cont. var.) 1 (1,1) 0.95 (0.86,1.05)
##
## DR1TFDFE (cont. var.) 1 (1,1) 1.04 (0.94,1.15)
##
## DR1TCHL (cont. var.) 0.9983 (0.9976,0.9989) 0.9989 (0.9979,0.9999)
##
## DR1TVB12 (cont. var.) 0.96 (0.94,0.99) 1.03 (0.99,1.06)
##
## DR1TB12A (cont. var.) 0.99 (0.94,1.03) 0.93 (0.85,1.02)
##
## DR1TVC (cont. var.) 0.9969 (0.9954,0.9985) 0.9994 (0.9977,1.0011)
##
## DR1TVD (cont. var.) 0.95 (0.93,0.98) 0.97 (0.93,1)
##
## DR1TVK (cont. var.) 0.998 (0.9969,0.9991) 0.9996 (0.9975,1.0017)
##
## P(Wald's test) P(LR-test)
## age (cont. var.) 0.157 0.157
##
## sex: 2 vs 1 < 0.001 < 0.001
##
## educ: ref.=1 0.01
## 2 0.756
## 3 0.028
## 4 0.034
## 5 0.005
##
## masts: ref.=1 < 0.001
## 2 0.25
## 3 < 0.001
## 4 0.071
## 5 0.392
## 6 0.636
##
## PIR (cont. var.) < 0.001 < 0.001
##
## SMQ020: 1 vs 2 0.002 0.002
##
## ALQ101: 1 vs 2 0.092 0.089
##
## PAQ665: 1 vs 2 < 0.001 < 0.001
##
## BMI (cont. var.) < 0.001 < 0.001
##
## SBP (cont. var.) 0.999 0.999
##
## DBP (cont. var.) 0.33 0.325
##
## DR1TATOC (cont. var.) 0.128 0.154
##
## DR1TATOA (cont. var.) 0.844 0.843
##
## DR1TRET (cont. var.) 0.85 0.85
##
## DR1TVARA (cont. var.) 0.855 0.855
##
## DR1TACAR (cont. var.) 0.88 0.88
##
## DR1TBCAR (cont. var.) 0.838 0.838
##
## DR1TCRYP (cont. var.) 0.568 0.567
##
## DR1TLYCO (cont. var.) 0.764 0.766
##
## DR1TLZ (cont. var.) 0.801 0.802
##
## DR1TVB1 (cont. var.) 0.353 0.348
##
## DR1TVB2 (cont. var.) 0.006 0.007
##
## DR1TNIAC (cont. var.) 0.008 0.007
##
## DR1TVB6 (cont. var.) 0.011 0.017
##
## DR1TFOLA (cont. var.) 0.798 0.797
##
## DR1TFA (cont. var.) 0.267 0.267
##
## DR1TFF (cont. var.) 0.305 0.303
##
## DR1TFDFE (cont. var.) 0.487 0.488
##
## DR1TCHL (cont. var.) 0.03 0.028
##
## DR1TVB12 (cont. var.) 0.182 0.217
##
## DR1TB12A (cont. var.) 0.149 0.146
##
## DR1TVC (cont. var.) 0.486 0.479
##
## DR1TVD (cont. var.) 0.053 0.041
##
## DR1TVK (cont. var.) 0.74 0.74
##
## Log-likelihood = -1094.176
## No. of observations = 4041
## AIC value = 2272.3519summary_model <- summary(model2)
# Extracting p-values
p_values <- summary_model$coefficients[, "Pr(>|z|)"]
# Sorting p-values and names in ascending order
sorted_p_values <- sort(p_values)
sorted_names <- names(p_values)[order(p_values)]
# Creating a bar plot in ascending order of -log(p-values)
barplot(-log(sorted_p_values), names.arg = sorted_names, horiz = TRUE, col = "blue", las = 1, main = "Important variables - based on p-value")
# Calculate OR(95% CI) for mineral variables of having DD
library(epiDisplay)
model3 = glm(dp10 ~ age + sex + educ + masts + PIR + SMQ020 + ALQ101 + PAQ665 + BMI + SBP + DBP + DR1TCALC + DR1TPHOS + DR1TMAGN + DR1TIRON + DR1TZINC + DR1TCOPP + DR1TSODI + DR1TPOTA + DR1TSELE + DR1TCAFF + DR1TTHEO, family = binomial, data = df_new)
logistic.display(model3)##
## Logistic regression predicting dp10 : 1 vs 0
##
## crude OR(95%CI) adj. OR(95%CI)
## age (cont. var.) 1.0093 (1.0032,1.0154) 1.0055 (0.9965,1.0146)
##
## sex: 2 vs 1 1.95 (1.56,2.44) 1.71 (1.32,2.21)
##
## educ: ref.=1
## 2 0.83 (0.55,1.24) 0.91 (0.59,1.4)
## 3 0.5 (0.34,0.74) 0.6 (0.39,0.92)
## 4 0.47 (0.32,0.68) 0.63 (0.41,0.95)
## 5 0.21 (0.13,0.32) 0.46 (0.28,0.77)
##
## masts: ref.=1
## 2 2.46 (1.67,3.61) 1.35 (0.87,2.1)
## 3 3.1 (2.32,4.15) 2.15 (1.57,2.94)
## 4 2.81 (1.69,4.67) 1.58 (0.92,2.72)
## 5 1.27 (0.93,1.72) 1.17 (0.83,1.66)
## 6 1.52 (1,2.31) 1.12 (0.71,1.76)
##
## PIR (cont. var.) 0.69 (0.64,0.75) 0.8 (0.73,0.87)
##
## SMQ020: 1 vs 2 1.84 (1.49,2.28) 1.43 (1.12,1.84)
##
## ALQ101: 1 vs 2 1.04 (0.81,1.32) 1.28 (0.96,1.7)
##
## PAQ665: 1 vs 2 0.44 (0.35,0.56) 0.56 (0.43,0.72)
##
## BMI (cont. var.) 1.05 (1.03,1.06) 1.04 (1.02,1.05)
##
## SBP (cont. var.) 1.0073 (1.0014,1.0133) 1.0002 (0.9927,1.0077)
##
## DBP (cont. var.) 1.0035 (0.9948,1.0123) 1.0045 (0.9947,1.0145)
##
## DR1TCALC (cont. var.) 0.9997 (0.9995,0.9999) 1.0001 (0.9998,1.0004)
##
## DR1TPHOS (cont. var.) 0.9995 (0.9994,0.9997) 0.9999 (0.9994,1.0005)
##
## DR1TMAGN (cont. var.) 0.9981 (0.9972,0.9989) 1.001 (0.9991,1.0029)
##
## DR1TIRON (cont. var.) 0.9775 (0.9635,0.9917) 1.0037 (0.9827,1.0251)
##
## DR1TZINC (cont. var.) 0.9555 (0.9368,0.9746) 0.9967 (0.9649,1.0295)
##
## DR1TCOPP (cont. var.) 0.63 (0.52,0.77) 1.02 (0.72,1.45)
##
## DR1TSODI (cont. var.) 0.9998 (0.9998,0.9999) 1 (0.9999,1.0001)
##
## DR1TPOTA (cont. var.) 0.9997 (0.9996,0.9998) 0.9998 (0.9996,1)
##
## DR1TSELE (cont. var.) 0.9948 (0.9929,0.9968) 0.9975 (0.994,1.001)
##
## DR1TCAFF (cont. var.) 1.0008 (1.0003,1.0013) 1.0007 (1.0002,1.0013)
##
## DR1TTHEO (cont. var.) 1.0013 (1.0004,1.0022) 1.0015 (1.0004,1.0026)
##
## P(Wald's test) P(LR-test)
## age (cont. var.) 0.234 0.234
##
## sex: 2 vs 1 < 0.001 < 0.001
##
## educ: ref.=1 0.007
## 2 0.665
## 3 0.018
## 4 0.029
## 5 0.003
##
## masts: ref.=1 < 0.001
## 2 0.184
## 3 < 0.001
## 4 0.095
## 5 0.365
## 6 0.637
##
## PIR (cont. var.) < 0.001 < 0.001
##
## SMQ020: 1 vs 2 0.005 0.005
##
## ALQ101: 1 vs 2 0.087 0.085
##
## PAQ665: 1 vs 2 < 0.001 < 0.001
##
## BMI (cont. var.) < 0.001 < 0.001
##
## SBP (cont. var.) 0.957 0.957
##
## DBP (cont. var.) 0.369 0.364
##
## DR1TCALC (cont. var.) 0.522 0.523
##
## DR1TPHOS (cont. var.) 0.804 0.803
##
## DR1TMAGN (cont. var.) 0.289 0.293
##
## DR1TIRON (cont. var.) 0.732 0.733
##
## DR1TZINC (cont. var.) 0.842 0.841
##
## DR1TCOPP (cont. var.) 0.92 0.92
##
## DR1TSODI (cont. var.) 0.772 0.772
##
## DR1TPOTA (cont. var.) 0.018 0.015
##
## DR1TSELE (cont. var.) 0.163 0.15
##
## DR1TCAFF (cont. var.) 0.008 0.01
##
## DR1TTHEO (cont. var.) 0.006 0.006
##
## Log-likelihood = -1099.482
## No. of observations = 4041
## AIC value = 2258.964summary_model <- summary(model3)
# Extracting p-values
p_values <- summary_model$coefficients[, "Pr(>|z|)"]
# Sorting p-values and names in ascending order
sorted_p_values <- sort(p_values)
sorted_names <- names(p_values)[order(p_values)]
# Creating a bar plot in ascending order of -log(p-values)
barplot(-log(sorted_p_values), names.arg = sorted_names, horiz = TRUE, col = "blue", las = 2, main = "Important variables - based on p-value")
Correlation coefficients
dat <- subset(df_new, select = c (
DR1TKCAL, DR1TPROT,
DR1TCARB, DR1TSUGR, DR1TFIBE,
DR1TTFAT, DR1TSFAT, DR1TMFAT,
DR1TPFAT, DR1TCHOL, DR1TATOC,
DR1TATOA, DR1TRET, DR1TVARA,
DR1TACAR, DR1TBCAR, DR1TCRYP,
DR1TLYCO, DR1TLZ, DR1TVB1, DR1TVB2,
DR1TNIAC, DR1TVB6, DR1TFOLA, DR1TFA,
DR1TFF, DR1TFDFE, DR1TCHL, DR1TVB12,
DR1TB12A, DR1TVC, DR1TVD, DR1TVK,
DR1TCALC, DR1TPHOS, DR1TMAGN, DR1TIRON,
DR1TZINC, DR1TCOPP, DR1TSODI, DR1TPOTA,
DR1TSELE, DR1TCAFF, DR1TTHEO, DR1TALCO,
DR1TMOIS, DR1TS040, DR1TS060, DR1TS080,
DR1TS100, DR1TS120, DR1TS140, DR1TS160,
DR1TS180, DR1TM161, DR1TM181, DR1TM201,
DR1TM221, DR1TP182, DR1TP183, DR1TP184,
DR1TP204, DR1TP205, DR1TP225, DR1TP226))# Correlation matrix
library(lattice)##
## Attaching package: 'lattice'## The following object is masked from 'package:epiDisplay':
##
## dotplot# rounding to 2 decimal places
corr_mat <- round(cor(dat),2)
head(corr_mat)## DR1TKCAL DR1TPROT DR1TCARB DR1TSUGR DR1TFIBE DR1TTFAT DR1TSFAT
## DR1TKCAL 1 NA NA NA NA NA NA
## DR1TPROT NA 1 NA NA NA NA NA
## DR1TCARB NA NA 1 NA NA NA NA
## DR1TSUGR NA NA NA 1 NA NA NA
## DR1TFIBE NA NA NA NA 1 NA NA
## DR1TTFAT NA NA NA NA NA 1 NA
## DR1TMFAT DR1TPFAT DR1TCHOL DR1TATOC DR1TATOA DR1TRET DR1TVARA DR1TACAR
## DR1TKCAL NA NA NA NA NA NA NA NA
## DR1TPROT NA NA NA NA NA NA NA NA
## DR1TCARB NA NA NA NA NA NA NA NA
## DR1TSUGR NA NA NA NA NA NA NA NA
## DR1TFIBE NA NA NA NA NA NA NA NA
## DR1TTFAT NA NA NA NA NA NA NA NA
## DR1TBCAR DR1TCRYP DR1TLYCO DR1TLZ DR1TVB1 DR1TVB2 DR1TNIAC DR1TVB6
## DR1TKCAL NA NA NA NA NA NA NA NA
## DR1TPROT NA NA NA NA NA NA NA NA
## DR1TCARB NA NA NA NA NA NA NA NA
## DR1TSUGR NA NA NA NA NA NA NA NA
## DR1TFIBE NA NA NA NA NA NA NA NA
## DR1TTFAT NA NA NA NA NA NA NA NA
## DR1TFOLA DR1TFA DR1TFF DR1TFDFE DR1TCHL DR1TVB12 DR1TB12A DR1TVC
## DR1TKCAL NA NA NA NA NA NA NA NA
## DR1TPROT NA NA NA NA NA NA NA NA
## DR1TCARB NA NA NA NA NA NA NA NA
## DR1TSUGR NA NA NA NA NA NA NA NA
## DR1TFIBE NA NA NA NA NA NA NA NA
## DR1TTFAT NA NA NA NA NA NA NA NA
## DR1TVD DR1TVK DR1TCALC DR1TPHOS DR1TMAGN DR1TIRON DR1TZINC DR1TCOPP
## DR1TKCAL NA NA NA NA NA NA NA NA
## DR1TPROT NA NA NA NA NA NA NA NA
## DR1TCARB NA NA NA NA NA NA NA NA
## DR1TSUGR NA NA NA NA NA NA NA NA
## DR1TFIBE NA NA NA NA NA NA NA NA
## DR1TTFAT NA NA NA NA NA NA NA NA
## DR1TSODI DR1TPOTA DR1TSELE DR1TCAFF DR1TTHEO DR1TALCO DR1TMOIS
## DR1TKCAL NA NA NA NA NA NA NA
## DR1TPROT NA NA NA NA NA NA NA
## DR1TCARB NA NA NA NA NA NA NA
## DR1TSUGR NA NA NA NA NA NA NA
## DR1TFIBE NA NA NA NA NA NA NA
## DR1TTFAT NA NA NA NA NA NA NA
## DR1TS040 DR1TS060 DR1TS080 DR1TS100 DR1TS120 DR1TS140 DR1TS160
## DR1TKCAL NA NA NA NA NA NA NA
## DR1TPROT NA NA NA NA NA NA NA
## DR1TCARB NA NA NA NA NA NA NA
## DR1TSUGR NA NA NA NA NA NA NA
## DR1TFIBE NA NA NA NA NA NA NA
## DR1TTFAT NA NA NA NA NA NA NA
## DR1TS180 DR1TM161 DR1TM181 DR1TM201 DR1TM221 DR1TP182 DR1TP183
## DR1TKCAL NA NA NA NA NA NA NA
## DR1TPROT NA NA NA NA NA NA NA
## DR1TCARB NA NA NA NA NA NA NA
## DR1TSUGR NA NA NA NA NA NA NA
## DR1TFIBE NA NA NA NA NA NA NA
## DR1TTFAT NA NA NA NA NA NA NA
## DR1TP184 DR1TP204 DR1TP205 DR1TP225 DR1TP226
## DR1TKCAL NA NA NA NA NA
## DR1TPROT NA NA NA NA NA
## DR1TCARB NA NA NA NA NA
## DR1TSUGR NA NA NA NA NA
## DR1TFIBE NA NA NA NA NA
## DR1TTFAT NA NA NA NA NA# Remove rows with missing values before calculating correlations
dat_complete <- na.omit(dat)
corr_mat <- round(cor(dat_complete), 2)
head(corr_mat)## DR1TKCAL DR1TPROT DR1TCARB DR1TSUGR DR1TFIBE DR1TTFAT DR1TSFAT
## DR1TKCAL 1.00 0.76 0.88 0.66 0.55 0.88 0.82
## DR1TPROT 0.76 1.00 0.53 0.31 0.47 0.70 0.63
## DR1TCARB 0.88 0.53 1.00 0.84 0.56 0.66 0.62
## DR1TSUGR 0.66 0.31 0.84 1.00 0.26 0.47 0.47
## DR1TFIBE 0.55 0.47 0.56 0.26 1.00 0.47 0.37
## DR1TTFAT 0.88 0.70 0.66 0.47 0.47 1.00 0.91
## DR1TMFAT DR1TPFAT DR1TCHOL DR1TATOC DR1TATOA DR1TRET DR1TVARA DR1TACAR
## DR1TKCAL 0.83 0.75 0.53 0.57 0.04 0.39 0.31 0.03
## DR1TPROT 0.67 0.57 0.67 0.50 0.07 0.35 0.33 0.05
## DR1TCARB 0.60 0.55 0.30 0.43 0.04 0.35 0.28 0.05
## DR1TSUGR 0.42 0.37 0.22 0.29 0.04 0.28 0.22 0.03
## DR1TFIBE 0.46 0.45 0.15 0.52 0.08 0.23 0.35 0.18
## DR1TTFAT 0.96 0.86 0.57 0.61 0.02 0.38 0.29 0.01
## DR1TBCAR DR1TCRYP DR1TLYCO DR1TLZ DR1TVB1 DR1TVB2 DR1TNIAC DR1TVB6
## DR1TKCAL 0.07 0.04 0.26 0.06 0.69 0.61 0.66 0.49
## DR1TPROT 0.13 0.03 0.19 0.10 0.63 0.61 0.74 0.55
## DR1TCARB 0.06 0.07 0.26 0.05 0.65 0.53 0.53 0.42
## DR1TSUGR 0.04 0.06 0.14 0.02 0.35 0.39 0.32 0.29
## DR1TFIBE 0.28 0.16 0.28 0.25 0.56 0.41 0.38 0.38
## DR1TTFAT 0.05 0.01 0.21 0.06 0.57 0.53 0.54 0.36
## DR1TFOLA DR1TFA DR1TFF DR1TFDFE DR1TCHL DR1TVB12 DR1TB12A DR1TVC
## DR1TKCAL 0.60 0.38 0.55 0.55 0.67 0.43 0.15 0.25
## DR1TPROT 0.51 0.27 0.53 0.46 0.81 0.51 0.10 0.23
## DR1TCARB 0.58 0.44 0.45 0.56 0.43 0.33 0.21 0.30
## DR1TSUGR 0.29 0.23 0.21 0.28 0.27 0.27 0.19 0.29
## DR1TFIBE 0.64 0.29 0.73 0.55 0.36 0.19 0.12 0.38
## DR1TTFAT 0.46 0.27 0.45 0.41 0.61 0.37 0.08 0.16
## DR1TVD DR1TVK DR1TCALC DR1TPHOS DR1TMAGN DR1TIRON DR1TZINC DR1TCOPP
## DR1TKCAL 0.27 0.17 0.61 0.83 0.71 0.65 0.66 0.58
## DR1TPROT 0.37 0.19 0.56 0.89 0.70 0.58 0.75 0.57
## DR1TCARB 0.21 0.12 0.53 0.64 0.59 0.63 0.52 0.50
## DR1TSUGR 0.20 0.06 0.38 0.41 0.34 0.38 0.34 0.29
## DR1TFIBE 0.13 0.32 0.45 0.59 0.75 0.58 0.50 0.66
## DR1TTFAT 0.24 0.18 0.58 0.76 0.61 0.55 0.60 0.53
## DR1TSODI DR1TPOTA DR1TSELE DR1TCAFF DR1TTHEO DR1TALCO DR1TMOIS
## DR1TKCAL 0.78 0.73 0.69 0.15 0.24 0.31 0.41
## DR1TPROT 0.79 0.75 0.85 0.07 0.09 0.14 0.35
## DR1TCARB 0.63 0.63 0.50 0.15 0.26 0.10 0.34
## DR1TSUGR 0.36 0.43 0.26 0.18 0.32 -0.01 0.24
## DR1TFIBE 0.47 0.70 0.39 -0.01 0.10 0.00 0.28
## DR1TTFAT 0.73 0.63 0.63 0.13 0.25 0.09 0.29
## DR1TS040 DR1TS060 DR1TS080 DR1TS100 DR1TS120 DR1TS140 DR1TS160
## DR1TKCAL 0.50 0.49 0.46 0.54 0.30 0.61 0.84
## DR1TPROT 0.36 0.36 0.32 0.40 0.18 0.47 0.66
## DR1TCARB 0.40 0.40 0.37 0.43 0.25 0.47 0.64
## DR1TSUGR 0.34 0.34 0.31 0.34 0.22 0.37 0.47
## DR1TFIBE 0.22 0.20 0.21 0.25 0.14 0.26 0.39
## DR1TTFAT 0.55 0.54 0.50 0.60 0.33 0.67 0.93
## DR1TS180 DR1TM161 DR1TM181 DR1TM201 DR1TM221 DR1TP182 DR1TP183
## DR1TKCAL 0.81 0.65 0.82 0.54 0.13 0.75 0.62
## DR1TPROT 0.62 0.65 0.65 0.49 0.13 0.56 0.47
## DR1TCARB 0.62 0.42 0.59 0.35 0.07 0.55 0.47
## DR1TSUGR 0.48 0.29 0.42 0.22 0.05 0.37 0.33
## DR1TFIBE 0.34 0.24 0.47 0.27 0.06 0.45 0.41
## DR1TTFAT 0.90 0.73 0.95 0.62 0.15 0.86 0.71
## DR1TP184 DR1TP204 DR1TP205 DR1TP225 DR1TP226
## DR1TKCAL 0.14 0.49 0.10 0.26 0.11
## DR1TPROT 0.17 0.65 0.23 0.44 0.27
## DR1TCARB 0.09 0.26 0.03 0.12 0.01
## DR1TSUGR 0.04 0.17 0.00 0.07 -0.01
## DR1TFIBE 0.05 0.13 0.02 0.06 0.03
## DR1TTFAT 0.14 0.54 0.08 0.26 0.10library(reshape2)##
## Attaching package: 'reshape2'## The following object is masked from 'package:tidyr':
##
## smiths# reduce the size of correlation matrix
melted_corr_mat <- melt(corr_mat)
head(melted_corr_mat)## Var1 Var2 value
## 1 DR1TKCAL DR1TKCAL 1.00
## 2 DR1TPROT DR1TKCAL 0.76
## 3 DR1TCARB DR1TKCAL 0.88
## 4 DR1TSUGR DR1TKCAL 0.66
## 5 DR1TFIBE DR1TKCAL 0.55
## 6 DR1TTFAT DR1TKCAL 0.88# plotting the correlation heatmap
library(ggplot2)
ggplot(data = melted_corr_mat, aes(x=Var1, y=Var2, fill=value)) + geom_tile() +
geom_text(aes(Var2, Var1, label = value), color = "black", size = 4)
library(plotly)##
## Attaching package: 'plotly'## The following object is masked from 'package:MASS':
##
## select## The following object is masked from 'package:ggplot2':
##
## last_plot## The following object is masked from 'package:stats':
##
## filter## The following object is masked from 'package:graphics':
##
## layoutlibrary(ggcorrplot)
# create corr matrix and
# corresponding p-value matrix
corr_mat <- round(cor(dat_complete),2)
p_mat <- cor_pmat(dat_complete)
# plotting the interactive corr heatmap
corr_mat <- ggcorrplot(
corr_mat, hc.order = TRUE, type = "lower",
outline.col = "white",
p.mat = p_mat
)
ggplotly(corr_mat)## Warning in L$marker$color[idx] <- aes2plotly(data, params, "fill")[idx]: number
## of items to replace is not a multiple of replacement length