library(NHANES)## Warning: package 'NHANES' was built under R version 4.4.1Using “install.package()” in my Rmd program can cause installation of the package each time my program is knitted. Instead, I make sure that the package is already installed before coding in the Console.
?NHANES## starting httpd help server ... doneThe “description” section of the help page shows an overview of the dataset. It depicts speciifc details of the dataset, such as where/when/what was gathered. In this specific dataset, a survey by the US National Center for Health Statistics conducted a data collection of health and nutrition surverys from 2009 to 2012.
When a “view()” command is in my .Rmd file it will open the data when I knit the doc. Typically, it can cause some issues such as creating a non-interactive environment and rendering issues.
head(NHANES)## ID SurveyYr Gender Age AgeDecade AgeMonths Race1 Race3 Education
## 1 51624 2009_10 male 34 30-39 409 White <NA> High School
## 2 51624 2009_10 male 34 30-39 409 White <NA> High School
## 3 51624 2009_10 male 34 30-39 409 White <NA> High School
## 4 51625 2009_10 male 4 0-9 49 Other <NA> <NA>
## 5 51630 2009_10 female 49 40-49 596 White <NA> Some College
## 6 51638 2009_10 male 9 0-9 115 White <NA> <NA>
## MaritalStatus HHIncome HHIncomeMid Poverty HomeRooms HomeOwn Work
## 1 Married 25000-34999 30000 1.36 6 Own NotWorking
## 2 Married 25000-34999 30000 1.36 6 Own NotWorking
## 3 Married 25000-34999 30000 1.36 6 Own NotWorking
## 4 <NA> 20000-24999 22500 1.07 9 Own <NA>
## 5 LivePartner 35000-44999 40000 1.91 5 Rent NotWorking
## 6 <NA> 75000-99999 87500 1.84 6 Rent <NA>
## Weight Length HeadCirc Height BMI BMICatUnder20yrs BMI_WHO Pulse BPSysAve
## 1 87.4 NA NA 164.7 32.22 <NA> 30.0_plus 70 113
## 2 87.4 NA NA 164.7 32.22 <NA> 30.0_plus 70 113
## 3 87.4 NA NA 164.7 32.22 <NA> 30.0_plus 70 113
## 4 17.0 NA NA 105.4 15.30 <NA> 12.0_18.5 NA NA
## 5 86.7 NA NA 168.4 30.57 <NA> 30.0_plus 86 112
## 6 29.8 NA NA 133.1 16.82 <NA> 12.0_18.5 82 86
## BPDiaAve BPSys1 BPDia1 BPSys2 BPDia2 BPSys3 BPDia3 Testosterone DirectChol
## 1 85 114 88 114 88 112 82 NA 1.29
## 2 85 114 88 114 88 112 82 NA 1.29
## 3 85 114 88 114 88 112 82 NA 1.29
## 4 NA NA NA NA NA NA NA NA NA
## 5 75 118 82 108 74 116 76 NA 1.16
## 6 47 84 50 84 50 88 44 NA 1.34
## TotChol UrineVol1 UrineFlow1 UrineVol2 UrineFlow2 Diabetes DiabetesAge
## 1 3.49 352 NA NA NA No NA
## 2 3.49 352 NA NA NA No NA
## 3 3.49 352 NA NA NA No NA
## 4 NA NA NA NA NA No NA
## 5 6.70 77 0.094 NA NA No NA
## 6 4.86 123 1.538 NA NA No NA
## HealthGen DaysPhysHlthBad DaysMentHlthBad LittleInterest Depressed
## 1 Good 0 15 Most Several
## 2 Good 0 15 Most Several
## 3 Good 0 15 Most Several
## 4 <NA> NA NA <NA> <NA>
## 5 Good 0 10 Several Several
## 6 <NA> NA NA <NA> <NA>
## nPregnancies nBabies Age1stBaby SleepHrsNight SleepTrouble PhysActive
## 1 NA NA NA 4 Yes No
## 2 NA NA NA 4 Yes No
## 3 NA NA NA 4 Yes No
## 4 NA NA NA NA <NA> <NA>
## 5 2 2 27 8 Yes No
## 6 NA NA NA NA <NA> <NA>
## PhysActiveDays TVHrsDay CompHrsDay TVHrsDayChild CompHrsDayChild
## 1 NA <NA> <NA> NA NA
## 2 NA <NA> <NA> NA NA
## 3 NA <NA> <NA> NA NA
## 4 NA <NA> <NA> 4 1
## 5 NA <NA> <NA> NA NA
## 6 NA <NA> <NA> 5 0
## Alcohol12PlusYr AlcoholDay AlcoholYear SmokeNow Smoke100 Smoke100n SmokeAge
## 1 Yes NA 0 No Yes Smoker 18
## 2 Yes NA 0 No Yes Smoker 18
## 3 Yes NA 0 No Yes Smoker 18
## 4 <NA> NA NA <NA> <NA> <NA> NA
## 5 Yes 2 20 Yes Yes Smoker 38
## 6 <NA> NA NA <NA> <NA> <NA> NA
## Marijuana AgeFirstMarij RegularMarij AgeRegMarij HardDrugs SexEver SexAge
## 1 Yes 17 No NA Yes Yes 16
## 2 Yes 17 No NA Yes Yes 16
## 3 Yes 17 No NA Yes Yes 16
## 4 <NA> NA <NA> NA <NA> <NA> NA
## 5 Yes 18 No NA Yes Yes 12
## 6 <NA> NA <NA> NA <NA> <NA> NA
## SexNumPartnLife SexNumPartYear SameSex SexOrientation PregnantNow
## 1 8 1 No Heterosexual <NA>
## 2 8 1 No Heterosexual <NA>
## 3 8 1 No Heterosexual <NA>
## 4 NA NA <NA> <NA> <NA>
## 5 10 1 Yes Heterosexual <NA>
## 6 NA NA <NA> <NA> <NA>summary(NHANES)## ID SurveyYr Gender Age AgeDecade
## Min. :51624 2009_10:5000 female:5020 Min. : 0.00 40-49 :1398
## 1st Qu.:56905 2011_12:5000 male :4980 1st Qu.:17.00 0-9 :1391
## Median :62160 Median :36.00 10-19 :1374
## Mean :61945 Mean :36.74 20-29 :1356
## 3rd Qu.:67039 3rd Qu.:54.00 30-39 :1338
## Max. :71915 Max. :80.00 (Other):2810
## NA's : 333
## AgeMonths Race1 Race3 Education
## Min. : 0.0 Black :1197 Asian : 288 8th Grade : 451
## 1st Qu.:199.0 Hispanic: 610 Black : 589 9 - 11th Grade: 888
## Median :418.0 Mexican :1015 Hispanic: 350 High School :1517
## Mean :420.1 White :6372 Mexican : 480 Some College :2267
## 3rd Qu.:624.0 Other : 806 White :3135 College Grad :2098
## Max. :959.0 Other : 158 NA's :2779
## NA's :5038 NA's :5000
## MaritalStatus HHIncome HHIncomeMid Poverty
## Divorced : 707 more 99999 :2220 Min. : 2500 Min. :0.000
## LivePartner : 560 75000-99999:1084 1st Qu.: 30000 1st Qu.:1.240
## Married :3945 25000-34999: 958 Median : 50000 Median :2.700
## NeverMarried:1380 35000-44999: 863 Mean : 57206 Mean :2.802
## Separated : 183 45000-54999: 784 3rd Qu.: 87500 3rd Qu.:4.710
## Widowed : 456 (Other) :3280 Max. :100000 Max. :5.000
## NA's :2769 NA's : 811 NA's :811 NA's :726
## HomeRooms HomeOwn Work Weight
## Min. : 1.000 Own :6425 Looking : 311 Min. : 2.80
## 1st Qu.: 5.000 Rent :3287 NotWorking:2847 1st Qu.: 56.10
## Median : 6.000 Other: 225 Working :4613 Median : 72.70
## Mean : 6.249 NA's : 63 NA's :2229 Mean : 70.98
## 3rd Qu.: 8.000 3rd Qu.: 88.90
## Max. :13.000 Max. :230.70
## NA's :69 NA's :78
## Length HeadCirc Height BMI
## Min. : 47.10 Min. :34.20 Min. : 83.6 Min. :12.88
## 1st Qu.: 75.70 1st Qu.:39.58 1st Qu.:156.8 1st Qu.:21.58
## Median : 87.00 Median :41.45 Median :166.0 Median :25.98
## Mean : 85.02 Mean :41.18 Mean :161.9 Mean :26.66
## 3rd Qu.: 96.10 3rd Qu.:42.92 3rd Qu.:174.5 3rd Qu.:30.89
## Max. :112.20 Max. :45.40 Max. :200.4 Max. :81.25
## NA's :9457 NA's :9912 NA's :353 NA's :366
## BMICatUnder20yrs BMI_WHO Pulse BPSysAve
## UnderWeight: 55 12.0_18.5 :1277 Min. : 40.00 Min. : 76.0
## NormWeight : 805 18.5_to_24.9:2911 1st Qu.: 64.00 1st Qu.:106.0
## OverWeight : 193 25.0_to_29.9:2664 Median : 72.00 Median :116.0
## Obese : 221 30.0_plus :2751 Mean : 73.56 Mean :118.2
## NA's :8726 NA's : 397 3rd Qu.: 82.00 3rd Qu.:127.0
## Max. :136.00 Max. :226.0
## NA's :1437 NA's :1449
## BPDiaAve BPSys1 BPDia1 BPSys2
## Min. : 0.00 Min. : 72.0 Min. : 0.00 Min. : 76.0
## 1st Qu.: 61.00 1st Qu.:106.0 1st Qu.: 62.00 1st Qu.:106.0
## Median : 69.00 Median :116.0 Median : 70.00 Median :116.0
## Mean : 67.48 Mean :119.1 Mean : 68.28 Mean :118.5
## 3rd Qu.: 76.00 3rd Qu.:128.0 3rd Qu.: 76.00 3rd Qu.:128.0
## Max. :116.00 Max. :232.0 Max. :118.00 Max. :226.0
## NA's :1449 NA's :1763 NA's :1763 NA's :1647
## BPDia2 BPSys3 BPDia3 Testosterone
## Min. : 0.00 Min. : 76.0 Min. : 0.0 Min. : 0.25
## 1st Qu.: 60.00 1st Qu.:106.0 1st Qu.: 60.0 1st Qu.: 17.70
## Median : 68.00 Median :116.0 Median : 68.0 Median : 43.82
## Mean : 67.66 Mean :117.9 Mean : 67.3 Mean : 197.90
## 3rd Qu.: 76.00 3rd Qu.:126.0 3rd Qu.: 76.0 3rd Qu.: 362.41
## Max. :118.00 Max. :226.0 Max. :116.0 Max. :1795.60
## NA's :1647 NA's :1635 NA's :1635 NA's :5874
## DirectChol TotChol UrineVol1 UrineFlow1
## Min. :0.390 Min. : 1.530 Min. : 0.0 Min. : 0.0000
## 1st Qu.:1.090 1st Qu.: 4.110 1st Qu.: 50.0 1st Qu.: 0.4030
## Median :1.290 Median : 4.780 Median : 94.0 Median : 0.6990
## Mean :1.365 Mean : 4.879 Mean :118.5 Mean : 0.9793
## 3rd Qu.:1.580 3rd Qu.: 5.530 3rd Qu.:164.0 3rd Qu.: 1.2210
## Max. :4.030 Max. :13.650 Max. :510.0 Max. :17.1670
## NA's :1526 NA's :1526 NA's :987 NA's :1603
## UrineVol2 UrineFlow2 Diabetes DiabetesAge HealthGen
## Min. : 0.0 Min. : 0.000 No :9098 Min. : 1.00 Excellent: 878
## 1st Qu.: 52.0 1st Qu.: 0.475 Yes : 760 1st Qu.:40.00 Vgood :2508
## Median : 95.0 Median : 0.760 NA's: 142 Median :50.00 Good :2956
## Mean :119.7 Mean : 1.149 Mean :48.42 Fair :1010
## 3rd Qu.:171.8 3rd Qu.: 1.513 3rd Qu.:58.00 Poor : 187
## Max. :409.0 Max. :13.692 Max. :80.00 NA's :2461
## NA's :8522 NA's :8524 NA's :9371
## DaysPhysHlthBad DaysMentHlthBad LittleInterest Depressed
## Min. : 0.000 Min. : 0.000 None :5103 None :5246
## 1st Qu.: 0.000 1st Qu.: 0.000 Several:1130 Several:1009
## Median : 0.000 Median : 0.000 Most : 434 Most : 418
## Mean : 3.335 Mean : 4.127 NA's :3333 NA's :3327
## 3rd Qu.: 3.000 3rd Qu.: 4.000
## Max. :30.000 Max. :30.000
## NA's :2468 NA's :2466
## nPregnancies nBabies Age1stBaby SleepHrsNight
## Min. : 1.000 Min. : 0.000 Min. :14.00 Min. : 2.000
## 1st Qu.: 2.000 1st Qu.: 2.000 1st Qu.:19.00 1st Qu.: 6.000
## Median : 3.000 Median : 2.000 Median :22.00 Median : 7.000
## Mean : 3.027 Mean : 2.457 Mean :22.65 Mean : 6.928
## 3rd Qu.: 4.000 3rd Qu.: 3.000 3rd Qu.:26.00 3rd Qu.: 8.000
## Max. :32.000 Max. :12.000 Max. :39.00 Max. :12.000
## NA's :7396 NA's :7584 NA's :8116 NA's :2245
## SleepTrouble PhysActive PhysActiveDays TVHrsDay CompHrsDay
## No :5799 No :3677 Min. :1.000 2_hr :1275 0_to_1_hr:1409
## Yes :1973 Yes :4649 1st Qu.:2.000 1_hr : 884 0_hrs :1073
## NA's:2228 NA's:1674 Median :3.000 3_hr : 836 1_hr :1030
## Mean :3.744 0_to_1_hr: 638 2_hr : 589
## 3rd Qu.:5.000 More_4_hr: 615 3_hr : 347
## Max. :7.000 (Other) : 611 (Other) : 415
## NA's :5337 NA's :5141 NA's :5137
## TVHrsDayChild CompHrsDayChild Alcohol12PlusYr AlcoholDay
## Min. :0.000 Min. :0.000 No :1368 Min. : 1.000
## 1st Qu.:1.000 1st Qu.:0.000 Yes :5212 1st Qu.: 1.000
## Median :2.000 Median :1.000 NA's:3420 Median : 2.000
## Mean :1.939 Mean :2.198 Mean : 2.914
## 3rd Qu.:3.000 3rd Qu.:6.000 3rd Qu.: 3.000
## Max. :6.000 Max. :6.000 Max. :82.000
## NA's :9347 NA's :9347 NA's :5086
## AlcoholYear SmokeNow Smoke100 Smoke100n SmokeAge
## Min. : 0.0 No :1745 No :4024 Non-Smoker:4024 Min. : 6.00
## 1st Qu.: 3.0 Yes :1466 Yes :3211 Smoker :3211 1st Qu.:15.00
## Median : 24.0 NA's:6789 NA's:2765 NA's :2765 Median :17.00
## Mean : 75.1 Mean :17.83
## 3rd Qu.:104.0 3rd Qu.:19.00
## Max. :364.0 Max. :72.00
## NA's :4078 NA's :6920
## Marijuana AgeFirstMarij RegularMarij AgeRegMarij HardDrugs
## No :2049 Min. : 1.00 No :3575 Min. : 5.00 No :4700
## Yes :2892 1st Qu.:15.00 Yes :1366 1st Qu.:15.00 Yes :1065
## NA's:5059 Median :16.00 NA's:5059 Median :17.00 NA's:4235
## Mean :17.02 Mean :17.69
## 3rd Qu.:19.00 3rd Qu.:19.00
## Max. :48.00 Max. :52.00
## NA's :7109 NA's :8634
## SexEver SexAge SexNumPartnLife SexNumPartYear SameSex
## No : 223 Min. : 9.00 Min. : 0.00 Min. : 0.000 No :5353
## Yes :5544 1st Qu.:15.00 1st Qu.: 2.00 1st Qu.: 1.000 Yes : 415
## NA's:4233 Median :17.00 Median : 5.00 Median : 1.000 NA's:4232
## Mean :17.43 Mean : 15.09 Mean : 1.342
## 3rd Qu.:19.00 3rd Qu.: 12.00 3rd Qu.: 1.000
## Max. :50.00 Max. :2000.00 Max. :69.000
## NA's :4460 NA's :4275 NA's :5072
## SexOrientation PregnantNow
## Bisexual : 119 Yes : 72
## Heterosexual:4638 No :1573
## Homosexual : 85 Unknown: 51
## NA's :5158 NA's :8304
##
##
## There are 78 missing values for weight and 353 missing values for height.
calculate_mean_difference <- function(df, i, col1, col2) {
filtered_df <- df[i, ]
filtered_df <- filtered_df[complete.cases(filtered_df[, c(col1, col2)]), ]
mean_diff <- mean(filtered_df[[col1]]) - mean(filtered_df[[col2]])
return(mean_diff)}calculate_mean_difference <- function(df, i)
{browser()
if (!is.numeric(i)) {
stop("Indices 'i' must be numeric.")}
filtered_df <- df[i, ]
filtered_df <- filtered_df[complete.cases(filtered_df[, c("Weight", "Height")]), ]
mean_diff <- mean(filtered_df$Weight) - mean(filtered_df$Height)
return(mean_diff)}
indices <- c(1, 2, 3, 5, 7) # Example numeric indices, adjust as needed
mean_diff <- calculate_mean_difference(NHANES, indices)## Called from: calculate_mean_difference(NHANES, indices)
## debug at <text>#3: if (!is.numeric(i)) {
## stop("Indices 'i' must be numeric.")
## }
## debug at <text>#5: filtered_df <- df[i, ]
## debug at <text>#6: filtered_df <- filtered_df[complete.cases(filtered_df[, c("Weight",
## "Height")]), ]
## debug at <text>#7: mean_diff <- mean(filtered_df$Weight) - mean(filtered_df$Height)
## debug at <text>#9: return(mean_diff)print(mean_diff)## [1] -81.8After looking at the “environment” tab, I saw variables such as ‘df’ and ‘i. These variables changed from ’NHANES’ to ‘df’ and ‘c(“a”, “b”, “c”)’to ’i’.
calculate_gender_weight_difference <- function(df) {
filtered_df <- df[df$Gender %in% c("male", "female"), ]
mean_weight_male <- mean(filtered_df$Weight[filtered_df$Gender == "male"], na.rm = TRUE)
mean_weight_female <- mean(filtered_df$Weight[filtered_df$Gender == "female"], na.rm = TRUE)
weight_difference <- mean_weight_male - mean_weight_female
return(weight_difference)
}
print(calculate_gender_weight_difference)## function(df) {
## filtered_df <- df[df$Gender %in% c("male", "female"), ]
## mean_weight_male <- mean(filtered_df$Weight[filtered_df$Gender == "male"], na.rm = TRUE)
## mean_weight_female <- mean(filtered_df$Weight[filtered_df$Gender == "female"], na.rm = TRUE)
## weight_difference <- mean_weight_male - mean_weight_female
## return(weight_difference)
## }difference <- calculate_gender_weight_difference(NHANES)
print(difference)## [1] 9.583432