Health Care Insurance Marketplace
A. Data Preparation
Data preparation and loading:
setwd("~/drexel_masters/data/INFO659")HIMP <- read.csv("final/HI_rate.csv")head(HIMP, 5)Creating subset for analysis
HI <- HIMP[,c(3,9,12,14,15,16,17,18,19,20,21,22,23,24)]head(HI,5)nrow(HI)[1] 549999summary(HI) StateCode FederalTIN PlanId
AK: 5657 59-2015694: 77089 48129FL0160004: 6586
AL: 40564 86-0307623: 60713 48129FL0160002: 6545
AZ: 75624 47-0397286: 52441 48129FL0160001: 6537
FL:316390 36-3097810: 45683 16842FL0010001: 6510
GA: 59671 59-2403696: 33956 16842FL0010002: 6480
IN: 52093 94-2761537: 33864 48129FL0160003: 6329
(Other) :246253 (Other) :511012
Tobacco Age
No Preference :366451 26 : 12122
Tobacco User/Non-Tobacco User:183548 44 : 12107
38 : 12088
47 : 12051
0-20 : 12036
52 : 12028
(Other):477567
IndividualRate IndividualTobaccoRate Couple
Min. : 0.0 Min. : 67.2 Min. : 15.6
1st Qu.: 25.7 1st Qu.: 350.0 1st Qu.: 29.2
Median : 233.0 Median : 472.0 Median : 38.9
Mean : 6917.9 Mean : 553.6 Mean : 43.2
3rd Qu.: 413.6 3rd Qu.: 699.4 3rd Qu.: 56.0
Max. :999999.0 Max. :2132.6 Max. :182.4
NA's :365958 NA's :548575
PrimarySubscriberAndOneDependent
Min. : 20.9
1st Qu.: 29.7
Median : 41.7
Mean : 44.1
3rd Qu.: 55.6
Max. :169.7
NA's :548575
PrimarySubscriberAndTwoDependents
Min. : 24.0
1st Qu.: 30.9
Median : 62.0
Mean : 60.3
3rd Qu.: 81.0
Max. :248.1
NA's :548575
PrimarySubscriberAndThreeOrMoreDependents
Min. : 24.0
1st Qu.: 30.9
Median : 85.2
Mean : 79.7
3rd Qu.:112.2
Max. :357.9
NA's :548575
CoupleAndOneDependent CoupleAndTwoDependents
Min. : 24.0 Min. : 24.0
1st Qu.: 31.8 1st Qu.: 33.8
Median : 62.1 Median : 78.5
Mean : 62.4 Mean : 78.5
3rd Qu.: 82.7 3rd Qu.:109.4
Max. :260.9 Max. :339.3
NA's :548575 NA's :548575
CoupleAndThreeOrMoreDependents
Min. : 24.0
1st Qu.: 33.8
Median :105.8
Mean : 98.0
3rd Qu.:139.5
Max. :449.1
NA's :548575 The column “Tobacco” contains two values: “No preference” (366,451 accounts) and “Tobacco User/Non-Tobacco User” (183,548 accounts). Therefore, almost 2/3 consumers were enrolled in plans that did not determine an insurance premium based on smoking status.
The values of the variable “IndividualRate”ranged from 0 to $999,999.0. The accounts with values of “0” and “999,999.0” are unexpected values. They do not make sense and should be considered as outliers. Therefore, these accounts should be excluded from further analyses.
outlier1 <- subset(HI, IndividualRate ==0)
outlier1summary(outlier1) StateCode FederalTIN PlanId
AK: 579 59-2876465:6467 30115FL0010001:3252
AL: 0 34-0648820:1215 30115FL0020001:3215
AZ:1680 47-0098400: 970 43499IN0070001: 419
FL:6467 93-0242990: 953 43499IN0070002: 406
GA: 0 91-1857813: 336 43499IN0060001: 390
IN:1215 06-6033492: 0 52147AZ0040002: 179
(Other) : 0 (Other) :2080
Tobacco Age
No Preference :9941 33 : 243
Tobacco User/Non-Tobacco User: 0 32 : 240
57 : 238
35 : 236
62 : 235
23 : 233
(Other):8516
IndividualRate IndividualTobaccoRate Couple
Min. :0 Min. : NA Min. : NA
1st Qu.:0 1st Qu.: NA 1st Qu.: NA
Median :0 Median : NA Median : NA
Mean :0 Mean :NaN Mean :NaN
3rd Qu.:0 3rd Qu.: NA 3rd Qu.: NA
Max. :0 Max. : NA Max. : NA
NA's :9941 NA's :9941
PrimarySubscriberAndOneDependent
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :9941
PrimarySubscriberAndTwoDependents
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :9941
PrimarySubscriberAndThreeOrMoreDependents
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :9941
CoupleAndOneDependent CoupleAndTwoDependents
Min. : NA Min. : NA
1st Qu.: NA 1st Qu.: NA
Median : NA Median : NA
Mean :NaN Mean :NaN
3rd Qu.: NA 3rd Qu.: NA
Max. : NA Max. : NA
NA's :9941 NA's :9941
CoupleAndThreeOrMoreDependents
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :9941 Only four FederalTins were associated with the “0” outliers
outlier2 <- subset(HI, IndividualRate ==999999.0)
outlier2summary(outlier2) StateCode FederalTIN PlanId
AK: 289 95-6042390:3643 83502GA0010002: 389
AL:1216 06-6033492: 0 83502GA0020001: 362
AZ: 666 13-5123390: 0 83502GA0020002: 361
FL: 0 13-5581829: 0 83502GA0010001: 360
GA:1472 14-1917982: 0 12538AL0010001: 312
IN: 0 20-3174593: 0 12538AL0020001: 304
(Other) : 0 (Other) :1555
Tobacco Age
No Preference :3643 47 : 94
Tobacco User/Non-Tobacco User: 0 63 : 94
25 : 93
31 : 93
21 : 89
43 : 87
(Other):3093
IndividualRate IndividualTobaccoRate Couple
Min. :1e+06 Min. : NA Min. : NA
1st Qu.:1e+06 1st Qu.: NA 1st Qu.: NA
Median :1e+06 Median : NA Median : NA
Mean :1e+06 Mean :NaN Mean :NaN
3rd Qu.:1e+06 3rd Qu.: NA 3rd Qu.: NA
Max. :1e+06 Max. : NA Max. : NA
NA's :3643 NA's :3643
PrimarySubscriberAndOneDependent
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :3643
PrimarySubscriberAndTwoDependents
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :3643
PrimarySubscriberAndThreeOrMoreDependents
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :3643
CoupleAndOneDependent CoupleAndTwoDependents
Min. : NA Min. : NA
1st Qu.: NA 1st Qu.: NA
Median : NA Median : NA
Mean :NaN Mean :NaN
3rd Qu.: NA 3rd Qu.: NA
Max. : NA Max. : NA
NA's :3643 NA's :3643
CoupleAndThreeOrMoreDependents
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :3643 Only one FederalTin was associated with the $999,999 outliers (the Best Life And Health Insurance Company).
Creating the new filtered subset without outliers:
filteredHI1 <- subset(HI, IndividualRate <999999.0)
newHI <- subset(filteredHI1, IndividualRate >0)
summary(newHI) StateCode FederalTIN PlanId
AK: 4789 59-2015694: 77089 48129FL0160004: 6586
AL: 39348 86-0307623: 60713 48129FL0160002: 6545
AZ: 73278 47-0397286: 52441 48129FL0160001: 6537
FL:309923 36-3097810: 45683 16842FL0010001: 6510
GA: 58199 59-2403696: 33956 16842FL0010002: 6480
IN: 50878 94-2761537: 33864 48129FL0160003: 6329
(Other) :232669 (Other) :497428
Tobacco Age
No Preference :352867 0-20 : 12036
Tobacco User/Non-Tobacco User:183548 44 : 11830
26 : 11818
38 : 11790
52 : 11738
47 : 11727
(Other):465476
IndividualRate IndividualTobaccoRate Couple
Min. : 7.82 Min. : 67.2 Min. : 15.6
1st Qu.: 26.74 1st Qu.: 350.0 1st Qu.: 29.2
Median : 237.94 Median : 472.0 Median : 38.9
Mean : 301.67 Mean : 553.6 Mean : 43.2
3rd Qu.: 413.06 3rd Qu.: 699.4 3rd Qu.: 56.0
Max. :9999.00 Max. :2132.6 Max. :182.4
NA's :352374 NA's :534991
PrimarySubscriberAndOneDependent
Min. : 20.9
1st Qu.: 29.7
Median : 41.7
Mean : 44.1
3rd Qu.: 55.6
Max. :169.7
NA's :534991
PrimarySubscriberAndTwoDependents
Min. : 24.0
1st Qu.: 30.9
Median : 62.0
Mean : 60.3
3rd Qu.: 81.0
Max. :248.1
NA's :534991
PrimarySubscriberAndThreeOrMoreDependents
Min. : 24.0
1st Qu.: 30.9
Median : 85.2
Mean : 79.7
3rd Qu.:112.2
Max. :357.9
NA's :534991
CoupleAndOneDependent CoupleAndTwoDependents
Min. : 24.0 Min. : 24.0
1st Qu.: 31.8 1st Qu.: 33.8
Median : 62.1 Median : 78.5
Mean : 62.4 Mean : 78.5
3rd Qu.: 82.7 3rd Qu.:109.4
Max. :260.9 Max. :339.3
NA's :534991 NA's :534991
CoupleAndThreeOrMoreDependents
Min. : 24.0
1st Qu.: 33.8
Median :105.8
Mean : 98.0
3rd Qu.:139.5
Max. :449.1
NA's :534991 nrow(newHI)[1] 536415A.2. Data distribution and anomalies
library(ggplot2)State code vs IndividualRate
ggplot(newHI, aes(x=StateCode, y=IndividualRate)) +
geom_boxplot() + scale_color_manual(values=c("black","black")) 
The visualization of the distribution of the insurance rate across the individual states showed more outliers with value “9,999.0”. Only one FederalTIN (belongs to the Cigna Health and Life Insurance Company) was associated with the $9999 outliers. These outliers will be excluded from the data.
outlier3 <- subset(newHI, IndividualRate ==9999.0)
summary(outlier3) StateCode FederalTIN PlanId
AK: 0 59-1031071:1992 48121FL0030001:1580
AL: 0 06-6033492: 0 50491GA0030001: 253
AZ: 159 13-5123390: 0 86830AZ0050001: 159
FL:1580 13-5581829: 0 12538AL0010001: 0
GA: 253 14-1917982: 0 12538AL0010002: 0
IN: 0 20-3174593: 0 12538AL0010003: 0
(Other) : 0 (Other) : 0
Tobacco Age
No Preference :1992 62 : 58
Tobacco User/Non-Tobacco User: 0 45 : 55
65 and over: 55
51 : 53
25 : 50
52 : 50
(Other) :1671
IndividualRate IndividualTobaccoRate Couple
Min. :9999 Min. : NA Min. : NA
1st Qu.:9999 1st Qu.: NA 1st Qu.: NA
Median :9999 Median : NA Median : NA
Mean :9999 Mean :NaN Mean :NaN
3rd Qu.:9999 3rd Qu.: NA 3rd Qu.: NA
Max. :9999 Max. : NA Max. : NA
NA's :1992 NA's :1992
PrimarySubscriberAndOneDependent
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :1992
PrimarySubscriberAndTwoDependents
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :1992
PrimarySubscriberAndThreeOrMoreDependents
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :1992
CoupleAndOneDependent CoupleAndTwoDependents
Min. : NA Min. : NA
1st Qu.: NA 1st Qu.: NA
Median : NA Median : NA
Mean :NaN Mean :NaN
3rd Qu.: NA 3rd Qu.: NA
Max. : NA Max. : NA
NA's :1992 NA's :1992
CoupleAndThreeOrMoreDependents
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :1992 Creating the final subset for our analysis
finalHI <- subset(newHI, IndividualRate <9999.0)
summary(finalHI) StateCode FederalTIN PlanId
AK: 4789 59-2015694: 77089 48129FL0160004: 6586
AL: 39348 86-0307623: 60713 48129FL0160002: 6545
AZ: 73119 47-0397286: 52441 48129FL0160001: 6537
FL:308343 36-3097810: 45683 16842FL0010001: 6510
GA: 57946 59-2403696: 33956 16842FL0010002: 6480
IN: 50878 94-2761537: 33864 48129FL0160003: 6329
(Other) :230677 (Other) :495436
Tobacco Age
No Preference :350875 0-20 : 12036
Tobacco User/Non-Tobacco User:183548 44 : 11784
26 : 11776
38 : 11757
52 : 11688
47 : 11686
(Other):463696
IndividualRate IndividualTobaccoRate Couple
Min. : 7.82 Min. : 67.2 Min. : 15.6
1st Qu.: 26.73 1st Qu.: 350.0 1st Qu.: 29.2
Median : 236.36 Median : 472.0 Median : 38.9
Mean : 265.53 Mean : 553.6 Mean : 43.2
3rd Qu.: 410.22 3rd Qu.: 699.4 3rd Qu.: 56.0
Max. :1898.28 Max. :2132.6 Max. :182.4
NA's :350382 NA's :532999
PrimarySubscriberAndOneDependent
Min. : 20.9
1st Qu.: 29.7
Median : 41.7
Mean : 44.1
3rd Qu.: 55.6
Max. :169.7
NA's :532999
PrimarySubscriberAndTwoDependents
Min. : 24.0
1st Qu.: 30.9
Median : 62.0
Mean : 60.3
3rd Qu.: 81.0
Max. :248.1
NA's :532999
PrimarySubscriberAndThreeOrMoreDependents
Min. : 24.0
1st Qu.: 30.9
Median : 85.2
Mean : 79.7
3rd Qu.:112.2
Max. :357.9
NA's :532999
CoupleAndOneDependent CoupleAndTwoDependents
Min. : 24.0 Min. : 24.0
1st Qu.: 31.8 1st Qu.: 33.8
Median : 62.1 Median : 78.5
Mean : 62.4 Mean : 78.5
3rd Qu.: 82.7 3rd Qu.:109.4
Max. :260.9 Max. :339.3
NA's :532999 NA's :532999
CoupleAndThreeOrMoreDependents
Min. : 24.0
1st Qu.: 33.8
Median :105.8
Mean : 98.0
3rd Qu.:139.5
Max. :449.1
NA's :532999 View(finalHI)Plotting State code vs IndividualRate
ggplot(finalHI, aes(x=StateCode, y=IndividualRate)) +
geom_boxplot() + scale_color_manual(values=c("black","black")) 
FederalTIN
ggplot(finalHI, aes(x=FederalTIN, y=IndividualRate)) +
geom_boxplot() + scale_color_manual(values=c("black","black"))
summary(finalHI$FederalTIN)06-6033492 13-5123390 13-5581829 14-1917982 20-3174593
4361 8649 4780 6467 1976
20-8937577 26-0155137 26-3238817 27-3835905 31-1069321
1975 220 16222 2902 25135
34-0648820 35-0472300 35-0781558 36-3097810 36-3691770
5775 7698 17140 45683 838
39-1263473 39-1821211 45-3131932 45-4370907 46-1509576
2694 1990 1741 1200 542
46-2210067 47-0098400 47-0397286 58-0469845 58-1592076
771 17 52441 3100 7156
58-1638390 58-2209549 58-2335921 59-1031071 59-1419293
9641 2029 1488 9435 113
59-2015694 59-2403696 59-2876465 59-3315064 61-1013183
77089 33956 6605 3150 229
61-1103898 63-0103830 63-1028262 65-0073323 65-0743731
1751 8964 5567 133 6636
65-0986441 75-1233841 86-0004538 86-0207231 86-0274899
1591 19869 7712 15039 2700
86-0307623 91-1857813 93-0242990 93-0438772 93-0989307
60713 21 17 69 4317
94-2761537 95-6042390
33864 252 plot(finalHI$StateCode, finalHI$FederalTIN)
ggplot(finalHI, aes(x=Tobacco, y=IndividualRate)) +
geom_boxplot() + scale_color_manual(values=c("black","black"))
Age vs. Individual Rate
ggplot(finalHI, aes(x=Age, y=IndividualRate)) +
geom_boxplot() 
Producing a histogram for the individual insurance rates
hist(finalHI$IndividualRate, breaks=50, xlab="IndividualRate", main="Individual Rate Values distribution")
Without the outliers, the values of the individual health insurance rates ranged from $7.82 to $1.898.28 with median $236.36 and $265.53. The histogram shape is skewed to the left (Fig.2). Almost half individual rates are in the groups below $100.
Producing a histogram for individual rates with log transformation
hist(log10(finalHI$IndividualRate), breaks=50, xlab="Individual Rate", main="Individual Rates: with log transformation")
With log transformation, the distribution of individual rates became bimodal with two peaks of data, which usually indicates the presence of two different groups (Fig.3). Therefore, we need to find out how different these groups are. Based on the histogram (Fig. 2), we assumed that the first group included individual rates with values below $100 and the second group included accounts with rates above $100. For further analysis, we created two different subsets: “Cheap Health Insurance” and “Expensive Health Insurance.”
cheapHI <- subset(finalHI, IndividualRate<=100)
summary(cheapHI) StateCode FederalTIN PlanId
AK: 472 86-0307623:60713 48129FL0160004: 6586
AL: 15739 47-0397286:52441 48129FL0160002: 6545
AZ: 10163 94-2761537:33864 48129FL0160001: 6537
FL:161346 75-1233841:19869 48129FL0160003: 6329
GA: 32668 13-5123390: 8649 30115FL0040001: 3241
IN: 14734 35-0472300: 7698 30115FL0050001: 3234
(Other) :51888 (Other) :202650
Tobacco Age
No Preference :235020 0-20 : 5777
Tobacco User/Non-Tobacco User: 102 38 : 5184
44 : 5175
47 : 5159
64 : 5155
26 : 5151
(Other):203521
IndividualRate IndividualTobaccoRate Couple
Min. : 7.82 Min. : 67.16 Min. : 15.61
1st Qu.: 18.79 1st Qu.: 87.00 1st Qu.: 29.24
Median : 24.61 Median : 98.25 Median : 38.94
Mean : 28.12 Mean : 98.93 Mean : 43.18
3rd Qu.: 31.52 3rd Qu.:109.00 3rd Qu.: 56.03
Max. :100.00 Max. :137.53 Max. :182.40
NA's :235020 NA's :233698
PrimarySubscriberAndOneDependent
Min. : 20.92
1st Qu.: 29.74
Median : 41.73
Mean : 44.13
3rd Qu.: 55.63
Max. :169.65
NA's :233698
PrimarySubscriberAndTwoDependents
Min. : 24.01
1st Qu.: 30.90
Median : 61.97
Mean : 60.27
3rd Qu.: 81.04
Max. :248.11
NA's :233698
PrimarySubscriberAndThreeOrMoreDependents
Min. : 24.01
1st Qu.: 30.90
Median : 85.21
Mean : 79.73
3rd Qu.:112.23
Max. :357.94
NA's :233698
CoupleAndOneDependent CoupleAndTwoDependents
Min. : 24.01 Min. : 24.01
1st Qu.: 31.76 1st Qu.: 33.82
Median : 62.07 Median : 78.50
Mean : 62.36 Mean : 78.50
3rd Qu.: 82.70 3rd Qu.:109.37
Max. :260.85 Max. :339.31
NA's :233698 NA's :233698
CoupleAndThreeOrMoreDependents
Min. : 24.01
1st Qu.: 33.82
Median :105.85
Mean : 97.96
3rd Qu.:139.53
Max. :449.14
NA's :233698 ggplot(cheapHI, aes(x=Age, y=IndividualRate)) +
geom_boxplot() + scale_color_manual(values=c("black","black")) 
summary(cheapHI$FederalTIN)06-6033492 13-5123390 13-5581829 14-1917982 20-3174593
14 8649 498 6467 1
20-8937577 26-0155137 26-3238817 27-3835905 31-1069321
0 0 0 0 4819
34-0648820 35-0472300 35-0781558 36-3097810 36-3691770
5775 7698 3302 65 838
39-1263473 39-1821211 45-3131932 45-4370907 46-1509576
2466 0 0 1 0
46-2210067 47-0098400 47-0397286 58-0469845 58-1592076
1 17 52441 3100 3
58-1638390 58-2209549 58-2335921 59-1031071 59-1419293
0 11 0 1835 0
59-2015694 59-2403696 59-2876465 59-3315064 61-1013183
2 0 6605 0 2
61-1103898 63-0103830 63-1028262 65-0073323 65-0743731
7 622 5567 133 6636
65-0986441 75-1233841 86-0004538 86-0207231 86-0274899
32 19869 10 0 2700
86-0307623 91-1857813 93-0242990 93-0438772 93-0989307
60713 21 17 69 0
94-2761537 95-6042390
33864 252
plot(cheapHI$StateCode, cheapHI$FederalTIN)
plot(cheapHI$IndividualRate, cheapHI$Couple)
expensiveHI <- subset(finalHI, IndividualRate>100)
summary(expensiveHI) StateCode FederalTIN PlanId
AK: 4317 59-2015694:77087 16842FL0010001: 6510
AL: 23609 36-3097810:45618 16842FL0010002: 6480
AZ: 62956 59-2403696:33956 30252FL0010001: 4195
FL:146997 31-1069321:20316 30252FL0010002: 4195
GA: 25278 26-3238817:16222 16842FL0070088: 1671
IN: 36144 86-0207231:15039 17575IN0720001: 1670
(Other) :91063 (Other) :274580
Tobacco Age
No Preference :115855 26 : 6625
Tobacco User/Non-Tobacco User:183446 44 : 6609
52 : 6591
57 : 6582
33 : 6580
65 and over: 6574
(Other) :259740
IndividualRate IndividualTobaccoRate Couple
Min. : 100.0 Min. : 100.3 Min. : NA
1st Qu.: 289.5 1st Qu.: 350.2 1st Qu.: NA
Median : 383.4 Median : 472.2 Median : NA
Mean : 452.0 Mean : 553.8 Mean :NaN
3rd Qu.: 568.2 3rd Qu.: 699.6 3rd Qu.: NA
Max. :1898.3 Max. :2132.6 Max. : NA
NA's :115362 NA's :299301
PrimarySubscriberAndOneDependent
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :299301
PrimarySubscriberAndTwoDependents
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :299301
PrimarySubscriberAndThreeOrMoreDependents
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :299301
CoupleAndOneDependent CoupleAndTwoDependents
Min. : NA Min. : NA
1st Qu.: NA 1st Qu.: NA
Median : NA Median : NA
Mean :NaN Mean :NaN
3rd Qu.: NA 3rd Qu.: NA
Max. : NA Max. : NA
NA's :299301 NA's :299301
CoupleAndThreeOrMoreDependents
Min. : NA
1st Qu.: NA
Median : NA
Mean :NaN
3rd Qu.: NA
Max. : NA
NA's :299301 plot(expensiveHI$IndividualRate, expensiveHI$IndividualTobaccoRate)
hist(expensiveHI$IndividualTobaccoRate, breaks=50, xlab="IndividualTobaccoRate", main="Individual Tobacco Rate distribution")
hist(log10(expensiveHI$IndividualTobaccoRate), breaks=50, xlab="Individual Tobacco Rate", main="Individual Tobacco Rates: with log transformation")
ggplot(expensiveHI, aes(x=StateCode, y=IndividualRate)) +
geom_boxplot() + scale_color_manual(values=c("black","black"))
summary(expensiveHI$FederalTIN)06-6033492 13-5123390 13-5581829 14-1917982 20-3174593
4347 0 4282 0 1975
20-8937577 26-0155137 26-3238817 27-3835905 31-1069321
1975 220 16222 2902 20316
34-0648820 35-0472300 35-0781558 36-3097810 36-3691770
0 0 13838 45618 0
39-1263473 39-1821211 45-3131932 45-4370907 46-1509576
228 1990 1741 1199 542
46-2210067 47-0098400 47-0397286 58-0469845 58-1592076
770 0 0 0 7153
58-1638390 58-2209549 58-2335921 59-1031071 59-1419293
9641 2018 1488 7600 113
59-2015694 59-2403696 59-2876465 59-3315064 61-1013183
77087 33956 0 3150 227
61-1103898 63-0103830 63-1028262 65-0073323 65-0743731
1744 8342 0 0 0
65-0986441 75-1233841 86-0004538 86-0207231 86-0274899
1559 0 7702 15039 0
86-0307623 91-1857813 93-0242990 93-0438772 93-0989307
0 0 0 0 4317
94-2761537 95-6042390
0 0 plot(expensiveHI$StateCode, expensiveHI$FederalTIN)
ggplot(expensiveHI, aes(x=Tobacco, y=IndividualRate)) +
geom_boxplot() + scale_color_manual(values=c("black","black"))
ggplot(expensiveHI, aes(x=Age, y=IndividualRate)) +
geom_boxplot() + scale_color_manual(values=c("black","black")) 
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