1 + 1[1] 2Homework 2
Quarto
Quarto enables you to weave together content and executable code into a finished document. To learn more about Quarto see https://quarto.org.
Running Code
When you click the Render button a document will be generated that includes both content and the output of embedded code. You can embed code like this:
You can add options to executable code like this
[1] 4The echo: false option disables the printing of code (only output is displayed).
##load libraries
library(haven)
library(survival)
library(car)Loading required package: carDatalibrary(muhaz)
library(tidyverse)── Attaching packages
───────────────────────────────────────
tidyverse 1.3.2 ──✔ ggplot2 3.3.6 ✔ purrr 0.3.4
✔ tibble 3.1.8 ✔ dplyr 1.0.9
✔ tidyr 1.2.0 ✔ stringr 1.4.1
✔ readr 2.1.2 ✔ forcats 0.5.2
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag() masks stats::lag()
✖ dplyr::recode() masks car::recode()
✖ purrr::some() masks car::some()library(ipumsr)##load data
nhis9 <- read_stata("C:/Users/okabe/OneDrive/Pictures/Stats 2/nhis_00010.dta.gz")
nhis9<-zap_labels(nhis9)
#iew(nhis9)##filter only respondants
nhis9 <- nhis9 %>%
filter(mortelig == 1)##Recode variables
#poor
nhis9$poor<-Recode(nhis9$pooryn, recodes ="7:9=NA; 1=0;2=1",as.factor=T)
##Alcohol
nhis9$alcohol<-Recode(nhis9$alclife, recodes ="1=1;2=0;7:9=NA;0=NA")
##smoking
nhis9$smoke<-Recode(nhis9$smokev, recodes ="7:9=NA;1=1;2=0; 0=NA")
##usborn
nhis9$born<-Recode(nhis9$usborn, recodes ="96:99=NA; 20=0;10:12=1;else=NA",as.factor=T)
##educ
nhis9$education<-Recode(nhis9$educ, recodes="101='0Prim'; 101:204='1somehs'; 300:302='2hsgrad'; 400:401='3somecol'; 500='4colgrad';600:603='5masteranddoc';402:403='6Techandacademic';604:999=NA;000=NA;100=NA; else= 'other'", as.factor=T)
##Recode
##citizen
nhis9$mycitizen<-Recode(nhis9$citizen, recodes ="7:9=NA; 1=1;2=0;else=NA",as.factor=T)
##Marital status
nhis9$marital<-Recode(nhis9$marstat, recodes="10='married'; 30='divorced'; 20='widowed'; 40='separated'; 50='nm'; else=NA", as.factor=T)
nhis9$marital<-relevel(nhis9$marital, ref='married')
#Age cut into intervals
nhis9$agec<-cut(nhis9$age, breaks = c( 30, 40, 50, 60, 70, 80, 100), include.lowest = T)
#race/ethnicity
nhis9$race<-Recode(nhis9$racesr, recodes="100='white'; 200='black'; else='other'", as.factor=T)
nhis9$race<-relevel(nhis9$race, ref = "white")
##Hispanic
nhis9$ethnicity<-Recode(nhis9$hispeth, recodes="10='not hispanic'; 20:70='hispanic'; else=NA", as.factor=T)
##disease
#nhis2$disease<- Recode(nhis2$mortucodld, recodes= "01= 0; 02=1; 03=2; 04=3;05=4; 06=5; 07=6; 08= 7; 09=8; 10=9; else=NA")
#nhis2$disease<- Recode(nhis2$mortucodld, recodes= "01= 'Diseases of heart'; 02='Malignant neoplasms'; 03='Chronic lower respiratory diseases'; 04='Accidents';05='Cerebrovascular disease'; 06='Alzheimers disease'; 07='Diabetes mellitus'; 08= 'Influenza and pneumonia'; 09='Nephritis'; 10='All other causes'; 96= NA; else=NA",as.factor=T )
##sex
nhis9$male<-as.factor(ifelse(nhis9$sex==1, "Male", "Female"))
nhis9$male<-relevel(nhis9$male, ref='Male')
##Earnings
#nhis9$inc<-Recode(brfss_17$incomg, recodes = "9= NA;1='1_lt15k'; 2='2_15-25k';3='3_25-35k';4='4_35-50k';5='5_50kplus'", as.factor = T)
##employment status
nhis9$employed<- Recode(nhis9$empstat, recodes= " 100:122='unemployed'; 200:217='Employed';220='notinlaborforce'; else=NA", as.factor=T)Submit either a link to an Rpub that has your homework published, or as a emailed Word document
Please answer the following questions, use appropriate figures and statistical output to answer the questions.
- Define your event variable
Death/mortality
- Define a duration or time variable
Data is collected from 2018. The age at death variable is if a respondent experienced the event based on age of of the survey, they are experiencing the event, if not, they are censored,this enables m to look at the variance between mortality rates for immigrants and US citizens based on age
- Define a censoring indicator
The respondent is censored if they did not experience the event. The of death is the censoring indicator
- Estimate the survival function for your outcome and plot it
##age at death
nhis9 <- nhis9 %>%
mutate(death_age = ifelse( mortstat ==1,
mortdody - (year - age),
2010 - (year - age)),
d.event = ifelse(mortstat == 1, 1, 0))
library(survival)
age_fit <- survfit(Surv(death_age, d.event)~ 1,
data = nhis9)
library(ggsurvfit)
age_fit %>%
ggsurvfit() +
add_confidence_interval(type = "ribbon") +
add_quantile() 
This shows that the median age for mortality is about 80-85 years of age. It also shows that the probability of survival declines the older the participants get
- Carry out the following analysis
- Kaplan-Meier survival analysis of the outcome
summary(age_fit)Call: survfit(formula = Surv(death_age, d.event) ~ 1, data = nhis9)
time n.risk n.event survival std.err lower 95% CI upper 95% CI
18 63776 3 1.0000 2.72e-05 0.9999 1.0000
19 62539 1 0.9999 3.15e-05 0.9999 1.0000
20 61335 1 0.9999 3.55e-05 0.9999 1.0000
21 60212 3 0.9999 4.57e-05 0.9998 1.0000
22 59085 5 0.9998 5.93e-05 0.9997 0.9999
23 57928 6 0.9997 7.28e-05 0.9995 0.9998
24 56696 9 0.9995 9.00e-05 0.9993 0.9997
25 55534 7 0.9994 1.02e-04 0.9992 0.9996
26 54347 8 0.9993 1.14e-04 0.9990 0.9995
27 53241 6 0.9991 1.23e-04 0.9989 0.9994
28 52013 12 0.9989 1.40e-04 0.9986 0.9992
29 50800 8 0.9988 1.51e-04 0.9985 0.9990
30 49604 17 0.9984 1.72e-04 0.9981 0.9987
31 48369 14 0.9981 1.88e-04 0.9977 0.9985
32 47233 9 0.9979 1.99e-04 0.9975 0.9983
33 46077 12 0.9977 2.12e-04 0.9973 0.9981
34 44905 10 0.9974 2.24e-04 0.9970 0.9979
35 43763 14 0.9971 2.39e-04 0.9967 0.9976
36 42589 18 0.9967 2.59e-04 0.9962 0.9972
37 41480 15 0.9963 2.75e-04 0.9958 0.9969
38 40304 18 0.9959 2.94e-04 0.9953 0.9965
39 39149 22 0.9953 3.17e-04 0.9947 0.9960
40 37937 14 0.9950 3.32e-04 0.9943 0.9956
41 36629 21 0.9944 3.54e-04 0.9937 0.9951
42 35523 14 0.9940 3.70e-04 0.9933 0.9947
43 34377 27 0.9932 3.99e-04 0.9925 0.9940
44 33208 23 0.9925 4.23e-04 0.9917 0.9934
45 32006 28 0.9917 4.54e-04 0.9908 0.9926
46 30774 34 0.9906 4.91e-04 0.9896 0.9915
47 29592 24 0.9898 5.17e-04 0.9888 0.9908
48 28421 24 0.9889 5.44e-04 0.9879 0.9900
49 27175 38 0.9876 5.88e-04 0.9864 0.9887
50 25957 46 0.9858 6.41e-04 0.9846 0.9871
51 24712 34 0.9845 6.81e-04 0.9831 0.9858
52 23571 47 0.9825 7.37e-04 0.9810 0.9839
53 22417 63 0.9797 8.13e-04 0.9781 0.9813
54 21231 57 0.9771 8.82e-04 0.9754 0.9788
55 20115 76 0.9734 9.75e-04 0.9715 0.9753
56 18946 64 0.9701 1.06e-03 0.9681 0.9722
57 17892 63 0.9667 1.14e-03 0.9645 0.9689
58 16901 66 0.9629 1.22e-03 0.9605 0.9653
59 15950 77 0.9583 1.33e-03 0.9557 0.9609
60 15102 88 0.9527 1.45e-03 0.9499 0.9555
61 14146 84 0.9470 1.56e-03 0.9440 0.9501
62 13295 78 0.9415 1.68e-03 0.9382 0.9448
63 12399 106 0.9334 1.84e-03 0.9298 0.9370
64 11462 86 0.9264 1.97e-03 0.9226 0.9303
65 10724 101 0.9177 2.13e-03 0.9135 0.9219
66 10022 113 0.9074 2.32e-03 0.9028 0.9119
67 9325 84 0.8992 2.47e-03 0.8944 0.9040
68 8668 121 0.8866 2.68e-03 0.8814 0.8919
69 8049 114 0.8741 2.89e-03 0.8684 0.8798
70 7518 137 0.8581 3.14e-03 0.8520 0.8643
71 6965 104 0.8453 3.34e-03 0.8388 0.8519
72 6472 119 0.8298 3.57e-03 0.8228 0.8368
73 5997 125 0.8125 3.81e-03 0.8051 0.8200
74 5552 136 0.7926 4.08e-03 0.7846 0.8006
75 5118 133 0.7720 4.35e-03 0.7635 0.7806
76 4689 113 0.7534 4.58e-03 0.7445 0.7624
77 4325 135 0.7299 4.87e-03 0.7204 0.7395
78 3989 130 0.7061 5.14e-03 0.6961 0.7162
79 3694 117 0.6837 5.37e-03 0.6733 0.6943
80 3389 130 0.6575 5.64e-03 0.6465 0.6686
81 3092 160 0.6235 5.95e-03 0.6119 0.6353
82 2804 159 0.5881 6.24e-03 0.5760 0.6005
83 2526 156 0.5518 6.50e-03 0.5392 0.5647
84 2269 156 0.5139 6.72e-03 0.5008 0.5272
85 2027 211 0.4604 6.96e-03 0.4469 0.4742
86 1502 265 0.3791 7.30e-03 0.3651 0.3937
87 1237 275 0.2949 7.24e-03 0.2810 0.3094
88 962 235 0.2228 6.83e-03 0.2098 0.2366
89 727 184 0.1664 6.24e-03 0.1546 0.1791
90 543 157 0.1183 5.49e-03 0.1080 0.1296
91 386 142 0.0748 4.53e-03 0.0664 0.0842
92 244 115 0.0395 3.38e-03 0.0334 0.0468
93 129 81 0.0147 2.10e-03 0.0111 0.0195
94 48 48 0.0000 NaN NA NA- Define a grouping variable, this can be dichotomous or categorical.
The grouping variable I would like to use is citizenship status(citizen) to see if mortality varies between non citizens and US citizens
- Do you have a research hypothesis about the survival patterns for the levels of the categorical variable? State it.
The hypothesis I would like to state is that overtime mortality rates of non-citizens mirrors that of US born the longer they reside in the United States. This takes into account SES(in this case living above or below the poverty threshold)
- Comparison of Kaplan-Meier survival across grouping variables in your data. Interpret your results
library(survival)
citfit <-survfit(Surv(death_age, d.event) ~ mycitizen+poor,
data = nhis9)
summary(citfit)Call: survfit(formula = Surv(death_age, d.event) ~ mycitizen + poor,
data = nhis9)
7832 observations deleted due to missingness
mycitizen=0, poor=0
time n.risk n.event survival std.err lower 95% CI upper 95% CI
18 42337 2 1.0000 3.34e-05 0.9999 1.0000
20 40900 1 0.9999 4.14e-05 0.9998 1.0000
21 40302 2 0.9999 5.43e-05 0.9998 1.0000
22 39689 4 0.9998 7.40e-05 0.9996 0.9999
23 39017 3 0.9997 8.63e-05 0.9995 0.9999
24 38289 6 0.9995 1.07e-04 0.9993 0.9998
25 37596 5 0.9994 1.23e-04 0.9992 0.9997
26 36880 4 0.9993 1.34e-04 0.9990 0.9996
27 36173 2 0.9992 1.40e-04 0.9990 0.9995
28 35403 6 0.9991 1.56e-04 0.9988 0.9994
29 34634 2 0.9990 1.61e-04 0.9987 0.9993
30 33878 8 0.9988 1.81e-04 0.9984 0.9991
31 33144 5 0.9986 1.93e-04 0.9983 0.9990
32 32447 4 0.9985 2.03e-04 0.9981 0.9989
33 31747 9 0.9982 2.24e-04 0.9978 0.9987
34 31012 7 0.9980 2.39e-04 0.9975 0.9985
35 30295 9 0.9977 2.59e-04 0.9972 0.9982
36 29580 9 0.9974 2.78e-04 0.9969 0.9979
37 28892 11 0.9970 3.00e-04 0.9964 0.9976
38 28147 10 0.9967 3.21e-04 0.9960 0.9973
39 27432 14 0.9962 3.48e-04 0.9955 0.9968
40 26638 8 0.9959 3.64e-04 0.9951 0.9966
41 25772 14 0.9953 3.91e-04 0.9946 0.9961
42 25040 6 0.9951 4.03e-04 0.9943 0.9959
43 24274 18 0.9943 4.39e-04 0.9935 0.9952
44 23485 13 0.9938 4.64e-04 0.9929 0.9947
45 22652 18 0.9930 5.00e-04 0.9920 0.9940
46 21831 22 0.9920 5.43e-04 0.9909 0.9931
47 21038 14 0.9913 5.70e-04 0.9902 0.9925
48 20238 16 0.9906 6.03e-04 0.9894 0.9917
49 19360 18 0.9896 6.40e-04 0.9884 0.9909
50 18499 28 0.9881 6.99e-04 0.9868 0.9895
51 17616 18 0.9871 7.38e-04 0.9857 0.9886
52 16775 36 0.9850 8.16e-04 0.9834 0.9866
53 15941 43 0.9824 9.09e-04 0.9806 0.9841
54 15092 37 0.9799 9.89e-04 0.9780 0.9819
55 14271 43 0.9770 1.08e-03 0.9749 0.9791
56 13436 37 0.9743 1.17e-03 0.9720 0.9766
57 12666 40 0.9712 1.26e-03 0.9688 0.9737
58 11930 39 0.9681 1.36e-03 0.9654 0.9707
59 11235 42 0.9644 1.46e-03 0.9616 0.9673
60 10620 55 0.9594 1.60e-03 0.9563 0.9626
61 9913 58 0.9538 1.75e-03 0.9504 0.9573
62 9266 52 0.9485 1.89e-03 0.9448 0.9522
63 8590 77 0.9400 2.11e-03 0.9358 0.9441
64 7873 62 0.9326 2.29e-03 0.9281 0.9371
65 7323 75 0.9230 2.52e-03 0.9181 0.9280
66 6820 79 0.9123 2.76e-03 0.9069 0.9178
67 6307 59 0.9038 2.95e-03 0.8980 0.9096
68 5810 89 0.8899 3.25e-03 0.8836 0.8963
69 5384 76 0.8774 3.51e-03 0.8705 0.8843
70 5019 94 0.8610 3.83e-03 0.8535 0.8685
71 4645 76 0.8469 4.10e-03 0.8389 0.8549
72 4286 87 0.8297 4.41e-03 0.8211 0.8384
73 3956 93 0.8102 4.75e-03 0.8009 0.8195
74 3655 92 0.7898 5.08e-03 0.7799 0.7998
75 3359 99 0.7665 5.44e-03 0.7559 0.7772
76 3061 84 0.7455 5.76e-03 0.7343 0.7568
77 2802 97 0.7197 6.13e-03 0.7078 0.7318
78 2574 89 0.6948 6.46e-03 0.6822 0.7075
79 2371 86 0.6696 6.77e-03 0.6564 0.6830
80 2166 97 0.6396 7.12e-03 0.6258 0.6537
81 1969 100 0.6071 7.46e-03 0.5927 0.6219
82 1788 113 0.5687 7.81e-03 0.5536 0.5843
83 1606 100 0.5333 8.09e-03 0.5177 0.5494
84 1438 105 0.4944 8.34e-03 0.4783 0.5110
85 1279 136 0.4418 8.59e-03 0.4253 0.4590
86 984 172 0.3646 8.88e-03 0.3476 0.3824
87 812 189 0.2797 8.70e-03 0.2632 0.2973
88 623 149 0.2128 8.16e-03 0.1974 0.2294
89 474 113 0.1621 7.48e-03 0.1481 0.1774
90 361 113 0.1114 6.49e-03 0.0993 0.1248
91 248 91 0.0705 5.34e-03 0.0608 0.0818
92 157 73 0.0377 4.00e-03 0.0306 0.0464
93 84 52 0.0144 2.51e-03 0.0102 0.0202
94 32 32 0.0000 NaN NA NA
mycitizen=0, poor=1
time n.risk n.event survival std.err lower 95% CI upper 95% CI
18 6437 1 0.9998 0.000155 0.99954 1.0000
21 5657 1 0.9997 0.000235 0.99921 1.0000
23 5227 2 0.9993 0.000358 0.99858 1.0000
24 5029 3 0.9987 0.000497 0.99772 0.9997
25 4847 1 0.9985 0.000538 0.99743 0.9995
26 4696 1 0.9983 0.000578 0.99714 0.9994
27 4564 2 0.9978 0.000655 0.99655 0.9991
28 4440 3 0.9972 0.000762 0.99567 0.9987
29 4318 2 0.9967 0.000828 0.99507 0.9983
30 4189 6 0.9953 0.001012 0.99329 0.9973
31 4059 3 0.9945 0.001096 0.99239 0.9967
32 3936 2 0.9940 0.001153 0.99177 0.9963
33 3815 2 0.9935 0.001210 0.99114 0.9959
34 3714 2 0.9930 0.001267 0.99049 0.9955
35 3611 1 0.9927 0.001296 0.99016 0.9952
36 3514 3 0.9918 0.001384 0.98914 0.9946
37 3413 1 0.9916 0.001414 0.98879 0.9943
38 3304 5 0.9901 0.001563 0.98700 0.9931
39 3201 3 0.9891 0.001651 0.98590 0.9924
40 3112 2 0.9885 0.001710 0.98515 0.9919
41 3017 2 0.9878 0.001770 0.98438 0.9913
42 2911 4 0.9865 0.001893 0.98278 0.9902
43 2826 6 0.9844 0.002074 0.98033 0.9885
44 2734 5 0.9826 0.002221 0.97825 0.9869
45 2641 6 0.9804 0.002395 0.97567 0.9851
46 2547 5 0.9784 0.002540 0.97346 0.9834
47 2433 4 0.9768 0.002661 0.97162 0.9821
48 2323 6 0.9743 0.002846 0.96874 0.9799
49 2211 10 0.9699 0.003156 0.96373 0.9761
50 2106 7 0.9667 0.003372 0.96008 0.9733
51 2024 6 0.9638 0.003560 0.95685 0.9708
52 1940 8 0.9598 0.003812 0.95239 0.9673
53 1854 8 0.9557 0.004067 0.94775 0.9637
54 1762 11 0.9497 0.004422 0.94109 0.9584
55 1681 19 0.9390 0.005011 0.92922 0.9489
56 1584 18 0.9283 0.005549 0.91750 0.9393
57 1488 6 0.9246 0.005734 0.91340 0.9359
58 1419 12 0.9168 0.006113 0.90485 0.9288
59 1338 20 0.9031 0.006746 0.88992 0.9164
60 1273 21 0.8882 0.007377 0.87381 0.9027
61 1200 13 0.8785 0.007764 0.86345 0.8939
62 1143 15 0.8670 0.008213 0.85105 0.8833
63 1070 16 0.8540 0.008707 0.83714 0.8713
64 1002 14 0.8421 0.009150 0.82436 0.8602
65 953 10 0.8333 0.009471 0.81491 0.8520
66 914 16 0.8187 0.009983 0.79935 0.8385
67 860 10 0.8092 0.010311 0.78920 0.8296
68 817 20 0.7894 0.010969 0.76815 0.8111
69 760 17 0.7717 0.011529 0.74943 0.7946
70 717 19 0.7512 0.012141 0.72783 0.7754
71 664 13 0.7365 0.012569 0.71231 0.7616
72 625 14 0.7200 0.013038 0.69494 0.7461
73 575 13 0.7038 0.013503 0.67779 0.7307
74 527 15 0.6837 0.014074 0.65670 0.7119
75 486 17 0.6598 0.014729 0.63157 0.6893
76 445 13 0.6405 0.015238 0.61136 0.6711
77 410 12 0.6218 0.015724 0.59173 0.6534
78 386 21 0.5880 0.016510 0.55648 0.6212
79 356 9 0.5731 0.016820 0.54106 0.6070
80 331 12 0.5523 0.017246 0.51953 0.5872
81 309 18 0.5201 0.017831 0.48635 0.5563
82 274 17 0.4879 0.018363 0.45318 0.5252
83 242 23 0.4415 0.018993 0.40581 0.4803
84 206 15 0.4094 0.019339 0.37316 0.4491
85 187 14 0.3787 0.019549 0.34227 0.4190
86 137 24 0.3124 0.020280 0.27505 0.3548
87 113 33 0.2211 0.019613 0.18586 0.2631
88 80 13 0.1852 0.018788 0.15182 0.2259
89 67 21 0.1272 0.016630 0.09841 0.1643
90 46 13 0.0912 0.014615 0.06664 0.1249
91 33 8 0.0691 0.012996 0.04780 0.0999
92 25 10 0.0415 0.010327 0.02545 0.0676
93 15 9 0.0166 0.006676 0.00754 0.0365
94 6 6 0.0000 NaN NA NA
mycitizen=1, poor=0
time n.risk n.event survival std.err lower 95% CI upper 95% CI
22 4600 1 0.9998 0.000217 0.99936 1.000
25 4306 1 0.9996 0.000318 0.99893 1.000
28 3899 1 0.9993 0.000408 0.99849 1.000
29 3764 1 0.9990 0.000487 0.99807 1.000
30 3630 1 0.9988 0.000559 0.99766 1.000
31 3480 2 0.9982 0.000691 0.99683 1.000
35 2857 1 0.9978 0.000774 0.99631 0.999
36 2697 2 0.9971 0.000933 0.99526 0.999
37 2549 2 0.9963 0.001084 0.99418 0.998
38 2404 1 0.9959 0.001160 0.99362 0.998
39 2260 1 0.9955 0.001241 0.99302 0.998
40 2124 3 0.9940 0.001481 0.99115 0.997
41 1987 2 0.9930 0.001640 0.98984 0.996
42 1874 3 0.9915 0.001876 0.98779 0.995
43 1763 2 0.9903 0.002036 0.98635 0.994
44 1647 1 0.9897 0.002122 0.98558 0.994
45 1540 1 0.9891 0.002215 0.98475 0.993
46 1437 3 0.9870 0.002511 0.98211 0.992
47 1344 1 0.9863 0.002615 0.98118 0.991
48 1261 1 0.9855 0.002727 0.98018 0.991
49 1148 4 0.9821 0.003213 0.97580 0.988
50 1073 2 0.9802 0.003458 0.97349 0.987
51 991 3 0.9773 0.003848 0.96976 0.985
53 852 3 0.9738 0.004317 0.96541 0.982
54 781 1 0.9726 0.004488 0.96383 0.981
55 711 5 0.9657 0.005399 0.95522 0.976
56 643 2 0.9627 0.005785 0.95147 0.974
57 588 4 0.9562 0.006608 0.94333 0.969
58 533 3 0.9508 0.007265 0.93668 0.965
59 482 3 0.9449 0.007983 0.92938 0.961
60 448 3 0.9386 0.008725 0.92162 0.956
61 408 4 0.9294 0.009778 0.91040 0.949
62 376 2 0.9244 0.010332 0.90439 0.945
63 349 1 0.9218 0.010636 0.90116 0.943
65 288 4 0.9090 0.012264 0.88525 0.933
66 259 2 0.9020 0.013136 0.87657 0.928
67 237 4 0.8867 0.014957 0.85789 0.917
68 216 2 0.8785 0.015906 0.84789 0.910
69 193 3 0.8649 0.017504 0.83123 0.900
70 173 1 0.8599 0.018102 0.82510 0.896
71 157 2 0.8489 0.019458 0.81162 0.888
74 117 5 0.8126 0.024473 0.76605 0.862
75 102 5 0.7728 0.029042 0.71792 0.832
77 81 3 0.7442 0.032328 0.68343 0.810
78 72 1 0.7338 0.033490 0.67105 0.803
79 65 3 0.7000 0.037218 0.63069 0.777
80 59 2 0.6762 0.039558 0.60299 0.758
81 51 5 0.6099 0.045453 0.52706 0.706
83 40 2 0.5794 0.048024 0.49257 0.682
84 36 3 0.5312 0.051482 0.43926 0.642
85 29 3 0.4762 0.055070 0.37963 0.597
87 15 3 0.3810 0.066029 0.27124 0.535
88 12 3 0.2857 0.068704 0.17835 0.458
89 9 5 0.1270 0.056322 0.05324 0.303
90 4 2 0.0635 0.042437 0.01713 0.235
92 2 1 0.0317 0.030890 0.00472 0.214
94 1 1 0.0000 NaN NA NA
mycitizen=1, poor=1
time n.risk n.event survival std.err lower 95% CI upper 95% CI
27 1852 2 0.9989 0.000763 0.9974 1.000
30 1637 1 0.9983 0.000977 0.9964 1.000
31 1551 1 0.9977 0.001169 0.9954 1.000
34 1336 1 0.9969 0.001386 0.9942 1.000
35 1256 2 0.9953 0.001782 0.9918 0.999
36 1176 1 0.9945 0.001971 0.9906 0.998
37 1104 1 0.9936 0.002165 0.9894 0.998
39 962 2 0.9915 0.002607 0.9864 0.997
41 827 1 0.9903 0.002866 0.9847 0.996
43 720 1 0.9889 0.003175 0.9827 0.995
44 661 3 0.9845 0.004084 0.9765 0.992
46 553 2 0.9809 0.004782 0.9716 0.990
47 504 2 0.9770 0.005499 0.9663 0.988
50 403 1 0.9746 0.005996 0.9629 0.986
51 370 1 0.9719 0.006533 0.9592 0.985
52 345 1 0.9691 0.007095 0.9553 0.983
53 314 3 0.9599 0.008814 0.9427 0.977
54 289 1 0.9565 0.009389 0.9383 0.975
55 274 2 0.9496 0.010538 0.9291 0.970
56 256 1 0.9459 0.011131 0.9243 0.968
58 226 1 0.9417 0.011842 0.9187 0.965
59 206 1 0.9371 0.012636 0.9127 0.962
61 169 1 0.9316 0.013724 0.9050 0.959
62 155 1 0.9255 0.014894 0.8968 0.955
64 133 3 0.9047 0.018813 0.8685 0.942
67 99 1 0.8955 0.020724 0.8558 0.937
68 91 1 0.8857 0.022713 0.8423 0.931
69 82 1 0.8749 0.024872 0.8275 0.925
70 74 1 0.8631 0.027201 0.8114 0.918
72 60 2 0.8343 0.033037 0.7720 0.902
73 56 2 0.8045 0.037986 0.7334 0.883
74 52 2 0.7736 0.042360 0.6948 0.861
76 43 2 0.7376 0.047418 0.6503 0.837
77 37 1 0.7176 0.050152 0.6258 0.823
78 32 1 0.6952 0.053364 0.5981 0.808
79 28 1 0.6704 0.056942 0.5676 0.792
80 25 1 0.6436 0.060651 0.5350 0.774
81 21 1 0.6129 0.065046 0.4978 0.755
82 18 1 0.5789 0.069778 0.4571 0.733
84 15 1 0.5403 0.075043 0.4115 0.709
86 8 2 0.4052 0.100046 0.2498 0.657
87 6 1 0.3377 0.103691 0.1850 0.616
90 5 1 0.2701 0.102615 0.1283 0.569
91 4 1 0.2026 0.096664 0.0795 0.516
92 3 2 0.0675 0.063866 0.0106 0.431
94 1 1 0.0000 NaN NA NAImportant to note:
Poor is coded, 0 for above the poverty threshold and 1 for below the poverty threshold Being a U.S citizen is coded 0 as being a citizen and 1 for not being a citizen
Interpretation of the results:
The data shows that U.S citizens both above and below the poverty line have a lesser probability of survival compared to non- U.S citizens above and below the poverty line.
The results including the graph below, also show that citizens below the poverty line have a lower probability of survival while non-citizens below the poverty threshold outlive both citizens and non-citizens above the poverty threshold. This therefore shows that my hypothesis is null because non-citizens out live U.S citizens. The paradox could probably support these results where we see immigrants living longer with low SES
##comparing the difference be difference among groups
survdiff(Surv(death_age, d.event) ~ mycitizen+poor,
data = nhis9)Call:
survdiff(formula = Surv(death_age, d.event) ~ mycitizen + poor,
data = nhis9)
n=55944, 7832 observations deleted due to missingness.
N Observed Expected (O-E)^2/E (O-E)^2/V
mycitizen=0, poor=0 42337 3847 4036.0 8.8470 61.8517
mycitizen=0, poor=1 6437 743 554.0 64.4437 80.9583
mycitizen=1, poor=0 4861 136 137.8 0.0231 0.0253
mycitizen=1, poor=1 2309 64 62.2 0.0513 0.0568
Chisq= 81.5 on 3 degrees of freedom, p= <2e-16 This shows that there is a difference in survival status first among those living above and below the poverty threshold as well as those who are citizens and not citizens. This is seen by looking at the differences between the observed v. expected deaths as well as by looking at the huge difference between the Chisq and the p value
e.Plot the survival function for the analysis for each level of the group variable
citfit%>%
ggsurvfit(xlim=c(0,12),
ylim=c(.90, 4),
conf.int=T,
title="Survival Function for mortality - citizen vs non citizen")Warning: Ignoring unknown parameters: xlim, ylim, conf.int, title
Citations: Lynn A. Blewett, Julia A. Rivera Drew, Miriam L. King, Kari C.W. Williams, Natalie Del Ponte and Pat Convey. IPUMS Health Surveys: National Health Interview Survey, Version 7.1 [dataset]. Minneapolis, MN: IPUMS, 2021. https://doi.org/10.18128/D070.V7.1