Flu 2019 Models

Load Packages

library(tidyverse)
library(codebookr)
library(summarytools)
library(broom) 
library(performance)
library(gt)
library(gtsummary)
library(janitor)
library(forcats)
library(margins)
library(ggplot2)
library(expss)
library(glmtoolbox)
library(DescTools)

Import Data

load("~/Desktop/R-Code/SDOH_Vax/flu_2019_later_1.8.22.rda")
View(flu_2019_later_1.8.22)

Include only patients from Michigan

flu_2019_MI <- flu_2019_later_1.8.22[ which(flu_2019_later_1.8.22$PATIENT_STATE_CD=='MI'), ]

codebook

flu_2019_MI %>% 
dplyr::select(ibd_3, age_yrs, gender, race_5, ethnic_3, lang_3, relig_affil, mstat_5, max_ch, PATIENT_STATE_CD, r_pct, IC, insurance, pop_dens, RPL_THEMES, RPL_4, RPL_THEME1, RPL_THEME2, RPL_THEME3, RPL_THEME4, act_tob, flu_2019, , prevnar, pvax, any_pneum, any_pneum, total_cov_vax, total_shingrix) -> flu_clean1
print(dfSummary(flu_clean1), method = 'render')

Data Frame Summary

flu_clean1

Dimensions: 11050 x 27
Duplicates: 0

No	Variable	Label	Stats / Values	Freqs (% of Valid)	Graph	Valid	Missing
1	ibd_3 [labelled, factor]	IBD Diagnosis	1. CD 2. UC 3. IC 4. Unknown	5508 ( 49.8% ) 5468 ( 49.5% ) 2 ( 0.0% ) 72 ( 0.7% )		11050 (100.0%)	0 (0.0%)
2	age_yrs [labelled, numeric]	Age	Mean (sd) : 48.8 (19.4) min ≤ med ≤ max: 1 ≤ 49.2 ≤ 99.9 IQR (CV) : 31.5 (0.4)	8992 distinct values		11050 (100.0%)	0 (0.0%)
3	gender [labelled, factor]	Gender	1. Male 2. Female	5029 ( 45.5% ) 6021 ( 54.5% )		11050 (100.0%)	0 (0.0%)
4	race_5 [labelled, factor]	Race	1. White 2. Black 3. Asian or Pacific Islander 4. American Indian or Alaska 5. Other	9554 ( 86.5% ) 724 ( 6.6% ) 277 ( 2.5% ) 42 ( 0.4% ) 453 ( 4.1% )		11050 (100.0%)	0 (0.0%)
5	ethnic_3 [labelled, factor]	Ethnicity	1. Hispanic 2. Non-Hispanic	231 ( 2.2% ) 10489 ( 97.8% )		10720 (97.0%)	330 (3.0%)
6	lang_3 [labelled, factor]	Preferred Language	1. English 2. Other	10933 ( 98.9% ) 117 ( 1.1% )		11050 (100.0%)	0 (0.0%)
7	relig_affil [labelled, factor]	Any Religious Affiliation	1. Yes 2. No	6071 ( 57.7% ) 4451 ( 42.3% )		10522 (95.2%)	528 (4.8%)
8	mstat_5 [labelled, factor]	Marital Status	1. Married 2. Single 3. Divorced/Separated 4. Widowed	4347 ( 52.6% ) 3383 ( 40.9% ) 338 ( 4.1% ) 194 ( 2.3% )		8262 (74.8%)	2788 (25.2%)
9	max_ch [labelled, numeric]	Charlson Comorbidity Index	Mean (sd) : 3.5 (5) min ≤ med ≤ max: 0 ≤ 1 ≤ 27 IQR (CV) : 5 (1.4)	28 distinct values		11050 (100.0%)	0 (0.0%)
10	PATIENT_STATE_CD [labelled, character]	State	1. MI	11050 ( 100.0% )		11050 (100.0%)	0 (0.0%)
11	r_pct [labelled, numeric]	Percentage Republican Voters in Census Tract	Mean (sd) : 44.5 (17.9) min ≤ med ≤ max: 1.8 ≤ 47.6 ≤ 81.2 IQR (CV) : 24.7 (0.4)	1922 distinct values		9469 (85.7%)	1581 (14.3%)
12	IC [labelled, numeric]	Immunocompromised	Min : 0 Mean : 0.6 Max : 1	0 : 3602 ( 38.0% ) 1 : 5872 ( 62.0% )		9474 (85.7%)	1576 (14.3%)
13	insurance [labelled, factor]	Insurance Type	1. Private Insurance 2. Medicaid 3. Medicare 4. Other Governmental 5. Other	7001 ( 63.5% ) 1747 ( 15.8% ) 2142 ( 19.4% ) 95 ( 0.9% ) 47 ( 0.4% )		11032 (99.8%)	18 (0.2%)
14	pop_dens [labelled, numeric]	Population Density of Census Tract	Mean (sd) : 2137 (2277.7) min ≤ med ≤ max: 2.5 ≤ 1520.7 ≤ 19280.6 IQR (CV) : 2957.6 (1.1)	2105 distinct values		10799 (97.7%)	251 (2.3%)
15	RPL_THEMES [labelled, numeric]	Social Vulnerability Index	Mean (sd) : 0.4 (0.3) min ≤ med ≤ max: 0 ≤ 0.3 ≤ 1 IQR (CV) : 0.4 (0.7)	2099 distinct values		11014 (99.7%)	36 (0.3%)
16	RPL_4 [labelled, factor]	SVI by Quartile	1. First 2. Second 3. Third 4. Fourth	4472 ( 40.6% ) 3317 ( 30.1% ) 2170 ( 19.7% ) 1055 ( 9.6% )		11014 (99.7%)	36 (0.3%)
17	RPL_THEME1 [labelled, numeric]	Socioeconomic Status	Mean (sd) : 0.3 (0.3) min ≤ med ≤ max: 0 ≤ 0.3 ≤ 1 IQR (CV) : 0.4 (0.7)	2062 distinct values		10970 (99.3%)	80 (0.7%)
18	RPL_THEME2 [labelled, numeric]	Household Composition	Mean (sd) : 0.4 (0.3) min ≤ med ≤ max: 0 ≤ 0.3 ≤ 1 IQR (CV) : 0.4 (0.7)	2018 distinct values		11014 (99.7%)	36 (0.3%)
19	RPL_THEME3 [labelled, numeric]	Minority and Language Status	Mean (sd) : 0.5 (0.3) min ≤ med ≤ max: 0 ≤ 0.5 ≤ 1 IQR (CV) : 0.5 (0.6)	1434 distinct values		11020 (99.7%)	30 (0.3%)
20	RPL_THEME4 [labelled, numeric]	Housing and Transportation	Mean (sd) : 0.4 (0.3) min ≤ med ≤ max: 0 ≤ 0.4 ≤ 1 IQR (CV) : 0.5 (0.7)	2034 distinct values		10997 (99.5%)	53 (0.5%)
21	act_tob [labelled, factor]	Active Tobacco Use	1. No 2. Yes	9574 ( 88.0% ) 1305 ( 12.0% )		10879 (98.5%)	171 (1.5%)
22	flu_2019 [labelled, numeric]	2019 Flu Vaccination	Min : 0 Mean : 0.4 Max : 1	0 : 6708 ( 60.7% ) 1 : 4342 ( 39.3% )		11050 (100.0%)	0 (0.0%)
23	prevnar [labelled, numeric]	Pneumococcal Conjugate Vaccination	Mean (sd) : 0.4 (0.6) min ≤ med ≤ max: 0 ≤ 0 ≤ 8 IQR (CV) : 1 (1.4)	0 : 6938 ( 62.8% ) 1 : 3856 ( 34.9% ) 2 : 198 ( 1.8% ) 3 : 27 ( 0.2% ) 4 : 24 ( 0.2% ) 5 : 4 ( 0.0% ) 6 : 1 ( 0.0% ) 7 : 1 ( 0.0% ) 8 : 1 ( 0.0% )		11050 (100.0%)	0 (0.0%)
24	pvax [labelled, numeric]	Pneumococcal Polysaccharide Vaccination	Mean (sd) : 0.4 (0.5) min ≤ med ≤ max: 0 ≤ 0 ≤ 6 IQR (CV) : 1 (1.5)	0 : 7439 ( 67.3% ) 1 : 3336 ( 30.2% ) 2 : 261 ( 2.4% ) 3 : 11 ( 0.1% ) 5 : 1 ( 0.0% ) 6 : 2 ( 0.0% )		11050 (100.0%)	0 (0.0%)
25	any_pneum [labelled, numeric]	Any Pneumonia Vaccine	Mean (sd) : 0.8 (0.9) min ≤ med ≤ max: 0 ≤ 0 ≤ 9 IQR (CV) : 1 (1.3)	0 : 5916 ( 53.5% ) 1 : 2397 ( 21.7% ) 2 : 2361 ( 21.4% ) 3 : 289 ( 2.6% ) 4 : 61 ( 0.6% ) 5 : 15 ( 0.1% ) 6 : 7 ( 0.1% ) 7 : 2 ( 0.0% ) 8 : 1 ( 0.0% ) 9 : 1 ( 0.0% )		11050 (100.0%)	0 (0.0%)
26	total_cov_vax [labelled, numeric]	Total Number of COVID-19 Vaccines	Mean (sd) : 1.9 (1.6) min ≤ med ≤ max: 0 ≤ 2 ≤ 7 IQR (CV) : 3 (0.8)	0 : 3894 ( 35.2% ) 1 : 397 ( 3.6% ) 2 : 2056 ( 18.6% ) 3 : 3045 ( 27.6% ) 4 : 1455 ( 13.2% ) 5 : 157 ( 1.4% ) 6 : 37 ( 0.3% ) 7 : 9 ( 0.1% )		11050 (100.0%)	0 (0.0%)
27	total_shingrix [labelled, numeric]	Total Number of Zoster Vaccines	Mean (sd) : 0.3 (0.7) min ≤ med ≤ max: 0 ≤ 0 ≤ 5 IQR (CV) : 0 (2.6)	0 : 9529 ( 86.2% ) 1 : 343 ( 3.1% ) 2 : 1081 ( 9.8% ) 3 : 86 ( 0.8% ) 4 : 9 ( 0.1% ) 5 : 2 ( 0.0% )		11050 (100.0%)	0 (0.0%)

Generated by summarytools 1.0.1 (R version 4.2.2)
2023-01-08

Patient Characteristics

Baseline Characteristics

flu_clean1 %>% 
  dplyr::select(ibd_3, age_yrs, gender, race_5, ethnic_3, lang_3, relig_affil, mstat_5, act_tob, max_ch, insurance, IC, pop_dens,r_pct, RPL_THEMES, RPL_4, RPL_THEME1, RPL_THEME2, RPL_THEME3, RPL_THEME4, flu_2019) -> baseline
baseline %>% tbl_summary(
        statistic = list(all_continuous() ~ "{mean} ({sd})"),
        missing_text = "(Missing)")

Characteristic	N = 11,0501
IBD Diagnosis
CD	5,508 (50%)
UC	5,468 (49%)
IC	2 (<0.1%)
Unknown	72 (0.7%)
Age	49 (19)
Gender
Male	5,029 (46%)
Female	6,021 (54%)
Race
White	9,554 (86%)
Black	724 (6.6%)
Asian or Pacific Islander	277 (2.5%)
American Indian or Alaska Native	42 (0.4%)
Other	453 (4.1%)
Ethnicity
Hispanic	231 (2.2%)
Non-Hispanic	10,489 (98%)
(Missing)	330
Preferred Language
English	10,933 (99%)
Other	117 (1.1%)
Any Religious Affiliation	6,071 (58%)
(Missing)	528
Marital Status
Married	4,347 (53%)
Single	3,383 (41%)
Divorced/Separated	338 (4.1%)
Widowed	194 (2.3%)
(Missing)	2,788
Active Tobacco Use	1,305 (12%)
(Missing)	171
Charlson Comorbidity Index	3.5 (5.0)
Insurance Type
Private Insurance	7,001 (63%)
Medicaid	1,747 (16%)
Medicare	2,142 (19%)
Other Governmental	95 (0.9%)
Other	47 (0.4%)
(Missing)	18
Immunocompromised	5,872 (62%)
(Missing)	1,576
Population Density of Census Tract	2,137 (2,278)
(Missing)	251
Percentage Republican Voters in Census Tract	45 (18)
(Missing)	1,581
Social Vulnerability Index	0.36 (0.26)
(Missing)	36
SVI by Quartile
First	4,472 (41%)
Second	3,317 (30%)
Third	2,170 (20%)
Fourth	1,055 (9.6%)
(Missing)	36
Socioeconomic Status	0.34 (0.25)
(Missing)	80
Household Composition	0.39 (0.26)
(Missing)	36
Minority and Language Status	0.48 (0.29)
(Missing)	30
Housing and Transportation	0.43 (0.29)
(Missing)	53
2019 Flu Vaccination	4,342 (39%)
1 n (%); Mean (SD)

Baseline characteristics by SVI Quartile

flu_clean1 %>% tbl_summary(by = RPL_4,
        statistic = list(all_continuous() ~ "{mean} ({sd})"),
        missing_text = "(Missing)") %>% add_p()

36 observations missing `RPL_4` have been removed. To include these observations, use `forcats::fct_explicit_na()` on `RPL_4` column before passing to `tbl_summary()`.
There was an error in 'add_p()/add_difference()' for variable 'ibd_3', p-value omitted:
Error in stats::fisher.test(structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, : FEXACT error 501.
The hash table key cannot be computed because the largest key
is larger than the largest representable int.
The algorithm cannot proceed.
Reduce the workspace, consider using 'simulate.p.value=TRUE' or another algorithm.
There was an error in 'add_p()/add_difference()' for variable 'race_5', p-value omitted:
Error in stats::fisher.test(structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, : FEXACT error 5.
The hash table key cannot be computed because the largest key
is larger than the largest representable int.
The algorithm cannot proceed.
Reduce the workspace, consider using 'simulate.p.value=TRUE' or another algorithm.
There was an error in 'add_p()/add_difference()' for variable 'PATIENT_STATE_CD', p-value omitted:
Error in stats::chisq.test(x = structure(c("MI", "MI", "MI", "MI", "MI", : 'x' and 'y' must have at least 2 levels
There was an error in 'add_p()/add_difference()' for variable 'insurance', p-value omitted:
Error in stats::fisher.test(structure(c(1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, : FEXACT error 5.
The hash table key cannot be computed because the largest key
is larger than the largest representable int.
The algorithm cannot proceed.
Reduce the workspace, consider using 'simulate.p.value=TRUE' or another algorithm.
There was an error in 'add_p()/add_difference()' for variable 'prevnar', p-value omitted:
Error in stats::fisher.test(structure(c(1, 1, 2, 0, 1, 0, 0, 0, 0, 1, : FEXACT error 5.
The hash table key cannot be computed because the largest key
is larger than the largest representable int.
The algorithm cannot proceed.
Reduce the workspace, consider using 'simulate.p.value=TRUE' or another algorithm.
There was an error in 'add_p()/add_difference()' for variable 'pvax', p-value omitted:
Error in stats::fisher.test(structure(c(1, 0, 2, 0, 0, 1, 0, 0, 0, 0, : FEXACT error 5.
The hash table key cannot be computed because the largest key
is larger than the largest representable int.
The algorithm cannot proceed.
Reduce the workspace, consider using 'simulate.p.value=TRUE' or another algorithm.
There was an error in 'add_p()/add_difference()' for variable 'total_cov_vax', p-value omitted:
Error in stats::fisher.test(structure(c(2, 1, 3, 1, 3, 2, 0, 0, 4, 3, : FEXACT error 5.
The hash table key cannot be computed because the largest key
is larger than the largest representable int.
The algorithm cannot proceed.
Reduce the workspace, consider using 'simulate.p.value=TRUE' or another algorithm.
There was an error in 'add_p()/add_difference()' for variable 'total_shingrix', p-value omitted:
Error in stats::fisher.test(structure(c(0, 0, 2, 0, 0, 0, 0, 0, 2, 0, : FEXACT error 5.
The hash table key cannot be computed because the largest key
is larger than the largest representable int.
The algorithm cannot proceed.
Reduce the workspace, consider using 'simulate.p.value=TRUE' or another algorithm.

Characteristic	First, N = 4,4721	Second, N = 3,3171	Third, N = 2,1701	Fourth, N = 1,0551	p-value2
IBD Diagnosis
CD	2,097 (47%)	1,621 (49%)	1,147 (53%)	625 (59%)
UC	2,346 (52%)	1,673 (50%)	1,009 (46%)	424 (40%)
IC	0 (0%)	0 (0%)	1 (<0.1%)	1 (<0.1%)
Unknown	29 (0.6%)	23 (0.7%)	13 (0.6%)	5 (0.5%)
Age	49 (20)	49 (19)	49 (19)	47 (19)	0.003
Gender					0.025
Male	2,091 (47%)	1,519 (46%)	933 (43%)	465 (44%)
Female	2,381 (53%)	1,798 (54%)	1,237 (57%)	590 (56%)
Race
White	4,043 (90%)	2,900 (87%)	1,852 (85%)	729 (69%)
Black	112 (2.5%)	168 (5.1%)	188 (8.7%)	252 (24%)
Asian or Pacific Islander	121 (2.7%)	102 (3.1%)	48 (2.2%)	6 (0.6%)
American Indian or Alaska Native	12 (0.3%)	20 (0.6%)	7 (0.3%)	3 (0.3%)
Other	184 (4.1%)	127 (3.8%)	75 (3.5%)	65 (6.2%)
Ethnicity					0.003
Hispanic	80 (1.8%)	68 (2.1%)	45 (2.1%)	38 (3.7%)
Non-Hispanic	4,251 (98%)	3,157 (98%)	2,064 (98%)	983 (96%)
(Missing)	141	92	61	34
Preferred Language					<0.001
English	4,444 (99%)	3,285 (99%)	2,136 (98%)	1,032 (98%)
Other	28 (0.6%)	32 (1.0%)	34 (1.6%)	23 (2.2%)
Any Religious Affiliation	2,509 (58%)	1,812 (57%)	1,194 (58%)	538 (55%)	0.2
(Missing)	179	163	114	70
Marital Status					<0.001
Married	2,020 (58%)	1,286 (52%)	752 (48%)	280 (39%)
Single	1,294 (37%)	1,002 (41%)	683 (44%)	392 (54%)
Divorced/Separated	91 (2.6%)	118 (4.8%)	89 (5.7%)	40 (5.5%)
Widowed	82 (2.4%)	60 (2.4%)	40 (2.6%)	12 (1.7%)
(Missing)	985	851	606	331
Charlson Comorbidity Index	3.4 (5.0)	3.6 (5.1)	3.5 (5.0)	3.5 (5.0)	0.010
State
MI	4,472 (100%)	3,317 (100%)	2,170 (100%)	1,055 (100%)
Percentage Republican Voters in Census Tract	45 (16)	46 (18)	45 (18)	36 (21)	<0.001
(Missing)	459	601	350	168
Immunocompromised	2,373 (61%)	1,737 (61%)	1,140 (62%)	601 (66%)	0.036
(Missing)	603	479	341	148
Insurance Type
Private Insurance	3,251 (73%)	2,142 (65%)	1,170 (54%)	415 (39%)
Medicaid	391 (8.8%)	482 (15%)	489 (23%)	378 (36%)
Medicare	776 (17%)	638 (19%)	475 (22%)	248 (24%)
Other Governmental	28 (0.6%)	27 (0.8%)	28 (1.3%)	12 (1.1%)
Other	17 (0.4%)	21 (0.6%)	8 (0.4%)	1 (<0.1%)
(Missing)	9	7	0	1
Population Density of Census Tract	1,880 (1,862)	2,086 (2,404)	2,325 (2,522)	3,034 (2,694)	<0.001
(Missing)	34	63	73	50
Social Vulnerability Index	0.12 (0.07)	0.37 (0.07)	0.61 (0.07)	0.86 (0.07)	<0.001
Socioeconomic Status	0.13 (0.11)	0.33 (0.16)	0.57 (0.15)	0.78 (0.11)	<0.001
(Missing)	44	0	0	0
Household Composition	0.21 (0.14)	0.37 (0.21)	0.59 (0.24)	0.76 (0.19)	<0.001
Minority and Language Status	0.41 (0.27)	0.48 (0.29)	0.52 (0.29)	0.66 (0.25)	<0.001
Housing and Transportation	0.19 (0.16)	0.49 (0.20)	0.63 (0.21)	0.81 (0.17)	<0.001
(Missing)	17	0	0	0
Active Tobacco Use	361 (8.2%)	406 (12%)	325 (15%)	207 (20%)	<0.001
(Missing)	49	60	36	25
2019 Flu Vaccination	1,990 (44%)	1,291 (39%)	731 (34%)	317 (30%)	<0.001
Pneumococcal Conjugate Vaccination
0	2,649 (59%)	2,129 (64%)	1,418 (65%)	717 (68%)
1	1,724 (39%)	1,107 (33%)	698 (32%)	317 (30%)
2	80 (1.8%)	63 (1.9%)	37 (1.7%)	17 (1.6%)
3	7 (0.2%)	10 (0.3%)	7 (0.3%)	3 (0.3%)
4	10 (0.2%)	6 (0.2%)	7 (0.3%)	1 (<0.1%)
5	1 (<0.1%)	2 (<0.1%)	1 (<0.1%)	0 (0%)
6	0 (0%)	0 (0%)	1 (<0.1%)	0 (0%)
7	1 (<0.1%)	0 (0%)	0 (0%)	0 (0%)
8	0 (0%)	0 (0%)	1 (<0.1%)	0 (0%)
Pneumococcal Polysaccharide Vaccination
0	2,903 (65%)	2,266 (68%)	1,497 (69%)	744 (71%)
1	1,467 (33%)	952 (29%)	625 (29%)	286 (27%)
2	96 (2.1%)	95 (2.9%)	46 (2.1%)	23 (2.2%)
3	5 (0.1%)	2 (<0.1%)	2 (<0.1%)	2 (0.2%)
5	0 (0%)	1 (<0.1%)	0 (0%)	0 (0%)
6	1 (<0.1%)	1 (<0.1%)	0 (0%)	0 (0%)
Any Pneumonia Vaccine	0.81 (0.95)	0.74 (0.96)	0.72 (0.95)	0.67 (0.91)	<0.001
Total Number of COVID-19 Vaccines
0	1,286 (29%)	1,205 (36%)	872 (40%)	515 (49%)
1	162 (3.6%)	103 (3.1%)	89 (4.1%)	42 (4.0%)
2	815 (18%)	615 (19%)	410 (19%)	211 (20%)
3	1,401 (31%)	871 (26%)	558 (26%)	204 (19%)
4	704 (16%)	464 (14%)	212 (9.8%)	72 (6.8%)
5	84 (1.9%)	44 (1.3%)	21 (1.0%)	8 (0.8%)
6	16 (0.4%)	13 (0.4%)	5 (0.2%)	3 (0.3%)
7	4 (<0.1%)	2 (<0.1%)	3 (0.1%)	0 (0%)
Total Number of Zoster Vaccines
0	3,699 (83%)	2,879 (87%)	1,933 (89%)	985 (93%)
1	163 (3.6%)	86 (2.6%)	72 (3.3%)	22 (2.1%)
2	560 (13%)	324 (9.8%)	154 (7.1%)	40 (3.8%)
3	46 (1.0%)	25 (0.8%)	9 (0.4%)	6 (0.6%)
4	4 (<0.1%)	3 (<0.1%)	1 (<0.1%)	1 (<0.1%)
5	0 (0%)	0 (0%)	1 (<0.1%)	1 (<0.1%)
1 n (%); Mean (SD)
2 Kruskal-Wallis rank sum test; Pearson's Chi-squared test

Bivariate Analysis

tbl_uv_ex1 <-
  tbl_uvregression(
    flu_clean1[c("flu_2019", "ibd_3", "age_yrs", "gender", "race_5", "ethnic_3", "lang_3", "mstat_5", "relig_affil", "act_tob", "max_ch", "IC", "insurance", "pop_dens", "r_pct", "RPL_THEMES", "RPL_THEME1", "RPL_THEME2", "RPL_THEME3", "RPL_THEME4")],
    method = glm,
    method.args = list(family = binomial),
    y = flu_2019,
  exponentiate = TRUE)

Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredWarning: glm.fit: fitted probabilities numerically 0 or 1 occurredWarning: glm.fit: fitted probabilities numerically 0 or 1 occurredWarning: glm.fit: fitted probabilities numerically 0 or 1 occurredWarning: glm.fit: fitted probabilities numerically 0 or 1 occurredWarning: glm.fit: fitted probabilities numerically 0 or 1 occurredWarning: glm.fit: fitted probabilities numerically 0 or 1 occurredWarning: glm.fit: fitted probabilities numerically 0 or 1 occurredWarning: glm.fit: fitted probabilities numerically 0 or 1 occurredWarning: glm.fit: fitted probabilities numerically 0 or 1 occurred

print(tbl_uv_ex1, method = render)

`...` must be empty.
✖ Problematic argument:
• method = render

Characteristic	N	OR1	95% CI1	p-value
IBD Diagnosis	11,050
CD		—	—
UC		0.98	0.91, 1.06	0.6
IC		0.00		>0.9
Unknown		0.47	0.26, 0.79	0.007
Age	11,050	0.99	0.99, 0.99	<0.001
Gender	11,050
Male		—	—
Female		1.10	1.02, 1.19	0.017
Race	11,050
White		—	—
Black		0.74	0.63, 0.86	<0.001
Asian or Pacific Islander		1.72	1.36, 2.19	<0.001
American Indian or Alaska Native		1.26	0.68, 2.31	0.5
Other		0.78	0.64, 0.96	0.017
Ethnicity	10,720
Hispanic		—	—
Non-Hispanic		0.78	0.60, 1.01	0.059
Preferred Language	11,050
English		—	—
Other		0.63	0.42, 0.93	0.024
Marital Status	8,262
Married		—	—
Single		0.96	0.87, 1.05	0.4
Divorced/Separated		0.89	0.71, 1.12	0.3
Widowed		0.58	0.42, 0.79	<0.001
Any Religious Affiliation	10,522
Yes		—	—
No		0.92	0.85, 1.00	0.047
Active Tobacco Use	10,879
No		—	—
Yes		0.70	0.62, 0.79	<0.001
Charlson Comorbidity Index	11,050	1.00	0.99, 1.01	0.9
Immunocompromised	9,474	1.61	1.47, 1.75	<0.001
Insurance Type	11,032
Private Insurance		—	—
Medicaid		0.53	0.47, 0.59	<0.001
Medicare		0.47	0.43, 0.53	<0.001
Other Governmental		0.28	0.16, 0.46	<0.001
Other		1.26	0.71, 2.25	0.4
Population Density of Census Tract	10,799	1.00	1.00, 1.00	<0.001
Percentage Republican Voters in Census Tract	9,469	0.99	0.99, 0.99	<0.001
Social Vulnerability Index	11,014	0.42	0.36, 0.49	<0.001
Socioeconomic Status	10,970	0.39	0.33, 0.45	<0.001
Household Composition	11,014	0.39	0.34, 0.45	<0.001
Minority and Language Status	11,020	1.34	1.17, 1.53	<0.001
Housing and Transportation	10,997	0.62	0.54, 0.71	<0.001
1 OR = Odds Ratio, CI = Confidence Interval

NULL

Flu 2019 with SVI as Continuous Variable

Flu2019_SVI <- glm(flu_2019 ~ ibd_3 + age_yrs + gender + race_5 + ethnic_3 + mstat_5 + relig_affil
                      + lang_3 + act_tob + max_ch + IC + insurance
                      + pop_dens + RPL_THEMES,
              family = "binomial", 
              data = flu_clean1)
summary(Flu2019_SVI )

Call:
glm(formula = flu_2019 ~ ibd_3 + age_yrs + gender + race_5 + 
    ethnic_3 + mstat_5 + relig_affil + lang_3 + act_tob + max_ch + 
    IC + insurance + pop_dens + RPL_THEMES, family = "binomial", 
    data = flu_clean1)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-1.8556  -1.0881  -0.7645   1.1471   2.1871  

Coefficients:
                                         Estimate Std. Error z value Pr(>|z|)    
(Intercept)                             7.124e-01  2.398e-01   2.971 0.002968 ** 
ibd_3UC                                 1.531e-02  5.508e-02   0.278 0.781014    
ibd_3Unknown                           -9.009e-03  4.847e-01  -0.019 0.985171    
age_yrs                                -8.070e-03  2.095e-03  -3.852 0.000117 ***
genderFemale                            1.598e-01  5.251e-02   3.043 0.002343 ** 
race_5Black                            -3.344e-01  1.128e-01  -2.965 0.003026 ** 
race_5Asian or Pacific Islander         6.545e-01  1.792e-01   3.652 0.000261 ***
race_5American Indian or Alaska Native  6.103e-02  4.298e-01   0.142 0.887080    
race_5Other                            -1.441e-01  1.613e-01  -0.893 0.371937    
ethnic_3Non-Hispanic                   -5.060e-01  1.978e-01  -2.558 0.010533 *  
mstat_5Single                          -1.776e-01  6.720e-02  -2.642 0.008235 ** 
mstat_5Divorced/Separated               1.249e-01  1.385e-01   0.902 0.367280    
mstat_5Widowed                         -3.099e-01  1.871e-01  -1.656 0.097638 .  
relig_affilNo                          -1.317e-01  5.377e-02  -2.449 0.014321 *  
lang_3Other                             3.723e-02  3.158e-01   0.118 0.906152    
act_tobYes                             -2.142e-01  8.557e-02  -2.503 0.012319 *  
max_ch                                  2.736e-02  5.732e-03   4.774 1.81e-06 ***
IC                                      4.450e-01  5.914e-02   7.525 5.27e-14 ***
insuranceMedicaid                      -4.876e-01  8.135e-02  -5.994 2.05e-09 ***
insuranceMedicare                      -5.956e-01  8.226e-02  -7.240 4.50e-13 ***
insuranceOther Governmental            -1.302e+00  3.789e-01  -3.436 0.000591 ***
insuranceOther                          3.923e-01  3.790e-01   1.035 0.300556    
pop_dens                                5.417e-05  1.195e-05   4.532 5.83e-06 ***
RPL_THEMES                             -7.006e-01  1.109e-01  -6.319 2.63e-10 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 8886.3  on 6443  degrees of freedom
Residual deviance: 8490.5  on 6420  degrees of freedom
  (4606 observations deleted due to missingness)
AIC: 8538.5

Number of Fisher Scoring iterations: 4

broom::glance(Flu2019_SVI )

broom::tidy(Flu2019_SVI , exponentiate = TRUE)

tbl_regression(Flu2019_SVI, exponentiate = TRUE)

Characteristic	OR1	95% CI1	p-value
IBD Diagnosis
CD	—	—
UC	1.02	0.91, 1.13	0.8
Unknown	0.99	0.37, 2.54	>0.9
Age	0.99	0.99, 1.00	<0.001
Gender
Male	—	—
Female	1.17	1.06, 1.30	0.002
Race
White	—	—
Black	0.72	0.57, 0.89	0.003
Asian or Pacific Islander	1.92	1.36, 2.75	<0.001
American Indian or Alaska Native	1.06	0.45, 2.48	0.9
Other	0.87	0.63, 1.19	0.4
Ethnicity
Hispanic	—	—
Non-Hispanic	0.60	0.41, 0.89	0.011
Marital Status
Married	—	—
Single	0.84	0.73, 0.96	0.008
Divorced/Separated	1.13	0.86, 1.49	0.4
Widowed	0.73	0.50, 1.05	0.10
Any Religious Affiliation
Yes	—	—
No	0.88	0.79, 0.97	0.014
Preferred Language
English	—	—
Other	1.04	0.55, 1.92	>0.9
Active Tobacco Use
No	—	—
Yes	0.81	0.68, 0.95	0.012
Charlson Comorbidity Index	1.03	1.02, 1.04	<0.001
Immunocompromised	1.56	1.39, 1.75	<0.001
Insurance Type
Private Insurance	—	—
Medicaid	0.61	0.52, 0.72	<0.001
Medicare	0.55	0.47, 0.65	<0.001
Other Governmental	0.27	0.12, 0.55	<0.001
Other	1.48	0.71, 3.19	0.3
Population Density of Census Tract	1.00	1.00, 1.00	<0.001
Social Vulnerability Index	0.50	0.40, 0.62	<0.001
1 OR = Odds Ratio, CI = Confidence Interval

# Hosmer-Lemeshow Goodness-of-Fit Test
hltest(Flu2019_SVI)

   The Hosmer-Lemeshow goodness-of-fit test

         Statistic =  12.83896 
degrees of freedom =  9 
           p-value =  0.17003 

# C-Statistic/AUROC 
Cstat(Flu2019_SVI)

[1] 0.6413064

# Model performance 
model_performance(Flu2019_SVI)

# Indices of model performance

AIC      |     AICc |      BIC | Tjur's R2 |  RMSE | Sigma | Log_loss | Score_log | Score_spherical |   PCP
-----------------------------------------------------------------------------------------------------------
8538.492 | 8538.679 | 8700.994 |     0.060 | 0.483 | 1.150 |    0.659 |      -Inf |       1.552e-04 | 0.533

performance::check_model(Flu2019_SVI)

Variable `Component` is not in your data frame :/

# Margins 

cplot(Flu2019_SVI, "RPL_THEMES", what = "prediction", main = "Predicted Likelihood of Flu Vaccine Given SVI")

Flu 2019 with log(SVI)

Flu2019_SVI_log <- glm(flu_2019 ~ ibd_3 + age_yrs + gender + race_5 + ethnic_3 + 
                         mstat_5 + relig_affil + lang_3 + act_tob + max_ch + IC + insurance
                      + pop_dens + log(RPL_THEMES),
              family = "binomial", 
              data = flu_clean1)
summary(Flu2019_SVI_log )

Call:
glm(formula = flu_2019 ~ ibd_3 + age_yrs + gender + race_5 + 
    ethnic_3 + mstat_5 + relig_affil + lang_3 + act_tob + max_ch + 
    IC + insurance + pop_dens + log(RPL_THEMES), family = "binomial", 
    data = flu_clean1)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-1.8243  -1.0884  -0.7733   1.1494   2.2051  

Coefficients:
                                         Estimate Std. Error z value Pr(>|z|)    
(Intercept)                             2.746e-01  2.399e-01   1.145 0.252341    
ibd_3UC                                 2.287e-02  5.498e-02   0.416 0.677399    
ibd_3Unknown                            3.166e-02  4.844e-01   0.065 0.947883    
age_yrs                                -7.929e-03  2.092e-03  -3.791 0.000150 ***
genderFemale                            1.573e-01  5.245e-02   2.998 0.002715 ** 
race_5Black                            -3.956e-01  1.114e-01  -3.550 0.000385 ***
race_5Asian or Pacific Islander         6.710e-01  1.791e-01   3.747 0.000179 ***
race_5American Indian or Alaska Native  8.687e-02  4.294e-01   0.202 0.839670    
race_5Other                            -1.404e-01  1.612e-01  -0.871 0.383552    
ethnic_3Non-Hispanic                   -4.810e-01  1.972e-01  -2.439 0.014718 *  
mstat_5Single                          -1.766e-01  6.710e-02  -2.633 0.008468 ** 
mstat_5Divorced/Separated               1.160e-01  1.383e-01   0.838 0.401812    
mstat_5Widowed                         -3.067e-01  1.871e-01  -1.639 0.101127    
relig_affilNo                          -1.336e-01  5.372e-02  -2.487 0.012872 *  
lang_3Other                             2.627e-03  3.144e-01   0.008 0.993333    
act_tobYes                             -2.213e-01  8.541e-02  -2.591 0.009581 ** 
max_ch                                  2.691e-02  5.725e-03   4.701 2.59e-06 ***
IC                                      4.457e-01  5.911e-02   7.540 4.70e-14 ***
insuranceMedicaid                      -5.162e-01  8.089e-02  -6.381 1.76e-10 ***
insuranceMedicare                      -6.107e-01  8.204e-02  -7.444 9.78e-14 ***
insuranceOther Governmental            -1.324e+00  3.781e-01  -3.502 0.000462 ***
insuranceOther                          3.967e-01  3.791e-01   1.046 0.295422    
pop_dens                                5.047e-05  1.188e-05   4.250 2.14e-05 ***
log(RPL_THEMES)                        -1.243e-01  2.396e-02  -5.187 2.14e-07 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 8886.3  on 6443  degrees of freedom
Residual deviance: 8503.7  on 6420  degrees of freedom
  (4606 observations deleted due to missingness)
AIC: 8551.7

Number of Fisher Scoring iterations: 4

broom::glance(Flu2019_SVI_log )

broom::tidy(Flu2019_SVI_log , exponentiate = TRUE)

tbl_regression(Flu2019_SVI_log, exponentiate = TRUE)

Characteristic	OR1	95% CI1	p-value
IBD Diagnosis
CD	—	—
UC	1.02	0.92, 1.14	0.7
Unknown	1.03	0.39, 2.65	>0.9
Age	0.99	0.99, 1.00	<0.001
Gender
Male	—	—
Female	1.17	1.06, 1.30	0.003
Race
White	—	—
Black	0.67	0.54, 0.84	<0.001
Asian or Pacific Islander	1.96	1.38, 2.80	<0.001
American Indian or Alaska Native	1.09	0.46, 2.54	0.8
Other	0.87	0.63, 1.19	0.4
Ethnicity
Hispanic	—	—
Non-Hispanic	0.62	0.42, 0.91	0.015
Marital Status
Married	—	—
Single	0.84	0.73, 0.96	0.008
Divorced/Separated	1.12	0.86, 1.47	0.4
Widowed	0.74	0.51, 1.06	0.10
Any Religious Affiliation
Yes	—	—
No	0.87	0.79, 0.97	0.013
Preferred Language
English	—	—
Other	1.00	0.54, 1.85	>0.9
Active Tobacco Use
No	—	—
Yes	0.80	0.68, 0.95	0.010
Charlson Comorbidity Index	1.03	1.02, 1.04	<0.001
Immunocompromised	1.56	1.39, 1.75	<0.001
Insurance Type
Private Insurance	—	—
Medicaid	0.60	0.51, 0.70	<0.001
Medicare	0.54	0.46, 0.64	<0.001
Other Governmental	0.27	0.12, 0.53	<0.001
Other	1.49	0.71, 3.21	0.3
Population Density of Census Tract	1.00	1.00, 1.00	<0.001
Social Vulnerability Index	0.88	0.84, 0.93	<0.001
1 OR = Odds Ratio, CI = Confidence Interval

# Hosmer-Lemeshow Goodness-of-Fit Test
hltest(Flu2019_SVI_log)

   The Hosmer-Lemeshow goodness-of-fit test

         Statistic =  12.99612 
degrees of freedom =  9 
           p-value =  0.16278 

# C-Statistic/AUROC 
Cstat(Flu2019_SVI_log)

[1] 0.6400605

# Model performance 
model_performance(Flu2019_SVI_log)

# Indices of model performance

AIC      |     AICc |      BIC | Tjur's R2 |  RMSE | Sigma | Log_loss | Score_log | Score_spherical |   PCP
-----------------------------------------------------------------------------------------------------------
8551.703 | 8551.890 | 8714.205 |     0.058 | 0.483 | 1.151 |    0.660 |      -Inf |       1.552e-04 | 0.532

performance::check_model(Flu2019_SVI_log, panel = TRUE)

Variable `Component` is not in your data frame :/

# Margins 
cplot(Flu2019_SVI_log, "RPL_THEMES", what = "prediction", main = "Predicted Likelihood of Flu Vaccine Given SVI")

Flu 2019 with SVI as Quadratic

Flu2019_SVI_quad <- glm(flu_2019 ~ ibd_3 + age_yrs + gender + race_5 + ethnic_3 + 
                      relig_affil + mstat_5 + lang_3 + act_tob + max_ch + IC + insurance
                      + pop_dens + I(RPL_THEMES^2),
              family = "binomial", 
              data = flu_clean1)
summary(Flu2019_SVI_quad )

Call:
glm(formula = flu_2019 ~ ibd_3 + age_yrs + gender + race_5 + 
    ethnic_3 + relig_affil + mstat_5 + lang_3 + act_tob + max_ch + 
    IC + insurance + pop_dens + I(RPL_THEMES^2), family = "binomial", 
    data = flu_clean1)

Deviance Residuals: 
   Min      1Q  Median      3Q     Max  
-1.873  -1.091  -0.764   1.145   2.171  

Coefficients:
                                         Estimate Std. Error z value Pr(>|z|)    
(Intercept)                             6.285e-01  2.383e-01   2.637 0.008365 ** 
ibd_3UC                                 1.412e-02  5.508e-02   0.256 0.797672    
ibd_3Unknown                           -1.118e-02  4.838e-01  -0.023 0.981559    
age_yrs                                -8.146e-03  2.095e-03  -3.888 0.000101 ***
genderFemale                            1.588e-01  5.249e-02   3.025 0.002486 ** 
race_5Black                            -3.193e-01  1.136e-01  -2.811 0.004933 ** 
race_5Asian or Pacific Islander         6.497e-01  1.792e-01   3.626 0.000288 ***
race_5American Indian or Alaska Native  4.100e-02  4.295e-01   0.095 0.923946    
race_5Other                            -1.416e-01  1.613e-01  -0.878 0.380182    
ethnic_3Non-Hispanic                   -5.137e-01  1.981e-01  -2.593 0.009502 ** 
relig_affilNo                          -1.309e-01  5.376e-02  -2.435 0.014895 *  
mstat_5Single                          -1.809e-01  6.718e-02  -2.692 0.007097 ** 
mstat_5Divorced/Separated               1.168e-01  1.385e-01   0.843 0.399101    
mstat_5Widowed                         -3.105e-01  1.871e-01  -1.659 0.097049 .  
lang_3Other                             4.946e-02  3.159e-01   0.157 0.875592    
act_tobYes                             -2.172e-01  8.557e-02  -2.538 0.011156 *  
max_ch                                  2.734e-02  5.732e-03   4.769 1.85e-06 ***
IC                                      4.431e-01  5.911e-02   7.495 6.61e-14 ***
insuranceMedicaid                      -4.906e-01  8.134e-02  -6.032 1.62e-09 ***
insuranceMedicare                      -5.971e-01  8.226e-02  -7.258 3.92e-13 ***
insuranceOther Governmental            -1.312e+00  3.793e-01  -3.458 0.000543 ***
insuranceOther                          3.818e-01  3.788e-01   1.008 0.313447    
pop_dens                                5.407e-05  1.197e-05   4.517 6.28e-06 ***
I(RPL_THEMES^2)                        -7.836e-01  1.292e-01  -6.064 1.33e-09 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 8886.3  on 6443  degrees of freedom
Residual deviance: 8493.3  on 6420  degrees of freedom
  (4606 observations deleted due to missingness)
AIC: 8541.3

Number of Fisher Scoring iterations: 4

broom::glance(Flu2019_SVI_quad )

broom::tidy(Flu2019_SVI_quad , exponentiate = TRUE)

tbl_regression(Flu2019_SVI_quad, exponentiate = TRUE)

Characteristic	OR1	95% CI1	p-value
IBD Diagnosis
CD	—	—
UC	1.01	0.91, 1.13	0.8
Unknown	0.99	0.37, 2.53	>0.9
Age	0.99	0.99, 1.00	<0.001
Gender
Male	—	—
Female	1.17	1.06, 1.30	0.002
Race
White	—	—
Black	0.73	0.58, 0.91	0.005
Asian or Pacific Islander	1.91	1.35, 2.74	<0.001
American Indian or Alaska Native	1.04	0.44, 2.43	>0.9
Other	0.87	0.63, 1.19	0.4
Ethnicity
Hispanic	—	—
Non-Hispanic	0.60	0.40, 0.88	0.010
Any Religious Affiliation
Yes	—	—
No	0.88	0.79, 0.97	0.015
Marital Status
Married	—	—
Single	0.83	0.73, 0.95	0.007
Divorced/Separated	1.12	0.86, 1.47	0.4
Widowed	0.73	0.50, 1.05	0.10
Preferred Language
English	—	—
Other	1.05	0.56, 1.95	0.9
Active Tobacco Use
No	—	—
Yes	0.80	0.68, 0.95	0.011
Charlson Comorbidity Index	1.03	1.02, 1.04	<0.001
Immunocompromised	1.56	1.39, 1.75	<0.001
Insurance Type
Private Insurance	—	—
Medicaid	0.61	0.52, 0.72	<0.001
Medicare	0.55	0.47, 0.65	<0.001
Other Governmental	0.27	0.12, 0.54	<0.001
Other	1.46	0.70, 3.16	0.3
Population Density of Census Tract	1.00	1.00, 1.00	<0.001
Social Vulnerability Index	0.46	0.35, 0.59	<0.001
1 OR = Odds Ratio, CI = Confidence Interval

# Hosmer-Lemeshow Goodness-of-Fit Test
hltest(Flu2019_SVI_quad)

   The Hosmer-Lemeshow goodness-of-fit test

         Statistic =  8.25476 
degrees of freedom =  9 
           p-value =  0.50869 

# C-Statistic/AUROC 
Cstat(Flu2019_SVI_quad)

[1] 0.6408574

# Model performance 
model_performance(Flu2019_SVI_quad)

# Indices of model performance

AIC      |     AICc |      BIC | Tjur's R2 |  RMSE | Sigma | Log_loss | Score_log | Score_spherical |   PCP
-----------------------------------------------------------------------------------------------------------
8561.720 | 8561.907 | 8724.221 |     0.059 | 0.483 | 1.150 |    0.659 |      -Inf |       1.552e-04 | 0.533

performance::check_model(Flu2019_SVI_quad, panel = TRUE)

Variable `Component` is not in your data frame :/

# Margins 
cplot(Flu2019_SVI_quad, "RPL_THEMES", what = "prediction", main = "Predicted Likelihood of Flu Vaccine Given SVI")

Flu 2019 with SVI as Quartile

Flu2019_SVI_quart <- glm(flu_2019 ~ ibd_3 + age_yrs + gender + race_5 + ethnic_3 + 
                      relig_affil + mstat_5 + lang_3 + act_tob + max_ch + IC + insurance
                      + pop_dens + RPL_4,
              family = "binomial", 
              data = flu_clean1)
summary(Flu2019_SVI_quart )

Call:
glm(formula = flu_2019 ~ ibd_3 + age_yrs + gender + race_5 + 
    ethnic_3 + relig_affil + mstat_5 + lang_3 + act_tob + max_ch + 
    IC + insurance + pop_dens + RPL_4, family = "binomial", data = flu_clean1)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-1.8519  -1.0878  -0.7654   1.1467   2.1766  

Coefficients:
                                         Estimate Std. Error z value Pr(>|z|)    
(Intercept)                             6.315e-01  2.387e-01   2.646 0.008156 ** 
ibd_3UC                                 1.421e-02  5.509e-02   0.258 0.796382    
ibd_3Unknown                           -2.033e-02  4.842e-01  -0.042 0.966511    
age_yrs                                -8.117e-03  2.095e-03  -3.874 0.000107 ***
genderFemale                            1.605e-01  5.250e-02   3.057 0.002239 ** 
race_5Black                            -3.479e-01  1.131e-01  -3.075 0.002103 ** 
race_5Asian or Pacific Islander         6.614e-01  1.794e-01   3.687 0.000227 ***
race_5American Indian or Alaska Native  3.377e-02  4.299e-01   0.079 0.937396    
race_5Other                            -1.480e-01  1.613e-01  -0.918 0.358854    
ethnic_3Non-Hispanic                   -5.011e-01  1.978e-01  -2.534 0.011289 *  
relig_affilNo                          -1.304e-01  5.377e-02  -2.426 0.015266 *  
mstat_5Single                          -1.808e-01  6.720e-02  -2.690 0.007153 ** 
mstat_5Divorced/Separated               1.181e-01  1.386e-01   0.852 0.394109    
mstat_5Widowed                         -3.132e-01  1.871e-01  -1.674 0.094046 .  
lang_3Other                             3.797e-02  3.163e-01   0.120 0.904446    
act_tobYes                             -2.169e-01  8.557e-02  -2.535 0.011242 *  
max_ch                                  2.750e-02  5.733e-03   4.796 1.62e-06 ***
IC                                      4.399e-01  5.910e-02   7.443 9.84e-14 ***
insuranceMedicaid                      -4.914e-01  8.133e-02  -6.042 1.52e-09 ***
insuranceMedicare                      -6.000e-01  8.220e-02  -7.299 2.90e-13 ***
insuranceOther Governmental            -1.301e+00  3.790e-01  -3.434 0.000595 ***
insuranceOther                          3.970e-01  3.786e-01   1.049 0.294383    
pop_dens                                5.304e-05  1.194e-05   4.441 8.95e-06 ***
RPL_4Second                            -1.492e-01  6.126e-02  -2.436 0.014854 *  
RPL_4Third                             -3.617e-01  7.391e-02  -4.894 9.89e-07 ***
RPL_4Fourth                            -5.104e-01  1.054e-01  -4.843 1.28e-06 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 8886.3  on 6443  degrees of freedom
Residual deviance: 8492.7  on 6418  degrees of freedom
  (4606 observations deleted due to missingness)
AIC: 8544.7

Number of Fisher Scoring iterations: 4

broom::glance(Flu2019_SVI_quart )

broom::tidy(Flu2019_SVI_quart , exponentiate = TRUE)

tbl_regression(Flu2019_SVI_quart, exponentiate = TRUE)

Characteristic	OR1	95% CI1	p-value
IBD Diagnosis
CD	—	—
UC	1.01	0.91, 1.13	0.8
Unknown	0.98	0.37, 2.51	>0.9
Age	0.99	0.99, 1.00	<0.001
Gender
Male	—	—
Female	1.17	1.06, 1.30	0.002
Race
White	—	—
Black	0.71	0.56, 0.88	0.002
Asian or Pacific Islander	1.94	1.37, 2.77	<0.001
American Indian or Alaska Native	1.03	0.44, 2.41	>0.9
Other	0.86	0.63, 1.18	0.4
Ethnicity
Hispanic	—	—
Non-Hispanic	0.61	0.41, 0.89	0.011
Any Religious Affiliation
Yes	—	—
No	0.88	0.79, 0.98	0.015
Marital Status
Married	—	—
Single	0.83	0.73, 0.95	0.007
Divorced/Separated	1.13	0.86, 1.48	0.4
Widowed	0.73	0.50, 1.05	0.094
Preferred Language
English	—	—
Other	1.04	0.55, 1.93	>0.9
Active Tobacco Use
No	—	—
Yes	0.80	0.68, 0.95	0.011
Charlson Comorbidity Index	1.03	1.02, 1.04	<0.001
Immunocompromised	1.55	1.38, 1.74	<0.001
Insurance Type
Private Insurance	—	—
Medicaid	0.61	0.52, 0.72	<0.001
Medicare	0.55	0.47, 0.64	<0.001
Other Governmental	0.27	0.12, 0.55	<0.001
Other	1.49	0.72, 3.20	0.3
Population Density of Census Tract	1.00	1.00, 1.00	<0.001
SVI by Quartile
First	—	—
Second	0.86	0.76, 0.97	0.015
Third	0.70	0.60, 0.80	<0.001
Fourth	0.60	0.49, 0.74	<0.001
1 OR = Odds Ratio, CI = Confidence Interval

# Hosmer-Lemeshow Goodness-of-Fit Test
hltest(Flu2019_SVI_quart)

   The Hosmer-Lemeshow goodness-of-fit test

         Statistic =  9.34888 
degrees of freedom =  9 
           p-value =  0.40571 

# C-Statistic/AUROC 
Cstat(Flu2019_SVI_quart)

[1] 0.6410718

# Model performance 
model_performance(Flu2019_SVI_quart)

# Indices of model performance

AIC      |     AICc |      BIC | Tjur's R2 |  RMSE | Sigma | Log_loss | Score_log | Score_spherical |   PCP
-----------------------------------------------------------------------------------------------------------
8544.655 | 8544.873 | 8720.698 |     0.059 | 0.483 | 1.150 |    0.659 |      -Inf |       1.552e-04 | 0.533

performance::check_model(Flu2019_SVI_quart, panel = TRUE)

Variable `Component` is not in your data frame :/

# Margins 
cplot(Flu2019_SVI_quart, "RPL_4", what = "prediction", main = "Predicted Likelihood of Flu Vaccine Given SVI")

NA
NA

Flu 2019 + All SVI Themes

Flu2019_all_themes <- glm(flu_2019 ~ ibd_3 + age_yrs + gender + race_5 + ethnic_3 + 
                      lang_3 + mstat_5 + relig_affil + act_tob + max_ch + IC
                      + pop_dens + RPL_THEME1 + RPL_THEME2 + RPL_THEME3
                      + RPL_THEME4,
              family = "binomial",
              data = flu_clean1)
summary(Flu2019_all_themes )

Call:
glm(formula = flu_2019 ~ ibd_3 + age_yrs + gender + race_5 + 
    ethnic_3 + lang_3 + mstat_5 + relig_affil + act_tob + max_ch + 
    IC + pop_dens + RPL_THEME1 + RPL_THEME2 + RPL_THEME3 + RPL_THEME4, 
    family = "binomial", data = flu_clean1)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-1.8416  -1.0867  -0.8063   1.1709   2.0183  

Coefficients:
                                         Estimate Std. Error z value Pr(>|z|)    
(Intercept)                             9.257e-01  2.434e-01   3.803 0.000143 ***
ibd_3UC                                 3.209e-02  5.498e-02   0.584 0.559448    
ibd_3Unknown                           -3.204e-04  4.769e-01  -0.001 0.999464    
age_yrs                                -1.324e-02  1.906e-03  -6.944 3.81e-12 ***
genderFemale                            1.558e-01  5.242e-02   2.972 0.002956 ** 
race_5Black                            -3.849e-01  1.139e-01  -3.380 0.000725 ***
race_5Asian or Pacific Islander         6.068e-01  1.821e-01   3.333 0.000860 ***
race_5American Indian or Alaska Native -2.720e-02  4.286e-01  -0.063 0.949400    
race_5Other                            -2.225e-01  1.612e-01  -1.381 0.167343    
ethnic_3Non-Hispanic                   -5.010e-01  1.977e-01  -2.534 0.011284 *  
lang_3Other                            -2.145e-01  3.113e-01  -0.689 0.490704    
mstat_5Single                          -3.076e-01  6.581e-02  -4.674 2.95e-06 ***
mstat_5Divorced/Separated               1.052e-02  1.370e-01   0.077 0.938835    
mstat_5Widowed                         -4.264e-01  1.858e-01  -2.295 0.021710 *  
relig_affilNo                          -1.293e-01  5.380e-02  -2.403 0.016243 *  
act_tobYes                             -2.542e-01  8.483e-02  -2.996 0.002732 ** 
max_ch                                  2.188e-02  5.676e-03   3.855 0.000116 ***
IC                                      4.728e-01  5.918e-02   7.989 1.36e-15 ***
pop_dens                                4.564e-05  1.319e-05   3.459 0.000543 ***
RPL_THEME1                             -6.516e-01  1.598e-01  -4.079 4.52e-05 ***
RPL_THEME2                             -5.544e-01  1.382e-01  -4.013 6.00e-05 ***
RPL_THEME3                              1.050e-01  9.959e-02   1.054 0.291726    
RPL_THEME4                              1.331e-01  1.102e-01   1.208 0.226863    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 8818.9  on 6396  degrees of freedom
Residual deviance: 8483.0  on 6374  degrees of freedom
  (4653 observations deleted due to missingness)
AIC: 8529

Number of Fisher Scoring iterations: 4

broom::glance(Flu2019_all_themes )

broom::tidy(Flu2019_all_themes , exponentiate = TRUE)

tbl_regression(Flu2019_all_themes, exponentiate = TRUE)

Characteristic	OR1	95% CI1	p-value
IBD Diagnosis
CD	—	—
UC	1.03	0.93, 1.15	0.6
Unknown	1.00	0.38, 2.53	>0.9
Age	0.99	0.98, 0.99	<0.001
Gender
Male	—	—
Female	1.17	1.05, 1.30	0.003
Race
White	—	—
Black	0.68	0.54, 0.85	<0.001
Asian or Pacific Islander	1.83	1.29, 2.64	<0.001
American Indian or Alaska Native	0.97	0.41, 2.27	>0.9
Other	0.80	0.58, 1.10	0.2
Ethnicity
Hispanic	—	—
Non-Hispanic	0.61	0.41, 0.89	0.011
Preferred Language
English	—	—
Other	0.81	0.43, 1.48	0.5
Marital Status
Married	—	—
Single	0.74	0.65, 0.84	<0.001
Divorced/Separated	1.01	0.77, 1.32	>0.9
Widowed	0.65	0.45, 0.93	0.022
Any Religious Affiliation
Yes	—	—
No	0.88	0.79, 0.98	0.016
Active Tobacco Use
No	—	—
Yes	0.78	0.66, 0.92	0.003
Charlson Comorbidity Index	1.02	1.01, 1.03	<0.001
Immunocompromised	1.60	1.43, 1.80	<0.001
Population Density of Census Tract	1.00	1.00, 1.00	<0.001
Socioeconomic Status	0.52	0.38, 0.71	<0.001
Household Composition	0.57	0.44, 0.75	<0.001
Minority and Language Status	1.11	0.91, 1.35	0.3
Housing and Transportation	1.14	0.92, 1.42	0.2
1 OR = Odds Ratio, CI = Confidence Interval

# Hosmer-Lemeshow Goodness-of-Fit Test
hltest(Flu2019_all_themes)

   The Hosmer-Lemeshow goodness-of-fit test

         Statistic =  8.31806 
degrees of freedom =  8 
           p-value =  0.40303 

# C-Statistic/AUROC 
Cstat(Flu2019_all_themes)

[1] 0.6315944

# Model performance 
model_performance(Flu2019_all_themes)

# Indices of model performance

AIC      |     AICc |      BIC | Tjur's R2 |  RMSE | Sigma | Log_loss | Score_log |   PCP
-----------------------------------------------------------------------------------------
8528.954 | 8529.127 | 8684.516 |     0.051 | 0.485 | 1.154 |    0.663 |      -Inf | 0.529

performance::check_model(Flu2019_all_themes, panel = TRUE)

Variable `Component` is not in your data frame :/

# Margins 
cplot(Flu2019_all_themes, "RPL_THEME1", what = "prediction", main = "Predicted Likelihood of Flu Vaccine Given THEME1")

cplot(Flu2019_all_themes, "RPL_THEME2", what = "prediction", main = "Predicted Likelihood of Flu Vaccine Given THEME2")

cplot(Flu2019_all_themes, "RPL_THEME3", what = "prediction", main = "Predicted Likelihood of Flu Vaccine Given THEME3")

cplot(Flu2019_all_themes, "RPL_THEME4", what = "prediction", main = "Predicted Likelihood of Flu Vaccine Given THEME4")