BilangualPopulations - Social, Economic, and Health Indicators
2024-07-23
Loading in Data
#all crosswalks
ddi <- read_ipums_ddi("usa_00013.xml")
all_indicator_data <- read_ipums_micro(ddi)## Use of data from IPUMS USA is subject to conditions including that users should cite the data appropriately. Use command `ipums_conditions()` for more details.#2022
poverty_2022 <- read.csv("../ACS_DATA/2022/ACSDT5Y2022.B16009-Data.csv")
language_2022 <- read.csv("../ACS_DATA/2022/ACSST5Y2022.S1601-Data.csv")
social_2022 <- read.csv("../ACS_DATA/2022/ACSCP5Y2022.CP02-Data.csv")
characteristics_2022 <- read.csv("../ACS_DATA/2022/ACSST5Y2022.S1603-Data.csv")
limited_eng_2022 <- read.csv("../ACS_DATA/2022/ACSST5Y2022.S1602-Data.csv")
household_2022 <- read.csv("../ACS_DATA/2022/ACSDT5Y2022.B16002-Data.csv")
education_2022 <- read.csv("../ACS_DATA/2022/ACSDT5Y2022.B16010-Data.csv")
#location data
regions <- read.csv("../location_data/County_12_Regions.csv")
rural_urban <-read.csv("../location_data/rural_urban.csv")POVERTY
Used ACS 5 Year 2022 Data to calculate regional percent point change of children below poverty line by primary langauge spoken at home. First cleaned 2022 data, merged with region data which has label for each county’s region then aggregated for each region.
children_poverty_2022 <- poverty_2022 |>
#grabbing all relevant variables below poverty line
select(Geographic.Area.Name,Estimate..Total.,
Estimate..Total...Income.in.the.past.12.months.below.poverty.level.,
Estimate..Total...Income.in.the.past.12.months.below.poverty.level...5.to.17.years.,
Estimate..Total...Income.in.the.past.12.months.below.poverty.level...5.to.17.years...Speak.only.English,
Estimate..Total...Income.in.the.past.12.months.below.poverty.level...5.to.17.years...Speak.Spanish,
Estimate..Total...Income.in.the.past.12.months.below.poverty.level...5.to.17.years...Speak.Asian.and.Pacific.Island.languages,
Estimate..Total...Income.in.the.past.12.months.below.poverty.level...5.to.17.years...Speak.other.Indo.European.languages,
Estimate..Total...Income.in.the.past.12.months.below.poverty.level...5.to.17.years...Speak.other.languages
)|>
#renaming for ease and clarity
rename(Total_Pop = Estimate..Total.,
Total_Below_Line = Estimate..Total...Income.in.the.past.12.months.below.poverty.level.,
Total_Children_Below_Line = Estimate..Total...Income.in.the.past.12.months.below.poverty.level...5.to.17.years.,
Only_English = Estimate..Total...Income.in.the.past.12.months.below.poverty.level...5.to.17.years...Speak.only.English,
Spanish = Estimate..Total...Income.in.the.past.12.months.below.poverty.level...5.to.17.years...Speak.Spanish,
Asian_Pacific_Lang = Estimate..Total...Income.in.the.past.12.months.below.poverty.level...5.to.17.years...Speak.Asian.and.Pacific.Island.languages,
Other_IndoEuro_Lang = Estimate..Total...Income.in.the.past.12.months.below.poverty.level...5.to.17.years...Speak.other.Indo.European.languages,
Other_Lang = Estimate..Total...Income.in.the.past.12.months.below.poverty.level...5.to.17.years...Speak.other.languages,
County = Geographic.Area.Name)|>
#fixing county names
mutate(County = sub(" County, Texas", "", County))children_poverty_2022_regions <- left_join(children_poverty_2022, regions, by = "County")
write.csv(file = "Poverty_Children_Languages_2022.csv", children_poverty_2022_regions)region_total <- function(bilangual_data) {
region_totals <- bilangual_data |>
group_by(Region)|>
summarise(Region_Total = sum(Total_Children_Below_Line, na.rm = TRUE))
aggregated_precursor <- bilangual_data|>
left_join(region_totals, by = "Region") |>
mutate(Weight = Total_Children_Below_Line / Region_Total)
aggregated_data <- aggregated_precursor |>
group_by(Region) |>
summarise(
Total_English = sum(Only_English * Weight, na.rm = TRUE),
Total_Spanish = sum(Spanish * Weight, na.rm = TRUE),
Total_Asian_Pacific = sum(Asian_Pacific_Lang * Weight, na.rm = TRUE),
Total_IndoEuro = sum(Other_IndoEuro_Lang * Weight, na.rm = TRUE),
Total_Other = sum(Other_Lang * Weight, na.rm = TRUE),
Total_Children_Below_Line = sum(Total_Children_Below_Line * Weight, na.rm = TRUE)
) |>
mutate(
Percent_English = round(Total_English / Total_Children_Below_Line, 3),
Percent_Spanish = round(Total_Spanish / Total_Children_Below_Line, 3),
Percent_Asian_Pacific = round(Total_Asian_Pacific / Total_Children_Below_Line, 3),
Percent_IndoEuro = round(Total_IndoEuro / Total_Children_Below_Line, 3),
Percent_Other = round(Total_Other / Total_Children_Below_Line, 3)
)
return(aggregated_data)
}region_children_poverty_2022 <- region_total(children_poverty_2022_regions)write.csv(file = "Poverty_Children_Languages_Regions.csv", region_children_poverty_2022)MICRODATA
Microdata was taken from IPUMS:
Steven Ruggles, Sarah Flood, Matthew Sobek, Daniel Backman, Annie Chen, Grace Cooper, Stephanie Richards, Renae Rodgers, and Megan Schouweiler. IPUMS USA: Version 15.0 [dataset]. Minneapolis, MN: IPUMS, 2024. https://doi.org/10.18128/D010.V15.0
The following data analysis used the same dataset which has harmonized data for various variables taken in the ACS. The specific documentation for the variables can be seen here.
A dataset was created by filtering out N/A values and “Bilingual” was added as a variable based on meeting criteria of speaking another language other than English as well as speaking English “well” or “very well” and “Not Bilingual” was dtermiend by speaking only English.
A version of the previously described data was also created with a more detailed variable named “Bilingual Status” which contains “English Monolingual”, “Bilingual” and “NE Monolingual” (Non-English Monolingual). The following parameters were taken:
English Monolingual: Only speaks English
Bilingual: Speaks a language other than English as well as speaks English “well” or “very well”
NE Monolingual: Speaks a language other than English as well as speaks English “not at all” or “less than well”
indicators_2022 <- all_indicator_data |>
filter(YEAR == 2022) |>
distinct(SERIAL, PERNUM, .keep_all = TRUE) LANUGUAGE CODES
| Language | Code |
|---|---|
| N/A | 0, 95, 96, 99 |
| English | 1 |
| Spanish | 12 |
| Asian/Pacific Islander Languages | 43-56 |
| Other Indo-European Langauges | 2-8, 10-11, 13-31, 33-34, 36-37, 38, 40, 41 |
| Other Languages | 9, 32, 35, 39, 42, 57-64, 70-93, 94 |
| Native Languages | 70-94 |
microdat_bilingual <- indicators_2022 |>
filter(LANGUAGE != 1 & LANGUAGE != 0 & LANGUAGE != 95 & LANGUAGE != 96) |> #doesn't speak english at home and gets rid of invalid entries
filter(SPEAKENG == 4 | SPEAKENG == 5) |> #speaks english well or very well
mutate(Bilingual = "Bilingual")
set.seed(123)
microdat_speaks_english <- indicators_2022 |>
filter(LANGUAGE == 1 & LANGUAGE != 0 & LANGUAGE != 95 & LANGUAGE != 96) |> #speaks english at home and gets rid of invalid entries
filter(SPEAKENG == 3) |> #speaks only english at home
mutate(Bilingual = "Not Bilingual") |>
sample_n(nrow(microdat_bilingual))
table(microdat_bilingual$LANGUAGE)##
## 2 3 4 5 6 7 10 11 12 13 14
## 3111 15 489 137 61 70 578 3162 230457 1452 332
## 15 16 17 18 19 20 21 22 23 25 26
## 45 344 153 1230 126 302 450 29 343 42 109
## 28 29 30 31 33 34 36 37 40 43 44
## 69 1441 272 11201 79 130 499 8 7005 7533 73
## 45 47 48 49 50 51 52 53 54 55 56
## 379 863 942 2537 6820 371 497 72 4182 199 20
## 57 58 59 60 61 62 63 71 72 74 75
## 3508 16 372 760 185 98 3438 2 52 3 35
## 81 82 84 89 94
## 7 132 31 15 117table(microdat_bilingual$SPEAKENG)##
## 4 5
## 230792 66208table(microdat_bilingual$AGE) #age ranges from 5 to 92##
## 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
## 3231 3606 3864 3968 3921 4333 4445 4581 4662 4733 4921 4990 5118 5510 5353 4827
## 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36
## 4864 4572 4568 4483 4525 4592 4495 4468 4674 4812 4571 4631 4468 4562 4765 4675
## 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52
## 4447 4713 4558 4845 4463 4533 4518 4436 4601 4314 4512 4279 4165 4345 4069 4030
## 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68
## 3885 3803 3872 3755 3648 3686 3555 3450 3267 3330 3112 3018 3016 2937 2719 2630
## 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84
## 2455 2422 2260 2082 1891 1831 1623 1465 1326 1192 1008 941 860 762 706 625
## 85 86 87 88 92
## 581 437 426 368 1440table(microdat_speaks_english$LANGUAGE)##
## 1
## 297000table(microdat_speaks_english$SPEAKENG)##
## 3
## 297000table(microdat_speaks_english$AGE) #age ranges from 5 to 92##
## 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
## 3699 3823 3912 3877 3919 3980 4187 4218 4172 4147 4131 4114 4163 4396 4309 3748
## 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36
## 3391 3416 3359 3407 3490 3507 3649 3653 3678 3941 3801 3866 3858 3745 3783 3762
## 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52
## 3842 3687 3870 3829 3511 3489 3445 3429 3180 3389 3518 3610 3673 3848 3833 3705
## 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68
## 3804 3778 3951 4172 4304 4507 4494 4524 4661 4537 4559 4525 4419 4354 4062 3985
## 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84
## 3861 3789 3719 3498 3199 3056 2766 2523 2338 2215 2022 1779 1671 1536 1335 1217
## 85 86 87 88 92
## 1089 1007 835 773 3177#english data set almost three times as large as bilingual dataset
language_micro_data <- rbind(microdat_bilingual, microdat_speaks_english)microdat_languages <- indicators_2022 |>
filter(LANGUAGE != 1 & LANGUAGE != 0 & LANGUAGE != 95 & LANGUAGE != 96) |> #doesn't speak English at home and removes invalid entries
filter(SPEAKENG %in% c(1, 4, 5, 6)) |> #considers only relevant SPEAKENG values
mutate(Language_Group = case_when(
LANGUAGE == 12 ~ "Spanish",
LANGUAGE %in% 43:56 ~ "Asian/Pacific Islander Languages",
LANGUAGE %in% c(2:8, 10:11, 13:31, 33:34, 36:37, 38, 40, 41) ~ "Other Indo-European Languages",
LANGUAGE %in% c(9, 32, 35, 39, 42, 57:64, 70:93, 94) ~ "Other Languages",
TRUE ~ "Other Languages"
),
Bilingual_Status = case_when(
SPEAKENG %in% c(4, 5) ~ "Bilingual",
SPEAKENG %in% c(1, 6) ~ "NE Monolingual"
))
microdat_speaks_english <- indicators_2022 |>
filter(LANGUAGE == 1 & LANGUAGE != 0 & LANGUAGE != 95 & LANGUAGE != 96) |> #speaks english at home and gets rid of invalid entries
filter(SPEAKENG == 3) |> #speaks only english at home
mutate(Language_Group = "English",
Bilingual_Status = "English Monolingual")
language_micro_data_full <- rbind(microdat_languages, microdat_speaks_english)table(language_micro_data_full$Language_Group)##
## Asian/Pacific Islander Languages English
## 30226 842925
## Other Indo-European Languages Other Languages
## 35613 9527
## Spanish
## 287048table(language_micro_data_full$Bilingual_Status)##
## Bilingual English Monolingual NE Monolingual
## 297000 842925 65414write.csv(file = "Extensive_Microdata_Bilingualism.csv", language_micro_data_full)write.csv(file = "Microdata_Bilingualism.csv", language_micro_data)OVERVIEW OF LANGUAGE ANF BILINGUAL STATUS POPUALTION COUNTS
survey_design <- svydesign(
id = ~CLUSTER,
weights = ~PERWT,
data = language_micro_data_full
)
#calculating the total weighted counts for each language group
bilingual_stat_dist <- svytotal(~Bilingual_Status, survey_design)
print(bilingual_stat_dist)## total SE
## Bilingual_StatusBilingual 7761055 31787
## Bilingual_StatusEnglish Monolingual 17695085 41195
## Bilingual_StatusNE Monolingual 1859404 13352language_group_dist <- svytotal(~Language_Group, survey_design)
print(language_group_dist)## total SE
## Language_GroupAsian/Pacific Islander Languages 668626 9090.9
## Language_GroupEnglish 17695085 41195.4
## Language_GroupOther Indo-European Languages 831164 10233.6
## Language_GroupOther Languages 293443 7647.2
## Language_GroupSpanish 7827226 35124.3bilingual_stat_df <- as.data.frame(bilingual_stat_dist)
language_group_df <- as.data.frame(language_group_dist)EMPLOYMENT IN MINORS
Finding average age of minors for each Bilingual Status group through survey design.
bilingual_employed_minors <- language_micro_data_full |>
filter(AGE > 13 & AGE < 18) |>
filter(EMPSTAT == 1) #means they are employed
survey_design_minors <- svydesign(
id = ~CLUSTER,
weights = ~PERWT,
data = bilingual_employed_minors
)
avg_working_age_by_status <- svyby(
~AGE,
~Language_Group,
survey_design_minors,
svymean,
vartype = "ci"
)
print(avg_working_age_by_status)## Language_Group AGE
## Asian/Pacific Islander Languages Asian/Pacific Islander Languages 16.53576
## English English 16.62641
## Other Indo-European Languages Other Indo-European Languages 16.60639
## Other Languages Other Languages 16.67224
## Spanish Spanish 16.67545
## ci_l ci_u
## Asian/Pacific Islander Languages 16.39453 16.67698
## English 16.60735 16.64547
## Other Indo-European Languages 16.48785 16.72493
## Other Languages 16.46134 16.88314
## Spanish 16.64305 16.70784HEALTHCARE COVERAGE
Finding percentage of healthcare coverage for each Bilingual_Status group.
language_micro_data_health <- language_micro_data_full |>
mutate(HCOVANY = ifelse(HCOVANY == 2, 1, 0))
healthcare_des <- svydesign(
id = ~CLUSTER,
weights = ~PERWT,
data = language_micro_data_health
)
healthcare_coverage_by_language <- svyby(
~HCOVANY,
~Bilingual_Status,
healthcare_des,
svymean
)
#subtracting to find no coverage values
healthcare_coverage_by_language <- healthcare_coverage_by_language |>
mutate(NoCoverage = 1-HCOVANY)write.csv(file = "HealthcareCoverage_By_Language.csv", healthcare_coverage_by_language)POVERTY
With micro data for each bilingual status group
language_micro_data_pov <- language_micro_data_full |>
filter(POVERTY != 0) |>
mutate(below_poverty_line = if_else(POVERTY < 100, 1, 0))
poverty_des <- svydesign(
id = ~CLUSTER,
weights = ~PERWT,
strata = ~STRATA,
data = language_micro_data_pov
)
poverty_by_biling_stat <- svyby(
~below_poverty_line,
~Bilingual_Status,
poverty_des,
svymean,
)
print(poverty_by_biling_stat)## Bilingual_Status below_poverty_line se
## Bilingual Bilingual 0.14605305 0.0015646012
## English Monolingual English Monolingual 0.09975716 0.0008041401
## NE Monolingual NE Monolingual 0.23037262 0.0031004821write.csv(file = "Poverty_Rate_BilingStat.csv", poverty_by_biling_stat)HOME OWNERSHIP
language_micro_data_home <- language_micro_data_full |>
select(CLUSTER, STRATA, PERWT, OWNERSHP, Bilingual_Status, Language_Group) |>
filter(OWNERSHP != 0) |>
mutate(OWNERSHP = if_else(OWNERSHP == 2, 0, 1))
poverty_des <- svydesign(
id = ~CLUSTER,
weights = ~PERWT,
strata = ~STRATA,
data = language_micro_data_home
)
homeownership_by_biling_stat <- svyby(
~OWNERSHP,
~Bilingual_Status,
poverty_des,
svymean,
)
print(homeownership_by_biling_stat)## Bilingual_Status OWNERSHP se
## Bilingual Bilingual 0.6646292 0.002031540
## English Monolingual English Monolingual 0.6789625 0.001306859
## NE Monolingual NE Monolingual 0.5516144 0.003705897write.csv(file = "HomeOwnership_By_BilingStat.csv", homeownership_by_biling_stat)FAMILY SIZE
Finding proportion of Bilingual_Status for each number of children in a household. First was done as just a simple overview to see if there is a remarkable difference in distribution and then when difference was seen a survey design was done.
household_data <- language_micro_data_full |>
select(SERIAL, NCHILD, HHWT, Bilingual_Status, STRATA, PERWT) |>
distinct(SERIAL, .keep_all = TRUE)
household_data <- household_data |>
mutate(Child_Category = case_when(
NCHILD == 0 ~ "0 Children",
NCHILD == 1 ~ "1 Child",
NCHILD == 2 ~ "2 Children",
NCHILD >= 3 ~ "More than 3 Children"
))
household_summary <- household_data |>
group_by(Bilingual_Status, Child_Category) |>
summarize(
Count = n(),
Total_Weight = sum(HHWT, na.rm = TRUE),
.groups = 'drop'
) |>
group_by(Bilingual_Status) |>
mutate(
Total_Households = sum(Total_Weight),
Percentage = Total_Weight / Total_Households * 100
)
print(household_summary)## # A tibble: 12 × 6
## # Groups: Bilingual_Status [3]
## Bilingual_Status Child_Category Count Total_Weight Total_Households
## <chr> <chr> <int> <dbl> <dbl>
## 1 Bilingual 0 Children 73918 1573350 3253211
## 2 Bilingual 1 Child 27073 656272 3253211
## 3 Bilingual 2 Children 22420 594798 3253211
## 4 Bilingual More than 3 Children 14772 428791 3253211
## 5 English Monolingual 0 Children 264844 4688190 7048317
## 6 English Monolingual 1 Child 53439 1126204 7048317
## 7 English Monolingual 2 Children 34742 794271 7048317
## 8 English Monolingual More than 3 Children 18084 439652 7048317
## 9 NE Monolingual 0 Children 13650 324519 795889
## 10 NE Monolingual 1 Child 6106 175213 795889
## 11 NE Monolingual 2 Children 4843 146405 795889
## 12 NE Monolingual More than 3 Children 4499 149752 795889
## # ℹ 1 more variable: Percentage <dbl>library(ggplot2)
ggplot(household_summary, aes(x = Child_Category, y = Percentage, fill = Bilingual_Status)) +
geom_bar(stat = "identity", position = "dodge") +
ggtitle("Percentage of Households by Number of Children and Bilingual Status") +
xlab("Number of Children") +
ylab("Percentage of Households") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
Survey Design
#creating the survey object
des_number_of_children <- svydesign(ids = ~1,
strata = ~STRATA,
weights = ~HHWT,
data = household_data)
household_data_at_least_one_kid <- household_data |>
filter(NCHILD > 0)
des_at_least_one_kid <- svydesign(ids = ~1,
strata = ~STRATA,
weights = ~HHWT,
data = household_data_at_least_one_kid)mean_by_bilingual <- svyby(~NCHILD, ~Bilingual_Status, des_number_of_children, svymean, na.rm = TRUE)
print(mean_by_bilingual)## Bilingual_Status NCHILD se
## Bilingual Bilingual 1.0183680 0.004989489
## English Monolingual English Monolingual 0.5973837 0.002646491
## NE Monolingual NE Monolingual 1.2481464 0.010952123options(scipen = 999)
tab <- svytable(~Bilingual_Status + NCHILD, des_number_of_children)
proportion_table <- prop.table(tab, margin = 2)
print(proportion_table)## NCHILD
## Bilingual_Status 0 1 2 3 4
## Bilingual 0.23889097 0.33522791 0.38737094 0.42292651 0.41720879
## English Monolingual 0.71183541 0.57527217 0.51728066 0.44208910 0.41008893
## NE Monolingual 0.04927362 0.08949992 0.09534841 0.13498439 0.17270228
## NCHILD
## Bilingual_Status 5 6 7 8 9
## Bilingual 0.42167388 0.38825633 0.43330778 0.51245387 0.31194472
## English Monolingual 0.39854910 0.42456036 0.45477194 0.24308118 0.49062192
## NE Monolingual 0.17977702 0.18718331 0.11192028 0.24446494 0.19743337bilingual_number_of_children <- as.data.frame(proportion_table)
num_children_by_language_cat <- bilingual_number_of_children |>
pivot_wider(names_from = NCHILD, values_from = Freq)write.csv(file = "Number_of_Children_AllLanguageCats.csv", num_children_by_language_cat)INCOME
Finding different distributions of income by education and diffrent bilingual groups and languages.
income_data_2022 <- language_micro_data |>
select(AGE, INCTOT, Bilingual, PERWT, SEX, EDUCD, AGE, CLUSTER, STRATA, YEAR) |>
filter(INCTOT != 9999999 & INCTOT > 0) |>
filter(AGE > 18 & AGE < 65)Using Survey Design for Overview Analysis of Simple Bilingual vs. Not Bilingual
#setting it up
options(survey.lonely.psu = "adjust")
#creating the survey object
income_des <- svydesign(ids = ~CLUSTER,
strata = ~STRATA,
weights = ~PERWT,
data = income_data_2022)
#calculatng median by setting quantile to %50
median_income <- svyby(~INCTOT,
~Bilingual,
income_des,
svyquantile,
quantiles = 0.5,
ci = TRUE)## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() availableprint(median_income)## Bilingual INCTOT se
## Bilingual Bilingual 36475 130.1030
## Not Bilingual Not Bilingual 45000 202.0427#splitting into proper quintiles
income_data <- income_data_2022 |>
group_by(Bilingual)|>
mutate(quintile = ntile(INCTOT, 5)) |>
ungroup()
#creating a survey design with modified income data
des <- svydesign(ids = ~CLUSTER,
strata = ~STRATA,
weights = ~PERWT,
data = income_data)
#median for each quintile in income group
median_by_quintile <- svyby(~INCTOT, ~interaction(Bilingual, quintile), des, svyquantile, quantiles = 0.5, ci = TRUE)## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() availableprint(median_by_quintile)## interaction(Bilingual, quintile) INCTOT se
## Bilingual.1 Bilingual.1 7584.811 81.88591
## Not Bilingual.1 Not Bilingual.1 7599.000 112.49741
## Bilingual.2 Bilingual.2 21900.000 62.24347
## Not Bilingual.2 Not Bilingual.2 24861.000 96.68145
## Bilingual.3 Bilingual.3 36400.000 122.95643
## Not Bilingual.3 Not Bilingual.3 45360.000 57.65174
## Bilingual.4 Bilingual.4 58453.000 106.23887
## Not Bilingual.4 Not Bilingual.4 71189.000 168.11449
## Bilingual.5 Bilingual.5 110000.000 565.80342
## Not Bilingual.5 Not Bilingual.5 135977.000 424.99025#changing the names of columns for clarity and separating interaction
final_median_by_quintile <- median_by_quintile |>
separate(`interaction(Bilingual, quintile)`, into = c("Bilingual", "Quintile"), sep = "\\.") |>
rename(median_income = INCTOT) Income Medians by Education
CODES:
| CODE | Educational Level |
|---|---|
| 001 & 999 | N/a & missing |
| 002 | no schooling completed |
| 10-61 | grade school |
| 062 | high school or GED |
| 65-100 | one or more years of college, no degree |
| 101 | bachelors |
| 114 | masters |
| 115 | professional degree beyond bachelors |
| 116 | doctoral |
library(dplyr)
income_data_education <- income_data_2022 |>
mutate(Educational_Level = case_when(
EDUCD %in% c(1, 999) ~ "N/A or Missing",
EDUCD == 2 ~ "No Schooling Completed",
EDUCD >= 10 & EDUCD < 62 ~ "No High School Degree or GED",
EDUCD >= 62 & EDUCD < 65 ~ "High School or GED",
EDUCD >= 65 & EDUCD <= 100 ~ "Some College, No Degree",
EDUCD == 101 ~ "Bachelor's",
EDUCD == 114 ~ "Master's",
EDUCD == 115 ~ "Professional Degree Beyond Bachelor's",
EDUCD == 116 ~ "Doctoral",
TRUE ~ NA_character_
))
print(income_data_education)## # A tibble: 319,848 × 10
## AGE INCTOT Bilingual PERWT SEX EDUCD CLUSTER STRATA YEAR
## <int+lbl> <dbl+lbl> <chr> <dbl> <int+lbl> <int+lbl> <dbl> <dbl> <int>
## 1 34 75989 Bilingual 20 1 [Male] 63 [Regu… 2.02e12 70048 2022
## 2 23 1169 Bilingual 8 1 [Male] 71 [1 or… 2.02e12 510048 2022
## 3 19 11691 Bilingual 8 1 [Male] 65 [Some… 2.02e12 400048 2022
## 4 19 701 Bilingual 11 1 [Male] 71 [1 or… 2.02e12 460348 2022
## 5 20 11691 Bilingual 10 1 [Male] 71 [1 or… 2.02e12 690048 2022
## 6 22 4676 Bilingual 16 2 [Female] 71 [1 or… 2.02e12 590248 2022
## 7 58 30863 Bilingual 17 1 [Male] 63 [Regu… 2.02e12 380148 2022
## 8 52 35072 Bilingual 18 1 [Male] 71 [1 or… 2.02e12 680748 2022
## 9 42 2104 Bilingual 6 1 [Male] 81 [Asso… 2.02e12 690048 2022
## 10 31 9352 Bilingual 16 1 [Male] 40 [Grad… 2.02e12 462548 2022
## # ℹ 319,838 more rows
## # ℹ 1 more variable: Educational_Level <chr>income_data_education |>
filter(is.na(Educational_Level))## # A tibble: 0 × 10
## # ℹ 10 variables: AGE <int+lbl>, INCTOT <dbl+lbl>, Bilingual <chr>,
## # PERWT <dbl>, SEX <int+lbl>, EDUCD <int+lbl>, CLUSTER <dbl>, STRATA <dbl>,
## # YEAR <int>, Educational_Level <chr>#creating survey design for education dataset
des_edu <- svydesign(ids = ~CLUSTER,
strata = ~STRATA,
weights = ~PERWT,
data = income_data_education)
#calculating the median income for each education level within each bilingual group
median_by_education <- svyby(~INCTOT, ~interaction(Bilingual, Educational_Level), des_edu, svyquantile, quantiles = 0.5, ci = TRUE)## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available#for clarity
median_by_education <- median_by_education |>
separate(`interaction(Bilingual, Educational_Level)`, into = c("Bilingual", "Educational_Level"), sep = "\\.")|>
rename(median_income = INCTOT) |>
rename(se_median_income = se) |>
select(Bilingual, Educational_Level, median_income, se_median_income)
print(median_by_education)## Bilingual
## Bilingual.Bachelor's Bilingual
## Not Bilingual.Bachelor's Not Bilingual
## Bilingual.Doctoral Bilingual
## Not Bilingual.Doctoral Not Bilingual
## Bilingual.High School or GED Bilingual
## Not Bilingual.High School or GED Not Bilingual
## Bilingual.Master's Bilingual
## Not Bilingual.Master's Not Bilingual
## Bilingual.No High School Degree or GED Bilingual
## Not Bilingual.No High School Degree or GED Not Bilingual
## Bilingual.No Schooling Completed Bilingual
## Not Bilingual.No Schooling Completed Not Bilingual
## Bilingual.Professional Degree Beyond Bachelor's Bilingual
## Not Bilingual.Professional Degree Beyond Bachelor's Not Bilingual
## Bilingual.Some College, No Degree Bilingual
## Not Bilingual.Some College, No Degree Not Bilingual
## Educational_Level
## Bilingual.Bachelor's Bachelor's
## Not Bilingual.Bachelor's Bachelor's
## Bilingual.Doctoral Doctoral
## Not Bilingual.Doctoral Doctoral
## Bilingual.High School or GED High School or GED
## Not Bilingual.High School or GED High School or GED
## Bilingual.Master's Master's
## Not Bilingual.Master's Master's
## Bilingual.No High School Degree or GED No High School Degree or GED
## Not Bilingual.No High School Degree or GED No High School Degree or GED
## Bilingual.No Schooling Completed No Schooling Completed
## Not Bilingual.No Schooling Completed No Schooling Completed
## Bilingual.Professional Degree Beyond Bachelor's Professional Degree Beyond Bachelor's
## Not Bilingual.Professional Degree Beyond Bachelor's Professional Degree Beyond Bachelor's
## Bilingual.Some College, No Degree Some College, No Degree
## Not Bilingual.Some College, No Degree Some College, No Degree
## median_income
## Bilingual.Bachelor's 56207
## Not Bilingual.Bachelor's 65000
## Bilingual.Doctoral 93525
## Not Bilingual.Doctoral 100000
## Bilingual.High School or GED 29854
## Not Bilingual.High School or GED 30000
## Bilingual.Master's 80375
## Not Bilingual.Master's 76745
## Bilingual.No High School Degree or GED 28329
## Not Bilingual.No High School Degree or GED 20898
## Bilingual.No Schooling Completed 30266
## Not Bilingual.No Schooling Completed 21618
## Bilingual.Professional Degree Beyond Bachelor's 95000
## Not Bilingual.Professional Degree Beyond Bachelor's 120000
## Bilingual.Some College, No Degree 32427
## Not Bilingual.Some College, No Degree 38000
## se_median_income
## Bilingual.Bachelor's 445.4339
## Not Bilingual.Bachelor's 221.1701
## Bilingual.Doctoral 2383.8568
## Not Bilingual.Doctoral 2598.1888
## Bilingual.High School or GED 197.4458
## Not Bilingual.High School or GED 235.4551
## Bilingual.Master's 613.4615
## Not Bilingual.Master's 996.9706
## Bilingual.No High School Degree or GED 179.8377
## Not Bilingual.No High School Degree or GED 514.2023
## Bilingual.No Schooling Completed 756.1098
## Not Bilingual.No Schooling Completed 1343.5167
## Bilingual.Professional Degree Beyond Bachelor's 4296.4547
## Not Bilingual.Professional Degree Beyond Bachelor's 3897.1960
## Bilingual.Some College, No Degree 187.2428
## Not Bilingual.Some College, No Degree 383.4156median_by_education_wide <- median_by_education |>
pivot_wider(names_from = Educational_Level,
values_from = c(median_income, se_median_income))
print(median_by_education_wide)## # A tibble: 2 × 17
## Bilingual median_income_Bachel…¹ median_income_Doctoral median_income_High S…²
## <chr> <dbl> <dbl> <dbl>
## 1 Bilingual 56207 93525 29854
## 2 Not Bili… 65000 100000 30000
## # ℹ abbreviated names: ¹`median_income_Bachelor's`,
## # ²`median_income_High School or GED`
## # ℹ 13 more variables: `median_income_Master's` <dbl>,
## # `median_income_No High School Degree or GED` <dbl>,
## # `median_income_No Schooling Completed` <dbl>,
## # `median_income_Professional Degree Beyond Bachelor's` <dbl>,
## # `median_income_Some College, No Degree` <dbl>, …EXTENSIVE BILINGUAL
income_data_full <- language_micro_data_full |>
select(AGE, INCTOT, Language_Group, PERWT, SEX, EDUCD, AGE, CLUSTER, STRATA, YEAR, Bilingual_Status) |>
filter(INCTOT != 9999999 & INCTOT > 0) |>
filter(AGE > 18 & AGE < 65) |>
filter(Bilingual_Status %in% c("English Monolingual", "Bilingual"))
#recalibrating weights similar to the previous dataset
sum_weights_filtered_full <- sum(income_data_full$PERWT, na.rm = TRUE)
sum_weights_original_full <- sum(language_micro_data_full$PERWT, na.rm = TRUE)
income_data_full <- income_data_full |>
mutate(recalibrated_weight = PERWT * (sum_weights_filtered_full / sum_weights_original_full))
#applying the educational level mapping function
income_data_full <- income_data_full |>
mutate(Educational_Level = case_when(
EDUCD %in% c(1, 999) ~ "N/A or Missing",
EDUCD == 2 ~ "No Schooling Completed",
EDUCD >= 10 & EDUCD < 62 ~ "No High School Degree or GED",
EDUCD >= 62 & EDUCD < 65 ~ "High School or GED",
EDUCD >= 65 & EDUCD <= 100 ~ "Some College, No Degree",
EDUCD == 101 ~ "Bachelor's",
EDUCD == 114 ~ "Master's",
EDUCD == 115 ~ "Professional Degree Beyond Bachelor's",
EDUCD == 116 ~ "Doctoral",
TRUE ~ NA_character_
)) |>
filter(!is.na(INCTOT), !is.na(PERWT), !is.na(EDUCD))#survey design object
des_full <- svydesign(ids = ~CLUSTER,
strata = ~STRATA,
weights = ~PERWT,
data = income_data_full)
#calculating the median income for each education level within each language group
median_by_education_full <- svyby(~INCTOT, ~interaction(Language_Group, Educational_Level), des_full, svyquantile, quantiles = 0.5, ci = TRUE)## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available#formatting the results for clarity
median_by_education_full <- median_by_education_full |>
separate(`interaction(Language_Group, Educational_Level)`, into = c("Language_Group", "Educational_Level"), sep = "\\.") |>
rename(median_income = INCTOT) |>
rename(se_median_income = se) |>
select(Language_Group, Educational_Level, median_income, se_median_income)
print(median_by_education_full)## Language_Group
## Asian/Pacific Islander Languages.Bachelor's Asian/Pacific Islander Languages
## English.Bachelor's English
## Other Indo-European Languages.Bachelor's Other Indo-European Languages
## Other Languages.Bachelor's Other Languages
## Spanish.Bachelor's Spanish
## Asian/Pacific Islander Languages.Doctoral Asian/Pacific Islander Languages
## English.Doctoral English
## Other Indo-European Languages.Doctoral Other Indo-European Languages
## Other Languages.Doctoral Other Languages
## Spanish.Doctoral Spanish
## Asian/Pacific Islander Languages.High School or GED Asian/Pacific Islander Languages
## English.High School or GED English
## Other Indo-European Languages.High School or GED Other Indo-European Languages
## Other Languages.High School or GED Other Languages
## Spanish.High School or GED Spanish
## Asian/Pacific Islander Languages.Master's Asian/Pacific Islander Languages
## English.Master's English
## Other Indo-European Languages.Master's Other Indo-European Languages
## Other Languages.Master's Other Languages
## Spanish.Master's Spanish
## Asian/Pacific Islander Languages.No High School Degree or GED Asian/Pacific Islander Languages
## English.No High School Degree or GED English
## Other Indo-European Languages.No High School Degree or GED Other Indo-European Languages
## Other Languages.No High School Degree or GED Other Languages
## Spanish.No High School Degree or GED Spanish
## Asian/Pacific Islander Languages.No Schooling Completed Asian/Pacific Islander Languages
## English.No Schooling Completed English
## Other Indo-European Languages.No Schooling Completed Other Indo-European Languages
## Other Languages.No Schooling Completed Other Languages
## Spanish.No Schooling Completed Spanish
## Asian/Pacific Islander Languages.Professional Degree Beyond Bachelor's Asian/Pacific Islander Languages
## English.Professional Degree Beyond Bachelor's English
## Other Indo-European Languages.Professional Degree Beyond Bachelor's Other Indo-European Languages
## Other Languages.Professional Degree Beyond Bachelor's Other Languages
## Spanish.Professional Degree Beyond Bachelor's Spanish
## Asian/Pacific Islander Languages.Some College, No Degree Asian/Pacific Islander Languages
## English.Some College, No Degree English
## Other Indo-European Languages.Some College, No Degree Other Indo-European Languages
## Other Languages.Some College, No Degree Other Languages
## Spanish.Some College, No Degree Spanish
## Educational_Level
## Asian/Pacific Islander Languages.Bachelor's Bachelor's
## English.Bachelor's Bachelor's
## Other Indo-European Languages.Bachelor's Bachelor's
## Other Languages.Bachelor's Bachelor's
## Spanish.Bachelor's Bachelor's
## Asian/Pacific Islander Languages.Doctoral Doctoral
## English.Doctoral Doctoral
## Other Indo-European Languages.Doctoral Doctoral
## Other Languages.Doctoral Doctoral
## Spanish.Doctoral Doctoral
## Asian/Pacific Islander Languages.High School or GED High School or GED
## English.High School or GED High School or GED
## Other Indo-European Languages.High School or GED High School or GED
## Other Languages.High School or GED High School or GED
## Spanish.High School or GED High School or GED
## Asian/Pacific Islander Languages.Master's Master's
## English.Master's Master's
## Other Indo-European Languages.Master's Master's
## Other Languages.Master's Master's
## Spanish.Master's Master's
## Asian/Pacific Islander Languages.No High School Degree or GED No High School Degree or GED
## English.No High School Degree or GED No High School Degree or GED
## Other Indo-European Languages.No High School Degree or GED No High School Degree or GED
## Other Languages.No High School Degree or GED No High School Degree or GED
## Spanish.No High School Degree or GED No High School Degree or GED
## Asian/Pacific Islander Languages.No Schooling Completed No Schooling Completed
## English.No Schooling Completed No Schooling Completed
## Other Indo-European Languages.No Schooling Completed No Schooling Completed
## Other Languages.No Schooling Completed No Schooling Completed
## Spanish.No Schooling Completed No Schooling Completed
## Asian/Pacific Islander Languages.Professional Degree Beyond Bachelor's Professional Degree Beyond Bachelor's
## English.Professional Degree Beyond Bachelor's Professional Degree Beyond Bachelor's
## Other Indo-European Languages.Professional Degree Beyond Bachelor's Professional Degree Beyond Bachelor's
## Other Languages.Professional Degree Beyond Bachelor's Professional Degree Beyond Bachelor's
## Spanish.Professional Degree Beyond Bachelor's Professional Degree Beyond Bachelor's
## Asian/Pacific Islander Languages.Some College, No Degree Some College, No Degree
## English.Some College, No Degree Some College, No Degree
## Other Indo-European Languages.Some College, No Degree Some College, No Degree
## Other Languages.Some College, No Degree Some College, No Degree
## Spanish.Some College, No Degree Some College, No Degree
## median_income
## Asian/Pacific Islander Languages.Bachelor's 59450.00
## English.Bachelor's 64855.00
## Other Indo-European Languages.Bachelor's 70000.00
## Other Languages.Bachelor's 47230.70
## Spanish.Bachelor's 54046.00
## Asian/Pacific Islander Languages.Doctoral 102239.00
## English.Doctoral 100000.00
## Other Indo-European Languages.Doctoral 101154.62
## Other Languages.Doctoral 81973.90
## Spanish.Doctoral 81068.00
## Asian/Pacific Islander Languages.High School or GED 28074.30
## English.High School or GED 30000.00
## Other Indo-European Languages.High School or GED 28705.00
## Other Languages.High School or GED 28057.00
## Spanish.High School or GED 30000.00
## Asian/Pacific Islander Languages.Master's 82850.08
## English.Master's 77826.00
## Other Indo-European Languages.Master's 103116.00
## Other Languages.Master's 74634.00
## Spanish.Master's 68893.00
## Asian/Pacific Islander Languages.No High School Degree or GED 31698.52
## English.No High School Degree or GED 20963.00
## Other Indo-European Languages.No High School Degree or GED 29904.83
## Other Languages.No High School Degree or GED 25000.00
## Spanish.No High School Degree or GED 28329.00
## Asian/Pacific Islander Languages.No Schooling Completed 30018.14
## English.No Schooling Completed 21618.00
## Other Indo-European Languages.No Schooling Completed 30419.41
## Other Languages.No Schooling Completed 33795.24
## Spanish.No Schooling Completed 30255.00
## Asian/Pacific Islander Languages.Professional Degree Beyond Bachelor's 91102.28
## English.Professional Degree Beyond Bachelor's 120000.00
## Other Indo-European Languages.Professional Degree Beyond Bachelor's 114617.83
## Other Languages.Professional Degree Beyond Bachelor's 124490.23
## Spanish.Professional Degree Beyond Bachelor's 78325.10
## Asian/Pacific Islander Languages.Some College, No Degree 30000.00
## English.Some College, No Degree 38000.00
## Other Indo-European Languages.Some College, No Degree 34447.00
## Other Languages.Some College, No Degree 30000.00
## Spanish.Some College, No Degree 32427.00
## se_median_income
## Asian/Pacific Islander Languages.Bachelor's 1362.4182
## English.Bachelor's 104.8475
## Other Indo-European Languages.Bachelor's 1141.4951
## Other Languages.Bachelor's 1723.9317
## Spanish.Bachelor's 519.1036
## Asian/Pacific Islander Languages.Doctoral 4196.6798
## English.Doctoral 1492.3125
## Other Indo-European Languages.Doctoral 4620.7485
## Other Languages.Doctoral 6719.6196
## Spanish.Doctoral 4290.6418
## Asian/Pacific Islander Languages.High School or GED 793.1265
## English.High School or GED 137.2455
## Other Indo-European Languages.High School or GED 652.8833
## Other Languages.High School or GED 1161.2904
## Spanish.High School or GED 197.4450
## Asian/Pacific Islander Languages.Master's 2017.9180
## English.Master's 826.0083
## Other Indo-European Languages.Master's 1434.2437
## Other Languages.Master's 4306.6470
## Spanish.Master's 513.1665
## Asian/Pacific Islander Languages.No High School Degree or GED 1638.2313
## English.No High School Degree or GED 311.4651
## Other Indo-European Languages.No High School Degree or GED 1637.4436
## Other Languages.No High School Degree or GED 2468.7922
## Spanish.No High School Degree or GED 179.8369
## Asian/Pacific Islander Languages.No Schooling Completed 1540.7231
## English.No Schooling Completed 649.7737
## Other Indo-European Languages.No Schooling Completed 2668.1416
## Other Languages.No Schooling Completed 5119.0325
## Spanish.No Schooling Completed 834.3075
## Asian/Pacific Islander Languages.Professional Degree Beyond Bachelor's 10855.4245
## English.Professional Degree Beyond Bachelor's 2635.8749
## Other Indo-European Languages.Professional Degree Beyond Bachelor's 4638.1206
## Other Languages.Professional Degree Beyond Bachelor's 17327.0681
## Spanish.Professional Degree Beyond Bachelor's 3580.6549
## Asian/Pacific Islander Languages.Some College, No Degree 1123.2330
## English.Some College, No Degree 190.5628
## Other Indo-European Languages.Some College, No Degree 1191.4365
## Other Languages.Some College, No Degree 1639.9328
## Spanish.Some College, No Degree 190.8130#pivoting the data wider to have one row per Educational_Level
income_data_wide <- median_by_education_full |>
pivot_wider(names_from = Language_Group,
values_from = c(median_income, se_median_income))
print(income_data_wide)## # A tibble: 8 × 11
## Educational_Level median_income_Asian/…¹ median_income_English
## <chr> <dbl> <dbl>
## 1 Bachelor's 59450 64855
## 2 Doctoral 102239 100000
## 3 High School or GED 28074. 30000
## 4 Master's 82850. 77826
## 5 No High School Degree or GED 31699. 20963
## 6 No Schooling Completed 30018. 21618
## 7 Professional Degree Beyond Bache… 91102. 120000
## 8 Some College, No Degree 30000 38000
## # ℹ abbreviated name: ¹`median_income_Asian/Pacific Islander Languages`
## # ℹ 8 more variables: `median_income_Other Indo-European Languages` <dbl>,
## # `median_income_Other Languages` <dbl>, median_income_Spanish <dbl>,
## # `se_median_income_Asian/Pacific Islander Languages` <dbl>,
## # se_median_income_English <dbl>,
## # `se_median_income_Other Indo-European Languages` <dbl>,
## # `se_median_income_Other Languages` <dbl>, se_median_income_Spanish <dbl>Bilingual and Non-English Monolingual
#filtering and setting up the data
income_data_full_NE <- language_micro_data_full |>
select(AGE, INCTOT, Language_Group, Bilingual_Status, PERWT, SEX, EDUCD, CLUSTER, STRATA, YEAR) |>
filter(INCTOT != 9999999 & INCTOT > 0) |>
filter(AGE > 18 & AGE < 65) |>
filter(Bilingual_Status %in% c("Bilingual", "NE Monolingual")) |>
mutate(Educational_Level = case_when(
EDUCD %in% c(1, 999) ~ "N/A or Missing",
EDUCD == 2 ~ "No Schooling Completed",
EDUCD >= 10 & EDUCD < 62 ~ "No High School Degree or GED",
EDUCD >= 62 & EDUCD < 65 ~ "High School or GED",
EDUCD >= 65 & EDUCD <= 100 ~ "Some College, No Degree",
EDUCD == 101 ~ "Bachelor's",
EDUCD == 114 ~ "Master's & Professional Degree Beyond Bachelor's",
EDUCD == 115 ~ "Master's & Professional Degree Beyond Bachelor's",
EDUCD == 116 ~ "Doctoral",
TRUE ~ NA_character_
)) |>
filter(!is.na(INCTOT), !is.na(PERWT), !is.na(EDUCD))
table(income_data_full_NE$Educational_Level)##
## Bachelor's
## 33554
## Doctoral
## 3131
## High School or GED
## 49626
## Master's & Professional Degree Beyond Bachelor's
## 19321
## No High School Degree or GED
## 35302
## No Schooling Completed
## 7551
## Some College, No Degree
## 51295des_full_NE <- svydesign(ids = ~CLUSTER,
strata = ~STRATA,
weights = ~PERWT,
data = income_data_full_NE)
#calculating the median income by education level for each language group and bilingual status
median_by_education_full_NE <- svyby(~INCTOT,
~interaction(Language_Group, Educational_Level, Bilingual_Status),
des_full_NE,
svyquantile,
quantiles = 0.5,
ci = TRUE)## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available#formatting the results for clarity
median_by_education_full_NE <- median_by_education_full_NE |>
separate(`interaction(Language_Group, Educational_Level, Bilingual_Status)`,
into = c("Language_Group", "Educational_Level", "Bilingual_Status"), sep = "\\.") |>
rename(median_income = INCTOT) |>
rename(se_median_income = se) |>
select(Language_Group, Educational_Level, Bilingual_Status, median_income, se_median_income)
print(median_by_education_full_NE)## Language_Group
## Asian/Pacific Islander Languages.Bachelor's.Bilingual Asian/Pacific Islander Languages
## Other Indo-European Languages.Bachelor's.Bilingual Other Indo-European Languages
## Other Languages.Bachelor's.Bilingual Other Languages
## Spanish.Bachelor's.Bilingual Spanish
## Asian/Pacific Islander Languages.Doctoral.Bilingual Asian/Pacific Islander Languages
## Other Indo-European Languages.Doctoral.Bilingual Other Indo-European Languages
## Other Languages.Doctoral.Bilingual Other Languages
## Spanish.Doctoral.Bilingual Spanish
## Asian/Pacific Islander Languages.High School or GED.Bilingual Asian/Pacific Islander Languages
## Other Indo-European Languages.High School or GED.Bilingual Other Indo-European Languages
## Other Languages.High School or GED.Bilingual Other Languages
## Spanish.High School or GED.Bilingual Spanish
## Asian/Pacific Islander Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual Asian/Pacific Islander Languages
## Other Indo-European Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual Other Indo-European Languages
## Other Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual Other Languages
## Spanish.Master's & Professional Degree Beyond Bachelor's.Bilingual Spanish
## Asian/Pacific Islander Languages.No High School Degree or GED.Bilingual Asian/Pacific Islander Languages
## Other Indo-European Languages.No High School Degree or GED.Bilingual Other Indo-European Languages
## Other Languages.No High School Degree or GED.Bilingual Other Languages
## Spanish.No High School Degree or GED.Bilingual Spanish
## Asian/Pacific Islander Languages.No Schooling Completed.Bilingual Asian/Pacific Islander Languages
## Other Indo-European Languages.No Schooling Completed.Bilingual Other Indo-European Languages
## Other Languages.No Schooling Completed.Bilingual Other Languages
## Spanish.No Schooling Completed.Bilingual Spanish
## Asian/Pacific Islander Languages.Some College, No Degree.Bilingual Asian/Pacific Islander Languages
## Other Indo-European Languages.Some College, No Degree.Bilingual Other Indo-European Languages
## Other Languages.Some College, No Degree.Bilingual Other Languages
## Spanish.Some College, No Degree.Bilingual Spanish
## Asian/Pacific Islander Languages.Bachelor's.NE Monolingual Asian/Pacific Islander Languages
## Other Indo-European Languages.Bachelor's.NE Monolingual Other Indo-European Languages
## Other Languages.Bachelor's.NE Monolingual Other Languages
## Spanish.Bachelor's.NE Monolingual Spanish
## Asian/Pacific Islander Languages.Doctoral.NE Monolingual Asian/Pacific Islander Languages
## Other Indo-European Languages.Doctoral.NE Monolingual Other Indo-European Languages
## Spanish.Doctoral.NE Monolingual Spanish
## Asian/Pacific Islander Languages.High School or GED.NE Monolingual Asian/Pacific Islander Languages
## Other Indo-European Languages.High School or GED.NE Monolingual Other Indo-European Languages
## Other Languages.High School or GED.NE Monolingual Other Languages
## Spanish.High School or GED.NE Monolingual Spanish
## Asian/Pacific Islander Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual Asian/Pacific Islander Languages
## Other Indo-European Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual Other Indo-European Languages
## Other Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual Other Languages
## Spanish.Master's & Professional Degree Beyond Bachelor's.NE Monolingual Spanish
## Asian/Pacific Islander Languages.No High School Degree or GED.NE Monolingual Asian/Pacific Islander Languages
## Other Indo-European Languages.No High School Degree or GED.NE Monolingual Other Indo-European Languages
## Other Languages.No High School Degree or GED.NE Monolingual Other Languages
## Spanish.No High School Degree or GED.NE Monolingual Spanish
## Asian/Pacific Islander Languages.No Schooling Completed.NE Monolingual Asian/Pacific Islander Languages
## Other Indo-European Languages.No Schooling Completed.NE Monolingual Other Indo-European Languages
## Other Languages.No Schooling Completed.NE Monolingual Other Languages
## Spanish.No Schooling Completed.NE Monolingual Spanish
## Asian/Pacific Islander Languages.Some College, No Degree.NE Monolingual Asian/Pacific Islander Languages
## Other Indo-European Languages.Some College, No Degree.NE Monolingual Other Indo-European Languages
## Other Languages.Some College, No Degree.NE Monolingual Other Languages
## Spanish.Some College, No Degree.NE Monolingual Spanish
## Educational_Level
## Asian/Pacific Islander Languages.Bachelor's.Bilingual Bachelor's
## Other Indo-European Languages.Bachelor's.Bilingual Bachelor's
## Other Languages.Bachelor's.Bilingual Bachelor's
## Spanish.Bachelor's.Bilingual Bachelor's
## Asian/Pacific Islander Languages.Doctoral.Bilingual Doctoral
## Other Indo-European Languages.Doctoral.Bilingual Doctoral
## Other Languages.Doctoral.Bilingual Doctoral
## Spanish.Doctoral.Bilingual Doctoral
## Asian/Pacific Islander Languages.High School or GED.Bilingual High School or GED
## Other Indo-European Languages.High School or GED.Bilingual High School or GED
## Other Languages.High School or GED.Bilingual High School or GED
## Spanish.High School or GED.Bilingual High School or GED
## Asian/Pacific Islander Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual Master's & Professional Degree Beyond Bachelor's
## Other Indo-European Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual Master's & Professional Degree Beyond Bachelor's
## Other Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual Master's & Professional Degree Beyond Bachelor's
## Spanish.Master's & Professional Degree Beyond Bachelor's.Bilingual Master's & Professional Degree Beyond Bachelor's
## Asian/Pacific Islander Languages.No High School Degree or GED.Bilingual No High School Degree or GED
## Other Indo-European Languages.No High School Degree or GED.Bilingual No High School Degree or GED
## Other Languages.No High School Degree or GED.Bilingual No High School Degree or GED
## Spanish.No High School Degree or GED.Bilingual No High School Degree or GED
## Asian/Pacific Islander Languages.No Schooling Completed.Bilingual No Schooling Completed
## Other Indo-European Languages.No Schooling Completed.Bilingual No Schooling Completed
## Other Languages.No Schooling Completed.Bilingual No Schooling Completed
## Spanish.No Schooling Completed.Bilingual No Schooling Completed
## Asian/Pacific Islander Languages.Some College, No Degree.Bilingual Some College, No Degree
## Other Indo-European Languages.Some College, No Degree.Bilingual Some College, No Degree
## Other Languages.Some College, No Degree.Bilingual Some College, No Degree
## Spanish.Some College, No Degree.Bilingual Some College, No Degree
## Asian/Pacific Islander Languages.Bachelor's.NE Monolingual Bachelor's
## Other Indo-European Languages.Bachelor's.NE Monolingual Bachelor's
## Other Languages.Bachelor's.NE Monolingual Bachelor's
## Spanish.Bachelor's.NE Monolingual Bachelor's
## Asian/Pacific Islander Languages.Doctoral.NE Monolingual Doctoral
## Other Indo-European Languages.Doctoral.NE Monolingual Doctoral
## Spanish.Doctoral.NE Monolingual Doctoral
## Asian/Pacific Islander Languages.High School or GED.NE Monolingual High School or GED
## Other Indo-European Languages.High School or GED.NE Monolingual High School or GED
## Other Languages.High School or GED.NE Monolingual High School or GED
## Spanish.High School or GED.NE Monolingual High School or GED
## Asian/Pacific Islander Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual Master's & Professional Degree Beyond Bachelor's
## Other Indo-European Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual Master's & Professional Degree Beyond Bachelor's
## Other Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual Master's & Professional Degree Beyond Bachelor's
## Spanish.Master's & Professional Degree Beyond Bachelor's.NE Monolingual Master's & Professional Degree Beyond Bachelor's
## Asian/Pacific Islander Languages.No High School Degree or GED.NE Monolingual No High School Degree or GED
## Other Indo-European Languages.No High School Degree or GED.NE Monolingual No High School Degree or GED
## Other Languages.No High School Degree or GED.NE Monolingual No High School Degree or GED
## Spanish.No High School Degree or GED.NE Monolingual No High School Degree or GED
## Asian/Pacific Islander Languages.No Schooling Completed.NE Monolingual No Schooling Completed
## Other Indo-European Languages.No Schooling Completed.NE Monolingual No Schooling Completed
## Other Languages.No Schooling Completed.NE Monolingual No Schooling Completed
## Spanish.No Schooling Completed.NE Monolingual No Schooling Completed
## Asian/Pacific Islander Languages.Some College, No Degree.NE Monolingual Some College, No Degree
## Other Indo-European Languages.Some College, No Degree.NE Monolingual Some College, No Degree
## Other Languages.Some College, No Degree.NE Monolingual Some College, No Degree
## Spanish.Some College, No Degree.NE Monolingual Some College, No Degree
## Bilingual_Status
## Asian/Pacific Islander Languages.Bachelor's.Bilingual Bilingual
## Other Indo-European Languages.Bachelor's.Bilingual Bilingual
## Other Languages.Bachelor's.Bilingual Bilingual
## Spanish.Bachelor's.Bilingual Bilingual
## Asian/Pacific Islander Languages.Doctoral.Bilingual Bilingual
## Other Indo-European Languages.Doctoral.Bilingual Bilingual
## Other Languages.Doctoral.Bilingual Bilingual
## Spanish.Doctoral.Bilingual Bilingual
## Asian/Pacific Islander Languages.High School or GED.Bilingual Bilingual
## Other Indo-European Languages.High School or GED.Bilingual Bilingual
## Other Languages.High School or GED.Bilingual Bilingual
## Spanish.High School or GED.Bilingual Bilingual
## Asian/Pacific Islander Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual Bilingual
## Other Indo-European Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual Bilingual
## Other Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual Bilingual
## Spanish.Master's & Professional Degree Beyond Bachelor's.Bilingual Bilingual
## Asian/Pacific Islander Languages.No High School Degree or GED.Bilingual Bilingual
## Other Indo-European Languages.No High School Degree or GED.Bilingual Bilingual
## Other Languages.No High School Degree or GED.Bilingual Bilingual
## Spanish.No High School Degree or GED.Bilingual Bilingual
## Asian/Pacific Islander Languages.No Schooling Completed.Bilingual Bilingual
## Other Indo-European Languages.No Schooling Completed.Bilingual Bilingual
## Other Languages.No Schooling Completed.Bilingual Bilingual
## Spanish.No Schooling Completed.Bilingual Bilingual
## Asian/Pacific Islander Languages.Some College, No Degree.Bilingual Bilingual
## Other Indo-European Languages.Some College, No Degree.Bilingual Bilingual
## Other Languages.Some College, No Degree.Bilingual Bilingual
## Spanish.Some College, No Degree.Bilingual Bilingual
## Asian/Pacific Islander Languages.Bachelor's.NE Monolingual NE Monolingual
## Other Indo-European Languages.Bachelor's.NE Monolingual NE Monolingual
## Other Languages.Bachelor's.NE Monolingual NE Monolingual
## Spanish.Bachelor's.NE Monolingual NE Monolingual
## Asian/Pacific Islander Languages.Doctoral.NE Monolingual NE Monolingual
## Other Indo-European Languages.Doctoral.NE Monolingual NE Monolingual
## Spanish.Doctoral.NE Monolingual NE Monolingual
## Asian/Pacific Islander Languages.High School or GED.NE Monolingual NE Monolingual
## Other Indo-European Languages.High School or GED.NE Monolingual NE Monolingual
## Other Languages.High School or GED.NE Monolingual NE Monolingual
## Spanish.High School or GED.NE Monolingual NE Monolingual
## Asian/Pacific Islander Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual NE Monolingual
## Other Indo-European Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual NE Monolingual
## Other Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual NE Monolingual
## Spanish.Master's & Professional Degree Beyond Bachelor's.NE Monolingual NE Monolingual
## Asian/Pacific Islander Languages.No High School Degree or GED.NE Monolingual NE Monolingual
## Other Indo-European Languages.No High School Degree or GED.NE Monolingual NE Monolingual
## Other Languages.No High School Degree or GED.NE Monolingual NE Monolingual
## Spanish.No High School Degree or GED.NE Monolingual NE Monolingual
## Asian/Pacific Islander Languages.No Schooling Completed.NE Monolingual NE Monolingual
## Other Indo-European Languages.No Schooling Completed.NE Monolingual NE Monolingual
## Other Languages.No Schooling Completed.NE Monolingual NE Monolingual
## Spanish.No Schooling Completed.NE Monolingual NE Monolingual
## Asian/Pacific Islander Languages.Some College, No Degree.NE Monolingual NE Monolingual
## Other Indo-European Languages.Some College, No Degree.NE Monolingual NE Monolingual
## Other Languages.Some College, No Degree.NE Monolingual NE Monolingual
## Spanish.Some College, No Degree.NE Monolingual NE Monolingual
## median_income
## Asian/Pacific Islander Languages.Bachelor's.Bilingual 59450.00
## Other Indo-European Languages.Bachelor's.Bilingual 70000.00
## Other Languages.Bachelor's.Bilingual 47230.70
## Spanish.Bachelor's.Bilingual 54046.00
## Asian/Pacific Islander Languages.Doctoral.Bilingual 102239.00
## Other Indo-European Languages.Doctoral.Bilingual 101154.62
## Other Languages.Doctoral.Bilingual 81973.90
## Spanish.Doctoral.Bilingual 81068.00
## Asian/Pacific Islander Languages.High School or GED.Bilingual 28074.30
## Other Indo-European Languages.High School or GED.Bilingual 28705.00
## Other Languages.High School or GED.Bilingual 28057.00
## Spanish.High School or GED.Bilingual 30000.00
## Asian/Pacific Islander Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual 84172.00
## Other Indo-European Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual 104652.53
## Other Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual 78961.25
## Spanish.Master's & Professional Degree Beyond Bachelor's.Bilingual 69400.51
## Asian/Pacific Islander Languages.No High School Degree or GED.Bilingual 31698.52
## Other Indo-European Languages.No High School Degree or GED.Bilingual 29904.83
## Other Languages.No High School Degree or GED.Bilingual 25000.00
## Spanish.No High School Degree or GED.Bilingual 28329.00
## Asian/Pacific Islander Languages.No Schooling Completed.Bilingual 30018.14
## Other Indo-European Languages.No Schooling Completed.Bilingual 30419.41
## Other Languages.No Schooling Completed.Bilingual 33795.24
## Spanish.No Schooling Completed.Bilingual 30255.00
## Asian/Pacific Islander Languages.Some College, No Degree.Bilingual 30000.00
## Other Indo-European Languages.Some College, No Degree.Bilingual 34447.00
## Other Languages.Some College, No Degree.Bilingual 30000.00
## Spanish.Some College, No Degree.Bilingual 32427.00
## Asian/Pacific Islander Languages.Bachelor's.NE Monolingual 35186.67
## Other Indo-European Languages.Bachelor's.NE Monolingual 27509.32
## Other Languages.Bachelor's.NE Monolingual 29785.71
## Spanish.Bachelor's.NE Monolingual 28817.47
## Asian/Pacific Islander Languages.Doctoral.NE Monolingual 55956.17
## Other Indo-European Languages.Doctoral.NE Monolingual 66093.05
## Spanish.Doctoral.NE Monolingual 44053.50
## Asian/Pacific Islander Languages.High School or GED.NE Monolingual 24113.00
## Other Indo-European Languages.High School or GED.NE Monolingual 22643.14
## Other Languages.High School or GED.NE Monolingual 21388.50
## Spanish.High School or GED.NE Monolingual 27023.00
## Asian/Pacific Islander Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual 35967.38
## Other Indo-European Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual 49720.18
## Other Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual 64088.28
## Spanish.Master's & Professional Degree Beyond Bachelor's.NE Monolingual 37803.87
## Asian/Pacific Islander Languages.No High School Degree or GED.NE Monolingual 24929.00
## Other Indo-European Languages.No High School Degree or GED.NE Monolingual 21043.00
## Other Languages.No High School Degree or GED.NE Monolingual 24113.00
## Spanish.No High School Degree or GED.NE Monolingual 24753.00
## Asian/Pacific Islander Languages.No Schooling Completed.NE Monolingual 26891.29
## Other Indo-European Languages.No Schooling Completed.NE Monolingual 24153.85
## Other Languages.No Schooling Completed.NE Monolingual 17616.67
## Spanish.No Schooling Completed.NE Monolingual 25000.00
## Asian/Pacific Islander Languages.Some College, No Degree.NE Monolingual 23941.93
## Other Indo-European Languages.Some College, No Degree.NE Monolingual 29887.33
## Other Languages.Some College, No Degree.NE Monolingual 26995.39
## Spanish.Some College, No Degree.NE Monolingual 28104.00
## se_median_income
## Asian/Pacific Islander Languages.Bachelor's.Bilingual 1360.5046
## Other Indo-European Languages.Bachelor's.Bilingual 1137.4522
## Other Languages.Bachelor's.Bilingual 1723.9317
## Spanish.Bachelor's.Bilingual 519.1036
## Asian/Pacific Islander Languages.Doctoral.Bilingual 4196.6798
## Other Indo-European Languages.Doctoral.Bilingual 4620.7485
## Other Languages.Doctoral.Bilingual 6719.6758
## Spanish.Doctoral.Bilingual 4290.6418
## Asian/Pacific Islander Languages.High School or GED.Bilingual 793.1265
## Other Indo-European Languages.High School or GED.Bilingual 652.8854
## Other Languages.High School or GED.Bilingual 1161.5210
## Spanish.High School or GED.Bilingual 197.4450
## Asian/Pacific Islander Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual 2549.8312
## Other Indo-European Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual 1557.8390
## Other Languages.Master's & Professional Degree Beyond Bachelor's.Bilingual 4069.0191
## Spanish.Master's & Professional Degree Beyond Bachelor's.Bilingual 551.4440
## Asian/Pacific Islander Languages.No High School Degree or GED.Bilingual 1638.2313
## Other Indo-European Languages.No High School Degree or GED.Bilingual 1637.3483
## Other Languages.No High School Degree or GED.Bilingual 2468.8177
## Spanish.No High School Degree or GED.Bilingual 179.8369
## Asian/Pacific Islander Languages.No Schooling Completed.Bilingual 1540.6815
## Other Indo-European Languages.No Schooling Completed.Bilingual 2667.9823
## Other Languages.No Schooling Completed.Bilingual 5119.1897
## Spanish.No Schooling Completed.Bilingual 834.2558
## Asian/Pacific Islander Languages.Some College, No Degree.Bilingual 1123.2330
## Other Indo-European Languages.Some College, No Degree.Bilingual 1190.4512
## Other Languages.Some College, No Degree.Bilingual 1639.9343
## Spanish.Some College, No Degree.Bilingual 190.8130
## Asian/Pacific Islander Languages.Bachelor's.NE Monolingual 3683.4568
## Other Indo-European Languages.Bachelor's.NE Monolingual 3352.4401
## Other Languages.Bachelor's.NE Monolingual 5400.1358
## Spanish.Bachelor's.NE Monolingual 1021.4365
## Asian/Pacific Islander Languages.Doctoral.NE Monolingual 18131.4416
## Other Indo-European Languages.Doctoral.NE Monolingual 8180.6096
## Spanish.Doctoral.NE Monolingual 21015.4020
## Asian/Pacific Islander Languages.High School or GED.NE Monolingual 1261.4210
## Other Indo-European Languages.High School or GED.NE Monolingual 2586.8476
## Other Languages.High School or GED.NE Monolingual 3238.7775
## Spanish.High School or GED.NE Monolingual 360.6477
## Asian/Pacific Islander Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual 8282.6804
## Other Indo-European Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual 11724.5220
## Other Languages.Master's & Professional Degree Beyond Bachelor's.NE Monolingual 8860.4349
## Spanish.Master's & Professional Degree Beyond Bachelor's.NE Monolingual 2294.7966
## Asian/Pacific Islander Languages.No High School Degree or GED.NE Monolingual 1117.6683
## Other Indo-European Languages.No High School Degree or GED.NE Monolingual 2963.4282
## Other Languages.No High School Degree or GED.NE Monolingual 2824.6095
## Spanish.No High School Degree or GED.NE Monolingual 255.0814
## Asian/Pacific Islander Languages.No Schooling Completed.NE Monolingual 1579.7710
## Other Indo-European Languages.No Schooling Completed.NE Monolingual 4249.3332
## Other Languages.No Schooling Completed.NE Monolingual 3209.0684
## Spanish.No Schooling Completed.NE Monolingual 731.3002
## Asian/Pacific Islander Languages.Some College, No Degree.NE Monolingual 1745.5763
## Other Indo-European Languages.Some College, No Degree.NE Monolingual 2377.5266
## Other Languages.Some College, No Degree.NE Monolingual 9977.1124
## Spanish.Some College, No Degree.NE Monolingual 517.8771income_data_wide_NE <- median_by_education_full_NE |>
pivot_wider(names_from = Language_Group,
values_from = c(median_income, se_median_income))
print(income_data_wide_NE)## # A tibble: 14 × 10
## Educational_Level Bilingual_Status median_income_Asian/…¹
## <chr> <chr> <dbl>
## 1 Bachelor's Bilingual 59450
## 2 Doctoral Bilingual 102239
## 3 High School or GED Bilingual 28074.
## 4 Master's & Professional Degree Beyon… Bilingual 84172
## 5 No High School Degree or GED Bilingual 31699.
## 6 No Schooling Completed Bilingual 30018.
## 7 Some College, No Degree Bilingual 30000
## 8 Bachelor's NE Monolingual 35187.
## 9 Doctoral NE Monolingual 55956.
## 10 High School or GED NE Monolingual 24113
## 11 Master's & Professional Degree Beyon… NE Monolingual 35967.
## 12 No High School Degree or GED NE Monolingual 24929
## 13 No Schooling Completed NE Monolingual 26891.
## 14 Some College, No Degree NE Monolingual 23942.
## # ℹ abbreviated name: ¹`median_income_Asian/Pacific Islander Languages`
## # ℹ 7 more variables: `median_income_Other Indo-European Languages` <dbl>,
## # `median_income_Other Languages` <dbl>, median_income_Spanish <dbl>,
## # `se_median_income_Asian/Pacific Islander Languages` <dbl>,
## # `se_median_income_Other Indo-European Languages` <dbl>,
## # `se_median_income_Other Languages` <dbl>, se_median_income_Spanish <dbl>#filtering and setting up the data
income_data_all_stat <- language_micro_data_full |>
select(AGE, INCTOT, Bilingual_Status, PERWT, SEX, CLUSTER, STRATA, YEAR) |>
filter(INCTOT != 9999999 & INCTOT > 0) |>
filter(AGE > 18 & AGE < 65) des_all_stat <- svydesign(ids = ~CLUSTER,
strata = ~STRATA,
weights = ~PERWT,
data = income_data_all_stat)
bilingual_median <- as.numeric(svyquantile(~INCTOT, subset(des_all_stat, Bilingual_Status == "Bilingual"), quantiles = 0.5, ci = FALSE))
english_mono_median <- as.numeric(svyquantile(~INCTOT, subset(des_all_stat, Bilingual_Status == "English Monolingual"), quantiles = 0.5, ci = FALSE))
non_english_mono_median <- as.numeric(svyquantile(~INCTOT, subset(des_all_stat, Bilingual_Status == "NE Monolingual"), quantiles = 0.5, ci = FALSE))
#combining results into a single data frame
median_by_bilingual_stat <- data.frame(
Bilingual_Status = c("Bilingual", "English Monolingual", "NE Monolingual"),
median_income = c(bilingual_median, english_mono_median, non_english_mono_median)
)
print(median_by_bilingual_stat)## Bilingual_Status median_income
## 1 Bilingual 36475
## 2 English Monolingual 44966
## 3 NE Monolingual 25942Linear Regression
lin_reg_income <- language_micro_data_full |>
select(AGE, RACE, INCTOT, Language_Group, Bilingual_Status, PERWT, SEX, EDUCD, CLUSTER, STRATA, YEAR) |>
filter(INCTOT != 9999999 & INCTOT > 0) |>
filter(AGE > 18 & AGE < 65) |>
filter(SEX != 9) |>
filter(Bilingual_Status %in% c("Bilingual", "English Monolingual")) |>
mutate(Educational_Level = case_when(
EDUCD %in% c(1, 999) ~ "N/A or Missing",
EDUCD == 2 ~ "No Schooling Completed",
EDUCD >= 10 & EDUCD < 62 ~ "No High School Degree or GED",
EDUCD >= 62 & EDUCD < 65 ~ "High School or GED",
EDUCD >= 65 & EDUCD <= 100 ~ "Some College, No Degree",
EDUCD == 101 ~ "Bachelor's",
EDUCD == 114 ~ "Master's & Professional Degree Beyond Bachelor's",
EDUCD == 115 ~ "Master's & Professional Degree Beyond Bachelor's",
EDUCD == 116 ~ "Doctoral",
TRUE ~ NA_character_
)) |>
filter(!is.na(INCTOT), !is.na(PERWT), !is.na(EDUCD))
des_edu_lin_reg <- svydesign(
ids = ~CLUSTER,
strata = ~STRATA,
weights = ~PERWT,
data = lin_reg_income
)
biling_model <- svyglm(
INCTOT ~ Educational_Level * Bilingual_Status,
design = des_edu_lin_reg
)
# summary(biling_model)
language_model <- svyglm(
INCTOT ~ Educational_Level * Language_Group,
design = des_edu_lin_reg
)
summary(language_model)##
## Call:
## svyglm(formula = INCTOT ~ Educational_Level * Language_Group,
## design = des_edu_lin_reg)
##
## Survey design:
## svydesign(ids = ~CLUSTER, strata = ~STRATA, weights = ~PERWT,
## data = lin_reg_income)
##
## Coefficients:
## Estimate
## (Intercept) 72412.2
## Educational_LevelDoctoral 54566.3
## Educational_LevelHigh School or GED -35387.3
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's 37536.7
## Educational_LevelNo High School Degree or GED -32303.6
## Educational_LevelNo Schooling Completed -31013.9
## Educational_LevelSome College, No Degree -30592.7
## Language_GroupEnglish 15997.6
## Language_GroupOther Indo-European Languages 13638.8
## Language_GroupOther Languages -11486.8
## Language_GroupSpanish -6887.7
## Educational_LevelDoctoral:Language_GroupEnglish -4664.2
## Educational_LevelHigh School or GED:Language_GroupEnglish -12585.4
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupEnglish -4151.5
## Educational_LevelNo High School Degree or GED:Language_GroupEnglish -24664.4
## Educational_LevelNo Schooling Completed:Language_GroupEnglish -24204.3
## Educational_LevelSome College, No Degree:Language_GroupEnglish -7204.5
## Educational_LevelDoctoral:Language_GroupOther Indo-European Languages -7480.2
## Educational_LevelHigh School or GED:Language_GroupOther Indo-European Languages -7335.8
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupOther Indo-European Languages -661.2
## Educational_LevelNo High School Degree or GED:Language_GroupOther Indo-European Languages -7749.3
## Educational_LevelNo Schooling Completed:Language_GroupOther Indo-European Languages -13556.6
## Educational_LevelSome College, No Degree:Language_GroupOther Indo-European Languages -6372.2
## Educational_LevelDoctoral:Language_GroupOther Languages -21904.9
## Educational_LevelHigh School or GED:Language_GroupOther Languages 12097.9
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupOther Languages 9093.5
## Educational_LevelNo High School Degree or GED:Language_GroupOther Languages 6025.3
## Educational_LevelNo Schooling Completed:Language_GroupOther Languages 15665.9
## Educational_LevelSome College, No Degree:Language_GroupOther Languages 10657.9
## Educational_LevelDoctoral:Language_GroupSpanish -2317.9
## Educational_LevelHigh School or GED:Language_GroupSpanish 7208.2
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupSpanish -7277.9
## Educational_LevelNo High School Degree or GED:Language_GroupSpanish 2265.3
## Educational_LevelNo Schooling Completed:Language_GroupSpanish 3511.8
## Educational_LevelSome College, No Degree:Language_GroupSpanish 6032.2
## Std. Error
## (Intercept) 1237.1
## Educational_LevelDoctoral 4764.1
## Educational_LevelHigh School or GED 1825.1
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's 3654.9
## Educational_LevelNo High School Degree or GED 3653.7
## Educational_LevelNo Schooling Completed 4141.5
## Educational_LevelSome College, No Degree 1734.6
## Language_GroupEnglish 1299.3
## Language_GroupOther Indo-European Languages 1871.6
## Language_GroupOther Languages 2452.9
## Language_GroupSpanish 1405.2
## Educational_LevelDoctoral:Language_GroupEnglish 5398.5
## Educational_LevelHigh School or GED:Language_GroupEnglish 1879.1
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupEnglish 3759.7
## Educational_LevelNo High School Degree or GED:Language_GroupEnglish 3699.2
## Educational_LevelNo Schooling Completed:Language_GroupEnglish 4297.6
## Educational_LevelSome College, No Degree:Language_GroupEnglish 1792.6
## Educational_LevelDoctoral:Language_GroupOther Indo-European Languages 7722.2
## Educational_LevelHigh School or GED:Language_GroupOther Indo-European Languages 2922.9
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupOther Indo-European Languages 4247.8
## Educational_LevelNo High School Degree or GED:Language_GroupOther Indo-European Languages 5070.3
## Educational_LevelNo Schooling Completed:Language_GroupOther Indo-European Languages 6368.8
## Educational_LevelSome College, No Degree:Language_GroupOther Indo-European Languages 2877.9
## Educational_LevelDoctoral:Language_GroupOther Languages 8290.3
## Educational_LevelHigh School or GED:Language_GroupOther Languages 3423.4
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupOther Languages 6412.4
## Educational_LevelNo High School Degree or GED:Language_GroupOther Languages 7886.6
## Educational_LevelNo Schooling Completed:Language_GroupOther Languages 12319.3
## Educational_LevelSome College, No Degree:Language_GroupOther Languages 3179.0
## Educational_LevelDoctoral:Language_GroupSpanish 7586.1
## Educational_LevelHigh School or GED:Language_GroupSpanish 1964.6
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupSpanish 4086.4
## Educational_LevelNo High School Degree or GED:Language_GroupSpanish 3735.5
## Educational_LevelNo Schooling Completed:Language_GroupSpanish 4312.8
## Educational_LevelSome College, No Degree:Language_GroupSpanish 1880.4
## t value
## (Intercept) 58.536
## Educational_LevelDoctoral 11.454
## Educational_LevelHigh School or GED -19.389
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's 10.270
## Educational_LevelNo High School Degree or GED -8.841
## Educational_LevelNo Schooling Completed -7.489
## Educational_LevelSome College, No Degree -17.637
## Language_GroupEnglish 12.313
## Language_GroupOther Indo-European Languages 7.287
## Language_GroupOther Languages -4.683
## Language_GroupSpanish -4.902
## Educational_LevelDoctoral:Language_GroupEnglish -0.864
## Educational_LevelHigh School or GED:Language_GroupEnglish -6.698
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupEnglish -1.104
## Educational_LevelNo High School Degree or GED:Language_GroupEnglish -6.667
## Educational_LevelNo Schooling Completed:Language_GroupEnglish -5.632
## Educational_LevelSome College, No Degree:Language_GroupEnglish -4.019
## Educational_LevelDoctoral:Language_GroupOther Indo-European Languages -0.969
## Educational_LevelHigh School or GED:Language_GroupOther Indo-European Languages -2.510
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupOther Indo-European Languages -0.156
## Educational_LevelNo High School Degree or GED:Language_GroupOther Indo-European Languages -1.528
## Educational_LevelNo Schooling Completed:Language_GroupOther Indo-European Languages -2.129
## Educational_LevelSome College, No Degree:Language_GroupOther Indo-European Languages -2.214
## Educational_LevelDoctoral:Language_GroupOther Languages -2.642
## Educational_LevelHigh School or GED:Language_GroupOther Languages 3.534
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupOther Languages 1.418
## Educational_LevelNo High School Degree or GED:Language_GroupOther Languages 0.764
## Educational_LevelNo Schooling Completed:Language_GroupOther Languages 1.272
## Educational_LevelSome College, No Degree:Language_GroupOther Languages 3.353
## Educational_LevelDoctoral:Language_GroupSpanish -0.306
## Educational_LevelHigh School or GED:Language_GroupSpanish 3.669
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupSpanish -1.781
## Educational_LevelNo High School Degree or GED:Language_GroupSpanish 0.606
## Educational_LevelNo Schooling Completed:Language_GroupSpanish 0.814
## Educational_LevelSome College, No Degree:Language_GroupSpanish 3.208
## Pr(>|t|)
## (Intercept) < 0.0000000000000002
## Educational_LevelDoctoral < 0.0000000000000002
## Educational_LevelHigh School or GED < 0.0000000000000002
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's < 0.0000000000000002
## Educational_LevelNo High School Degree or GED < 0.0000000000000002
## Educational_LevelNo Schooling Completed 0.0000000000000698
## Educational_LevelSome College, No Degree < 0.0000000000000002
## Language_GroupEnglish < 0.0000000000000002
## Language_GroupOther Indo-European Languages 0.0000000000003172
## Language_GroupOther Languages 0.0000028280810162
## Language_GroupSpanish 0.0000009502625355
## Educational_LevelDoctoral:Language_GroupEnglish 0.387606
## Educational_LevelHigh School or GED:Language_GroupEnglish 0.0000000000212101
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupEnglish 0.269501
## Educational_LevelNo High School Degree or GED:Language_GroupEnglish 0.0000000000260697
## Educational_LevelNo Schooling Completed:Language_GroupEnglish 0.0000000178139346
## Educational_LevelSome College, No Degree:Language_GroupEnglish 0.0000584801479471
## Educational_LevelDoctoral:Language_GroupOther Indo-European Languages 0.332713
## Educational_LevelHigh School or GED:Language_GroupOther Indo-European Languages 0.012082
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupOther Indo-European Languages 0.876306
## Educational_LevelNo High School Degree or GED:Language_GroupOther Indo-European Languages 0.126418
## Educational_LevelNo Schooling Completed:Language_GroupOther Indo-European Languages 0.033288
## Educational_LevelSome College, No Degree:Language_GroupOther Indo-European Languages 0.026819
## Educational_LevelDoctoral:Language_GroupOther Languages 0.008237
## Educational_LevelHigh School or GED:Language_GroupOther Languages 0.000410
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupOther Languages 0.156159
## Educational_LevelNo High School Degree or GED:Language_GroupOther Languages 0.444868
## Educational_LevelNo Schooling Completed:Language_GroupOther Languages 0.203497
## Educational_LevelSome College, No Degree:Language_GroupOther Languages 0.000801
## Educational_LevelDoctoral:Language_GroupSpanish 0.759946
## Educational_LevelHigh School or GED:Language_GroupSpanish 0.000243
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupSpanish 0.074909
## Educational_LevelNo High School Degree or GED:Language_GroupSpanish 0.544243
## Educational_LevelNo Schooling Completed:Language_GroupSpanish 0.415484
## Educational_LevelSome College, No Degree:Language_GroupSpanish 0.001337
##
## (Intercept) ***
## Educational_LevelDoctoral ***
## Educational_LevelHigh School or GED ***
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's ***
## Educational_LevelNo High School Degree or GED ***
## Educational_LevelNo Schooling Completed ***
## Educational_LevelSome College, No Degree ***
## Language_GroupEnglish ***
## Language_GroupOther Indo-European Languages ***
## Language_GroupOther Languages ***
## Language_GroupSpanish ***
## Educational_LevelDoctoral:Language_GroupEnglish
## Educational_LevelHigh School or GED:Language_GroupEnglish ***
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupEnglish
## Educational_LevelNo High School Degree or GED:Language_GroupEnglish ***
## Educational_LevelNo Schooling Completed:Language_GroupEnglish ***
## Educational_LevelSome College, No Degree:Language_GroupEnglish ***
## Educational_LevelDoctoral:Language_GroupOther Indo-European Languages
## Educational_LevelHigh School or GED:Language_GroupOther Indo-European Languages *
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupOther Indo-European Languages
## Educational_LevelNo High School Degree or GED:Language_GroupOther Indo-European Languages
## Educational_LevelNo Schooling Completed:Language_GroupOther Indo-European Languages *
## Educational_LevelSome College, No Degree:Language_GroupOther Indo-European Languages *
## Educational_LevelDoctoral:Language_GroupOther Languages **
## Educational_LevelHigh School or GED:Language_GroupOther Languages ***
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupOther Languages
## Educational_LevelNo High School Degree or GED:Language_GroupOther Languages
## Educational_LevelNo Schooling Completed:Language_GroupOther Languages
## Educational_LevelSome College, No Degree:Language_GroupOther Languages ***
## Educational_LevelDoctoral:Language_GroupSpanish
## Educational_LevelHigh School or GED:Language_GroupSpanish ***
## Educational_LevelMaster's & Professional Degree Beyond Bachelor's:Language_GroupSpanish .
## Educational_LevelNo High School Degree or GED:Language_GroupSpanish
## Educational_LevelNo Schooling Completed:Language_GroupSpanish
## Educational_LevelSome College, No Degree:Language_GroupSpanish **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 4968419129)
##
## Number of Fisher Scoring iterations: 2CSV FILES
write.csv(file = "Income_SD_Median_Income.csv", median_income)
write.csv(file = "Income_SD_Quintile_Medians.csv", final_median_by_quintile)
write.csv(file = "Income_SD_ByEducation_Medians.csv", median_by_education_wide)write.csv(file = "Income_SD_ByEducation_ByLanguage_Medians.csv", income_data_wide)write.csv(file = "Income_SD_ByEducation_Bilingual_Monolingual_Medians.csv", income_data_wide_NE)write.csv(file = "Income_All_Biling_Stat.csv", median_by_bilingual_stat)EMPLOYMENT
FInding unemployment rates for each bilingual groups.
| Label | Code |
|---|---|
| N/A or Unknown | 0; 9 |
| Employed | 1 |
| Unemployed | 2 |
| Not in labor force | 3 |
employment_2022 <- language_micro_data_full |>
select(EMPSTAT, AGE, CLUSTER, PERWT, STRATA, Bilingual_Status, Language_Group) |>
filter(EMPSTAT != 0 & EMPSTAT != 9)
employment_2022 |>
filter(EMPSTAT == 3) |>
group_by(AGE) |>
summarise(count = n())## # A tibble: 74 × 2
## AGE count
## <int+lbl> <int>
## 1 16 14213
## 2 17 12761
## 3 18 10504
## 4 19 8397
## 5 20 5701
## 6 21 4754
## 7 22 4034
## 8 23 3569
## 9 24 3239
## 10 25 3313
## # ℹ 64 more rowsemployment_2022 <- employment_2022 |>
filter(EMPSTAT != 3)employment_2022_binary <- employment_2022 |>
mutate(EMPSTAT = ifelse(EMPSTAT == 2, 0, 1))
survey_design <- svydesign(
id = ~CLUSTER,
weights = ~PERWT,
data = employment_2022_binary
)
empstat_by_bilingual <- svyby(
~EMPSTAT,
~Bilingual_Status,
survey_design,
svymean,
vartype = "ci"
)
empstat_by_bilingual <- empstat_by_bilingual |>
mutate(unemployment = 1 - EMPSTAT) |>
rename(employment = EMPSTAT)write.csv(file = "Employment_Rates_by_Language_Group.csv", empstat_by_bilingual)OCCUPATIONS
Codes: https://usa.ipums.org/usa/volii/occ2018.shtml#manager
| Industry | Codes |
|---|---|
| Management, Business, and Financial Occupations | 10-960 |
| Computer, Engineering, and Science Occupations | 1005-1980 |
| Education, Legal, Community Service, Arts, and Media Occupations: | 2001-2920 |
| Healthcare Practitioners and Technical Occupations | 3000-3550 |
| Service Occupations | 3601-4655 |
| Sales and Office Occupations | Sales and Related Occupations (4700-4965) Office and Administrative Support Occupations (5000-5940) |
| Natural Resources, Construction, and Maintenance Occupations | Farming, Fishing, and Forestry Occupations(6005-6130) Construction and Extraction Occupations (6200-6950) Installation, Maintenance, and Repair Occupations(7000-7640) |
| Production, Transportation, and Material Moving Occupations | Production Occupations (7770-8990) Transportation and Material Moving Occupations (9005-9760) |
| Military Occupations: | 9800-9830 |
| Unemployed | 9920 |
occupations_2022 <- language_micro_data_full |>
select(PERWT, CLUSTER, STRATA, OCC,Bilingual_Status, Language_Group , AGE, EMPSTAT)|>
filter(OCC != 9920 & OCC != 0 & AGE < 65) |>
filter(EMPSTAT == 1)
occupations_2022_full <- occupations_2022 |>
mutate(Occupation_Label = case_when(
OCC >= 10 & OCC <= 960 ~ "Management, Business, and Financial Occupations",
OCC >= 1005 & OCC <= 1980 ~ "Computer, Engineering, and Science Occupations",
OCC >= 2001 & OCC <= 2920 ~ "Education, Legal, Community Service, Arts, and Media Occupations",
OCC >= 3000 & OCC <= 3550 ~ "Healthcare Practitioners and Technical Occupations",
OCC >= 3601 & OCC <= 4655 ~ "Service Occupations",
OCC >= 4700 & OCC <= 4965 ~ "Sales and Related Occupations",
OCC >= 5000 & OCC <= 5940 ~ "Office and Administrative Support Occupations",
OCC >= 6005 & OCC <= 6130 ~ "Farming, Fishing, and Forestry Occupations",
OCC >= 6200 & OCC <= 6950 ~ "Construction and Extraction Occupations",
OCC >= 7000 & OCC <= 7640 ~ "Installation, Maintenance, and Repair Occupations",
OCC >= 7700 & OCC <= 8990 ~ "Production Occupations",
OCC >= 9005 & OCC <= 9760 ~ "Transportation and Material Moving Occupations",
OCC >= 9800 & OCC <= 9830 ~ "Military Occupations"
))
table(occupations_2022_full$Occupation_Label)##
## Computer, Engineering, and Science Occupations
## 37776
## Construction and Extraction Occupations
## 30806
## Education, Legal, Community Service, Arts, and Media Occupations
## 61467
## Farming, Fishing, and Forestry Occupations
## 2202
## Healthcare Practitioners and Technical Occupations
## 31792
## Installation, Maintenance, and Repair Occupations
## 18571
## Management, Business, and Financial Occupations
## 95064
## Military Occupations
## 2561
## Office and Administrative Support Occupations
## 58736
## Production Occupations
## 25404
## Sales and Related Occupations
## 53342
## Service Occupations
## 82333
## Transportation and Material Moving Occupations
## 39517survey_design <- svydesign(
id = ~CLUSTER,
weights = ~PERWT,
data = occupations_2022_full
)
bilingual_occupation_distribution <- svyby(
~Bilingual_Status,
~Occupation_Label,
survey_design,
svytotal,
vartype = NULL
)
print(bilingual_occupation_distribution)## Occupation_Label
## Computer, Engineering, and Science Occupations Computer, Engineering, and Science Occupations
## Construction and Extraction Occupations Construction and Extraction Occupations
## Education, Legal, Community Service, Arts, and Media Occupations Education, Legal, Community Service, Arts, and Media Occupations
## Farming, Fishing, and Forestry Occupations Farming, Fishing, and Forestry Occupations
## Healthcare Practitioners and Technical Occupations Healthcare Practitioners and Technical Occupations
## Installation, Maintenance, and Repair Occupations Installation, Maintenance, and Repair Occupations
## Management, Business, and Financial Occupations Management, Business, and Financial Occupations
## Military Occupations Military Occupations
## Office and Administrative Support Occupations Office and Administrative Support Occupations
## Production Occupations Production Occupations
## Sales and Related Occupations Sales and Related Occupations
## Service Occupations Service Occupations
## Transportation and Material Moving Occupations Transportation and Material Moving Occupations
## Bilingual_StatusBilingual
## Computer, Engineering, and Science Occupations 286519
## Construction and Extraction Occupations 330087
## Education, Legal, Community Service, Arts, and Media Occupations 348518
## Farming, Fishing, and Forestry Occupations 14691
## Healthcare Practitioners and Technical Occupations 216669
## Installation, Maintenance, and Repair Occupations 149078
## Management, Business, and Financial Occupations 539334
## Military Occupations 10072
## Office and Administrative Support Occupations 416942
## Production Occupations 214243
## Sales and Related Occupations 397599
## Service Occupations 701085
## Transportation and Material Moving Occupations 343654
## Bilingual_StatusEnglish Monolingual
## Computer, Engineering, and Science Occupations 574274
## Construction and Extraction Occupations 332908
## Education, Legal, Community Service, Arts, and Media Occupations 981873
## Farming, Fishing, and Forestry Occupations 21677
## Healthcare Practitioners and Technical Occupations 503000
## Installation, Maintenance, and Repair Occupations 277572
## Management, Business, and Financial Occupations 1595743
## Military Occupations 46644
## Office and Administrative Support Occupations 974287
## Production Occupations 337752
## Sales and Related Occupations 890231
## Service Occupations 1193736
## Transportation and Material Moving Occupations 642826
## Bilingual_StatusNE Monolingual
## Computer, Engineering, and Science Occupations 8590
## Construction and Extraction Occupations 230901
## Education, Legal, Community Service, Arts, and Media Occupations 19379
## Farming, Fishing, and Forestry Occupations 10304
## Healthcare Practitioners and Technical Occupations 6908
## Installation, Maintenance, and Repair Occupations 38157
## Management, Business, and Financial Occupations 35941
## Military Occupations 351
## Office and Administrative Support Occupations 29375
## Production Occupations 94833
## Sales and Related Occupations 43234
## Service Occupations 294366
## Transportation and Material Moving Occupations 89378
## se.Bilingual_StatusBilingual
## Computer, Engineering, and Science Occupations 3983.2143
## Construction and Extraction Occupations 4598.1750
## Education, Legal, Community Service, Arts, and Media Occupations 4298.7611
## Farming, Fishing, and Forestry Occupations 936.7557
## Healthcare Practitioners and Technical Occupations 3717.9425
## Installation, Maintenance, and Repair Occupations 2869.5776
## Management, Business, and Financial Occupations 5824.9229
## Military Occupations 690.9699
## Office and Administrative Support Occupations 4827.1293
## Production Occupations 3432.3756
## Sales and Related Occupations 4879.3959
## Service Occupations 6816.7154
## Transportation and Material Moving Occupations 4724.4913
## se.Bilingual_StatusEnglish Monolingual
## Computer, Engineering, and Science Occupations 5254.7847
## Construction and Extraction Occupations 4282.6467
## Education, Legal, Community Service, Arts, and Media Occupations 7091.8780
## Farming, Fishing, and Forestry Occupations 997.2829
## Healthcare Practitioners and Technical Occupations 4981.0724
## Installation, Maintenance, and Repair Occupations 3768.9222
## Management, Business, and Financial Occupations 9047.5348
## Military Occupations 1475.7345
## Office and Administrative Support Occupations 7219.8145
## Production Occupations 4223.9744
## Sales and Related Occupations 6969.9454
## Service Occupations 8258.6304
## Transportation and Material Moving Occupations 6194.7719
## se.Bilingual_StatusNE Monolingual
## Computer, Engineering, and Science Occupations 639.5010
## Construction and Extraction Occupations 4162.2797
## Education, Legal, Community Service, Arts, and Media Occupations 1072.3463
## Farming, Fishing, and Forestry Occupations 802.8262
## Healthcare Practitioners and Technical Occupations 512.9042
## Installation, Maintenance, and Repair Occupations 1519.4302
## Management, Business, and Financial Occupations 1383.6573
## Military Occupations 121.4441
## Office and Administrative Support Occupations 1218.4149
## Production Occupations 2334.2013
## Sales and Related Occupations 1545.3696
## Service Occupations 4485.0630
## Transportation and Material Moving Occupations 2304.0715sum(bilingual_occupation_distribution$Bilingual_StatusBilingual) +
sum(bilingual_occupation_distribution$`Bilingual_StatusEnglish Monolingual`) +
sum(bilingual_occupation_distribution$`Bilingual_StatusNE Monolingual`)## [1] 13242731table(occupations_2022_full$EMPSTAT)##
## 1
## 539571write.csv(file = "Occupations_by_LanguageGroup_FullSet.csv", bilingual_occupation_distribution)LINGUISTIC ISOLATION
Looking at different indicators for linguistic isolation group in Texas.
| Label | Code |
|---|---|
| N/A | 0 |
| Not linguistically isolated | 1 |
| Linguistically isolated | 2 |
linguistic_iso_2022 <- language_micro_data_full |>
select(LANGUAGE, LANGUAGED, LINGISOL, AGE, CLUSTER, STRATA, PERWT, POVERTY, INCTOT, OCC, SEX, , HCOVANY, Language_Group, Bilingual_Status, EMPSTAT, EDUCD, YEAR) |>
filter(LINGISOL != 0 & LANGUAGE != 1 & LANGUAGED != 100) |>
mutate(LINGISOL = ifelse(LINGISOL == 1, "Not linguistically isolated", "Linguistically isolated")) OVERVIEW DEMOGRAPHICS
isolated_2022 <- linguistic_iso_2022 |>
filter(LINGISOL == "Linguistically isolated")
# table(isolated_2022$AGE)
survey_design <- svydesign(
id = ~CLUSTER,
weights = ~PERWT,
data = isolated_2022
)
ling_iso_age_distribution <- svyby(~I(AGE == AGE), ~AGE, survey_design, svytotal)
print(ling_iso_age_distribution)## AGE I(AGE == AGE)FALSE I(AGE == AGE)TRUE se.I(AGE == AGE)FALSE
## 5 5 0 35465 0
## 6 6 0 35134 0
## 7 7 0 35585 0
## 8 8 0 37001 0
## 9 9 0 34852 0
## 10 10 0 33293 0
## 11 11 0 37030 0
## 12 12 0 35053 0
## 13 13 0 33998 0
## 14 14 0 13042 0
## 15 15 0 14629 0
## 16 16 0 12045 0
## 17 17 0 12847 0
## 18 18 0 14353 0
## 19 19 0 12470 0
## 20 20 0 14705 0
## 21 21 0 17703 0
## 22 22 0 17867 0
## 23 23 0 20324 0
## 24 24 0 20247 0
## 25 25 0 24490 0
## 26 26 0 24712 0
## 27 27 0 27036 0
## 28 28 0 27520 0
## 29 29 0 26191 0
## 30 30 0 31606 0
## 31 31 0 30755 0
## 32 32 0 33166 0
## 33 33 0 31863 0
## 34 34 0 33426 0
## 35 35 0 34196 0
## 36 36 0 31523 0
## 37 37 0 30730 0
## 38 38 0 31703 0
## 39 39 0 25333 0
## 40 40 0 31213 0
## 41 41 0 25186 0
## 42 42 0 27063 0
## 43 43 0 21461 0
## 44 44 0 21777 0
## 45 45 0 26062 0
## 46 46 0 21757 0
## 47 47 0 24568 0
## 48 48 0 21061 0
## 49 49 0 19811 0
## 50 50 0 23083 0
## 51 51 0 19351 0
## 52 52 0 21501 0
## 53 53 0 21955 0
## 54 54 0 21675 0
## 55 55 0 23647 0
## 56 56 0 23189 0
## 57 57 0 18152 0
## 58 58 0 21116 0
## 59 59 0 21647 0
## 60 60 0 22874 0
## 61 61 0 20287 0
## 62 62 0 22376 0
## 63 63 0 19643 0
## 64 64 0 19989 0
## 65 65 0 20388 0
## 66 66 0 18551 0
## 67 67 0 17994 0
## 68 68 0 17036 0
## 69 69 0 16867 0
## 70 70 0 15422 0
## 71 71 0 13747 0
## 72 72 0 14158 0
## 73 73 0 12154 0
## 74 74 0 12946 0
## 75 75 0 11685 0
## 76 76 0 10695 0
## 77 77 0 8904 0
## 78 78 0 8080 0
## 79 79 0 8197 0
## 80 80 0 6303 0
## 81 81 0 6516 0
## 82 82 0 6160 0
## 83 83 0 5609 0
## 84 84 0 4915 0
## 85 85 0 4915 0
## 86 86 0 4036 0
## 87 87 0 3256 0
## 88 88 0 2904 0
## 92 92 0 12527 0
## se.I(AGE == AGE)TRUE
## 5 1497.2114
## 6 1386.5306
## 7 1410.3080
## 8 1487.9484
## 9 1344.2221
## 10 1330.9944
## 11 1472.0148
## 12 1407.1724
## 13 1386.6957
## 14 817.6877
## 15 1002.5848
## 16 781.6413
## 17 804.5655
## 18 942.3409
## 19 876.3682
## 20 896.7930
## 21 1062.6265
## 22 1029.7246
## 23 1118.8209
## 24 1085.4929
## 25 1266.4312
## 26 1163.0431
## 27 1257.7198
## 28 1327.9242
## 29 1179.9470
## 30 1259.8250
## 31 1331.1592
## 32 1339.4248
## 33 1459.0824
## 34 1431.1780
## 35 1389.1017
## 36 1404.6109
## 37 1419.0920
## 38 1400.9528
## 39 1140.4415
## 40 1342.2515
## 41 1239.8676
## 42 1276.8795
## 43 1014.6390
## 44 1090.9687
## 45 1189.6438
## 46 1117.9478
## 47 1209.6322
## 48 1020.0673
## 49 1030.1544
## 50 1078.2160
## 51 1026.1939
## 52 1059.0985
## 53 1063.9211
## 54 1028.6618
## 55 1100.4791
## 56 1214.2687
## 57 875.9257
## 58 937.7216
## 59 1065.1334
## 60 1096.6269
## 61 996.0991
## 62 1111.8114
## 63 876.6017
## 64 951.1845
## 65 936.6509
## 66 961.9264
## 67 899.4701
## 68 961.2870
## 69 943.6823
## 70 818.2443
## 71 851.1543
## 72 790.0398
## 73 709.7378
## 74 798.0683
## 75 759.5752
## 76 719.6895
## 77 585.5399
## 78 565.0736
## 79 595.7663
## 80 432.9640
## 81 486.2518
## 82 528.0461
## 83 532.1314
## 84 457.8947
## 85 530.0096
## 86 430.1223
## 87 365.4989
## 88 329.3044
## 92 769.4183write.csv(file = "Lingustically_Isolated_Ages.csv", ling_iso_age_distribution)ling_iso_age_sex_distribution <- svyby(
~I(AGE == AGE),
~interaction(AGE, SEX),
survey_design,
svytotal
)
ling_iso_age_sex_df <- as.data.frame(ling_iso_age_sex_distribution)
ling_iso_age_sex_df <- ling_iso_age_sex_df |>
mutate(
AGE = as.numeric(sub("\\..*", "", rownames(ling_iso_age_sex_df))),
SEX = as.factor(sub(".*\\.", "", rownames(ling_iso_age_sex_df)))
)
ling_iso_age_sex_df <- ling_iso_age_sex_df |>
select(AGE, SEX, everything())
print(ling_iso_age_sex_df)## AGE SEX interaction(AGE, SEX) I(AGE == AGE)FALSE I(AGE == AGE)TRUE
## 5.1 5 1 5.1 0 17960
## 6.1 6 1 6.1 0 18767
## 7.1 7 1 7.1 0 18261
## 8.1 8 1 8.1 0 19400
## 9.1 9 1 9.1 0 17862
## 10.1 10 1 10.1 0 17298
## 11.1 11 1 11.1 0 18649
## 12.1 12 1 12.1 0 16575
## 13.1 13 1 13.1 0 18427
## 14.1 14 1 14.1 0 6928
## 15.1 15 1 15.1 0 7195
## 16.1 16 1 16.1 0 6530
## 17.1 17 1 17.1 0 7555
## 18.1 18 1 18.1 0 7641
## 19.1 19 1 19.1 0 6679
## 20.1 20 1 20.1 0 7906
## 21.1 21 1 21.1 0 10323
## 22.1 22 1 22.1 0 9479
## 23.1 23 1 23.1 0 9956
## 24.1 24 1 24.1 0 10124
## 25.1 25 1 25.1 0 13075
## 26.1 26 1 26.1 0 12627
## 27.1 27 1 27.1 0 13383
## 28.1 28 1 28.1 0 13051
## 29.1 29 1 29.1 0 11426
## 30.1 30 1 30.1 0 16657
## 31.1 31 1 31.1 0 16746
## 32.1 32 1 32.1 0 17113
## 33.1 33 1 33.1 0 18378
## 34.1 34 1 34.1 0 18058
## 35.1 35 1 35.1 0 20591
## 36.1 36 1 36.1 0 17453
## 37.1 37 1 37.1 0 17037
## 38.1 38 1 38.1 0 17334
## 39.1 39 1 39.1 0 13889
## 40.1 40 1 40.1 0 18064
## 41.1 41 1 41.1 0 14285
## 42.1 42 1 42.1 0 15913
## 43.1 43 1 43.1 0 12617
## 44.1 44 1 44.1 0 12135
## 45.1 45 1 45.1 0 15983
## 46.1 46 1 46.1 0 11581
## 47.1 47 1 47.1 0 13763
## 48.1 48 1 48.1 0 10368
## 49.1 49 1 49.1 0 10580
## 50.1 50 1 50.1 0 12094
## 51.1 51 1 51.1 0 10432
## 52.1 52 1 52.1 0 11777
## 53.1 53 1 53.1 0 11768
## 54.1 54 1 54.1 0 11190
## 55.1 55 1 55.1 0 12424
## 56.1 56 1 56.1 0 12620
## 57.1 57 1 57.1 0 9279
## 58.1 58 1 58.1 0 10571
## 59.1 59 1 59.1 0 11893
## 60.1 60 1 60.1 0 12163
## 61.1 61 1 61.1 0 10103
## 62.1 62 1 62.1 0 11022
## 63.1 63 1 63.1 0 9029
## 64.1 64 1 64.1 0 9974
## 65.1 65 1 65.1 0 9565
## 66.1 66 1 66.1 0 9239
## 67.1 67 1 67.1 0 8508
## 68.1 68 1 68.1 0 8136
## 69.1 69 1 69.1 0 8215
## 70.1 70 1 70.1 0 7622
## 71.1 71 1 71.1 0 6616
## 72.1 72 1 72.1 0 6819
## 73.1 73 1 73.1 0 5715
## 74.1 74 1 74.1 0 5615
## 75.1 75 1 75.1 0 5827
## 76.1 76 1 76.1 0 4533
## 77.1 77 1 77.1 0 3816
## 78.1 78 1 78.1 0 3315
## 79.1 79 1 79.1 0 3859
## 80.1 80 1 80.1 0 2673
## 81.1 81 1 81.1 0 2969
## 82.1 82 1 82.1 0 2535
## 83.1 83 1 83.1 0 2271
## 84.1 84 1 84.1 0 2222
## 85.1 85 1 85.1 0 1503
## 86.1 86 1 86.1 0 1556
## 87.1 87 1 87.1 0 1390
## 88.1 88 1 88.1 0 838
## 92.1 92 1 92.1 0 4133
## 5.2 5 2 5.2 0 17505
## 6.2 6 2 6.2 0 16367
## 7.2 7 2 7.2 0 17324
## 8.2 8 2 8.2 0 17601
## 9.2 9 2 9.2 0 16990
## 10.2 10 2 10.2 0 15995
## 11.2 11 2 11.2 0 18381
## 12.2 12 2 12.2 0 18478
## 13.2 13 2 13.2 0 15571
## 14.2 14 2 14.2 0 6114
## 15.2 15 2 15.2 0 7434
## 16.2 16 2 16.2 0 5515
## 17.2 17 2 17.2 0 5292
## 18.2 18 2 18.2 0 6712
## 19.2 19 2 19.2 0 5791
## 20.2 20 2 20.2 0 6799
## 21.2 21 2 21.2 0 7380
## 22.2 22 2 22.2 0 8388
## 23.2 23 2 23.2 0 10368
## 24.2 24 2 24.2 0 10123
## 25.2 25 2 25.2 0 11415
## 26.2 26 2 26.2 0 12085
## 27.2 27 2 27.2 0 13653
## 28.2 28 2 28.2 0 14469
## 29.2 29 2 29.2 0 14765
## 30.2 30 2 30.2 0 14949
## 31.2 31 2 31.2 0 14009
## 32.2 32 2 32.2 0 16053
## 33.2 33 2 33.2 0 13485
## 34.2 34 2 34.2 0 15368
## 35.2 35 2 35.2 0 13605
## 36.2 36 2 36.2 0 14070
## 37.2 37 2 37.2 0 13693
## 38.2 38 2 38.2 0 14369
## 39.2 39 2 39.2 0 11444
## 40.2 40 2 40.2 0 13149
## 41.2 41 2 41.2 0 10901
## 42.2 42 2 42.2 0 11150
## 43.2 43 2 43.2 0 8844
## 44.2 44 2 44.2 0 9642
## 45.2 45 2 45.2 0 10079
## 46.2 46 2 46.2 0 10176
## 47.2 47 2 47.2 0 10805
## 48.2 48 2 48.2 0 10693
## 49.2 49 2 49.2 0 9231
## 50.2 50 2 50.2 0 10989
## 51.2 51 2 51.2 0 8919
## 52.2 52 2 52.2 0 9724
## 53.2 53 2 53.2 0 10187
## 54.2 54 2 54.2 0 10485
## 55.2 55 2 55.2 0 11223
## 56.2 56 2 56.2 0 10569
## 57.2 57 2 57.2 0 8873
## 58.2 58 2 58.2 0 10545
## 59.2 59 2 59.2 0 9754
## 60.2 60 2 60.2 0 10711
## 61.2 61 2 61.2 0 10184
## 62.2 62 2 62.2 0 11354
## 63.2 63 2 63.2 0 10614
## 64.2 64 2 64.2 0 10015
## 65.2 65 2 65.2 0 10823
## 66.2 66 2 66.2 0 9312
## 67.2 67 2 67.2 0 9486
## 68.2 68 2 68.2 0 8900
## 69.2 69 2 69.2 0 8652
## 70.2 70 2 70.2 0 7800
## 71.2 71 2 71.2 0 7131
## 72.2 72 2 72.2 0 7339
## 73.2 73 2 73.2 0 6439
## 74.2 74 2 74.2 0 7331
## 75.2 75 2 75.2 0 5858
## 76.2 76 2 76.2 0 6162
## 77.2 77 2 77.2 0 5088
## 78.2 78 2 78.2 0 4765
## 79.2 79 2 79.2 0 4338
## 80.2 80 2 80.2 0 3630
## 81.2 81 2 81.2 0 3547
## 82.2 82 2 82.2 0 3625
## 83.2 83 2 83.2 0 3338
## 84.2 84 2 84.2 0 2693
## 85.2 85 2 85.2 0 3412
## 86.2 86 2 86.2 0 2480
## 87.2 87 2 87.2 0 1866
## 88.2 88 2 88.2 0 2066
## 92.2 92 2 92.2 0 8394
## se.I(AGE == AGE)FALSE se.I(AGE == AGE)TRUE
## 5.1 0 1065.8547
## 6.1 0 998.8706
## 7.1 0 996.0418
## 8.1 0 1057.9473
## 9.1 0 1000.2551
## 10.1 0 967.6361
## 11.1 0 1087.6176
## 12.1 0 972.4416
## 13.1 0 1075.2284
## 14.1 0 609.0970
## 15.1 0 674.3683
## 16.1 0 547.0177
## 17.1 0 639.7068
## 18.1 0 706.3281
## 19.1 0 602.9397
## 20.1 0 635.8154
## 21.1 0 850.8433
## 22.1 0 765.1070
## 23.1 0 764.0561
## 24.1 0 793.4883
## 25.1 0 920.5404
## 26.1 0 883.7385
## 27.1 0 842.8864
## 28.1 0 961.1310
## 29.1 0 761.1800
## 30.1 0 932.9010
## 31.1 0 984.7649
## 32.1 0 943.3178
## 33.1 0 1106.9069
## 34.1 0 983.8111
## 35.1 0 1070.6090
## 36.1 0 1075.4580
## 37.1 0 1035.1271
## 38.1 0 974.2174
## 39.1 0 799.9175
## 40.1 0 990.4356
## 41.1 0 904.5620
## 42.1 0 1033.4000
## 43.1 0 816.5322
## 44.1 0 831.6856
## 45.1 0 975.5460
## 46.1 0 727.7644
## 47.1 0 873.2403
## 48.1 0 717.8195
## 49.1 0 775.7257
## 50.1 0 770.4319
## 51.1 0 727.3979
## 52.1 0 810.4980
## 53.1 0 780.1206
## 54.1 0 739.3097
## 55.1 0 796.3649
## 56.1 0 879.9392
## 57.1 0 608.7172
## 58.1 0 682.5067
## 59.1 0 841.2945
## 60.1 0 840.0929
## 61.1 0 734.8028
## 62.1 0 756.7794
## 63.1 0 557.3429
## 64.1 0 675.2700
## 65.1 0 606.8719
## 66.1 0 652.0048
## 67.1 0 653.8879
## 68.1 0 656.4332
## 69.1 0 669.7955
## 70.1 0 642.7239
## 71.1 0 628.2306
## 72.1 0 598.2170
## 73.1 0 448.0759
## 74.1 0 514.3468
## 75.1 0 554.2596
## 76.1 0 425.5904
## 77.1 0 359.0982
## 78.1 0 322.3925
## 79.1 0 446.5276
## 80.1 0 264.1345
## 81.1 0 317.8426
## 82.1 0 356.4828
## 83.1 0 301.2407
## 84.1 0 339.0400
## 85.1 0 216.6298
## 86.1 0 262.4886
## 87.1 0 233.4737
## 88.1 0 158.7474
## 92.1 0 415.4951
## 5.2 0 1052.2586
## 6.2 0 963.3834
## 7.2 0 977.3100
## 8.2 0 1000.8489
## 9.2 0 909.5491
## 10.2 0 919.0950
## 11.2 0 995.7646
## 12.2 0 1014.9562
## 13.2 0 875.7386
## 14.2 0 548.4292
## 15.2 0 696.5101
## 16.2 0 553.6783
## 17.2 0 489.8287
## 18.2 0 604.8892
## 19.2 0 629.5210
## 20.2 0 615.7715
## 21.2 0 623.2388
## 22.2 0 672.1651
## 23.2 0 802.0484
## 24.2 0 697.8997
## 25.2 0 796.1277
## 26.2 0 746.4791
## 27.2 0 891.3284
## 28.2 0 889.6314
## 29.2 0 858.0158
## 30.2 0 820.1749
## 31.2 0 812.8603
## 32.2 0 889.7698
## 33.2 0 855.0041
## 34.2 0 1014.4462
## 35.2 0 847.1011
## 36.2 0 826.1330
## 37.2 0 892.9085
## 38.2 0 924.6913
## 39.2 0 756.1754
## 40.2 0 865.6400
## 41.2 0 801.1876
## 42.2 0 725.0872
## 43.2 0 595.6351
## 44.2 0 680.3432
## 45.2 0 653.5128
## 46.2 0 816.5155
## 47.2 0 747.7983
## 48.2 0 700.3010
## 49.2 0 649.1130
## 50.2 0 724.7906
## 51.2 0 651.8996
## 52.2 0 640.8726
## 53.2 0 679.0321
## 54.2 0 699.5040
## 55.2 0 742.2779
## 56.2 0 777.3970
## 57.2 0 599.0168
## 58.2 0 630.8560
## 59.2 0 628.9780
## 60.2 0 643.5622
## 61.2 0 637.0257
## 62.2 0 734.5575
## 63.2 0 644.0780
## 64.2 0 640.6921
## 65.2 0 704.0208
## 66.2 0 689.8063
## 67.2 0 602.6711
## 68.2 0 643.4643
## 69.2 0 644.5578
## 70.2 0 487.0124
## 71.2 0 552.9478
## 72.2 0 498.3782
## 73.2 0 502.7441
## 74.2 0 581.7255
## 75.2 0 508.5385
## 76.2 0 575.5726
## 77.2 0 453.1334
## 78.2 0 425.8271
## 79.2 0 392.7565
## 80.2 0 340.4155
## 81.2 0 358.7010
## 82.2 0 388.0340
## 83.2 0 438.4535
## 84.2 0 303.1994
## 85.2 0 483.9467
## 86.2 0 341.1640
## 87.2 0 280.2196
## 88.2 0 282.3362
## 92.2 0 586.2100ling_iso_age_sex_df <- ling_iso_age_sex_df |>
select(AGE, SEX, `I(AGE == AGE)TRUE`)
ling_iso_age_sex_df <- ling_iso_age_sex_df |>
mutate(Age_Group = cut(AGE, breaks = seq(0, 100, by = 5), right = FALSE))
age_sex_summary <- ling_iso_age_sex_df |>
group_by(Age_Group, SEX) |>
summarise(Count = sum(`I(AGE == AGE)TRUE`, na.rm = TRUE))## `summarise()` has grouped output by 'Age_Group'. You can override using the
## `.groups` argument.age_sex_summary_wide <- age_sex_summary |>
pivot_wider(names_from = SEX, values_from = Count, names_prefix = "Sex_")
colnames(age_sex_summary_wide) <- c("Age_Group", "Men", "Women")
print(age_sex_summary_wide)## # A tibble: 18 × 3
## # Groups: Age_Group [18]
## Age_Group Men Women
## <fct> <dbl> <dbl>
## 1 [5,10) 92250 85787
## 2 [10,15) 77877 74539
## 3 [15,20) 35600 30744
## 4 [20,25) 47788 43058
## 5 [25,30) 63562 66387
## 6 [30,35) 86952 73864
## 7 [35,40) 86304 67181
## 8 [40,45) 73014 53686
## 9 [45,50) 62275 50984
## 10 [50,55) 57261 50304
## 11 [55,60) 56787 50964
## 12 [60,65) 52291 52878
## 13 [65,70) 43663 47173
## 14 [70,75) 32387 36040
## 15 [75,80) 21350 26211
## 16 [80,85) 12670 16833
## 17 [85,90) 5287 9824
## 18 [90,95) 4133 8394age_sex_summary_wide <- age_sex_summary_wide |>
mutate(Total_Pop = Men + Women)
age_sex_summary_wide <- age_sex_summary_wide |>
mutate(
Men_Percent = - (Men / Total_Pop) ,
Women_Percent = (Women / Total_Pop)
)
age_sex_summary_wide <- age_sex_summary_wide |>
select(Age_Group, Men_Percent, Women_Percent)
write.csv(file = "Linguistically_Isolated_PopPyramid.csv",age_sex_summary_wide, row.names = FALSE)write.csv(file = "Linguistically_Isolated_PopPyramid.csv",age_sex_summary_wide )BY LANGUAGE
survey_design <- svydesign(
id = ~CLUSTER,
weights = ~PERWT,
data = isolated_2022
)
ling_iso_language_distribution <- svytotal(~Language_Group, survey_design)
print(ling_iso_language_distribution)## total SE
## Language_GroupAsian/Pacific Islander Languages 151611 4051.8
## Language_GroupOther Indo-European Languages 79157 3119.9
## Language_GroupOther Languages 40397 2732.9
## Language_GroupSpanish 1485137 12743.6ling_iso_language_distribution <- as.data.frame(ling_iso_language_distribution)write.csv(file = "Linguistically_Isolated_Languages.csv",ling_iso_language_distribution)HEALTHCARE
ling_iso_health <- linguistic_iso_2022 |>
mutate(HCOVANY = ifelse(HCOVANY == 2, 1, 0))
survey_design <- svydesign(
id = ~CLUSTER,
weights = ~PERWT,
data = ling_iso_health
)
ling_isohealthcare_coverage <- svyby(
~HCOVANY,
~LINGISOL,
survey_design,
svymean,
)
ling_isohealthcare_coverage <- ling_isohealthcare_coverage |>
mutate(NoCoverage = 1-HCOVANY)write.csv(file = "Linguistically_Isolated_Healthcare.csv", ling_isohealthcare_coverage)OCCUPATIONS
ling_iso_occupations <- linguistic_iso_2022 |>
filter(OCC != 0 & OCC != 9920 & AGE < 65) |>
filter(EMPSTAT == 1) |>
mutate(Occupation_Label = case_when(
OCC >= 10 & OCC <= 960 ~ "Management, Business, and Financial Occupations",
OCC >= 1005 & OCC <= 1980 ~ "Computer, Engineering, and Science Occupations",
OCC >= 2001 & OCC <= 2920 ~ "Education, Legal, Community Service, Arts, and Media Occupations",
OCC >= 3000 & OCC <= 3550 ~ "Healthcare Practitioners and Technical Occupations",
OCC >= 3601 & OCC <= 4655 ~ "Service Occupations",
OCC >= 4700 & OCC <= 4965 ~ "Sales and Related Occupations",
OCC >= 5000 & OCC <= 5940 ~ "Office and Administrative Support Occupations",
OCC >= 6005 & OCC <= 6130 ~ "Farming, Fishing, and Forestry Occupations",
OCC >= 6200 & OCC <= 6950 ~ "Construction and Extraction Occupations",
OCC >= 7000 & OCC <= 7640 ~ "Installation, Maintenance, and Repair Occupations",
OCC >= 7700 & OCC <= 8990 ~ "Production Occupations",
OCC >= 9005 & OCC <= 9760 ~ "Transportation and Material Moving Occupations",
OCC >= 9800 & OCC <= 9830 ~ "Military Occupations"
))
table(ling_iso_occupations$Occupation_Label)##
## Computer, Engineering, and Science Occupations
## 11746
## Construction and Extraction Occupations
## 16936
## Education, Legal, Community Service, Arts, and Media Occupations
## 14852
## Farming, Fishing, and Forestry Occupations
## 972
## Healthcare Practitioners and Technical Occupations
## 8827
## Installation, Maintenance, and Repair Occupations
## 6296
## Management, Business, and Financial Occupations
## 21754
## Military Occupations
## 270
## Office and Administrative Support Occupations
## 16725
## Production Occupations
## 10768
## Sales and Related Occupations
## 15464
## Service Occupations
## 33539
## Transportation and Material Moving Occupations
## 14279survey_design <- svydesign(
id = ~CLUSTER,
weights = ~PERWT,
data = ling_iso_occupations
)
ling_iso_occupation_distribution <- svyby(
~LINGISOL,
~Occupation_Label,
survey_design,
svytotal,
vartype = NULL
)
print(ling_iso_occupation_distribution)## Occupation_Label
## Computer, Engineering, and Science Occupations Computer, Engineering, and Science Occupations
## Construction and Extraction Occupations Construction and Extraction Occupations
## Education, Legal, Community Service, Arts, and Media Occupations Education, Legal, Community Service, Arts, and Media Occupations
## Farming, Fishing, and Forestry Occupations Farming, Fishing, and Forestry Occupations
## Healthcare Practitioners and Technical Occupations Healthcare Practitioners and Technical Occupations
## Installation, Maintenance, and Repair Occupations Installation, Maintenance, and Repair Occupations
## Management, Business, and Financial Occupations Management, Business, and Financial Occupations
## Military Occupations Military Occupations
## Office and Administrative Support Occupations Office and Administrative Support Occupations
## Production Occupations Production Occupations
## Sales and Related Occupations Sales and Related Occupations
## Service Occupations Service Occupations
## Transportation and Material Moving Occupations Transportation and Material Moving Occupations
## LINGISOLLinguistically isolated
## Computer, Engineering, and Science Occupations 22807
## Construction and Extraction Occupations 176886
## Education, Legal, Community Service, Arts, and Media Occupations 27885
## Farming, Fishing, and Forestry Occupations 7252
## Healthcare Practitioners and Technical Occupations 14411
## Installation, Maintenance, and Repair Occupations 34932
## Management, Business, and Financial Occupations 45052
## Military Occupations 453
## Office and Administrative Support Occupations 38015
## Production Occupations 72411
## Sales and Related Occupations 51267
## Service Occupations 216492
## Transportation and Material Moving Occupations 81861
## LINGISOLNot linguistically isolated
## Computer, Engineering, and Science Occupations 271545
## Construction and Extraction Occupations 383658
## Education, Legal, Community Service, Arts, and Media Occupations 336867
## Farming, Fishing, and Forestry Occupations 17485
## Healthcare Practitioners and Technical Occupations 208630
## Installation, Maintenance, and Repair Occupations 151301
## Management, Business, and Financial Occupations 529099
## Military Occupations 7091
## Office and Administrative Support Occupations 406010
## Production Occupations 236488
## Sales and Related Occupations 387711
## Service Occupations 774354
## Transportation and Material Moving Occupations 349933
## se.LINGISOLLinguistically isolated
## Computer, Engineering, and Science Occupations 993.3948
## Construction and Extraction Occupations 3706.8116
## Education, Legal, Community Service, Arts, and Media Occupations 1185.0259
## Farming, Fishing, and Forestry Occupations 691.8161
## Healthcare Practitioners and Technical Occupations 896.3208
## Installation, Maintenance, and Repair Occupations 1457.1691
## Management, Business, and Financial Occupations 1660.2977
## Military Occupations 126.7017
## Office and Administrative Support Occupations 1418.6427
## Production Occupations 2097.0011
## Sales and Related Occupations 1743.3616
## Service Occupations 3953.6424
## Transportation and Material Moving Occupations 2272.2934
## se.LINGISOLNot linguistically isolated
## Computer, Engineering, and Science Occupations 3860.282
## Construction and Extraction Occupations 5121.641
## Education, Legal, Community Service, Arts, and Media Occupations 4201.952
## Farming, Fishing, and Forestry Occupations 1036.695
## Healthcare Practitioners and Technical Occupations 3612.331
## Installation, Maintenance, and Repair Occupations 2920.762
## Management, Business, and Financial Occupations 5629.916
## Military Occupations 639.583
## Office and Administrative Support Occupations 4689.204
## Production Occupations 3630.113
## Sales and Related Occupations 4765.748
## Service Occupations 7290.672
## Transportation and Material Moving Occupations 4746.227sum(ling_iso_occupation_distribution$`LINGISOLLinguistically isolated`) + sum(ling_iso_occupation_distribution$`LINGISOLNot linguistically isolated`)## [1] 4849896write.csv(file = "Linguistically_Isolated_Occupations.csv", ling_iso_occupation_distribution)POVERTY
ling_iso_poverty_2022 <- linguistic_iso_2022 |>
filter(POVERTY != 0 & POVERTY <= 100) |>
filter(LINGISOL == "Linguistically isolated")
poverty_survey_design <- svydesign(
id = ~CLUSTER,
strata = ~STRATA,
weights = ~PERWT,
data = ling_iso_poverty_2022
)
ling_iso_poverty_distribution <- svyby(
~POVERTY,
~Language_Group,
poverty_survey_design,
svytotal,
vartype = NULL
)
print(ling_iso_poverty_distribution)## Language_Group POVERTY
## Asian/Pacific Islander Languages Asian/Pacific Islander Languages 1378680
## Other Indo-European Languages Other Indo-European Languages 860488
## Other Languages Other Languages 711344
## Spanish Spanish 25721212
## se
## Asian/Pacific Islander Languages 104275.72
## Other Indo-European Languages 101334.97
## Other Languages 92778.81
## Spanish 487204.22#very high se, not very reliable INCOME
ling_iso_income_2022 <- linguistic_iso_2022 |>
select(AGE, INCTOT, PERWT, SEX, EDUCD, AGE, CLUSTER, STRATA, YEAR, Language_Group, Bilingual_Status, LINGISOL) |>
filter(INCTOT != 9999999 & INCTOT > 0) |>
filter(AGE > 18 & AGE < 65) des_ling_iso_income <- svydesign(
ids = ~CLUSTER,
strata = ~STRATA,
weights = ~PERWT,
data = ling_iso_income_2022)
median_income_ling_iso <- svyby(
~INCTOT,
~LINGISOL,
des_ling_iso_income,
svyquantile,
quantiles = 0.5,
ci = TRUE
)## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() available
## Warning in vcov.svyquantile(X[[i]], ...): Only diagonal of vcov() availableprint(median_income_ling_iso)## LINGISOL INCTOT se
## Linguistically isolated Linguistically isolated 27557 208.6641
## Not linguistically isolated Not linguistically isolated 35130 179.0736write.csv(file = "Linguistically_Isolated_MedianPersonal_Income.csv", median_income_ling_iso)