title: “Parcial 2 - Big Data y Análisis de Datos”

author: “Laura Pineda y Mariana Meneses”

date: “30-10-2025”

output: html_document

Punto 1. Carga de datos

# Cargar la base desde el archivo subido a Posit Cloud
file_path <- "C:/Users/PCE/Downloads/ParcialBigData/2. covid_example_data.xlsx"
sheets <- excel_sheets(file_path)
print(sheets)
## [1] "in"
# Leer hoja 'in'
covid_data <- read_excel(file_path, sheet = "in")

# Visualizar las primeras filas
head(covid_data)
## # A tibble: 6 x 31
##   PID            reprt_creationdt_FALSE case_dob_FALSE      case_age case_gender
##   <chr>          <dttm>                 <dttm>                 <dbl> <chr>      
## 1 3a85e6992a5ac~ 2020-03-22 00:00:00    2004-11-08 00:00:00       16 Male       
## 2 c6b5281d5fc50~ 2020-02-01 00:00:00    1964-06-07 00:00:00       57 Male       
## 3 53495ad0dca4e~ 2020-02-10 00:00:00    1944-04-06 00:00:00       77 Female     
## 4 2948a265da0d0~ 2020-03-20 00:00:00    1964-06-25 00:00:00       57 Female     
## 5 a5524aadd1ca0~ 2020-02-26 00:00:00    1964-12-21 00:00:00       56 Male       
## 6 db14eeabe531f~ 2020-02-11 00:00:00    1956-06-21 00:00:00       65 Male       
## # i 26 more variables: case_race <chr>, case_eth <chr>, case_zip <dbl>,
## #   Contact_id <chr>, sym_startdt_FALSE <dttm>, sym_fever <chr>,
## #   sym_subjfever <chr>, sym_myalgia <chr>, sym_losstastesmell <chr>,
## #   sym_sorethroat <chr>, sym_cough <chr>, sym_headache <chr>,
## #   sym_resolved <chr>, sym_resolveddt_FALSE <dttm>, contact_household <chr>,
## #   hospitalized <chr>, hosp_admidt_FALSE <dttm>, hosp_dischdt_FALSE <dttm>,
## #   died <chr>, died_covid <chr>, died_dt_FALSE <dttm>, ...

Punto 2. Inspección inicial de la base

# Exploración general
glimpse(covid_data)
## Rows: 82,101
## Columns: 31
## $ PID                    <chr> "3a85e6992a5ac52f", "c6b5281d5fc50b96", "53495a~
## $ reprt_creationdt_FALSE <dttm> 2020-03-22, 2020-02-01, 2020-02-10, 2020-03-20~
## $ case_dob_FALSE         <dttm> 2004-11-08, 1964-06-07, 1944-04-06, 1964-06-25~
## $ case_age               <dbl> 16, 57, 77, 57, 56, 65, 47, 61, 36, 42, 74, 27,~
## $ case_gender            <chr> "Male", "Male", "Female", "Female", "Male", "Ma~
## $ case_race              <chr> "WHITE", "WHITE", "BLACK", "BLACK", "WHITE", "B~
## $ case_eth               <chr> "NON-HISPANIC/LATINO", "NON-HISPANIC/LATINO", "~
## $ case_zip               <dbl> 30308, 30308, 30315, 30213, 30004, 30314, 30313~
## $ Contact_id             <chr> "Yes-Symptomatic", "Yes-Symptomatic", "Yes-Symp~
## $ sym_startdt_FALSE      <dttm> 2020-03-20, 2020-01-28, 2020-02-10, 2021-05-19~
## $ sym_fever              <chr> "Yes", "No", "Yes", "No", "Yes", "Yes", "No", "~
## $ sym_subjfever          <chr> "Yes", "No", NA, "Yes", "Yes", "Yes", "No", "Ye~
## $ sym_myalgia            <chr> "No", "Yes", "Yes", "Yes", "Yes", "No", "Unk", ~
## $ sym_losstastesmell     <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, "Yes", NA, ~
## $ sym_sorethroat         <chr> "Yes", "No", "Yes", "Yes", "No", "Unk", "Yes", ~
## $ sym_cough              <chr> "Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "Yes"~
## $ sym_headache           <chr> "Yes", "No", NA, "Yes", "No", "Unk", "Yes", "No~
## $ sym_resolved           <chr> "No, still symptomatic", "No, still symptomatic~
## $ sym_resolveddt_FALSE   <dttm> NA, NA, NA, NA, NA, 2020-02-21, NA, NA, NA, NA~
## $ contact_household      <chr> "Yes", "No", NA, "No", "No", "No", "No", "No", ~
## $ hospitalized           <chr> "No", "No", "Yes", NA, "Yes", "Yes", "Yes", "No~
## $ hosp_admidt_FALSE      <dttm> NA, NA, 2020-02-08, NA, 2020-02-26, 2020-01-27~
## $ hosp_dischdt_FALSE     <dttm> NA, NA, NA, NA, NA, 2020-02-21, NA, NA, NA, 20~
## $ died                   <chr> "No", "No", "No", "No", NA, "Yes", "No", NA, "N~
## $ died_covid             <chr> "No", "No", "No", "No", NA, "Yes", "No", NA, "N~
## $ died_dt_FALSE          <dttm> NA, NA, NA, NA, NA, 2020-02-21, NA, NA, NA, NA~
## $ confirmed_case         <chr> "Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "Yes"~
## $ covid_dx               <chr> "Confirmed", "Confirmed", "Confirmed", "Confirm~
## $ pos_sampledt_FALSE     <dttm> 2020-03-22, 2020-02-01, 2020-02-10, 2021-01-17~
## $ latitude_JITT          <dbl> 33.776645460, 33.780510140, 33.730233310, 33.55~
## $ longitude_JITT         <dbl> -84.385685230, -84.389474740, -84.384251890, -8~
skim(covid_data)
Data summary
Name covid_data
Number of rows 82101
Number of columns 31
_______________________
Column type frequency:
character 19
numeric 4
POSIXct 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
PID 0 1.00 8 22 0 82087 0
case_gender 63 1.00 4 7 0 3 0
case_race 2630 0.97 5 32 0 7 0
case_eth 2574 0.97 13 19 0 3 0
Contact_id 32205 0.61 7 15 0 3 0
sym_fever 31577 0.62 2 3 0 3 0
sym_subjfever 37908 0.54 2 3 0 3 0
sym_myalgia 32137 0.61 2 3 0 4 0
sym_losstastesmell 50724 0.38 2 3 0 3 0
sym_sorethroat 32241 0.61 2 3 0 3 0
sym_cough 31630 0.61 2 3 0 3 0
sym_headache 32018 0.61 2 3 0 3 0
sym_resolved 42294 0.48 17 25 0 4 0
contact_household 36737 0.55 2 3 0 3 0
hospitalized 32482 0.60 2 3 0 2 0
died 36832 0.55 2 7 0 3 0
died_covid 42302 0.48 2 12 0 3 0
confirmed_case 9 1.00 2 7 0 3 0
covid_dx 0 1.00 9 9 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
case_age 48 1 39.69 19.16 -20.0 25.00 37.00 53.00 106.00 <U+2581><U+2587><U+2587><U+2583><U+2581>
case_zip 13 1 30249.72 123.83 30000.0 30213.00 30312.00 30331.00 31707.00 <U+2587><U+2582><U+2581><U+2581><U+2581>
latitude_JITT 94 1 32.58 6.38 0.0 33.69 33.78 33.98 34.19 <U+2581><U+2581><U+2581><U+2581><U+2587>
longitude_JITT 200 1 -81.39 15.65 -84.8 -84.46 -84.38 -84.35 0.00 <U+2587><U+2581><U+2581><U+2581><U+2581>

Variable type: POSIXct

skim_variable n_missing complete_rate min max median n_unique
reprt_creationdt_FALSE 0 1.00 2019-12-27 2021-07-27 2020-12-04 533
case_dob_FALSE 48 1.00 1914-12-28 2042-06-07 1984-05-13 26773
sym_startdt_FALSE 37480 0.54 1941-03-08 2030-12-03 2020-11-22 601
sym_resolveddt_FALSE 65799 0.20 2001-11-08 2102-02-03 2020-11-27 612
hosp_admidt_FALSE 77115 0.06 2019-12-26 2032-05-22 2020-10-14 517
hosp_dischdt_FALSE 78600 0.04 2019-12-04 2029-12-29 2020-10-24 504
died_dt_FALSE 80394 0.02 2020-02-21 2021-07-01 2020-12-11 429
pos_sampledt_FALSE 122 1.00 2020-02-01 2021-07-23 2020-12-03 526 
# Revisión de valores faltantes por variable
colSums(is.na(covid_data))
##                    PID reprt_creationdt_FALSE         case_dob_FALSE 
##                      0                      0                     48 
##               case_age            case_gender              case_race 
##                     48                     63                   2630 
##               case_eth               case_zip             Contact_id 
##                   2574                     13                  32205 
##      sym_startdt_FALSE              sym_fever          sym_subjfever 
##                  37480                  31577                  37908 
##            sym_myalgia     sym_losstastesmell         sym_sorethroat 
##                  32137                  50724                  32241 
##              sym_cough           sym_headache           sym_resolved 
##                  31630                  32018                  42294 
##   sym_resolveddt_FALSE      contact_household           hospitalized 
##                  65799                  36737                  32482 
##      hosp_admidt_FALSE     hosp_dischdt_FALSE                   died 
##                  77115                  78600                  36832 
##             died_covid          died_dt_FALSE         confirmed_case 
##                  42302                  80394                      9 
##               covid_dx     pos_sampledt_FALSE          latitude_JITT 
##                      0                    122                     94 
##         longitude_JITT 
##                    200

Punto 3. Limpieza y transformación de datos

covid_data <- covid_data %>%
  rename(
    id = PID,
    fecha_reporte = reprt_creationdt_FALSE,
    edad = case_age,
    sexo = case_gender,
    raza = case_race,
    etnia = case_eth,
    fecha_inicio_sintomas = sym_startdt_FALSE,
    hospitalizado = hospitalized,
    fallecido = died,
    confirmado = confirmed_case,
    latitud = latitude_JITT,
    longitud = longitude_JITT
  ) %>%
  mutate(
    fecha_reporte = as.Date(fecha_reporte, format = "%d/%m/%Y"),
    fecha_inicio_sintomas = as.Date(fecha_inicio_sintomas, format = "%d/%m/%Y"),
    edad = as.numeric(edad),
    fallecido = ifelse(fallecido == "Yes", 1, 0),
    confirmado = ifelse(confirmado == "Yes", 1, 0)
  )

# Confirmar estructura limpia
glimpse(covid_data)
## Rows: 82,101
## Columns: 31
## $ id                    <chr> "3a85e6992a5ac52f", "c6b5281d5fc50b96", "53495ad~
## $ fecha_reporte         <date> 2020-03-22, 2020-02-01, 2020-02-10, 2020-03-20,~
## $ case_dob_FALSE        <dttm> 2004-11-08, 1964-06-07, 1944-04-06, 1964-06-25,~
## $ edad                  <dbl> 16, 57, 77, 57, 56, 65, 47, 61, 36, 42, 74, 27, ~
## $ sexo                  <chr> "Male", "Male", "Female", "Female", "Male", "Mal~
## $ raza                  <chr> "WHITE", "WHITE", "BLACK", "BLACK", "WHITE", "BL~
## $ etnia                 <chr> "NON-HISPANIC/LATINO", "NON-HISPANIC/LATINO", "N~
## $ case_zip              <dbl> 30308, 30308, 30315, 30213, 30004, 30314, 30313,~
## $ Contact_id            <chr> "Yes-Symptomatic", "Yes-Symptomatic", "Yes-Sympt~
## $ fecha_inicio_sintomas <date> 2020-03-20, 2020-01-28, 2020-02-10, 2021-05-19,~
## $ sym_fever             <chr> "Yes", "No", "Yes", "No", "Yes", "Yes", "No", "Y~
## $ sym_subjfever         <chr> "Yes", "No", NA, "Yes", "Yes", "Yes", "No", "Yes~
## $ sym_myalgia           <chr> "No", "Yes", "Yes", "Yes", "Yes", "No", "Unk", "~
## $ sym_losstastesmell    <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, "Yes", NA, N~
## $ sym_sorethroat        <chr> "Yes", "No", "Yes", "Yes", "No", "Unk", "Yes", "~
## $ sym_cough             <chr> "Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "Yes",~
## $ sym_headache          <chr> "Yes", "No", NA, "Yes", "No", "Unk", "Yes", "No"~
## $ sym_resolved          <chr> "No, still symptomatic", "No, still symptomatic"~
## $ sym_resolveddt_FALSE  <dttm> NA, NA, NA, NA, NA, 2020-02-21, NA, NA, NA, NA,~
## $ contact_household     <chr> "Yes", "No", NA, "No", "No", "No", "No", "No", "~
## $ hospitalizado         <chr> "No", "No", "Yes", NA, "Yes", "Yes", "Yes", "No"~
## $ hosp_admidt_FALSE     <dttm> NA, NA, 2020-02-08, NA, 2020-02-26, 2020-01-27,~
## $ hosp_dischdt_FALSE    <dttm> NA, NA, NA, NA, NA, 2020-02-21, NA, NA, NA, 202~
## $ fallecido             <dbl> 0, 0, 0, 0, NA, 1, 0, NA, 0, 0, NA, 0, 1, 0, 0, ~
## $ died_covid            <chr> "No", "No", "No", "No", NA, "Yes", "No", NA, "No~
## $ died_dt_FALSE         <dttm> NA, NA, NA, NA, NA, 2020-02-21, NA, NA, NA, NA,~
## $ confirmado            <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ~
## $ covid_dx              <chr> "Confirmed", "Confirmed", "Confirmed", "Confirme~
## $ pos_sampledt_FALSE    <dttm> 2020-03-22, 2020-02-01, 2020-02-10, 2021-01-17,~
## $ latitud               <dbl> 33.776645460, 33.780510140, 33.730233310, 33.555~
## $ longitud              <dbl> -84.385685230, -84.389474740, -84.384251890, -84~

Punto 4. Estadísticas descriptivas

# Estadísticas básicas
summary(select(covid_data, edad, fallecido, confirmado))
##       edad          fallecido       confirmado    
##  Min.   :-20.00   Min.   :0.000   Min.   :0.0000  
##  1st Qu.: 25.00   1st Qu.:0.000   1st Qu.:1.0000  
##  Median : 37.00   Median :0.000   Median :1.0000  
##  Mean   : 39.69   Mean   :0.038   Mean   :0.9996  
##  3rd Qu.: 53.00   3rd Qu.:0.000   3rd Qu.:1.0000  
##  Max.   :106.00   Max.   :1.000   Max.   :1.0000  
##  NA's   :48       NA's   :36832   NA's   :9
# Tablas de frecuencia para variables categóricas
table(covid_data$sexo)
## 
##  Female    Male Unknown 
##   43299   38393     346
table(covid_data$raza)
## 
##    AMERICAN INDIAN/ALASKA NATIVE                            ASIAN 
##                               84                             3075 
##                            BLACK NATIVE HAWAIIAN/PACIFIC ISLANDER 
##                            35048                               79 
##                            OTHER                          UNKNOWN 
##                             5863                             3723 
##                            WHITE 
##                            31599
table(covid_data$etnia)
## 
##     HISPANIC/LATINO NON-HISPANIC/LATINO       NOT SPECIFIED 
##                8625               62677                8225

Punto 5. Análisis gráfico

Distribución de la edad

ggplot(covid_data, aes(x = edad)) +
  geom_histogram(binwidth = 5, fill = "steelblue", color = "white") +
  labs(title = "Distribución de edades", x = "Edad", y = "Frecuencia")
## Warning: Removed 48 rows containing non-finite outside the scale range
## (`stat_bin()`).

Fallecimientos por sexo

ggplot(covid_data, aes(x = sexo, fill = as.factor(fallecido))) +
  geom_bar(position = "fill") +
  labs(title = "Proporción de fallecidos por sexo",
       y = "Proporción", fill = "Fallecido")

Punto 6. Correlaciones

num_data <- select(covid_data, edad, fallecido, confirmado, latitud, longitud)
corrplot(cor(num_data, use = "pairwise.complete.obs"), method = "number")

Punto 7. Análisis de regresión logística

El objetivo es estimar la probabilidad de fallecer en función de la edad, sexo, raza, etnia y hospitalización.

modelo_logit <- glm(fallecido ~ edad + sexo + raza + etnia + hospitalizado,
                    data = covid_data, family = binomial)
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
summary(modelo_logit)
## 
## Call:
## glm(formula = fallecido ~ edad + sexo + raza + etnia + hospitalizado, 
##     family = binomial, data = covid_data)
## 
## Coefficients:
##                                        Estimate Std. Error z value Pr(>|z|)    
## (Intercept)                           -23.21762  785.16423  -0.030  0.97641    
## edad                                    0.09161    0.00252  36.349  < 2e-16 ***
## sexoMale                                0.44187    0.07225   6.116 9.62e-10 ***
## sexoUnknown                           -14.92653  745.35887  -0.020  0.98402    
## razaASIAN                              13.15723  785.16423   0.017  0.98663    
## razaBLACK                              13.32844  785.16419   0.017  0.98646    
## razaNATIVE HAWAIIAN/PACIFIC ISLANDER    0.77895 1241.00545   0.001  0.99950    
## razaOTHER                              12.70708  785.16424   0.016  0.98709    
## razaUNKNOWN                             0.51511  810.42217   0.001  0.99949    
## razaWHITE                              13.00273  785.16419   0.017  0.98679    
## etniaNON-HISPANIC/LATINO                0.05683    0.18847   0.302  0.76302    
## etniaNOT SPECIFIED                     -2.98037    1.02528  -2.907  0.00365 ** 
## hospitalizadoYes                        2.35121    0.07784  30.205  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 11300.2  on 43580  degrees of freedom
## Residual deviance:  5783.8  on 43568  degrees of freedom
##   (38520 observations deleted due to missingness)
## AIC: 5809.8
## 
## Number of Fisher Scoring iterations: 17

Punto 8. Interpretación del modelo

Se muestran los odds ratios (razones de momios) e intervalos de confianza.

exp(cbind(OddsRatio = coef(modelo_logit), confint(modelo_logit)))
## Waiting for profiling to be done...
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
##                                         OddsRatio         2.5 %        97.5 %
## (Intercept)                          8.254957e-11 9.224029e-125  1.566003e+04
## edad                                 1.095938e+00  1.090597e+00  1.101427e+00
## sexoMale                             1.555614e+00  1.350526e+00  1.792804e+00
## sexoUnknown                          3.292216e-07 2.929620e-107  3.579320e+08
## razaASIAN                            5.177420e+05 7.571023e+279           Inf
## razaBLACK                            6.144227e+05  3.377594e-09 6.920154e+119
## razaNATIVE HAWAIIAN/PACIFIC ISLANDER 2.179178e+00  3.100013e-02  1.496621e+02
## razaOTHER                            3.300781e+05 1.077409e+282           Inf
## razaUNKNOWN                          1.673829e+00  1.095426e-01  2.512491e+01
## razaWHITE                            4.436214e+05  2.495939e-09 5.674435e+119
## etniaNON-HISPANIC/LATINO             1.058473e+00  7.383495e-01  1.547002e+00
## etniaNOT SPECIFIED                   5.077396e-02  2.826165e-03  2.426766e-01
## hospitalizadoYes                     1.049821e+01  9.023954e+00  1.224502e+01

Punto 9. Resultados e implicaciones

Análisis: - Una edad mayor aumenta la probabilidad de fallecimiento (coeficiente positivo en el modelo). - Los pacientes hospitalizados muestran mayor probabilidad de fallecer. - Las variables de raza y etnia permiten observar diferencias demográficas relevantes. - Los gráficos previos ayudan a identificar los grupos más vulnerables.

Punto 10. Exportación de la base limpia

write.csv(covid_data, "covid_clean.csv", row.names = FALSE)