Supporting Statistical Analysis for Research

4.9 Duplicate observations

These exercises use the PSID.csv data set that was imported in the prior section.

1. Import the PSID.csv data set.

   library(tidyverse)

   psid_path <- file.path("..", "datasets", "PSID.csv")
   psid_in <- read_csv(psid_path, col_types = cols())

   Warning: Missing column names filled in: 'X1' [1]

   psid_in <-
     rename(
       psid_in,
       obs_num = X1,
       intvw_num = intnum,
       person_id = persnum,
       marital_status = married
       )
   
   psid <-
     psid_in %>%
     select(-obs_num)
   glimpse(psid)

   Observations: 4,856
   Variables: 8
   $ intvw_num      <dbl> 4, 4, 4, 4, 5, 6, 6, 7, 7, 7, 10, 10, 10, 11, 1...
   $ person_id      <dbl> 4, 6, 7, 173, 2, 4, 172, 4, 170, 171, 3, 171, 1...
   $ age            <dbl> 39, 35, 33, 39, 47, 44, 38, 38, 39, 37, 48, 47,...
   $ educatn        <dbl> 12, 12, 12, 10, 9, 12, 16, 9, 12, 11, 13, 12, 1...
   $ earnings       <dbl> 77250, 12000, 8000, 15000, 6500, 6500, 7000, 50...
   $ hours          <dbl> 2940, 2040, 693, 1904, 1683, 2024, 1144, 2080, ...
   $ kids           <dbl> 2, 2, 1, 2, 5, 2, 3, 4, 3, 5, 98, 3, 0, 0, 2, 0...
   $ marital_status <chr> "married", "divorced", "married", "married", "m...

2. What variables define an observation in this data set?

   The variable that contains the interviewer number, the variable that contains the number identifying a person, and the variable that contains the age of that person.

3. Are there any duplicate observations?

   dups <- 
     duplicated(select(psid, intvw_num, person_id, age)) |
     duplicated(select(psid, intvw_num, person_id, age), fromLast=TRUE)
   dup_person_age <-
     psid %>%
     filter(dups) %>%
     select(person_id, age, educatn, earnings) %>%
     arrange(person_id, age)
   
   head(dup_person_age)

   # A tibble: 0 x 4
   # ... with 4 variables: person_id <dbl>, age <dbl>, educatn <dbl>,
   #   earnings <dbl>

   There are no duplicates occurances.