<- readr::read_csv(paste0(here::here(), "/data/csv/screening/agg/PLAY-screening-datab-latest.csv"),
scr_df show_col_types = FALSE)
<- datadictionary::create_dictionary(scr_df)
scr_dd
::write_csv(scr_dd, paste0(here::here(), "/data/csv/screening/dd/PLAY-screening-data-dictionary.csv")) readr
Data dictionary
Background
We make use of the datadictionary
package here.
This is not a perfect solution. Among other challenges, this package throws many warnings. But we will use it for the time being.
Note
This data dictionary workflow does not include the questions that were asked. Adding that, and more descriptive information, is a high priority.
Load data and generate dictionary
Note
This data dictionary workflow does not include the questions that were asked. Adding that, and more descriptive information, is a high priority.
Here are the data this package provides:
|>
scr_dd ::kable() |>
kableExtra::kable_classic() kableExtra
item | label | class | summary | value |
---|---|---|---|---|
Rows in dataset | 855 | |||
Columns in dataset | 68 | |||
session_id | No label | numeric | mean | 66176 |
median | 67167 | |||
min | 38196 | |||
max | 74521 | |||
missing | 0 | |||
session_name | No label | character | unique responses | 820 |
missing | 0 | |||
session_date | No label | Date | mean | 2023-07-01 |
mode | 2023-08-13 | |||
min | 2019-06-09 | |||
max | 2024-10-12 | |||
missing | 0 | |||
session_release | No label | character | unique responses | 3 |
missing | 0 | |||
participant_ID | No label | character | unique responses | 93 |
missing | 0 | |||
participant_birthdate | No label | Date | mean | 2022-01-04 |
mode | 2021-08-18 | |||
min | 2017-06-08 | |||
max | 2023-10-27 | |||
missing | 0 | |||
participant_gender | No label | character | unique responses | 2 |
missing | 0 | |||
participant_race | No label | character | unique responses | 10 |
missing | 0 | |||
participant_ethnicity | No label | character | unique responses | 3 |
missing | 0 | |||
participant_language | No label | character | unique responses | 13 |
missing | 0 | |||
exclusion_reason | No label | character | unique responses | 15 |
missing | 794 | |||
group_name | No label | character | unique responses | 2 |
missing | 0 | |||
context_setting | No label | character | unique responses | 2 |
missing | 9 | |||
context_country | No label | character | unique responses | 2 |
missing | 50 | |||
context_state | No label | character | unique responses | 19 |
missing | 34 | |||
vol_id | No label | numeric | mean | 1288 |
median | 1370 | |||
min | 899 | |||
max | 1705 | |||
missing | 0 | |||
participant_disability | No label | character | unique responses | 5 |
missing | 697 | |||
pilot_pilot | No label | logical | missing | 855 |
submit_date | No label | POSIXct POSIXt | mean | 2023-06-09 |
mode | 2024-02-09 2024-04-19 | |||
min | 2019-10-08 | |||
max | 2024-09-08 | |||
missing | 25 | |||
site_id | No label | character | unique responses | 31 |
missing | 25 | |||
play_id | No label | character | unique responses | 691 |
missing | 147 | |||
child_age_mos | No label | numeric | mean | 18 |
median | 18 | |||
min | 9.24 | |||
max | 42.6 | |||
missing | 27 | |||
child_sex | No label | character | unique responses | 3 |
missing | 27 | |||
child_bornonduedate | No label | character | unique responses | 3 |
missing | 33 | |||
child_onterm | No label | character | unique responses | 3 |
missing | 141 | |||
child_birthage | No label | numeric | mean | 5 |
median | 3 | |||
min | -20 | |||
max | 367 | |||
missing | 54 | |||
child_weight_pounds | No label | numeric | mean | 7 |
median | 7 | |||
min | 4 | |||
max | 100 | |||
missing | 37 | |||
child_weight_ounces | No label | numeric | mean | 7 |
median | 7 | |||
min | 0 | |||
max | 143 | |||
missing | 49 | |||
child_birth_complications | No label | character | unique responses | 3 |
missing | 37 | |||
child_birth_complications_specify | No label | character | unique responses | 67 |
missing | 789 | |||
child_hearing_disabilities | No label | character | unique responses | 3 |
missing | 37 | |||
child_hearing_disabilities_specify | No label | character | unique responses | 2 |
missing | 854 | |||
child_vision_disabilities | No label | character | unique responses | 3 |
missing | 37 | |||
child_vision_disabilities_specify | No label | character | unique responses | 6 |
missing | 850 | |||
child_major_illnesses_injuries | No label | character | unique responses | 3 |
missing | 37 | |||
child_illnesses_injuries_specify | No label | character | unique responses | 30 |
missing | 822 | |||
child_developmentaldelays | No label | character | unique responses | 3 |
missing | 149 | |||
child_developmentaldelays_specify | No label | character | unique responses | 9 |
missing | 847 | |||
child_sleep_time | No label | character | unique responses | 98 |
missing | 38 | |||
child_wake_time | No label | character | unique responses | 114 |
missing | 39 | |||
child_nap_hours | No label | character | unique responses | 39 |
missing | 39 | |||
child_sleep_location | No label | character | unique responses | 6 |
missing | 39 | |||
mom_bio | No label | character | unique responses | 4 |
missing | 51 | |||
mom_childbirth_age | No label | numeric | mean | 33 |
median | 33 | |||
min | 20.22 | |||
max | 121.22 | |||
missing | 54 | |||
mom_race | No label | character | unique responses | 9 |
missing | 44 | |||
mom_birth_country | No label | character | unique responses | 5 |
missing | 44 | |||
mom_birth_country_specify | No label | character | unique responses | 39 |
missing | 767 | |||
mom_education | No label | character | unique responses | 15 |
missing | 45 | |||
mom_employment | No label | character | unique responses | 4 |
missing | 45 | |||
mom_occupation | No label | character | unique responses | 485 |
missing | 241 | |||
mom_jobs_number | No label | character | unique responses | 7 |
missing | 239 | |||
mom_training | No label | character | unique responses | 3 |
missing | 47 | |||
biodad_childbirth_age | No label | character | unique responses | 638 |
missing | 25 | |||
biodad_race | No label | character | unique responses | 13 |
missing | 25 | |||
language_spoken_mom | No label | character | unique responses | 6 |
missing | 33 | |||
language_spoken_mom_comments | No label | character | unique responses | 17 |
missing | 839 | |||
language_spoken_child | No label | character | unique responses | 6 |
missing | 27 | |||
language_spoken_home_comments | No label | character | unique responses | 831 |
missing | 25 | |||
language_spoken_child_comments | No label | character | unique responses | 14 |
missing | 842 | |||
language_spoken_home | No label | character | unique responses | 7 |
missing | 32 | |||
language_spoken_house_other | No label | character | unique responses | 15 |
missing | 841 | |||
language_spoken_home_other | No label | character | unique responses | 2 |
missing | 854 | |||
childcare_types | No label | character | unique responses | 14 |
missing | 232 | |||
childcare_location | No label | character | unique responses | 26 |
missing | 830 | |||
childcare_hours | No label | character | unique responses | 71 |
missing | 423 | |||
childcare_number | No label | numeric | mean | 6 |
median | 6 | |||
min | 0 | |||
max | 25 | |||
missing | 426 | |||
childcare_age | No label | numeric | mean | 7 |
median | 5 | |||
min | 0 | |||
max | 45 | |||
missing | 536 | |||
childcare_language | No label | character | unique responses | 37 |
missing | 422 |
Extracting questions
An alternative approach to generating the data dictionary starts with the questionnaire files themselves.