Several questions in the GBHS can be made into long format data, as they either contain data from multiple choice questions (each answer separated with a ';') or come from a group of questions exploring the same theme with the same response scale. This function collects these questions and responses into dedicated columns where the "key" column in the question asked and responses are stored in "value" ( response category), "continuous" (ordinal scale), and "bin" (binary scale). All other data remain in the data frame, but the number of rows is increased, and the "submission_id" column denotes the individual respondent.
Arguments
- data
data.frame to work on. Needs to be a
gbhsderivative- question
integer indicating which question to make the data longer from. Values accepted are
1,2,3,4
Examples
data(gbhs)
gbhs_long_q(gbhs, 2)
#> # A tibble: 302,037 × 100
#> form_id submis…¹ langu…² langu…³ conse…⁴ age educa…⁵ gender q01_t…⁶ q03_a…⁷
#> <dbl> <dbl> <chr> <chr> <chr> <ord> <fct> <fct> <ord> <ord>
#> 1 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Very i…
#> 2 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Very i…
#> 3 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Very i…
#> 4 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Very i…
#> 5 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Very i…
#> 6 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Very i…
#> 7 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Very i…
#> 8 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Very i…
#> 9 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Very i…
#> 10 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Very i…
#> # … with 302,027 more rows, 90 more variables: q03_child <ord>,
#> # q03_middle <ord>, q03_older <ord>, q03_womb <ord>, q03_youngadult <ord>,
#> # q04_brain_disease <chr>, q05_alcohol_gen <ord>, q05_diet_gen <ord>,
#> # q05_excercise_gen <ord>, q05_intellect_gen <ord>, q05_protection_gen <ord>,
#> # q05_relax_gen <ord>, q05_sleep_gen <ord>, q05_smoke_gen <ord>,
#> # q05_socialise_gen <ord>, q05_supplements_gen <ord>,
#> # q05_wlbalance_gen <ord>, q06_brainhealth_purp_spec <chr>, …
gbhs_long_q(gbhs, 4)
#> # A tibble: 357,890 × 111
#> form_id submis…¹ langu…² langu…³ conse…⁴ age educa…⁵ gender q01_t…⁶ q02_d…⁷
#> <dbl> <dbl> <chr> <chr> <chr> <ord> <fct> <fct> <ord> <ord>
#> 1 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Modera…
#> 2 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Modera…
#> 3 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Modera…
#> 4 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Modera…
#> 5 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Modera…
#> 6 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Modera…
#> 7 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Modera…
#> 8 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Modera…
#> 9 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Modera…
#> 10 114338 4903486 english en Yes 26-40 "Grad\… Male Occasi… Modera…
#> # … with 357,880 more rows, 101 more variables: q02_education_infl <ord>,
#> # q02_genetics_infl <ord>, q02_income_infl <ord>, q02_lifegoals_infl <ord>,
#> # q02_physenv_infl <ord>, q02_physhealth_infl <ord>,
#> # q02_profession_infl <ord>, q02_sleep_infl <ord>, q02_socenv_infl <ord>,
#> # q02_substance_infl <ord>, q03_adolescence <ord>, q03_child <ord>,
#> # q03_middle <ord>, q03_older <ord>, q03_womb <ord>, q03_youngadult <ord>,
#> # q05_alcohol_gen <ord>, q05_diet_gen <ord>, q05_excercise_gen <ord>, …