Package {tripaccess}

House data

Description

Include household characteristics categorical and numeric variables.

Usage

house

Format

A data frame with 129695 rows (each row is a household) and 9 columns

household_id

Household identifier. Use this variable to join the house dataset and the person dataset as well as join the house dataset and the trip dataset.

region

2010 Census division classification for the respondent's home address.

number_drivers

Number of drivers in household.

count_household_members

Count of household members.

number_vehicles

Count of household vehicles.

household_life_cycle

Life Cycle classification for the household, derived by attributes pertaining to age, relationship, and work status.

count_adult_household_members

Count of adult household members at least 18 years old.

number_workers

Number of workers in household.

count_young_child

Count of persons with an age between 0 and 4 in household.

Source

https://nhts.ornl.gov/

Examples

if (require("tidyverse")) {
# Filtered to households with at least one driver
house_with_drivers <- house |>
  filter(number_drivers > 0)

# Filtered to households with at least one vehicle
house_with_vehicles <- house_with_drivers |>
  filter(number_vehicles > 0)

# Plot household vehicles by number of drivers
ggplot(data = house_with_vehicles,
       aes(x = number_drivers,
           y = number_vehicles)) +
  geom_jitter(alpha = 0.08, width = 0.15, height = 0.15) +
  geom_smooth(method = lm, se = FALSE, formula = y ~ x, color = "blue") +
  labs(title = "Household Vehicles versus Number of Drivers",
       x = "Number of Drivers in Household",
       y = "Number of Household Vehicles") +
  theme_bw()
}

Person data

Description

Include disability, mobility, and other demographic categorical and numeric variables.

Usage

person

Format

A data frame with 99564 rows (each row is a person) and 32 columns

household_id

Household identifier. Use this variable to join the person dataset and the house dataset. Use both this variable and person_id to join the person dataset and the trip dataset.

person_id

Person identifier. Use both this variable and household_id to join the person dataset and the trip dataset.

travel_disability

How long the respondent has had a medical condition that makes it difficult to travel outside of home. Values include 6_months_or_less_disability, More_than_6_months_of_disability, Lifelong_disability, and No_disability.

sex

Sex of the respondent. Values include Male and Female.

race

Race of the respondent. Values include White, Black, Asian, American Indian, Hawaiian/Pacific Islander, Multiracial, and Other.

hispanic_ethnicity

Hispanic or Latino origin. Values include Hispanic and Non-Hispanic.

nativity

Born in United States. Values include Yes and No.

age

Age of the respondent. Filtered to ages 18 to 61.

education

Educational attainment. Values include Less than a high school graduate, High school graduate or GED, Some college or associates degree, Bachelor's degree, and Graduate degree or professional degree.

self_rated_health

Opinion of health. Values include Excellent, Very good, Good, Fair, and Poor.

employment_status

Primary activity in previous week. Values include Employed and Unemployed.

household_income

Household income. Values include Under $10,000, $10,000 to $34,999, $35,000 to $74,999, $75,000 to $149,999, and $150,000 and over.

household_structure

Count of household members. Values include Lives alone and Does not live alone.

population_density

Category of population density (persons per square mile) in the census block group of the household's home location. Values include 0-99, 100-499, 500-999, 1,000-1,999, 2,000-3,999, 4,000-9,999, 10,000-24,999, and 25,000 and over.

urban_rural

Household in urban or rural area. Values include Urban and Rural.

state

Household state. Includes the 50 states and Washington, DC.

driver_status

Driver status. Values include Drives and Does not drive.

cane

Does the respondent use a cane to aid their travel?

manual_wheelchair

Does the respondent use a manual wheelchair to aid their travel?

crutches

Does the respondent use a crutch to aid their travel?

dog

Does the respondent use a dog to aid their travel?

motorized_wheelchair

Does the respondent use a motorized wheelchair to aid their travel?

scooter

Does the respondent use a scooter to aid their travel?

white_cane

Does the respondent use a white cane to aid their travel?

walker

Does the respondent use a walker to aid their travel?

other_accommodation

Derived from the original W_NONE variable. Indicates whether no listed mobility aid was reported.

yearly_miles_personally_driven

Miles personally driven in all vehicles. Values range from 0 to 200000.

count_of_public_transit_usage

Count of public transit usage in last month. Values range from 0 to 30.

count_of_rideshare_app_usage

Count of rideshare app usage in last month. Values range from 0 to 99.

count_of_bike_trips

Count of bike trips in past week. Values range from 0 to 99.

count_of_walk_trips

Count of walk trips in past week. Values range from 0 to 200.

count_of_online_delivery

Count of times purchased online for delivery in last 30 days. Values range from 0 to 99.

Source

https://nhts.ornl.gov/

Examples

if (require("tidyverse")) {
# Summary statistics of public transit use by travel disability status
transit_summary <- person |>
  group_by(travel_disability) |>
  summarize(
    people = n(),
    public_transit_users = sum(count_of_public_transit_usage > 0),
    public_transit_use_prop = mean(count_of_public_transit_usage > 0),
    public_transit_usage_median = median(count_of_public_transit_usage),
    public_transit_usage_mean = mean(count_of_public_transit_usage),
    public_transit_usage_sd = sd(count_of_public_transit_usage)
  )
# Test whether public transit use differs by travel disability status
prop.test(
  x = transit_summary$public_transit_users,
  n = transit_summary$people
)
}

Trip data

Description

Include trip related categorical and numeric variables.

Usage

trip

Format

A data frame with 921590 rows (each row is a trip) and 8 columns

household_id

Household identifier. Use both this variable and person_id to join the trip dataset and the person dataset. Use this variable to join the trip dataset and the house dataset.

person_id

Person identifier. Use both this variable and household_id to join the trip dataset and the person dataset.

trip_purpose

Generalized purpose of trip on travel day. A travel day is a 24-hour day that starts at 4:00 a.m. (local time) of the assigned travel day and ends at 3:59 a.m. of the following day. The NHTS randomly assigns the travel days for one-seventh of the sample addresses to each day of the week and the remaining six-sevenths of the households to evenly across weekdays (Monday-Friday).

gas_price

Price of gasoline, in cents, on respondent's travel day.

num_of_people_on_trip

Number of people on trip including respondent on respondent's travel day.

trip_miles

Trip distance in miles on respondent's travel day, derived from route geometry returned. Google Maps was used for routing the shortest path for motorized travel on the road network. Non-motorized modes, like walk and bike, had the shortest path calculated using network routes paths.

trip_duration

Trip duration in minutes on respondent's travel day.

trip_miles_personally_driven_vehicle

Trip distance in miles for personally driven vehicle trips on respondent's travel day. -1 = Appropriate skip.

Source

https://nhts.ornl.gov/

Examples

if (require("tidyverse")) {
# Filtered to shorter trips for a clearer introductory visualization
short_trips <- trip |>
  filter(trip_miles <= 50,
         trip_duration <= 180)

# Filtered to trips with positive distance and duration
positive_distance_trips <- short_trips |>
  filter(trip_miles > 0,
         trip_duration > 0)

# Fit a simple linear regression model
duration_miles_model <- lm(trip_duration ~ trip_miles,
                           data = positive_distance_trips)
summary(duration_miles_model)

# Correlation between trip distance and trip duration
cor(positive_distance_trips$trip_miles, positive_distance_trips$trip_duration)
}

Tripaccess data

Description

Include disability and other demographic as well as mobility and trip categorical and numeric variables for data visualization and single table analysis.

Usage

tripaccess

Format

A data frame with 86521 rows (each row is a person) and 40 columns

household_id

Household identifier.

person_id

Person identifier.

travel_disability

How long does the respondent have a medical condition that makes it difficult to travel outside of home?

sex

Sex of the respondent.

race

Race of the respondent.

hispanic_ethnicity

Hispanic or Latino origin.

nativity

Born in United States.

age

Age of the respondent.

education

Educational attainment.

self_rated_health

Opinion of health.

employment_status

Primary activity in previous week.

household_income

Household income of the respondent.

household_structure

Count of household members.

population_density

Category of population density (persons per square mile) in the census block group of the households home location.

urban_rural

Household in urban or rural area.

state

Household state.

driver_status

Driver status.

cane

Does the respondent use a cane to aid their travel?

manual_wheelchair

Does the respondent use a manual wheelchair to aid their travel?

crutches

Does the respondent use a crutch to aid their travel?

dog

Does the respondent use a dog to aid their travel?

motorized_wheelchair

Does the respondent use a motorized wheelchair to aid their travel?

scooter

Does the respondent use a scooter to aid their travel?

white_cane

Does the respondent use a white cane to aid their travel?

walker

Does the respondent use a walker to aid their travel?

other_accommodation

Does the respondent use any other accommodation rather than those listed?

yearly_miles_personally_driven

Miles personally drive in all vehicles.

count_of_public_transit_usage

Count of public transit usage in last month.

count_of_rideshare_app_usage

Count of rideshare app usage in last month.

count_of_bike_trips

Count of bike trips in past week.

count_of_walk_trips

Count of walk trips in past week.

count_of_online_delivery

Count of times purchased online for delivery in last 30 days.

avg_num_of_people_on_trip

Average number of people on the respondent's trip including the respondent on the respondent's travel day. A travel day is a 24 hour day that starts at 4 am (local time) of the assigned travel day and ends at 3:59 am of the following day. The NHTS randomly assigns the travel days for one-seventh of the sample addresses to each day of the week and the remaining six-sevenths of the households to evenly across weekdays (Monday to Friday). The following variables are related to trip information on travel day.

avg_trip_distance_in_miles

Average trip distance in miles on the respondent's travel day.

avg_trip_duration_in_minutes

Average trip duration in minutes on the respondent's travel day.

shopping_trip

Whether having shopping trips on the respondent's travel day.

social_recreational_trip

Whether having social or recreational trips on the respondent's travel day.

other_home_based_trip

Whether having other home-based trips on the respondent's travel day.

work_trip

Whether having work trips on the respondent's travel day.

other_non_home_based_trip

Whether having other non home-based trips on the respondent's travel day.

Source

https://nhts.ornl.gov/

Examples

if (require("tidyverse")) {
# Filtered to people who have a travel disability
tripaccess_disabled <- tripaccess |>
  filter(travel_disability != "No_disability")

# Summary statistics of public transit usage by disabled people who use a walker
tripaccess_disabled |>
  filter(walker == "True") |>
  group_by(travel_disability) |>
  summarize(public_transit_usage_median = median(count_of_public_transit_usage),
  public_transit_usage_mean = mean(count_of_public_transit_usage),
  public_transit_usage_sd = sd(count_of_public_transit_usage))
}