In paezha/discrtr: A Companion Package for the Book "Discrete Choice Analysis with 'R'"

Introduction

In this notebook we prepare a data object with the table used in Lavery, T. A., Antonio Páez, and Pavlos S. Kanaroglou. "Driving out of choices: An investigation of transport modality in a university sample." Transportation research part A: policy and practice 57 (2013): 37-46.

Preliminaries

Clear environment:

rm(list = ls())

Load packages used in the notebook:

library(readxl)
library(tidyverse)
#library(MASS)
#library(reshape2)
#library(plyr)
#library(kableExtra)
#library(gridExtra)

Load dataframe:

mc_modality <- read_excel("input-data-files/Number_Alternatives.xlsx")
geocodes <- read_excel("input-data-files/Database+Geocodes.xlsx")

Retrieve geocodes from file Database+Geocodes.xlsx:

geocodes <- geocodes %>%
  transmute(id = Respondent,
            LAT,
            LONG)

Note that the number of observations is 10 less than in file Number_Alternatives.xlsx.

Select and pre-process variables from file Number_Alternatives.xlsx (which does not have geocodes):

mc_modality <- mc_modality %>%
  transmute(id = Respondent,
            choice = factor(MODE, 
                            levels = c(1, 2, 3, 4),
                            labels = c( "Active Travel", "HSR","Car", "GO")),
            shared_vehicle = factor(case_when(SHARE_ACCE == 1 ~ "Yes",
                                              TRUE == 0 ~ "No")),
            bicycle = factor(case_when(OWN_BIKE_B == 1 ~ "Yes",
                                       TRUE ~ "No")),
            gender = factor(case_when(GENDER_BIN == 1 ~ "Woman",
                                      TRUE ~ "Man")),
            age = AGE_SND * 10,
            status = factor(case_when(Faculty_St == 1 ~ "Staff or Faculty",
                                      Student == 1 ~ "Student")),
            care_giver = factor(case_when(PRIM_CARE_ == 1 ~ "Yes",
                                          TRUE ~ "No")),
            modality = factor(case_when(NUM_ALT == 1 ~ "One Mode",
                                        NUM_ALT == 2 ~ "Two Modes",
                                        NUM_ALT == 3 ~ "Three Modes",
                                        NUM_ALT == 4 ~ "Four Modes"),
                              ordered = TRUE),
            Boring = case_when(BORING_SD == 1 ~ "STRONGLY DISAGREE",
                               BORING_D == 1 ~ "DISAGREE",
                               BORING_A == 1 ~ "AGREE",
                               BORING_SA == 1 ~ "STRONGLY AGREE",
                               TRUE ~ "NEUTRAL") %>%
              factor(levels = c("STRONGLY DISAGREE", "DISAGREE", "NEUTRAL", "AGREE", "STRONGLY AGREE"),
                     ordered = TRUE),
            Buses_Comfortable = case_when(BUSES_CO_3 == 1 ~ "STRONGLY DISAGREE",
                                          BUSES_CO_2 == 1 ~ "DISAGREE",
                                          BUSES_CO_1 == 1 ~ "AGREE",
                                          BUSES_COMF == 1 ~ "STRONGLY AGREE",
                                          TRUE ~ "NEUTRAL") %>%
              factor(levels = c("STRONGLY DISAGREE", "DISAGREE", "NEUTRAL", "AGREE", "STRONGLY AGREE"),
                     ordered = TRUE),
            Clean_Fuel = case_when(HYBRID_SD == 1 ~ "STRONGLY DISAGREE",
                               HYBRID_D == 1 ~ "DISAGREE",
                               HYBRID_A == 1 ~ "AGREE",
                               HYBRID_SA == 1 ~ "STRONGLY AGREE",
                               TRUE ~ "NEUTRAL") %>%
              factor(levels = c("STRONGLY DISAGREE", "DISAGREE", "NEUTRAL", "AGREE", "STRONGLY AGREE"),
                     ordered = TRUE),
            Limit_Driving = case_when(LIMIT_SD == 1 ~ "STRONGLY DISAGREE",
                                      LIMIT_D == 1 ~ "DISAGREE",
                                      LIMIT_A == 1 ~ "AGREE",
                                      LIMIT_SA == 1 ~ "STRONGLY AGREE",
                                      TRUE ~ "NEUTRAL") %>%
              factor(levels = c("STRONGLY DISAGREE", "DISAGREE", "NEUTRAL", "AGREE", "STRONGLY AGREE"),
                     ordered = TRUE),
            Productive_Time = case_when(PRODUCTI_3 == 1 ~ "STRONGLY DISAGREE",
                                        PRODUCTI_2 == 1 ~ "DISAGREE",
                                        PRODUCTI_1 == 1 ~ "AGREE",
                                        PRODUCTIVE == 1 ~ "STRONGLY AGREE",
                                        TRUE ~ "NEUTRAL") %>%
              factor(levels = c("STRONGLY DISAGREE", "DISAGREE", "NEUTRAL", "AGREE", "STRONGLY AGREE"),
                     ordered = TRUE),
            Safe_Cycle = case_when(SAFE_CYC_3 == 1 ~ "STRONGLY DISAGREE",
                                   SAFE_CYC_2 == 1 ~ "DISAGREE",
                                   SAFE_CYC_1 == 1 ~ "AGREE",
                                   SAFE_CYCLE == 1 ~ "STRONGLY AGREE",
                                   TRUE ~ "NEUTRAL") %>%
              factor(levels = c("STRONGLY DISAGREE", "DISAGREE", "NEUTRAL", "AGREE", "STRONGLY AGREE"),
                     ordered = TRUE),
            Shops_Services = case_when(SHOPS_SE_3 == 1 ~ "STRONGLY DISAGREE",
                                       SHOPS_SE_2 == 1 ~ "DISAGREE",
                                       SHOPS_SE_1 == 1 ~ "AGREE",
                                       SHOPS_SERV == 1 ~ "STRONGLY AGREE",
                                       TRUE ~ "NEUTRAL") %>%
              factor(levels = c("STRONGLY DISAGREE", "DISAGREE", "NEUTRAL", "AGREE", "STRONGLY AGREE"),
                     ordered = TRUE),
            Someone_Else = case_when(SOMEONE__3 == 1 ~ "STRONGLY DISAGREE",
                                     SOMEONE__2 == 1 ~ "DISAGREE",
                                     SOMEONE__1 == 1 ~ "AGREE",
                                     SOMEONE_EL == 1 ~ "STRONGLY AGREE",
                                     TRUE ~ "NEUTRAL") %>%
              factor(levels = c("STRONGLY DISAGREE", "DISAGREE", "NEUTRAL", "AGREE", "STRONGLY AGREE"),
                     ordered = TRUE),
            Stuck_Traffic = case_when(STUCK_TR_3 == 1 ~ "STRONGLY DISAGREE",
                                      STUCK_TR_2 == 1 ~ "DISAGREE",
                                      STUCK_TR_1 == 1 ~ "AGREE",
                                      STUCK_TRAF == 1 ~ "STRONGLY AGREE",
                                      TRUE ~ "NEUTRAL") %>%
              factor(levels = c("STRONGLY DISAGREE", "DISAGREE", "NEUTRAL", "AGREE", "STRONGLY AGREE"),
                     ordered = TRUE),
            Transition = case_when(TRANSITI_3 == 1 ~ "STRONGLY DISAGREE",
                                   TRANSITI_2 == 1 ~ "DISAGREE",
                                   TRANSITI_1 == 1 ~ "AGREE",
                                   TRANSITION == 1 ~ "STRONGLY AGREE",
                                   TRUE ~ "NEUTRAL") %>%
              factor(levels = c("STRONGLY DISAGREE", "DISAGREE", "NEUTRAL", "AGREE", "STRONGLY AGREE"),
                     ordered = TRUE),
            Travel_Alone = case_when(ALONE_SD == 1 ~ "STRONGLY DISAGREE",
                                     ALONE_D == 1 ~ "DISAGREE",
                                     ALONE_A == 1 ~ "AGREE",
                                     ALONE_SA == 1 ~ "STRONGLY AGREE",
                                     TRUE ~ "NEUTRAL") %>%
              factor(levels = c("STRONGLY DISAGREE", "DISAGREE", "NEUTRAL", "AGREE", "STRONGLY AGREE"),
                     ordered = TRUE),
            Travel_Tiring = case_when(TIRING_SD == 1 ~ "STRONGLY DISAGREE",
                                      TIRING_D == 1 ~ "DISAGREE",
                                      TIRING_A == 1 ~ "AGREE",
                                      TIRING_SA == 1 ~ "STRONGLY AGREE",
                                      TRUE ~ "NEUTRAL") %>%
              factor(levels = c("STRONGLY DISAGREE", "DISAGREE", "NEUTRAL", "AGREE", "STRONGLY AGREE"),
                     ordered = TRUE),
            Wasted_Time = case_when(WASTED_SD == 1 ~ "STRONGLY DISAGREE",
                                    WASTED_D == 1 ~ "DISAGREE",
                                    WASTED_A == 1 ~ "AGREE",
                                    WASTED_SA == 1 ~ "STRONGLY AGREE",
                                    TRUE ~ "NEUTRAL") %>%
              factor(levels = c("STRONGLY DISAGREE", "DISAGREE", "NEUTRAL", "AGREE", "STRONGLY AGREE"),
                     ordered = TRUE),

            Rate_Immigrant = PER_IMMIGR/100,
            Rate_Non_Canadian = PER_NONCAN/100,
            Rate_Labor = LABOUR_RAT/100,
            Rate_Unemployment = UNEMPLOY/100,
            Rate_Married = PER_MARRIE,
            Mean_Age = AVG_AGE,
            Mean_Children = AVG_CHILDR,
            Median_HH_Income = MED_INCOME/10000,
            LITA,
            LUM,
            MAC_DISTANCE = MAC_DIST/1000,
            POPULATION_DENSITY = POP_DENSIT,
            SF_P_RATIO = SF_P_ratio)

mc_modality <- mc_modality %>%
  inner_join(geocodes,
             by = "id") %>%
  select(id, choice, LAT, LONG, everything())

Save data:

usethis::use_data(mc_modality,
                  overwrite = TRUE)

paezha/discrtr documentation built on March 1, 2023, 5:25 p.m.