Quantitative Methods of Analysis in Transportation

Materials to be used at the MQAT course

Content

• R scripts to prepare the databases
• R scripts for "hand-on" R programming classes
• Database on IMOB trips AML 2018 (refer to INE 2018)
• Database of AML administrative boundaries and areas at freguesia level (DICOFRE), from CAOP 2022 (refer to DGTerritório/CAOP)
• Database of socio-demographic statistics from Census 2021 for the AML at BGRI level (refer to INE Census 2021 for other downloads), including these variables

Download R and RStudio

Instructions for installing R and RStudio. Note that it is very important to install first R and then RStudio.

For classes and home assignments

Introduction to R

• R script for R_Basics.R
• Database of IMOB trips at municipal level: TRIPSmode_mun.Rds

Exploratory Data Analysis

• R script for Exploratory Data Analysis
• Database of IMOB trips at a district level (Freguesias): IMOBmodel.Rds

Multiple Linear Regression

• R script for Multiple Linear Regression
• Database of IMOB trips at a district level: IMOBmodel.Rds

Variables included in IMOBmodel database:

• Origin_dicofre16 - Code of Freguesias as set by INE after 2016 (Distrito + Concelho + Freguesia)
• Total - number of trips with origin in Origin_dicofre16
• Walk - number of walking trips with origin in Origin_dicofre16
• Bike - number of bike trips with origin in Origin_dicofre16
• Car - number of car trips with origin in Origin_dicofre16. Includes taxi and motorcycle.
• PTransit - number of Public Transit trips with origin in Origin_dicofre16
• Other - number of other trips (truck, van, tractor, aviation) with origin in Origin_dicofre16
• Distance - average trip distance (km) with origin in Origin_dicofre16
• Duration - average trip duration (minutes) with origin in Origin_dicofre16
• Car_perc - percentage of car trips with origin in Origin_dicofre16
• N_INDIVIDUOS - number of residents in Origin_dicofre16 (Censos 2021)
• Male_perc - percentage of male residents in Origin_dicofre16 (Censos 2021)
• IncomeHH - average household income in Origin_dicofre16
• Nvehicles - average number of car/motorcycle vehicles in the household in Origin_dicofre16
• DrivingLic - percentage of car driving licence holders in Origin_dicofre16
• CarParkFree_Work - percentage of respondents with free car parking at the work location, in Origin_dicofre16
• PTpass - percentage of public transit monthly pass holders in Origin_dicofre16
• internal - binary variable (factor). "Yes": internal trips in that freguesia (Origin_dicofre16), "No": external trips from that freguesia
• Lisboa - binary variable (factor). "Yes": the freguesia is part of Lisbon municipality, "No": otherwise
• Area_km2 - area of in Origin_dicofre16, in km2

Exploratory Factor Analysis

• R script for Exploratory Factor Analysis
• Database of Residential location satisfaction in the Lisbon metropolitan are: example_fact.sav.

Cluster Analysis

• R script for Cluster Analysis
• Database of international airports: Data_Aeroports_Clustersv1

Other materials

• Getting Started with Data in R

• A gentle introduction to tidy statistics in R (video)

• Work with data, Tidy your data, Report reproducibility (tutorials)

• Intro to R basics (free online course)

• Data Frames in R (free online course with video)

• CheatSheet of Data transformation with dplyr: pay attention to filter(), select(), distinct(), arrange(), mutate(), group_by() & summarize(), left_join()

• CheatSheet of Data transformation with tidyr: pay attention to pivot_longer(), pivot_wider()