Week 1 and 2 Flashcards
The VISTA data set is structured into four main tables. What are they?
●Household (H) Table: Contains household-level information like the number of residents, vehicles, and location.
●Person (P) Table: Stores individual-level information for each resident within a household, including demographics, employment status, and car ownership.
●Trip (T) Table: Records details of each trip made by individuals, including the purpose, origin, destination, and mode of transport.
●Stop (S) Table: Documents information about each stop made during a trip, such as the location, activity, arrival and departure times.
Difference between trips and stops?
●Trips: A trip is defined as a journey with a unique purpose. It represents movement from an origin to a destination where an activity takes place. For instance, traveling from home to work for the purpose of working is considered one trip, even if it involves multiple stops for transfers or other reasons.
●Stops: Stops are instances of pausing during a trip. They can occur for various reasons, including transfers between modes of transport, errands, or other activities.
To illustrate this distinction, the source provides two scenarios:
Examples:
Scenario 1: A person travels from home to a train station by car, takes the train to Melbourne Central, and then walks to the university. This entire journey, from home to the university for the purpose of attending university, is considered one trip.
●
Scenario 2: A person travels from home to a shopping center by car, does some shopping, and then drives to the train station, takes the train to Melbourne Central, and walks to the university. This journey is considered two trips because there are two distinct purposes:
○
Trip 1: From home to the shopping center for the purpose of shopping.
○
Trip 2: From the shopping center to the university for the purpose of attending university.
What are the 4 steps of travel demand forecasting models?
1.Trip Generation
2.Trip Distribution
3.Mode Choice
4.Traffic Assignment
What are the roles of Transport Modelling?
The role of transport models is to provide
structured forecasts to provide information on
implications of transport interventions
What two things can transport models outputs do?
The model outputs are used both to:
* establish a structured understanding of
the performance of the transport systems,
today and forecasts of the future; and
* compare the performance of transport
systems with and without interventions to
understand their merits.
What are the 3 scopes of Transport Models?
- Strategic planning and
forecasting
2.Operational
management - Real-time decisions and
control
What 4 things SHOULD Transport Analysis Zones have?
- Transport zones should ideally
contain homogeneous land use (for example, solely residential, industrial or commercial use or parking lots).
2.They should not cross significant
barriers to travel (such as rivers,
freeways and rail lines).
- Transport zones should match, as far as practically possible, Australian Bureau of Statistics (ABS) Statistical
Area boundaries (SA1, SA2, etc). - In general practice, transport zones will be aggregations of the Statistical Area Level 1 (SA1) or mesh block boundaries
What does each statistical area entail?
SA1 - Statistical Area Level 1
- Smallest areas in the Census with detailed spatial data; population of 200-800.
- Balances spatial detail and usable Census data.
- Divides areas with distinct geographic traits; aggregates Mesh Blocks.
- Often combines Locality boundaries in rural zones.
SA2 - Statistical Area Level 2
- Represents community areas for social and economic analysis; population 3,000-25,000.
- Reflects one or more suburbs, especially in urban areas.
- Smallest area for many ABS statistics (e.g., population, health data).
- Composed of entire SA1 areas.
SA3 - Statistical Area Level 3
- Used for regional data analysis; groups SA2s with similar regional traits.
- Population range of 30,000-130,000; includes regional towns or city clusters.
- Aligns with administrative or labour market boundaries.
- Aggregates entire SA2s.
SA4 - Statistical Area Level 4
- Designed for Labour Force Survey data; represents labour markets.
- Population typically over 100,000 in regional areas; 300,000-500,000 in metro areas.
- Supports sufficient sample size for labour estimates.
- Aggregates entire SA3s.
Trip Generation Inputs and Outputs
Trip generation is the procedure where land use, population and economic forecasts are used to estimate how many person trips are produced within, and attracted to, each zone.
Trip Generation Inputs and Outputs
The trip ends from step 1 are linked to
form an origin–destination (OD) matrix
of trips.
Mode Choice inputs and Outputs
Mode choice allocates the origin–destination
trips from step 2 to the available travel modes,
by trip purpose.
This step estimates the choice between travel
modes based on the characteristics of:
* the trip maker (car ownership, age, gender,
income, …)
* the trip itself (trip purpose, the origin and
destination) and
* the characteristics of the travel mode (fares,
vehicle operating costs, travel time, parking
availability and cost, reliability).
The outcome of this step is an estimate of
travel by all available travel modes between all
transport zones.
14
Traffic Assignment Inputs and Outputs
Trip assignment assigns the mode-
specific trip matrices to the alternative
routes or paths available in the
network.
Vehicle trips are assigned to the
roadway network and public transport
trips are assigned to the public
transport network.
This step provides an indication of the
likely distribution of traffic (cars or
transit passengers) on the transport
network (congestion levels and delays). 15
Factor Affecting Trip
Production?
Number of households (in
zones)
* Household sizes
* Larger households have
more travel needs
* Some travel needs are
shared among members
* Socioeconomics variable
* Age, gender,
employment, income,
education, etc.
* Transport subscriptions
* Car ownership, driving
licenses
* Number of bikes, bike
share passes, etc.
* Public transport passes,
discounts
19
What Percent of trips start at the household?
85% of trips start or end
at home
What are the 3 Trip Generation Modelling Methods?
- Growth factor modelling
- Cross Classification Analysis
- Linear Regression
What does growth factor entail, how does it factor, what are pros/cons?
- Growth factor models predict the
number of trips produced or
attracted by zones by applying a
growth factor (multiplier) to the
current number of trips. - Growth factor usually calculated
based on population growth,
average income growth, and
average household car ownership
growth. - Fast and simple but has limitations:
- New and evolving zones
- Difficult to evaluate and
interpret the model
What does cross classification entail, how does it factor, what are pros/cons?
Predicts households trip production
based on household classification
* Classifies households based on
household attribute levels in the
current year
* Household size (5-10 levels)
* Income (3-6 levels)
* Car ownership (3-4 levels)
* More accurate than Growth Factor
* Limitations:
* Data intensive (minimum 50-100
observations in each category)
* Cannot extrapolate beyond
calibration categories
* Difficult to interpret
What does linear regression entail, how does it factor, what are pros/cons?
Linear regression attempts to model the relationship
between a target variable (e.g. trip generation) and a set of
k independent explanatory variables
Done by fitting a linear equation to observed data.
* Model simplicity and transparency of linear regression is a major
advantage
Aspects of a linear model to check :
●
Coefficients: The coefficients represent the estimated impact of each independent variable on the target variable.
○
Magnitude: A larger coefficient indicates a stronger relationship between the independent variable and trip production. For example, a coefficient of 1.9 for household size implies that each additional household member is associated with approximately 1.9 more trips produced.
○
Sign: The sign (positive or negative) indicates the direction of the relationship. A positive sign suggests that an increase in the independent variable leads to an increase in trip production, while a negative sign suggests the opposite. For instance, a positive coefficient for income implies that higher-income households tend to produce more trips.
●
Significance Tests: The output also includes statistical tests, specifically p-values, which help assess the reliability of the estimated coefficients.
○
P-value: A low p-value (typically less than 0.05) indicates that the relationship between the independent variable and trip production is statistically significant. In other words, it’s highly unlikely that the observed relationship is purely due to chance.
R-squared is a common measure of goodness of fit, representing the proportion of variance in the dependent variable (trip production in this case) that is explained by the independent variables included in the model. A higher R-squared value (closer to 1) generally indicates a better fit.
What are dummy variables?
Dummy variables can be used to
incorporate categorical (non-
numeric) variables, such as
gender, employment status, etc.
* You can define and add binary
variables that take on a value of
0 or 1, depending on the
absence or presence of a pre-
defined effect.
* For example:
* non-smoker = 0, smoker = 1
* male = 0, female = 1
Key Points to Remember
●
One Dummy Variable Per Category: If you have a categorical variable with multiple categories (e.g., mode of transport: car, bus, train, bike), you would create a separate dummy variable for each category.
●
Reference Category: When you have multiple dummy variables for a categorical variable, one category is left out as the “reference category.” The coefficients of the other dummy variables are then interpreted relative to that reference category
Difference between F tests and T tests?
○
F-test: This test examines the overall significance of the model, evaluating whether the independent variables, as a group, have a statistically significant impact on the dependent variable.
○
T-test: This test assesses the individual significance of each independent variable, determining whether its estimated coefficient is reliably different from zero. A low p-value (typically less than 0.05) in the t-test suggests that the variable’s contribution to predicting the dependent variable is unlikely due to random chance.
What is Vista?
VISTA (The Victorian Integrated Survey of Travel & Activity)
* An ongoing survey of household travel activity.
* Randomly selected households filling out a one-day travel diary
* Coverage across greater Melbourne and Geelong
* Over 32,000 households and 82,000 people have contributed to the
ongoing survey since 2012
What is it for?
* to understand Victorian household travel behavior
* to help the government make better transport and land-use planning
decisions
7
