This document provides an overview of discrete choice analysis and nested logit models. It begins with a review of binary and multinomial logit models and the independence from irrelevant alternatives property. It then introduces nested logit models as a way to address IIA violations when alternatives are correlated or choices are multidimensional. The document provides an example of a nested logit specification and calculation of choice probabilities. It concludes with extensions like mixed logit models and an appendix on additional model specifications.
Road Safety for India, tech century sociology education future shift happens technology change shifthappens globalization trends china world shift happens web2.0 presentation design facts know india web did you palo innovation internet alto cool statistics 2.0 stats interesting social population marketing global media best good ....? e.g: information great futuro us eg inspiration did you know misc usa knowledge ppt data info development new culture changing style business paradigm learning presentations 'social of shit ideas computers media' layout general changes tecnologia didyouknow evolution communication strategy cambio flatworld separate tags by comma globalisation awesome zen creative demographics trend excellent the it society wow 21st powerpoint thinking life fisch web 2.0 futurology winner educação shifts content my a brenman mudanças economy numbers jobs stuff next digital amazing career work vision study visual to flat shift_happens teaching pace jeff myspace brand flat world economia in fav mankind statistik exemplo social_media scenario social media examples shock futur shifting graphics branding slideshare slide goodpresentation elearning pedagogy time clean pop singularity image karl curiosidades will idea sociologie tics issues simple is viz fun veranderingen edu concepts. de personal socialmedia america shithappens countries template think predictions best presentation computer management contest web20 humanity transformation presentationzen impacto happen figures pres shift cambio nice conhecimento brilliant mindshift high u generation worldchindiathe competitive sci-fi pov ,
how to make money on the internet ,how to make moneyo make money fast,how to make money online,how to make quick money,make money on the internet,make money now , make money,make money at home,make money easy,make money quick ,make money fast,make money online ,make money online fast, leadership powerpoint ,powerpoint on leadership,free ebooks leadership ,
leadership powerpoint presentations , leadership powerpoints ,leadership ppt , wordpress, youtube videos, blogpost
Traffic congestion have a big impact on our personal life, career, future and even our safety. it causes stress, annoy and frustrate us. the traffic jams burns fuel at a higher rate .
The high fuel consumption hiked fares for public means and it also contributes greatly to the amount of emissions of greenhouse gases that create air pollution and eventually global warming.
we trying here partially to solve this problem in critical segments such as bridge, viaduct or tunnel etc. by using Excel simulation for Flow – Density relationship.
Road Safety for India, tech century sociology education future shift happens technology change shifthappens globalization trends china world shift happens web2.0 presentation design facts know india web did you palo innovation internet alto cool statistics 2.0 stats interesting social population marketing global media best good ....? e.g: information great futuro us eg inspiration did you know misc usa knowledge ppt data info development new culture changing style business paradigm learning presentations 'social of shit ideas computers media' layout general changes tecnologia didyouknow evolution communication strategy cambio flatworld separate tags by comma globalisation awesome zen creative demographics trend excellent the it society wow 21st powerpoint thinking life fisch web 2.0 futurology winner educação shifts content my a brenman mudanças economy numbers jobs stuff next digital amazing career work vision study visual to flat shift_happens teaching pace jeff myspace brand flat world economia in fav mankind statistik exemplo social_media scenario social media examples shock futur shifting graphics branding slideshare slide goodpresentation elearning pedagogy time clean pop singularity image karl curiosidades will idea sociologie tics issues simple is viz fun veranderingen edu concepts. de personal socialmedia america shithappens countries template think predictions best presentation computer management contest web20 humanity transformation presentationzen impacto happen figures pres shift cambio nice conhecimento brilliant mindshift high u generation worldchindiathe competitive sci-fi pov ,
how to make money on the internet ,how to make moneyo make money fast,how to make money online,how to make quick money,make money on the internet,make money now , make money,make money at home,make money easy,make money quick ,make money fast,make money online ,make money online fast, leadership powerpoint ,powerpoint on leadership,free ebooks leadership ,
leadership powerpoint presentations , leadership powerpoints ,leadership ppt , wordpress, youtube videos, blogpost
Traffic congestion have a big impact on our personal life, career, future and even our safety. it causes stress, annoy and frustrate us. the traffic jams burns fuel at a higher rate .
The high fuel consumption hiked fares for public means and it also contributes greatly to the amount of emissions of greenhouse gases that create air pollution and eventually global warming.
we trying here partially to solve this problem in critical segments such as bridge, viaduct or tunnel etc. by using Excel simulation for Flow – Density relationship.
Adjusting the flow in crucial areas can maximize the overall throughput of traffic along a stretch of road. This is of particular interest in regions of high traffic density, which may be caused by high volume peak time traffic, accidents or closure of one or more lanes of the road.
this is a brief introduction to various traffic engineering basic characteristics which are useful in designing any corridor or passage with safety & reliability.
Capacity & Level of Service: Highways & Signalized Intersections (Indo-HCM)Vijai Krishnan V
This presentation gives a glimpse on estimating the capacity and Level of Service (LOS) of highway midblock sections and signalized intersections under heterogeneous traffic conditions using the Indo-HCM 2017 Manual. It also compares the Indo-HCM LOS estimation methods with US-HCM. Some practice questions are also included.
I acknowledge the co-author Ms. Sethulakshmi G (Ph. D. Scholar, NIT Surathkal) for her valuable contribution to this presentation.
Adjusting the flow in crucial areas can maximize the overall throughput of traffic along a stretch of road. This is of particular interest in regions of high traffic density, which may be caused by high volume peak time traffic, accidents or closure of one or more lanes of the road.
this is a brief introduction to various traffic engineering basic characteristics which are useful in designing any corridor or passage with safety & reliability.
Capacity & Level of Service: Highways & Signalized Intersections (Indo-HCM)Vijai Krishnan V
This presentation gives a glimpse on estimating the capacity and Level of Service (LOS) of highway midblock sections and signalized intersections under heterogeneous traffic conditions using the Indo-HCM 2017 Manual. It also compares the Indo-HCM LOS estimation methods with US-HCM. Some practice questions are also included.
I acknowledge the co-author Ms. Sethulakshmi G (Ph. D. Scholar, NIT Surathkal) for her valuable contribution to this presentation.
Presentation of GreenYourMove's hybrid approach in the 3rd Conference on Sust...GreenYourMove
Presentation of our hybrid approach to the journey planning problem with the use of mathematical programming and other modern techniques. Our technique is based on the combination of heuristic techniques and mathematical programming.
Research is still underway.
The article presents different approaches to finding the optimal solution for a problem, which extends the classical traveling salesman problem. Takes into consideration the possibility of choosing a toll highway and the standard road between two cities. Describes the experimentation system. Provides mathematical model, results of the investigation, and a conclusion.
Presentation of GreenYourMove's hybrid approach in 3rd International Conferen...GreenYourMove
Presentation of the Journey planning problem and GreenYourMove's hybrid approach.
Dr. Georgios Saharidis, Fragogios Antonis, Rizopoulos Dimitris, Chrysostomos Chatzigeorgiou
My first presentation as a PhD student in which I outline the background to my research project. This presentation was given as part of the University of Southampton Transportation Research Group seminar programme.
“An Alternate Approach to Find an Optimal Solution of a Transportation Problem.”IOSRJM
The Transportation Problem is the special class of Linear Programming Problem. It arises when the situation in which a commodity is shipped from sources to destinations. The main object is to determine the amounts shipped from each sources to each destinations which minimize the total shipping cost while satisfying both supply criteria and demand requirements. In this paper, we are giving the idea about to finding the Initial Basic Feasible solution as well as the optimal solution or near to the optimal solution of a Transportation problem using the method known as “An Alternate Approach to find an optimal Solution of a Transportation Problem”. An Algorithm provided here, concentrate at unoccupied cells and proceeds further. Also, the numerical examples are provided to explain the proposed algorithm. However, the above method gives a step by step development of the solution procedure for finding an optimal solution.
A New Approach to Solve Initial Basic Feasible Solution for the Transportatio...Dr. Amarjeet Singh
In transportation problem the main requirement is
to find the Initial Basic Feasible Solution for the transportation
problem. The objective of the transportation problem is to
minimize the cost. In this paper, a new algorithm (i.e.) Row
Implied Cost Method(RICM) which is proposed to find an
initial basic feasible solution for the transportation problem.
This method is illustrated with numerical examples.
We are interested in finding a permutation of the entries of a given square matrix so that the maximum number of its nonzero entries are moved to one of the corners in a L-shaped fashion.
If we interpret the nonzero entries of the matrix as the edges of a graph, this problem boils down to the so-called core–periphery structure, consisting of two sets: the core, a set of nodes that is highly connected across the whole graph, and the periphery, a set of nodes that is well connected only to the nodes that are in the core.
Matrix reordering problems have applications in sparse factorizations and preconditioning, while revealing core–periphery structures in networks has applications in economic, social and communication networks.
Graph theory - Traveling Salesman and Chinese PostmanChristian Kehl
Traveling Salesman and Chinese Postman problems
1. Problem Description and Complexity
2. Theoretical Approach
3. Practical Approaches and Possible Solutions
4. Examples
Differential game theory for Traffic Flow ModellingSerge Hoogendoorn
Lecture given at the INdAM symposium in Rome, 2017. The lecture shows how you can use differential games to model traffic flows, focussing on pedestrian simulation.
Most small businesses struggle to see marketing results. In this session, we will eliminate any confusion about what to do next, solving your marketing problems so your business can thrive. You’ll learn how to create a foundational marketing OS (operating system) based on neuroscience and backed by real-world results. You’ll be taught how to develop deep customer connections, and how to have your CRM dynamically segment and sell at any stage in the customer’s journey. By the end of the session, you’ll remove confusion and chaos and replace it with clarity and confidence for long-term marketing success.
Key Takeaways:
• Uncover the power of a foundational marketing system that dynamically communicates with prospects and customers on autopilot.
• Harness neuroscience and Tribal Alignment to transform your communication strategies, turning potential clients into fans and those fans into loyal customers.
• Discover the art of automated segmentation, pinpointing your most lucrative customers and identifying the optimal moments for successful conversions.
• Streamline your business with a content production plan that eliminates guesswork, wasted time, and money.
The digital marketing industry is changing faster than ever and those who don’t adapt with the times are losing market share. Where should marketers be focusing their efforts? What strategies are the experts seeing get the best results? Get up-to-speed with the latest industry insights, trends and predictions for the future in this panel discussion with some leading digital marketing experts.
For too many years marketing and sales have operated in silos...while in some forward thinking companies, the two organizations work together to drive new opportunity development and revenue. This session will explore the lessons learned in that beautiful dance that can occur when marketing and sales work together...to drive new opportunity development, account expansion and customer satisfaction.
No, this is not a conversation about MQLs and SQLs. Instead we will focus on a framework that allows the two organizations to drive company success together.
Financial curveballs sent many American families reeling in 2023. Household budgets were squeezed by rising interest rates, surging prices on everyday goods, and a stagnating housing market. Consumers were feeling strapped. That sentiment, however, appears to be waning. The question is, to what extent?
To take the pulse of consumers’ feelings about their financial well-being ahead of a highly anticipated election, ThinkNow conducted a nationally representative quantitative survey. The survey highlights consumers’ hopes and anxieties as we move into 2024. Let's unpack the key findings to gain insights about where we stand.
AI-Powered Personalization: Principles, Use Cases, and Its Impact on CROVWO
In today’s era of AI, personalization is more than just a trend—it’s a fundamental strategy that unlocks numerous opportunities.
When done effectively, personalization builds trust, loyalty, and satisfaction among your users—key factors for business success. However, relying solely on AI capabilities isn’t enough. You need to anchor your approach in solid principles, understand your users’ context, and master the art of persuasion.
Join us as Sarjak Patel and Naitry Saggu from 3rd Eye Consulting unveil a transformative framework. This approach seamlessly integrates your unique context, consumer insights, and conversion goals, paving the way for unparalleled success in personalization.
How to Run Landing Page Tests On and Off Paid Social PlatformsVWO
Join us for an exclusive webinar featuring Mariate, Alexandra and Nima where we will unveil a comprehensive blueprint for crafting a successful paid media strategy focused on landing page testing.With escalating costs in paid advertising, understanding how to maximize each visitor’s experience is crucial for retention and conversion.
This session will dive into the methodologies for executing and analyzing landing page tests within paid social channels, offering a blend of theoretical knowledge and practical insights.
The Pearmill team will guide you through the nuances of setting up and managing landing page experiments on paid social platforms. You will learn about the critical rules to follow, the structure of effective tests, optimal conversion duration and budget allocation.
The session will also cover data analysis techniques and criteria for graduating landing pages.
In the second part of the webinar, Pearmill will explore the use of A/B testing platforms. Discover common pitfalls to avoid in A/B testing and gain insights into analyzing A/B tests results effectively.
Unleash the power of UK SEO with Brand Highlighters! Our guide delves into the unique search landscape of Britain, equipping you with targeted strategies to dominate UK search engine results. Discover local SEO tactics, keyword magic for UK audiences, and mobile optimization secrets. Get your website seen by the right people and propel your brand to the top of UK searches.
To learn more: https://brandhighlighters.co.uk/blog/top-seo-agencies-uk/
A.I. (artificial intelligence) platforms are popping up all the time, and many of them can and should be used to help grow your brand, increase your sales and decrease your marketing costs.In this presentation:We will review some of the best AI platforms that are available for you to use.We will interact with some of the platforms in real-time, so attendees can see how they work.We will also look at some current brands that are using AI to help them create marketing messages, saving them time and money in the process. Lastly, we will discuss the pros and cons of using AI in marketing & branding and have a lively conversation that includes comments from the audience.
Key Takeaways:
Attendees will learn about LLM platforms, like ChatGPT, and how they work, with preset examples and real time interactions with the platform. Attendees will learn about other AI platforms that are creating graphic design elements at the push of a button...pre-set examples and real-time interactions.Attendees will discuss the pros & cons of AI in marketing + branding and share their perspectives with one another. Attendees will learn about the cost savings and the time savings associated with using AI, should they choose to.
The What, Why & How of 3D and AR in Digital CommercePushON Ltd
Vladimir Mulhem has over 20 years of experience in commercialising cutting edge creative technology across construction, marketing and retail.
Previously the founder and Tech and Innovation Director of Creative Content Works working with the likes of Next, John Lewis and JD Sport, he now helps retailers, brands and agencies solve challenges of applying the emerging technologies 3D, AR, VR and Gen AI to real-world problems.
In this webinar, Vladimir will be covering the following topics:
Applications of 3D and AR in Digital Commerce,
Benefits of 3D and AR,
Tools to create, manage and publish 3D and AR in Digital Commerce.
SMM Cheap - No. 1 SMM panel in the worldsmmpanel567
Boost your social media marketing with our SMM Panel services offering SMM Cheap services! Get cost-effective services for your business and increase followers, likes, and engagement across all social media platforms. Get affordable services perfect for businesses and influencers looking to increase their social proof. See how cheap SMM strategies can help improve your social media presence and be a pro at the social media game.
The session includes a brief history of the evolution of search before diving into the roles technology, content, and links play in developing a powerful SEO strategy in a world of Generative AI and social search. Discover how to optimize for TikTok searches, Google's Gemini, and Search Generative Experience while developing a powerful arsenal of tools and templates to help maximize the effectiveness of your SEO initiatives.
Key Takeaways:
Understand how search engines work
Be able to find out where your users search
Know what is required for each discipline of SEO
Feel confident creating an SEO Plan
Confidently measure SEO performance
SEO as the Backbone of Digital MarketingFelipe Bazon
In this talk Felipe Bazon will share how him and his team at Hedgehog Digital share our journey of making C-Levels alike, specially CMOS realize that SEO is the backbone of digital marketing by showing how SEO can contribute to brand awareness, reputation and authority and above all how to use SEO to create more robust global marketing strategies.
Mastering Multi-Touchpoint Content Strategy: Navigate Fragmented User JourneysSearch Engine Journal
Digital platforms are constantly multiplying, and with that, user engagement is becoming more intricate and fragmented.
So how do you effectively navigate distributing and tailoring your content across these various touchpoints?
Watch this webinar as we dive into the evolving landscape of content strategy tailored for today's fragmented user journeys. Understanding how to deliver your content to your users is more crucial than ever, and we’ll provide actionable tips for navigating these intricate challenges.
You’ll learn:
- How today’s users engage with content across various channels and devices.
- The latest methodologies for identifying and addressing content gaps to keep your content strategy proactive and relevant.
- What digital shelf space is and how your content strategy needs to pivot.
With Wayne Cichanski, we’ll explore innovative strategies to map out and meet the diverse needs of your audience, ensuring every piece of content resonates and connects, regardless of where or how it is consumed.
Mastering Multi-Touchpoint Content Strategy: Navigate Fragmented User Journeys
Dcm
1. Discrete Choice Analysis II
Moshe Ben-Akiva
1.201 / 11.545 / ESD.210
Transportation Systems Analysis: Demand & Economics
Fall 2008
2. Review – Last Lecture
●Introduction to Discrete Choice Analysis
●A simple example – route choice
●The Random Utility Model
– Systematic utility
– Random components
●Derivation of the Probit and Logit models
– Binary Probit
– Binary Logit
– Multinomial Logit
2
3. Outline – This Lecture
● Model specification and estimation
● Aggregation and forecasting
● Independence from Irrelevant Alternatives (IIA) property –
Motivation for Nested Logit
● Nested Logit - specification and an example
● Appendix:
– Nested Logit model specification
– Advanced Choice Models
3
4. Specification of Systematic Components
● Types of Variables
– Attributes of alternatives: Zin, e.g., travel time, travel cost
– Characteristics of decision-makers: Sn, e.g., age, gender, income,
occupation
– Therefore: Xin = h(Zin, Sn)
● Examples:
– Xin1 = Zin1 = travel cost
– Xin2 = log(Zin2) = log (travel time)
– Xin3 = Zin1/Sn1 = travel cost / income
● Functional Form: Linear in the Parameters
Vin = β1Xin1 + β2Xin2 + ... + βkXinK
Vjn = β1Xjn1 + β2Xjn2 + ... + βkXjnK
4
5. Data Collection
●Data collection for each individual in the sample:
– Choice set: available alternatives
– Socio-economic characteristics
– Attributes of available alternatives
– Actual choice
n Income Auto Time Transit Time Choice
1 35 15.4 58.2 Auto
2 45 14.2 31.0 Transit
3 37 19.6 43.6 Auto
4 42 50.8 59.9 Auto
5 32 55.5 33.8 Transit
6 15 N/A 48.4 Transit
5
6. Model Specification Example
Vauto = β0 + β1 TTauto + β2 ln(Income)
Vtransit = β1 TTtransit
ββββ0 ββββ1 ββββ2
Auto 1 TTauto ln(Income)
Transit 0 TTtransit 0
6
8. Maximum Likelihood Estimation
● Find the values of β that are most likely to result in the choices observed
in the sample:
– max L*(ββββ) = P1(Auto)P2(Transit)…P6(Transit)
0, if person
1, if person n chose alternative i
● If yin =
n chose alternative j
● Then we maximize, over choices of {β1, β2 …, βk}, the following
expression:
N
L*
( β 1 , β 2 ,..., β k ) = ∏ Pn (i) y in
Pn ( j )
y jn
n =1
● β* = arg maxβ L* (β1, β2,…, βk)
= arg maxβ log L* (β1, β2, …, βk)
8
9. Sources of Data on User Behavior
● Revealed Preferences Data
– Travel Diaries
– Field Tests
● Stated Preferences Data
– Surveys
– Simulators
9
10. Stated Preferences / Conjoint Experiments
● Used for product design and pricing
– For products with significantly different attributes
– When attributes are strongly correlated in real markets
– Where market tests are expensive or infeasible
● Uses data from survey “trade-off” experiments in which
attributes of the product are systematically varied
● Applied in transportation studies since the early 1980s
10
11. Aggregation and Forecasting
● Objective is to make aggregate predictions from
– A disaggregate model, P( i | Xn )
– Which is based on individual attributes and
characteristics, Xn
– Having only limited information about the explanatory
variables
11
12. The Aggregate Forecasting Problem
● The fraction of population T choosing alt. i is:
( ) P i X ) (W i = ∫ ( | p X dX) , p(X) is the density function of X
X
NT
( |=
1
∑P i X ) , NT is the # in the population of interestNT n=1
n
● Not feasible to calculate because:
– We never know each individual’s complete vector of
relevant attributes
– p(X) is generally unknown
● The problem is to reduce the required data
12
13. ˆp
Sample Enumeration
● Use a sample to represent the entire population
● For a random sample:
Ns
Wˆ (i) =
1
∑Pˆ(i | xn ) where Ns is the # of obs. in sample
Ns n=1
● For a weighted sample:
Ns
w
n
W iˆ ( ) = ∑
∑
Pˆ ( |i xn ) ,where
1
is xn 's selection prob.
n=1 wn wn
n
● No aggregations bias, but there is sampling error
13
14. Disaggregate Prediction
Generate a representative population
Apply demand model
• Calculate probabilities or simulate
decision for each decision maker
• Translate into trips
14
• Aggregate trips to OD matrices
Assign traffic to a network
Predict system performance
16. Review
● Empirical issues
– Model specification and estimation
– Aggregate forecasting
● Next…More theoretical issues
– Independence from Irrelevant Alternatives (IIA) property –
Motivation for Nested Logit
– Nested Logit - specification and an example
16
17. Summary of Basic Discrete Choice Models
● Binary Probit:
2
Pn | n = Φ Vn ∫ e dε(i C ) ( ) =
Vn
1 −
1
ε2
2π−∞
● Binary Logit:
Pn ( | n ) =
1+
1
e−Vn
eVin
e
+
Vin
e
Vjn
i C =
● Multinomial Logit:
Vin
P ( | ) =
e
e jn
i Cn n V
∑j∈Cn
17
18. Independence from
Irrelevant Alternatives (IIA)
●Property of the Multinomial Logit Model
– εjn independent identically distributed (i.i.d.)
– εjn ~ ExtremeValue(0,µ) ∀ j
eµVin
P i C– n ( | n ) =
∑e
µVjn
j Cn∈
P( | ) P(i C| )so
i C1
=
2
∀ i, j, C1, C2
P( | ) P(j C| )j C1 2
such that i, j ∈ C1, i, j ∈ C2, C1 ⊆ Cn and C2 ⊆ Cn
18
19. Examples of IIA
● Route choice with an overlapping segment
O
Path 1
Path 2
a
b
D
T-δ
T
δ
eµT
1
P( |{ , a, }) = P(2a|{ , a, }) = P(2 |{ , a
∑eµT
3
1 1 2 2b 1 2 2b b 1 2 ,2b}) = =
j { , a,2b}∈ 1 2
19
20. Red Bus / Blue Bus Paradox
●Consider that initially auto and bus have the same utility
– Cn = {auto, bus} and Vauto = Vbus = V
– P(auto) = P(bus) = 1/2
●Suppose that a new bus service is introduced that is identical
to the existing bus service, except the buses are painted
differently (red vs. blue)
– Cn = {auto, red bus, blue bus}; Vred bus = Vblue bus = V
– Logit now predicts
P(auto) = P(red bus) = P(blue bus) =1/3
– We’d expect
P(auto) =1/2, P(red bus) = P(blue bus) =1/4
20
21. IIA and Aggregation
●Divide the population into two equally-sized groups: those
who prefer autos, and those who prefer transit
●Mode shares before introducing blue bus:
●Auto and red bus share ratios remain constant for each
group after introducing blue bus:
Population Auto Share Red Bus Share
Auto people 90% 10% P(auto)/P(red bus) = 9
Transit people 10% 90% P(auto)/P(red bus) = 1/9
Total 50% 50%
21
Population Auto Share Red Bus Share Blue Bus Share
Auto people 81.8% 9.1% 9.1%
Transit people 5.2% 47.4% 47.4%
Total 43.5% 28.25% 28.25%
22. Motivation for Nested Logit
● Overcome the IIA Problem of Multinomial Logit when
– Alternatives are correlated
(e.g., red bus and blue bus)
– Multidimensional choices are considered (e.g., departure
time and route)
22
23. Tree Representation of Nested Logit
● Example: Mode Choice (Correlated Alternatives)
motorized non-motorized
auto transit bicycle walk
drive carpool bus metro
alone
23
24. Tree Representation of Nested Logit
● Example: Route and Departure Time Choice (Multidimensional Choice)
Route 1
8:30
....
Route 2 Route 3
8:408:208:10 8:50
....
8:30 8:408:208:10 8:50
Route 1 Route 2 Route 3
.... ....
24
25. Nested Model Estimation
● Logit at each node
● Utilities at lower level enter at the node as the inclusive value
= ∑∈ NM
i
Ci
V
NM eI ln
Walk Bike Car Taxi Bus
Non-
motorized
(NM)
Motorized
(M)
● The inclusive value is often referred to as logsum
25
26. Nested Model – Example
Walk Bike Car Taxi Bus
Non-
motorized
(NM)
Motorized
(M)
µNMVi
e
i =Walk, BikeP(i | NM ) =
eµNMVWalk
+ eµNMVBike
INM =
1
ln(eµNMVWalk
+ eµNMVBike
)
µNM
26
27. Nested Model – Example
Walk Bike Car Taxi Bus
Non-
motorized
(NM)
Motorized
(M)
µMVi
e
i = Car,Taxi, BusP(i | M ) =
eµMVCar
+ eµMVTaxi
+ eµMVBus
IM =
1
ln(eµMVCar
+ eµMVTaxi
+ eµMVBus
)
µM
27
28. Nested Model – Example
Walk Bike Car Taxi Bus
Non-
motorized
(NM)
Motorized
(M)
µINM
e
P(NM ) = µINM µIM
e + e
µIM
e
P(M ) =
eµINM
+ eµIM
28
29. Nested Model – Example
● Calculation of choice probabilities
P(Bus)=P(Bus|M)⋅P(M)
eµM
VBus µI
M
e
=
⋅
VCar VTaxi VBus µI µI
eµM
+eµM
+eµM
+
NM
M
e
e
µ
ln(eµMVCar+eµMVTaxi+eµMVBus)
eµMVBus
eµM
=
⋅
eµMVCar
+eµMVTaxi
+eµMVBus µ µ µ µ
e NMVWalk e NMVBike µMVCar eµMVTaxi eµMVBusln(
)
ln(e
)
+
+
+
eµNM
+eµM
29
30. Extensions to Discrete Choice Modeling
● Multinomial Probit (MNP)
● Sampling and Estimation Methods
● Combined Data Sets
● Taste Heterogeneity
● Cross Nested Logit and GEV Models
● Mixed Logit and Probit (Hybrid Models)
● Latent Variables (e.g., Attitudes and Perceptions)
● Choice Set Generation
30
31. Summary
● Introduction to Discrete Choice Analysis
● A simple example
● The Random Utility Model
● Specification and Estimation of Discrete Choice Models
● Forecasting with Discrete Choice Models
● IIA Property - Motivation for Nested Logit Models
● Nested Logit
31
32. Additional Readings
● Ben-Akiva, M. and Bierlaire, M. (2003), ‘Discrete Choice Models With Applications to
Departure Time and Route Choice,’ The Handbook of Transportation Science, 2nd ed.,
(eds.) R.W. Hall, Kluwer, pp. 7 – 38.
● Ben-Akiva, M. and Lerman, S. (1985), Discrete Choice Analysis, MIT Press, Cambridge,
Massachusetts.
● Train, K. (2003), Discrete Choice Methods with Simulation, Cambridge University Press,
United Kingdom.
● And/Or take 1.202 next semester!
32
34. Nested Logit Model Specification
● Partition Cn into M non-overlapping nests:
Cmn ∩ Cm’n = ∅ ∀ m≠m’
● Deterministic utility term for nest Cmn:
~
V
VC
=V
~ +
1
ln ∑e
µm jn
mn Cmn µm j∈Cmn
● Model: P(i | Cn ) = P(Cmn | Cn )P(i | Cmn ),i ∈Cmn ⊆ Cn
where
e
µVCmn
eµmV
~
in
P(Cmn | Cn ) = and P(i | Cmn ) = ~
∑e
µVCln ∑e
µmVjn
l
j∈Cmn
34
35. Continuous Logit Mixture
Example:
● Combining Probit and Logit
● Error decomposed into two parts
– Probit-type portion for flexibility
– i.i.d. Extreme Value for tractability
● An intuitive, practical, and powerful method
– Correlations across alternatives
– Taste heterogeneity
– Correlations across space and time
● Requires simulation-based estimation
35
36. Cont. Logit Mixture: Error Component
Illustration
● Utility:
U = β Xauto auto
U bus = β X bus
U subway = β X subway
auto
bus
auto
bus
subw subwaay y
ν
ν+
ν
ξ
ξ
ξ
+ +
+
+ + ν i.i.d. Extreme Value
ε e.g. ξ ~ N(0,Σ)
● Probability:
β Xauto +ξauto
Λ(auto|X, )ξ =
eβ Xauto +ξauto
+ e
e
β Xbus +ξbus
+ e
β Xsubway +ξsubway
ξ unknown •
P(auto|X) = ∫Λ(auto | X , )ξ f (ξ ξ)d
36
ξ
37. Continuous Logit Mixture
Random Taste Variation
● Logit: β is a constant vector
– Can segment, e.g. βlow inc , βmed inc , βhigh inc
● Logit Mixture: β can be randomly distributed
– Can be a function of personal characteristics
– Distribution can be Normal, Lognormal, Triangular, etc
37
38. Discrete Logit Mixture
Latent Classes
Main Postulate:
• Unobserved heterogeneity is “generated” by discrete or
categorical constructs such as
�Different decision protocols adopted
�Choice sets considered may vary
�Segments of the population with varying tastes
• Above constructs characterized as latent classes
38
39. Latent Class Choice Model
P i( ) =
S
∑Λ( | ) ( )i s Q s
s=1
Class-specific Class
Choice Model Membership
Model
(probability of (probability of
choosing i belonging to
conditional on class s)
belonging to
class s)
39
40. Summary of Discrete Choice Models
Handles unobserved taste
heterogeneity
Flexible substitution pattern
Logit NL/CNL Probit Logit Mixture
No No Yes Yes
No Yes Yes Yes
No No Yes YesHandles panel data
Requires error terms normally
distributed
Closed-form choice probabilities
available
No No Yes No
Yes Yes No No (cont.)
Yes (discrete)
Numerical approximation and/or
simulation needed
No No Yes Yes (cont.)
No (discrete)
40
41. 6. Revealed and Stated Preferences
• Revealed Preferences Data
– Travel Diaries
– Field Tests
• Stated Preferences Data
– Surveys
– Simulators
41
42. Stated Preferences / Conjoint
Experiments
• Used for product design and pricing
– For products with significantly different attributes
– When attributes are strongly correlated in real markets
– Where market tests are expensive or infeasible
• Uses data from survey “trade-off” experiments in which
attributes of the product are systematically varied
• Applied in transportation studies since the early 1980s
• Can be combined with Revealed Preferences Data
– Benefit from strengths
– Correct for weaknesses
– Improve efficiency
42
43. Framework for Combining Data
Utility
Attributes of Alternatives
& Characteristics of
Decision-Maker
Revealed Preferences
Stated Preferences
43
44. MIT OpenCourseWare
http://ocw.mit.edu
1.201J / 11.545J / ESD.210J Transportation Systems Analysis: Demand and Economics
Fall 2008
For information about citing these materials or our Terms of Use, visit: http://ocw.mit.edu/terms.