You are on page 1of 68

PEMODELAN PEMODELAN PEMODELAN PEMODELAN

STATE OF THE ART
KEBIJAKSANAAN PERENCANAAN
DAN PENGEMBANGAN TRANSPORTASI
Ahli Ek i Ahli H k Ahli Ahli Ekonomi
Transportasi
Ahli Sistim Transportasi
Perencana Transportasi Perkotaan
Perencana Transportasi Wilayah
Perencana Moda Transportasi
Perencana Transportasi Nasional
Ahli Analisis Sistim dan Informasi
Ahli Hukum
Transportasi
Ahli
Lingkungan
Ahli
Keselamatan Ahli Analisis Sistim dan Informasi Keselamatan
Transportasi
Ahli Prasarana Transportasi
Jalan Raya, Jalan K.A,
Pelabuhan Laut/ Udara, Terminal
Bid P d k
Ahli Sarana Transportasi
Mobil, Pesawat Terbang,
Kereta Api, Kapal Laut dll.
Ahli Operasi, Pemeliharaan
dan Manajemen Transportasi
Bidang Pendukung:
Bidang Pendukung:
Mekanika Tanah
Struktur/ Konstruksi
Mekanika Teknik
Material dll.
p p
Bidang Pendukung:
Teknologi Mekanik
Teknologi Bahan
Mekanika Fluida
T Di ik dll
g g
Riset Operasi/Manajemen
Statistik
Computer/ ICT
Administrasi Bisnis dll.
Termo Dinamika dll.
Values, Goals, Objectives and Measures of Effectiveness (MOE) in
Transport Operation
VALUES
Need for order
Need to earn a living (survival)
GOALS
Increase efficiency
of existing road
network
Minimize cost
associated with
travel
Improve quality of
public
transportation
OBJECTIVES
Minimize out-
of-pocket
Reduce
number of
Increase person
carrying
Increase
safety of
Improve
reliability of of-pocket
costs per trip
number of
vehicle on the
network
carrying
capacity of
existing system
safety of
travel
reliability of
service
MEASURE OF
EFFECTIVENESS
Percent
of bus
trips on
time
Number of
accident
per 10.000
registered
Person-
flow per
hour
Average
delay per
vehicle per
trip
Average
number
occupants
per vehicle
Dollar
costs per
mile
g
vehicles
p p
Steps in an Urban Transportation Planning Process
Information on the
Transportation
System
Information on the
Policy, Organizational,
Fiscal, Regulations etc
Information on the
Urban Activity
System
Diagnosis
Identify Possible Plans,
Projects or Strategies
Analysis
Operations Monitoring
Evaluation
P j t D l t
Scheduling and
Budgeting
Project Development
and Implementation
Best Plan
Information on the
Transportation
System
Information on
the Urban
Activity System
Decision Making
Process
Information on the
Policy, Organizational,
Fiscal, Regulations etc
System
Diagnosis
Activity System
Problem
Identification and
Definition
Identify Possible
Plans, Projects or
Strategies
Planning
Analysis
Evaluation
Debate and
Policy
Formulation
Process
S h d li d
Best Plan
Scheduling and
Budgeting
Project Development
and Implementation
Implementation
and Implementation
Operations Monitoring
Evaluation and
Feedback
INTRODUCTION TO INTRODUCTION TO
SYSTEMS MODELING
Sebuah “ model” merupakan representasi dari sebuah
realita, yang dapat meliputi:
Physical model
(model arsitek, terowongan, jaringan transportasi dsb)
realita, yang dapat meliputi:
Peta, diagram
Statistical and Mathematical models mendiskripsikan Statistical and Mathematical models, mendiskripsikan
beberapa aspek seperti aspek fisik, sosial dan ekonomi
(economic models, transport demand models, traffic
accident models) accident models)
H i d l lib tk d h Hampir semua model melibatkan penyederhanaan
dari keadaan sebenarnya (the real world), yang
dibuat untuk tujuan tertentu seperti klarifikasi, j
pemahaman ataupun prediksi
B b d l l bih d k ti k d Beberapa model lebih mendekati keadaan
sebenarnya dibanding yang lain yang lebih
mendekati the real world umumnya memiliki
kompleksitas yang lebih tinggi
N th l d l li t d tid k l l Nevertheless, model yang complicated tidak selalu
merupakan model yang terbaik; sometimes sebuah
model yang sederhana is more appropriate to the y g pp p
particular purpose in hand
The Choice of Explanatory Variables The Choice of Explanatory Variables p y p y
should primarily based on: should primarily based on:
The theory to be relied on, The theory to be relied on,
The question to be answered, and The question to be answered, and qq
The professional knowledge, The professional knowledge,
rather than rather than the multiple correlation the multiple correlation and and curve curve
fitting ambition fitting ambition fitting ambition fitting ambition
OECDScientific Expert Group (1997) OECDScientific Expert Group (1997) OECD Scientific Expert Group (1997) OECD Scientific Expert Group (1997)
Sufficiently Accurate Models: Sufficiently Accurate Models: Sufficiently Accurate Models: Sufficiently Accurate Models:
Produce useful quantitative results for comparing Produce useful quantitative results for comparing Produce useful quantitative results for comparing Produce useful quantitative results for comparing
and evaluating different and evaluating different transport policies or transport policies or
investment options investment options
Provides insights into the consequences of Provides insights into the consequences of
alternative courses of actions alternative courses of actions
Helps make Helps make the right planning decisions the right planning decisions under under
alternative courses of actions alternative courses of actions
proper application and sensible interpretation of the proper application and sensible interpretation of the
results results
RULES FOR THE DESIGN OF
MATHEMATICAL MODELS
1. What is the purpose of the model?
2. What should variables be put into the
model?
3. Which of the variables can be controlled
by the planner or engineer?
4. What are the theories used to represent in
the model?
RULES FOR THE DESIGN OF
MATHEMATICAL MODELS
5. How should the model be aggregated?
6. How should time be treated?
7. What are the techniques used? Are they
available?
8. Are the data available?
9. How can the model be calibrated and
validated?
PENERAPAN “ RULES” UNTUK PENERAPAN RULES UNTUK
LAND USE – TRANSPORT MODEL
1. What is the purpose of the model?
Membantu memahami bagaimana sistim (Land Use
Transport) bekerja p ) j
Memprediksi kemungkinan perubahan arus lalu p g p
lintas sebagai dampak dari perubahan land use
dan transport (sarana dan prasarana)
2. What should variables be put into the
Variabel utama yang digunakan adalah LAND USE
model?
Variabel utama yang digunakan adalah LAND USE,
TRANSPORT dan TRAFFIC
3. Which of the variables can be
controlled by the planner or engineer? controlled by the planner or engineer?
Planner atau Engineer dapat sepenuhnya Planner atau Engineer dapat sepenuhnya
mengendalikan lokasi land use dan fasilitas
transportasi
4. What are the theories be used to 4. What are the theories be used to
represent in the model?
Teori yang digunakan meliputi: accessibility, trip
generation, trip distribution, trip assignment (mode
and route choice) dan the dynamic of traffic flow
(traffic on the transport network)
masing-masing teori (konsep) merupakan
sub-model dari final model
5. How should the model be aggregated?
Pengelompokan dapat dilakukan/ dipilih untuk
zona besar atau zona kecil
Apakah lalu lintas diperhitungkan secara
keseluruhan atau dipisahkan menurut tujuan keseluruhan atau dipisahkan menurut tujuan
perjalanan, waktu perjalanan, arah dll
6 How should time be treated?
D i d l kk i b l k k
6. How should time be treated?
Dynamic models memasukkan variabel waktu ke
dalam hubungan matematik lebih complicated
Static models tidak mengandung variabel waktu,
tetapi mampu “ melihat” dampak dari sebuah
perilaku terhadap kejadian pada masa yang akan perilaku terhadap kejadian pada masa yang akan
datang (design year) transport model dapat
memprediksi kebutuhan transportasi pada
tahun tahun yang di rencanakan di masa tahun-tahun yang di rencanakan di masa
mendatang design year dapat jangka pendek
atau panjang
7. What are the techniques used? Are
they available?
Teknik yang digunakan untuk system modeling
terutama berasal dari matematik statistik dan terutama berasal dari matematik, statistik dan
operational research, dan teknik ini telah
tersedia / dibuat tersedia / dibuat
8. Are the data available?
Data sangat penting dalam systems modelling
dan harus dengan kualitas yang baik dan dengan
j l h k jumlah yang cukup
Model yang komplek dengan pembagian zona y g p g p g
yang lebih kecil (banyak) memerlukan lebih
banyak data menjadi masalah pada pemodelan
kawasan perkotaan di mana reliable official data kawasan perkotaan di mana reliable official data
tidak cukup tersedia
9 How can the model be calibrated and 9. How can the model be calibrated and
validated?
KALIBRASI merupakan proses estimasi
parameter model agar “ fit” (sesuai/ cocok)
dengan data observasi dan VALIDASI dengan data observasi, dan VALIDASI
merupakan proses pengujian model terhadap
kondisi yang ada (real world) untuk melihat
j h k i t k k sejauh mana kesesuaian atau kecocokannya
Kalibrasi model dilakukan dengan bantuan Kalibrasi model dilakukan dengan bantuan
komputer (packaged program) dengan
algoritma yang telah dibuat sebelumnya
d f fit di li i d d k t goodness of fit dianalisis dengan pendekatan
statistik
DIAGRAM ALIR PEMODELAN
SISTIM JARINGAN TRANSPORTASI
Pendekatan Pemodelan Pendekatan Pemodelan
Transportasi 4-Tahap
Kegiatan ekonomi &
populasi
Tata guna
lahan
Karakteristik
perjalanan
Jaringan
transportasi
Inventarisasi data
Proyeksi kegiatan
ekonomi &
populasi
Model bangkitan
perjalanan masa
sekarang
Seleksi J aringan &
zona
Survai Perjalanan
Masa sekarang
Peramalan
tata gunalahan tata guna lahan
Pembebanan awal &
penyesuaian jaringan
Model distribusi perjalanan
masa sekarang
Kebijaksanaan/ Peraturan,
dan keinginan masyarakat
Analisis keadaan yang
ada dan kalibrasi
parameter model
J aringan yang
akan datang
masa sekarang
Tata guna lahan yang
akan datang
Kegiatan ekonomi &
Populasi yang akan datang
Peramalan
Model bangkitan perjalanan masa
yang akan datang
Model distribusi
perjalanan yang akan datang
Model pembebanan perjalanan
(T i A i t M d l) (Trip Assignment Model)
Analisis sistim jaringan
transportasi
Feedback
Analisis sistem
Sistem jaringan yang
direkomendasikan
Implementasi
CONTOH PROSES CONTOH PROSES CONTOH PROSES CONTOH PROSES CONTOH PROSES CONTOH PROSES
PEMODELAN KECELAKAAN PEMODELAN KECELAKAAN
CONTOH PROSES CONTOH PROSES
PEMODELAN KECELAKAAN PEMODELAN KECELAKAAN PEMODELAN KECELAKAAN PEMODELAN KECELAKAAN
DI PERSIMPANGAN DI PERSIMPANGAN
PEMODELAN KECELAKAAN PEMODELAN KECELAKAAN
DI PERSIMPANGAN DI PERSIMPANGAN




The Identification of Model Variables
Response Variable : Motorcycle Accidents
Explanatory Variables : Traffic Flow, Approach Speed, Junction
Geometry, Number of Legs, Junction Control and




Land Use
Analysis of Error Distribution
Goodness of Fit Test (Analysis of Deviance) for the Poisson and Negative




Binomial Error Distributions; Hypothesis Test on the Selected Error Distribution
Model Specification
ResponseVariable, ExplanatoryVariables, Error Distribution, Link Function,




Response Variable, Explanatory Variables, Error Distribution, Link Function,
Quasi Likelihood (Dispersion Parameter) and Offset Variable
Model Fitting
Estimate Parameters that Minimise Deviance (Internal Process in GLIM 4)




The Fitted Model
Analysis of Deviance, Estimated Parameters and Significance Level



No


Meet the
Requirements?

Yes



The Final Model
The Variables of the Model The Variables of the Model The Variables of the Model The Variables of the Model
A. Full Model A. Full Model
Continuous Variables Continuous Variables Continuous Variables Continuous Variables
1. QNMm 1. QNMm : Non : Non--motorcycle flow on major road (vpd) motorcycle flow on major road (vpd)
2 QNMn 2 QNMn : Non : Non motorcycle flowon minor road (vpd) motorcycle flowon minor road (vpd) 2. QNMn 2. QNMn : Non : Non--motorcycle flow on minor road (vpd) motorcycle flow on minor road (vpd)
3. QMm 3. QMm : Motorcycle flow on major road (vpd) : Motorcycle flow on major road (vpd)
4. QMn 4. QMn : Motorcycle flow on minor road (vpd) : Motorcycle flow on minor road (vpd) QQ oto cyc e o o o oad ( pd) oto cyc e o o o oad ( pd)
5. QPED 5. QPED : Pedestrian flow (ped/hr) : Pedestrian flow (ped/hr)
6. SPEED 6. SPEED : Approach speed (km/h) : Approach speed (km/h)
7. LWm 7. LWm : Average lane width on major road (m) : Average lane width on major road (m)
8. LWn 8. LWn : Average lane width on minor road (m) : Average lane width on minor road (m)
9. LNm 9. LNm : Number of lanes on major road : Number of lanes on major road
10. LNn 10. LNn : Number of lanes on minor road : Number of lanes on minor road
Categorical Variables Categorical Variables gg
11. SHDW 11. SHDW : Average shoulder width : Average shoulder width
(1) SHDW=0 0 m (1) SHDW=0 0 m (1) SHDW 0.0 m (1) SHDW 0.0 m
(2) 0.0 m < SHDW (2) 0.0 m < SHDW <<1.0 m 1.0 m
(3) SHDW > 1.0 m (3) SHDW > 1.0 m
12. NL 12. NL : Number of intersecting legs : Number of intersecting legs
(1) Three (1) Three--legged legged
(2) Four (2) Four--legged legged
13. CTRL 13. CTRL : J unction control : J unction control (1) Signalised (1) Signalised 13. CTRL 13. CTRL : J unction control : J unction control (1) Signalised (1) Signalised
(2) Non (2) Non--signalised signalised
14 LU 14 LU : Land use category : Land use category(1) Non (1) Non Commercial Area Commercial Area 14. LU 14. LU : Land use category : Land use category(1) Non (1) Non--Commercial Area Commercial Area
(2) Commercial Area (2) Commercial Area
B. Simplified Model B. Simplified Model
Continuous Variables Continuous Variables
1. Qmajor 1. Qmajor : Traffic flow on major road (vpd) : Traffic flow on major road (vpd)
2 Qminor 2 Qminor : Traffic flowon minor road (vpd) : Traffic flowon minor road (vpd) 2. Qminor 2. Qminor : Traffic flow on minor road (vpd) : Traffic flow on minor road (vpd)
3. SHDW 3. SHDW : : Average shoulder width (m) Average shoulder width (m)
Model Formulation Model Formulation Model Formulation Model Formulation Model Formulation Model Formulation Model Formulation Model Formulation
Full Model Full Model
MCA = k
1
QNMm
α
1

QNMn
α
2

QMm
α
3

QMn
α
4

QPED
α
5
EXP
(β1SPEED + β2LWm + β3LWn + β4LNm + β5LNn + β6NL + β7SHDW + β8LU + e)


Simplified Model

δ δ (λ SHDW )
MCA = k
2
Qmajor
δ
1
Qminor
δ
2
EXP

1
SHDW + e)

Log Log- -Linear Version of the Linear Version of the Log Log- -Linear Version of the Linear Version of the
Model Model Model Model
Ln(MCA) = Ln(k) + α1Ln(QNMm) + α2Ln(QNMn) + α3Ln(QMm) + α4Ln(QMn)
Full Model
+ α5Ln(QPED) + β1(SPEED) + β2(LWm) + β3(LWn) + β4(LNm)
+ β5(LNn) + β6(NL) + β7(SHDW) + β8(LU) + e
Simplified Model
Ln(MCA) = Ln(k) +δ1Ln(Qmajor) +δ2Ln(Qminor) +λ1(SHDW) +e Ln(MCA) = Ln(k) + δ1Ln(Qmajor) + δ2Ln(Qminor) + λ1(SHDW) + e
Statistical Analysis Statistical Analysis Statistical Analysis Statistical Analysis yyyy
The Significance of the models were The Significance of the models were
Univariate and Multivariate Analyses were employed to Univariate and Multivariate Analyses were employed to
develop the models develop the models
The Significance of the models were The Significance of the models were
assessed by: assessed by:
* Th diff i l d d i f ddi * Th diff i l d d i f ddi
Only variables found significant (p<0.05) in univariate Only variables found significant (p<0.05) in univariate
analysis were included in multivariate analysis analysis were included in multivariate analysis develop the models develop the models
* The difference in scaled deviance from adding or * The difference in scaled deviance from adding or
removing the variables removing the variables
analysis were included in multivariate analysis analysis were included in multivariate analysis
* The ratio of scaled deviance to its degrees of freedom * The ratio of scaled deviance to its degrees of freedom
(mean deviance (mean deviance ~~ 1) 1)
* The t * The t- -statistic of parameter estimates at 5% statistic of parameter estimates at 5%
significance level significance level
The Final Models The Final Models The Final Models The Final Models

Full Model (All Junctions) ( )

MCA = 0.01109 QNMm
0.2685
QNMn
0.0515
QMm
0.1036
QMn
0.1263

EXP
(0.01515 SPEED – 0.1171 LWm – 0.0874 LWn – 0.01694 LNm + β
5
CTRL – β
6
SHDW + β
7
LU)

where:
β
5
= 0.0 and 0.0315 for CTRL = 1 and 2, respectively
β
6
= 0 0 0 02174 and 0 02745 for SHDW= 1 2 and 3 respectively
i i i i
β
6
0.0, 0.02174 and 0.02745 for SHDW 1, 2 and 3, respectively
β
7
= 0.0 and 0.01873 for LU = 1 and 2, respectively

Simplified Model (All Junctions)

MCA = 0.0003446 Qmajor
0.5906
Qminor
0.281
EXP
– 0.0708 SHDW
Q j Q

The Other Junction Groups The Other Junction Groups The Other Junction Groups The Other Junction Groups
Full Model

Three-Legged Non-signalised J unctions ee eggedNo sg a sedJ u ct o s
MCA =0.005294 QNMm
0.2188
QNMn
0.0665
QMm
0.132
QMn
0.1808

EXP
( 0.02279 SPEED – 0.0969 LWm – 0.0706 LWn – 0.00738 LNm – β
5
SHDW +β
6
LU )

where: β
5
=0.00, 0.00903 and 0.02099 for SHDW =1, 2 and 3, respectively
β
6
=0.00 and 0.00755 for LU =1 and 2, respectively

Three-Legged Signalised J unctions
MCA =0.003686QNMm
0.2841
QNMn
0.03934
QMm
0.0734
QMn
0.2586
MCA 0.003686 QNMm QNMn QMm QMn
EXP
( 0.02232 SPEED – 0.1293 LWm – 0.0848 LWn – 0.01532 LNm – β
5
SHDW +β
6
LU )

where: β
5
=0.00, 0.01011 and 0.01918 for SHDW =1, 2 and 3, respectively
β
6
=0.00 and 0.01163 for LU =1 and 2, respectively

Four-Legged Non-signalised J unctions
MCA =0.01193 QNMm
0.28658
QNMn
0.1358
QMm
0.06238
QMn
0.12371

EXP
( 0.00859 SPEED – 0.1878 LWm – 0.04619 LWn – 0.00876 LNm – β
5
SHDW +β
6
LU )
EXP
where: β
5
=0.00, 0.00564 and 0.00785 for SHDW =1, 2 and 3, respectively
β
6
=0.00 and 0.00403 for LU =1 and 2, respectively
Full Model

Four-Legged Signalised J unctions
MCA =0.003706 QNMm
0.273
QNMn
0.0718
QMm
0.0425
QMn
0.2042

EXP
( 0.0246 SPEED – 0.0852 LWm – 0.0828 LWn – 0.01016 LNm – β
5
SHDW +β
6
LU )
EXP
where: β
5
=0.00, 0.01373 and 0.02438 for SHDW =1, 2 and 3, respectively
β
6
=0.00 and 0.00788 for LU =1 and 2, respectively

Non-signalised J unctions
MCA =0.01316 QNMm
0.1597
QNMn
0.0973
QMm
0.1071
QMn
0.1336

EXP
( 0.02418 SPEED – 0.0967 LWm – 0.0907 LWn – 0.01079 LNm – β
5
SHDW +β
6
LU )
EXP
where: β
5
=0.00, 0.01809 and 0.0502 for SHDW =1, 2 and 3, respectively
β
6
=0.00 and 0.01789 for LU =1 and 2, respectively

Signalised J unctions
MCA =0.002822 QNMm
0.3241
QNMn
0.0835
QMm
0.0683
QMn
0.1296

EXP
( 0.02602 SPEED – 0.0727 LWm – 0.0718 LWn – 0.01758 LNm – β
5
SHDW +β
6
LU )
EXP
where: β
5
=0.00, 0.01755 and 0.02554 for SHDW =1, 2 and 3, respectively
β
6
=0.00 and 0.01591 for LU =1 and 2, respectively
Simplified Model

Th l dN i li dJ i Three-legged Non-signalised J unctions
MCA =0.0007581 Qmajor
0.5897
Qminor
0.206
EXP
– 0.0972 SHDW


Three-leggedSignalisedJ unctions Threelegged Signalised J unctions
MCA =0.000294 Qmajor
0.6184
Qminor
0.263
EXP
– 0.0791 SHDW


Four-legged Non-signalised J unctions
MCA 0001635Q j
0.4935
Q i
0.2298
EXP
– 0.0648SHDW
MCA =0.001635 Qmajor
0.4935
Qminor
0.2298
EXP
0.0648 SHDW

Four-legged Signalised J unctions
MCA =0.0001196 Qmajor
0.5756
Qminor
0.4033
EXP
– 0.0295 SHDW
Q j Q

Non-signalised J unctions
MCA =0.0006039 Qmajor
0.5369
Qminor
0.2869
EXP
– 0.0864 SHDW


Signalised J unctions
MCA =0.0004693 Qmajor
0.5948
Qminor
0.2411
EXP
– 0.0589 SHDW



Observed vs Modeled Accidents Observed vs Modeled Accidents Observed vs Modeled Accidents Observed vs Modeled Accidents
15
20
d
e
n
t
s
10
v
e
d

A
c
c
i
d
E
q
u
a
l
i
t
y

L
i
n
e
0
5
O
b
s
e
r
v
0 5 10 15 20
Modeled Accidents
Traffic Flow Traffic Flow –– Accidents Accidents
Full Model Full Model
Traffic Flow Traffic Flow –– Accidents Accidents
Full Model Full Model Full Model Full Model Full Model Full Model
50
60
n
t

(
%
)
QNMm
Total
20
30
40
s

I
n
c
r
e
m
e
QNMm
QNMn
QMm
QMn
0
10
20
A
c
c
i
d
e
n
t
0
0 20 40 60 80 100 120
Tr af f ic Flow Incr ement (%)
Traffic Flow Traffic Flow –– Accidents Accidents
Simplified Model Simplified Model
Traffic Flow Traffic Flow –– Accidents Accidents
Simplified Model Simplified Model Simplified Model Simplified Model Simplified Model Simplified Model
Total
80
100
e
n
t

(
%
)

Qmajor
Total
40
60
t
s

I
n
c
r
e
m
Qminor
0
20
A
c
c
i
d
e
n
0 20 40 60 80 100 120
Traffic Flow Increment (%)
Traffic Flow Traffic Flow –– Accidents Accidents
Full Model Full Model
Traffic Flow Traffic Flow –– Accidents Accidents
Full Model Full Model Full Model Full Model Full Model Full Model
60
80
e
n
t
s

(
%
)
40
e

i
n

A
c
c
i
d
e
0
20
I
n
c
r
e
a
s
e
0 5 10 15 20 25 30
Increase in Approach Speed (km/h)
Lane Width Lane Width - - Accidents Accidents Lane Width Lane Width - - Accidents Accidents
15
20
e
n
t
s

(
%
)
M
a
j
o
r

R
o
a
d
M
in
o
r
R
o
a
d
10
n

i
n

A
c
c
i
d
e
0
5
R
e
d
u
c
t
i
o
n
0 0.5 1
Incr ease in Lane Widt h (m)
Shoulder Width Shoulder Width – – Accidents Accidents
Full Model Full Model
Shoulder Width Shoulder Width – – Accidents Accidents
Full Model Full Model Full Model Full Model Full Model Full Model
4
e
n
t
s

(
%
)
S
H
D
W
2
S
H
D
W

3
2
n

i
n

A
c
c
i
d
e
0
R
e
d
u
c
t
i
o
0 0.5 1
Incr ease in Shoulder Widt h (m)
Shoulder Width Shoulder Width – – Accidents Accidents
Simplified Model Simplified Model
Shoulder Width Shoulder Width – – Accidents Accidents
Simplified Model Simplified Model Simplified Model Simplified Model Simplified Model Simplified Model
20
e
n
t
s

(
%
)
10
n

i
n

A
c
c
i
d
e
0
R
e
d
u
c
t
i
o
0 0.5 1 1.5 2
Incr ease Shoulder Widt h (m)
Traffic Flows on Signalised and Traffic Flows on Signalised and
Non Non--signalised Junctions Those Reflecting signalised Junctions Those Reflecting
Traffic Flows on Signalised and Traffic Flows on Signalised and
Non Non--signalised Junctions Those Reflecting signalised Junctions Those Reflecting
Junction Safety Junction Safety Junction Safety Junction Safety
Non-signalised
J unction
Signalised J unction
15000
20,000
a
y

b
o
t
h

Motorcycle Accidents =1.0 PIA's per year
J unction
10,000
15,000
v
e
h
i
c
l
e
s

p
e
r

d
a
c
t
i
o
n
s
)
5,000
R
o
a
d

F
l
o
w



(
v
d
i
r
e
c
0
0 5,000 10,000 15,000 20,000 25,000 30,000 35,000 40,000
M
i
n
o
r

R
, , , , , , , ,
Major Road Flow (vehicles per day bot h dir ect ions)
Proposed Junctions with Proposed Junctions with
NN l i l i Non Non- -exclusive exclusive
Motorcycle Lanes Motorcycle Lanes Motorcycle Lanes Motorcycle Lanes
GENERALIZED LINEAR MODEL GENERALIZED LINEAR MODEL
Komponen dalam GLM Komponen dalam GLM
In generalized linear modeling, a statistical model consists of
three components: the systematic component, random
components and link function components and link function
The random component describes the error term or probability
distribution
The systematic component describes the way in which the
explanatory or covariate variables combine together to explain
the variation of response variable. The linear combination of the
explanatory variables is called linear predictor
Link f nction or parameter transformation This f nction links Link function or parameter transformation. This function links
the linear predictor to the random component
1. The random component: Error or probability distribution f(y)
which has a mean “ μ” which has a mean “ μ
2. The systematic component: Linear predictor or linear
i f ti ( ) regression function (η)
For ‘n’ explanatory variables:
n
η = Σ βi Xi = β0 + β1 X1 + … + βn Xn
i = 0
where: β0 (sometimes called intercept) and βi are parameters
to be estimated; Xi is covariates X1 , X2 , …Xn
3. Link function or parameter transformation (g), η = g(μ).
This function links the linear predictor “ η” (systematic
component) to the mean “ μ” (random component)
In conventional linear regression analysis, In conventional linear regression analysis,
the assumptions are: the assumptions are: the assumptions are: the assumptions are:
1. The probability distribution of the response variable “ y” is
normal, N (μ,σ2), with mean μ and constant variance σ2
2 Th li di t (f i 2. The linear predictor (for ‘n’ explanatory variables) is:
n
η = Σ βi xi = β0 + β1 x1 + … + βn xn
i = 0
3. The link function is identity (i.e. no transformation) y ( )
Model Fitting and Parameter Estimates Model Fitting and Parameter Estimates ode tt g a d a a ete st ates ode tt g a d a a ete st ates
The modelling process may be thought of as one
in which the data: y1, y2, .., yn are matched by a
set of theoretical values: μ1 μ2 μn set of theoretical values: μ1, μ2, .., μn
For a good model, the set of “μ” must close to For a good model, the set of μ must close to
the data, “y”. Thus the “μ” are highly patterned,
and therefore easier to understand and interpret
than the “y”
Model fitting is used to explain the relation
between the response and the explanatory
variables
The process of model fitting involves two
basic decisions: basic decisions:
i. The choice of the relationship between the theoretical
values (μ’s) and the underlying parameters of the
model
ii. The choice of a measure of discrepancy which
defines how close a given set of μ’s is to the data g μ
The first choice relates μ’s to the systematic
component (η) of the model, and p (η) ,
The second is governed by assumptions of the
random component
The first choice generally depends on the The first choice generally depends on the
characteristics of the data under study, and the
data can be drawn fromcertain types of variation, data can be drawn from certain types of variation,
spatial or temporal
Th d ti l t f d l fitti i t The second essential aspect of model fitting is to
minimise a measure of discrepancy between the
observed data and the corresponding fitted observed data and the corresponding fitted
values
Thus the parameters of the model are estimated
by minimising the deviance or maximising the
likelihood or log likelihood of the parameters in
the linear predictor
In generalized linear modeling a measure of In generalized linear modeling, a measure of
discrepancy is called the deviance
This term is expressed as parameter D (y;μ), s e s e p essed as pa a e e (y;μ),
which is defined by:
⎩ ⎩ D (y;μ) = 2 ⎩(y;y) – 2 ⎩(μ;y) = exact model – current model
⎩(y;y) is the maximumlikelihood for an exact fit in which ⎩(y;y) is the maximum likelihood for an exact fit in which
the fitted values are exactly equal to the observed data
and ⎩(μ;y) is that of the current model. In order to
minimise deviance, ⎩(μ;y) must be maximised.
In conventional linear regression analysis the deviance is
a well-known residual sum of squares
FITTING ERROR (PROBABILITY) FITTING ERROR (PROBABILITY)
DISTRIBUTIONS DISTRIBUTIONS