Professional Documents
Culture Documents
Requests the Council to develop one single set of long term traffic forecast, from
which customized or more detailed forecasts can be produced for various purposes,
such as air navigation systems planning and environmental analysis
Main terms and definitions
used in forecasting
analysis
Types of Data
Medium-term Forecasts
The trend element generally dominates long term situations and must be
considered in the determination of any long-run decisions.
It is also important that since the time span of the forecast horizon is long,
forecasts should be calibrated and revised at periodic intervals (every two or
three years depending on the situation).
When looking at a 30-year horizon, it is advisable to consider a forecast scenario rather than
a forecast itself, because of the uncertainty associated with such a longer-term forecast.
Source: BAA (2011)
Such longer-term outlooks should take into account mega trends and the market maturity
likely to occur over the period.
Alternative Forecasting
Techniques
Bottom-up approach
11
Basic Principle
In order to
or modelled value
1,400,000
Modelled
generate a forecast 1,200,000 values
1,000,000
from a time series, Actual
800,000
Observatio
a mathematical 600,000
ns
= actual value
Difference
equation is to be 400,000
actual vs.
200,000 modelled
found to replicate data
0
0 5 10 15 20 25
the historical
Some Definitions
Error
Y1 Y2 K Yn 1 i n
Y Yi
n n i 1
Some Definitions
Mean isX = 12
18
From the table, we have
MAD 2.57,
7
58
S
2
9.67 and S 3.11.
6
Some Definitions
Differences and Growth Rates
The (first) difference of a time series is given by:
DYt Yt Yt 1
The growth rate for a time series is given by:
GYt 100
Yt Yt 1
Yt 1
Some Definitions
Source: Song, Witt and Li (2009) The Advanced Econometrics of Tourism Demand,
London: Routledge.
Practical Example of Time
Series Models with Excel
Linear Trend
A Forecasting Model linear trend
Practical Example
Dataset
Linear Trend
1,200,000
trend. 200,000
0
0 5 10 15 20 25
Linear Trend
Excel Illustration
Excel Illustration
Excel Illustration
Then select
Linear
and
1,400,000
600,000
0
0 5 10 15 20 25
Linear Trend
Generating Forecasts
Y=a(1+b)T 800,000
600,000
or
200,000
By taking logarithms, the exponential
formulation can be converted to a linear 0
formulation. 0 5 10 15 20 25
Exponential Trend
Analysis
To select exponential trend
analysis in EXCEL, we simply
tick the box for
Exponential
and
Display Equation
200,000
Y= a + bT + cT2
100,000
With three constants, this
family of curves covers a wide
variety of shapes (either 0
1995 1997 1999 2001 2003 2005 2007 2009 2011
concave or convex).
Polynomial Trend Analysis
Polynomial
and
Display Equation
n n
X X Y Y
2 2
i i
i 1 i 1
b 0 y b1x
The Multiple Regression
Model
Least Squares Estimators for
Linear Models with two
Independent Variables
2
y i y x1i x1 x2 i x2 yi y x2i x2 x1i x1 x2 i x2
b1 i i i i
2
2 2
x1i x1 x2 i x2 x1i x1 x2 i x2
i i i
2
y i y x2 i x2 x1i x1 yi y x1i x1 x2 i x2 x1i x1
b2 i i i i
2
2 2
x1i x1 x2 i x2 x1i x1 x2i x2
i i i
b0 y b1 x1 b2 x2
T-value
t Value
The t statistic corresponding to a
particular coefficient estimate is a
statistical measure of the confidence that
can be placed in the estimate.
note:
0 R2 1
This measure has a value between 0 and 1. If it is near to 1 then most of the
variation is explained by the regression line, there is little unexplained variation and
the line is a good fit of the data. If the value is near to 0 then most of the variation is
unexplained and the line is not a good fit.
Multiple Linear
Regression
Least Square Estimators
Too
We have to calculate the
coefficients for each of the complicated
independent variable, but after
seeing the arithmetic for multiple by hand!
regression with two independent
variables in the previous slide, you
might guess, quite rightly, that the
arithmetic is even more messy for a
regression with more than two
independent variables.
i) Linear
Y = a + bX1 + cX2 + ...zXn
iii) Linearlog
eY = aX1b X2c ... Xn z
Y = log(a) + b log X1 + c log X2 + ... z log Xn
iv) Loglinear
log Y = a + bX1 + cX2 + ... zXn