Time-varying trading day adjustment in SEASABS Lujuan Chen, - - PowerPoint PPT Presentation

▶

May 07, 2023 190 likes •331 views

Time-varying trading day adjustment in SEASABS Lujuan Chen, Jonathan Campbell Australian Bureau of Statistics Views expressed are those of the authors and do not necessarily represent those of the ABS. Where quoted or used, they should be

SLIDE 1

Time-varying trading day adjustment in SEASABS

Lujuan Chen, Jonathan Campbell Australian Bureau of Statistics

Views expressed are those of the authors and do not necessarily represent those of the ABS. Where quoted or used, they should be attributed clearly to the authors.

SLIDE 2

Outline

SEASABS
Estimation of Trading Day
Improvements in SeasABS

– Modified Regression – Split Trading Day – Moving Trading Day – Example

Conclusion
Future work

SLIDE 3

SEASABS

SLIDE 4

Background – Seasonal Adjustment

Most official statistical agencies publish original and

seasonally adjusted estimates

, ,

ˆ

ˆ /  

 



           

 

combined factor, seasonal factor

seasonal trend irregular

thers including TD effect

estimate to produce seasonally adjusted estimates

t t t t t i t t t i i t i t t t t t

S

O S T I S s S s SA O S T I

SLIDE 5

Trading day

An effect present in many time series due to

1. the difference of the number of days in each

period is different

2. the different levels of activity associated with

different days of the week; and

3. the changing composition of the days of the

week in each period

SLIDE 6

Estimation of trading-day

X-11 regression method - Young, A. (1965) implemented in X-11 -

Shiskin, J. (1967)

ARIMAX method - Hillmer, S. (1982) implemented as RegARIMA in X-12-

ARIMA - Findley (1998) and Tramo - Maravell (1996)

other methods including regression and state-space models

6 7 1

1 ( ) , ~ (0, )  



   



t j jt t t t j

I D D e e NID

      



6 7 1

log( ) ( ) , (1 ) (1 ) (log ) , ~ (0, )

t j jt t t t j d s D s t t t

O D D z z ARIMA B B B B O X B B e e NID     



        



SLIDE 7

Static Trading Day in Retail

0.900 0.925 0.950 0.975 1.000 1.025 1.050 1.075

Mon Tue Tue Wed Wed Thu Thu Fri Fri Sat Sat Sun Sun Mon Mon Tue Wed Tue Wed Thu Wed Thu Fri Thu Fri Sat Fri Sat Sun Sat Sun Mon Sun Mon Tue Non leap Feb Leap Feb Trading Day Tday * Irreg

SLIDE 8

Modified regression

Does it make sense for a day’s weight to

be negative?

Many series are strictly non-negative
Option to constrain the regression so that

daily weights are at least zero

Basic method used, improvement possible

SLIDE 9

Split Trading Day

Sudden change in weekly cycle
Can be done with pre-specified weights

static regression or moving regression

Not much used in practice

0.2 0.4 0.6 0.8 1 1.2 1.4 M T W T F S S M T W T F S S M T W T F S S M T W T F S S

SLIDE 10

Time-varying trading day

Standard regression on 7 year moving spans
Shorter spans at series ends
Negative daily weights not allowed
Smoothed using 3x3 moving average