Grouped time-series forecasting with an
application to regional infant mortality counts
Grouped time-series forecasting with an
application to regional infant mortality counts
We describe two methods for forecasting a grouped time series, which provides point forecasts that are aggregated appropriately across different levels of the hierarchy. Using the regional infant mortality counts in Australia, we investigate the one-step-ahead to ten-step-ahead point forecast accuracy, and examine statistical significance of the point forecast accuracy between methods. Furthermore, we introduce a novel bootstrap methodology for constructing point-wise prediction interval in a grouped time series, investigate the interval forecast accuracy, and examine the statistical significance of the interval forecast accuracy
ESRC Centre for Population Change
Shang, Han Lin
1625ecc8-1ab1-4ef8-b87e-e5a2382d34c5
Smith, Peter W.F.
961a01a3-bf4c-43ca-9599-5be4fd5d3940
McGowan, Teresa
4524e894-04de-4822-8508-f4b966e12ae2
30 November 2013
Shang, Han Lin
1625ecc8-1ab1-4ef8-b87e-e5a2382d34c5
Smith, Peter W.F.
961a01a3-bf4c-43ca-9599-5be4fd5d3940
McGowan, Teresa
4524e894-04de-4822-8508-f4b966e12ae2
Shang, Han Lin and Smith, Peter W.F.
,
McGowan, Teresa
(ed.)
(2013)
Grouped time-series forecasting with an
application to regional infant mortality counts
(ESRC Centre for Population Change Working Paper Series, 40)
Southampton, GB.
ESRC Centre for Population Change
Record type:
Monograph
(Working Paper)
Abstract
We describe two methods for forecasting a grouped time series, which provides point forecasts that are aggregated appropriately across different levels of the hierarchy. Using the regional infant mortality counts in Australia, we investigate the one-step-ahead to ten-step-ahead point forecast accuracy, and examine statistical significance of the point forecast accuracy between methods. Furthermore, we introduce a novel bootstrap methodology for constructing point-wise prediction interval in a grouped time series, investigate the interval forecast accuracy, and examine the statistical significance of the interval forecast accuracy
Text
2013_WP40_Grouped_Time-Series_Forecasting_Shang_et_al.pdf
- Other
More information
Published date: 30 November 2013
Organisations:
Social Statistics & Demography, Centre for Population Change
Identifiers
Local EPrints ID: 360720
URI: http://eprints.soton.ac.uk/id/eprint/360720
PURE UUID: 3ae7f8cc-37b2-458d-ad58-4bb16b380aad
Catalogue record
Date deposited: 06 Jan 2014 13:47
Last modified: 15 Mar 2024 03:23
Export record
Contributors
Author:
Han Lin Shang
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
