Investigating the predictive ability of ONS big data-based indicators

George Kapetanios; Fotis Papailias

doi:10.1002/for.2805

Investigating the predictive ability of ONS big data-based indicators

George Kapetanios, Fotis Papailias^*

^*Corresponding author for this work

Banking & Finance

King’s College London. Andreas Kornelakis is Senior Lecturer in International Management at King’s Business School

Research output: Contribution to journal › Article › peer-review

2 Citations (Scopus)

Abstract

This paper investigates the predictive ability of a brand new dataset that is based on big unstructured data published by the UK Office for National Statistics as “Faster Indicators of UK Economic Activity.” We consider some indicative ways for use in macroeconomic nowcasting. Even though the ONS confirms that the newly introduced big data-based indicators are not constructed with forecasting purposes in mind, and applied researchers should be cautious when using them in this way, a simple out-of-sample nowcasting exercise reveals partial evidence that this dataset has some predictive power over GDP growth. Our results, which show a positive and encouraging first step towards the use of this type of data, suggest that national statistics agencies should allocate more resources in constructing big data-based databases.

Original language	English
Journal	JOURNAL OF FORECASTING
Volume	41
Issue number	2
Early online date	26 Aug 2021
DOIs	https://doi.org/10.1002/for.2805
Publication status	E-pub ahead of print - 26 Aug 2021

Keywords

big data
factor models
nowcasting
sparse regressions

Access to Document

10.1002/for.2805

Cite this

@article{7a3de5d0c638471bac490eae0c9a0311,

title = "Investigating the predictive ability of ONS big data-based indicators",

abstract = "This paper investigates the predictive ability of a brand new dataset that is based on big unstructured data published by the UK Office for National Statistics as “Faster Indicators of UK Economic Activity.” We consider some indicative ways for use in macroeconomic nowcasting. Even though the ONS confirms that the newly introduced big data-based indicators are not constructed with forecasting purposes in mind, and applied researchers should be cautious when using them in this way, a simple out-of-sample nowcasting exercise reveals partial evidence that this dataset has some predictive power over GDP growth. Our results, which show a positive and encouraging first step towards the use of this type of data, suggest that national statistics agencies should allocate more resources in constructing big data-based databases.",

keywords = "big data, factor models, nowcasting, sparse regressions",

author = "George Kapetanios and Fotis Papailias",

year = "2021",

month = aug,

day = "26",

doi = "10.1002/for.2805",

language = "English",

volume = "41",

journal = "JOURNAL OF FORECASTING",

issn = "0277-6693",

publisher = "John Wiley and Sons Ltd",

number = "2",

}

TY - JOUR

T1 - Investigating the predictive ability of ONS big data-based indicators

AU - Kapetanios, George

AU - Papailias, Fotis

PY - 2021/8/26

Y1 - 2021/8/26

N2 - This paper investigates the predictive ability of a brand new dataset that is based on big unstructured data published by the UK Office for National Statistics as “Faster Indicators of UK Economic Activity.” We consider some indicative ways for use in macroeconomic nowcasting. Even though the ONS confirms that the newly introduced big data-based indicators are not constructed with forecasting purposes in mind, and applied researchers should be cautious when using them in this way, a simple out-of-sample nowcasting exercise reveals partial evidence that this dataset has some predictive power over GDP growth. Our results, which show a positive and encouraging first step towards the use of this type of data, suggest that national statistics agencies should allocate more resources in constructing big data-based databases.

AB - This paper investigates the predictive ability of a brand new dataset that is based on big unstructured data published by the UK Office for National Statistics as “Faster Indicators of UK Economic Activity.” We consider some indicative ways for use in macroeconomic nowcasting. Even though the ONS confirms that the newly introduced big data-based indicators are not constructed with forecasting purposes in mind, and applied researchers should be cautious when using them in this way, a simple out-of-sample nowcasting exercise reveals partial evidence that this dataset has some predictive power over GDP growth. Our results, which show a positive and encouraging first step towards the use of this type of data, suggest that national statistics agencies should allocate more resources in constructing big data-based databases.

KW - big data

KW - factor models

KW - nowcasting

KW - sparse regressions

UR - http://www.scopus.com/inward/record.url?scp=85113500467&partnerID=8YFLogxK

U2 - 10.1002/for.2805

DO - 10.1002/for.2805

M3 - Article

AN - SCOPUS:85113500467

SN - 0277-6693

VL - 41

JO - JOURNAL OF FORECASTING

JF - JOURNAL OF FORECASTING

IS - 2

ER -

Investigating the predictive ability of ONS big data-based indicators

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this