Skip navigation

The effects of outdated data and outliers on Kenya’s 2019 Global Food Security Index score and rank

The effects of outdated data and outliers on Kenya’s 2019 Global Food Security Index score and rank

Atieno, Prisca and Hendriks, Sheryl L ORCID logoORCID: https://orcid.org/0000-0002-1487-4302 (2023) The effects of outdated data and outliers on Kenya’s 2019 Global Food Security Index score and rank. CABI Agriculture and Bioscience, 4:6. ISSN 2662-4044 (doi:10.1186/s43170-023-00140-y)

[thumbnail of Open Access Article]
Preview
PDF (Open Access Article)
41661 HENDRIKS_The_Effects_Of_Outdated_Data_And_Outliers_(OA)_2023.pdf - Published Version
Available under License Creative Commons Attribution.

Download (816kB) | Preview

Abstract

The use of composite indicators for benchmarking has increased over time. However, their construction is complex and has drawbacks that could hinder reliability. This study aimed to determine the impact of outdated data and outliers on the Global Food Security Index (GFSI) using Kenya as a case study. The first objective was to determine the proportion of outdated data and outliers in the 2019 GFSI result. The second objective was to determine the statistical significance of the outdated data and outliers on Kenya's 2019 GFSI scores and ranking. Lastly, we aimed to determine if updating Kenya's 2019 GFSI outdated data could change Kenya's scores and ranking relative to the 113 countries in the GFSI. Winsorisation was carried out to remove the outlier data points, while Paired t-test and Spearman's rank correlation were used to test the statistical significance of results. The 2019 GFSI database contained outdated data and outliers. The outlier data points affected countries' scores and ranking, even if a country did not have outlier data points. For example, Kenya's 2019 overall GFSI score reduced by six points after the winsorisation of outlier data points for other countries. On the other hand, updating Kenya's 2019 GFSI outdated data increased Kenya's 2019 GFSI score and rank, even though the change was not significantly different from zero.

Item Type: Article
Uncontrolled Keywords: composite indicators, food security, global food security index, outdated data, outliers, winsorisation.
Subjects: S Agriculture > S Agriculture (General)
Faculty / School / Research Centre / Research Group: Faculty of Engineering & Science
Faculty of Engineering & Science > Natural Resources Institute
Faculty of Engineering & Science > Natural Resources Institute > Centre for Food Systems Research
Faculty of Engineering & Science > Natural Resources Institute > Centre for Food Systems Research > Food Systems & Nutrition
Related URLs:
Last Modified: 27 Nov 2024 14:51
URI: http://gala.gre.ac.uk/id/eprint/41661

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics