A new paper 'A simplified measure of nutritional empowerment: Using machine learning to abbreviate the Women’s Empowerment in Nutrition Index (WENI)' in the journal World Development, uses machine learning techniques (LASSO) with survey data from five Indian states to abbreviate a recently developed measure of nutritional empowerment, the Women’s Empowerment in Nutrition Index (WENI). The newly created Abridged Women’s Empowerment in Nutrition Index (A-WENI) contains only 20 indicators, down from the 33 used in WENI, and was validated using a new field survey in the western Indian state of Maharashtra.
Results showed that A-WENI was capable of reproducing well the empowerment scores and status generated by the longer WENI, and predicting nutritional outcomes such as BMI and dietary diversity.
As many of the indicators in A-WENI are often collected routinely in contemporary household surveys this new tool can easily be incorporated in any general purpose survey conducted in rural contexts with little additional respondent burden.
Using this index, in the Maharashtra sample, on average, only 35.9% of mothers of children under the age of 5 years are nutritionally empowered, whereas 77.2% of their spouses were nutritionally empowered. Whilst only 14.6% of the elderly women were nutritionally empowered. These estimates are broadly consistent with those based on the 33-indicator WENI.
This study builds on work from the IMMANA grant The Women’s Empowerment in Nutrition Index (WENI): Measuring nutritional empowerment to better link agriculture to nutrition