ABSTRACT The poor are not evenly distributed within the country and they do not share the same socio-economic and demographic characteristics. It is against this background that analysis of the characteristics that differentiate the poor from the non-poor in Ghana cannot be underestimated. Poverty indicators make it possible to analyze the likely determinants and are, therefore, essential for formulating policy interventions that may contribute directly or indirectly to its alleviation. This study therefore aims at determining the most important characteristics that differentiate poor households from non-poor households in Ghana.To achieve this objective, data was obtained from the Ghana Statistical Service. It consists of 49,005 households surveyed in the country of which 17.2 percent were classified as being poor (extremely poor). The analysis of the data relied mainly on logistic regression. It was found that the region a household resides in, the number of persons in that household, access to improved sources of water and sanitation, are the most important characteristics. These and other interesting results are discussed.
SEIDU, O (2021). MODELING POVERTY STATUS OF GHANAIANS: A LOGISTIC REGRESSION APPROACH. Afribary. Retrieved from https://track.afribary.com/works/modeling-poverty-status-of-ghanaians-a-logistic-regression-approach
SEIDU, OMAR "MODELING POVERTY STATUS OF GHANAIANS: A LOGISTIC REGRESSION APPROACH" Afribary. Afribary, 08 Mar. 2021, https://track.afribary.com/works/modeling-poverty-status-of-ghanaians-a-logistic-regression-approach. Accessed 23 Nov. 2024.
SEIDU, OMAR . "MODELING POVERTY STATUS OF GHANAIANS: A LOGISTIC REGRESSION APPROACH". Afribary, Afribary, 08 Mar. 2021. Web. 23 Nov. 2024. < https://track.afribary.com/works/modeling-poverty-status-of-ghanaians-a-logistic-regression-approach >.
SEIDU, OMAR . "MODELING POVERTY STATUS OF GHANAIANS: A LOGISTIC REGRESSION APPROACH" Afribary (2021). Accessed November 23, 2024. https://track.afribary.com/works/modeling-poverty-status-of-ghanaians-a-logistic-regression-approach