Previous 23 / 106 Next
Normal view
Agricultural assistance/ infrastructure Road density, expenditure on farm to market roads, expenditure on irrigation, cost of fertilizer policy variables (Secondary data) 1 In the case of this study, agriculture production is potentially endogenous in explaining food consumption. 1 The first stage equation includes dummy for time (quarter) to control for the pooled time-series. The variables in Table 4 will be the initial set of variables in estimating the models as discussed in the following model scenarios. Model scenarios Consider the following model π‘Žπ‘”π‘Ÿπ‘– π‘–π‘›π‘π‘œπ‘šπ‘’, β„Žβ„Ž β„Žπ‘’π‘Žπ‘‘ π‘β„Žπ‘Žπ‘Ÿπ‘Žπ‘π‘‘π‘’π‘Ÿπ‘–π‘ π‘‘π‘–π‘π‘ , π‘Žπ‘π‘π‘’π‘ π‘  π‘‘π‘œ π‘šπ‘–π‘”π‘Ÿπ‘Žπ‘‘π‘–π‘œπ‘› π‘β„Žπ‘Žπ‘›π‘›π‘’π‘™π‘ , food security = 𝑓 +𝑒 β„Žπ‘œπ‘’π‘ π‘’β„Žπ‘œπ‘™π‘‘ 𝑑𝑀𝑒𝑙𝑙𝑖𝑛𝑔, π‘›π‘œπ‘› βˆ’ π‘Žπ‘”π‘Ÿπ‘–π‘π‘’π‘™π‘‘π‘’π‘Ÿπ‘Žπ‘™ π‘Žπ‘ π‘ π‘’π‘‘π‘ , π‘π‘œπ‘šπ‘šπ‘’π‘›π‘–π‘π‘Žπ‘‘π‘–π‘œπ‘› π‘–π‘›π‘“π‘Ÿπ‘Ž, (β„Žπ‘œπ‘’π‘ π‘’β„Žπ‘œπ‘™π‘‘ π‘‘π‘Ÿπ‘Žπ‘›π‘ π‘π‘œπ‘Ÿπ‘‘, π‘ π‘œπ‘π‘–π‘Žπ‘™ π‘–π‘›π‘“π‘Ÿπ‘Ž, π‘ π‘œπ‘π‘–π‘Žπ‘™ π‘π‘Ÿπ‘œπ‘‘π‘’π‘π‘‘π‘–π‘œπ‘›) (1) [π‘π‘™π‘–π‘šπ‘Žπ‘‘π‘œπ‘™π‘œπ‘”π‘¦: π‘Ÿπ‘Žπ‘–π‘›π‘“π‘Žπ‘™π‘™, π‘ π‘’π‘Žπ‘ π‘œπ‘›π‘Žπ‘™π‘–π‘‘π‘¦, π‘£π‘œπ‘™π‘Žπ‘‘π‘–π‘™π‘–π‘‘π‘¦, π‘‘π‘’π‘šπ‘π‘’π‘Ÿπ‘Žπ‘‘π‘’π‘Ÿπ‘’], agri income = 𝑓 +𝑣 π‘Žπ‘”π‘Ÿπ‘– π‘Žπ‘ π‘ π‘’π‘‘π‘ , π‘Žπ‘”π‘Ÿπ‘– π‘Žπ‘ π‘ π‘–π‘ π‘‘π‘Žπ‘›οΏ½οΏ½π‘’ π‘œπ‘Ÿ π‘–π‘›π‘“π‘Ÿπ‘Žπ‘ π‘‘π‘Ÿπ‘’π‘π‘‘π‘’π‘Ÿπ‘’, 𝑒𝑑𝑐. , [π‘ π‘’π‘π‘œπ‘›π‘‘ π‘ π‘‘π‘Žπ‘”π‘’ π‘£π‘Žπ‘Ÿπ‘–π‘Žπ‘π‘™π‘’π‘ ] ( ) (2) where the dependent variable has finite mean and the explanatory variables can be continuous or categorical. By assumption, the error terms u and v have zero mean and zero correlation with any of the explanatory variables. In the event that at least one of the explanatory variables, say agricultural productivity, is correlated with the error term, estimates for the coefficients of the independent variables can be inconsistent2. Instrumental variables (IV) method addresses this by introducing observable variable that is uncorrelated with the error term but partially correlated with the endogenous variable. Similar to FAO study of Karfakis, et al. (201), modeling using FIES dataset will work around the twostage least squares (2SLS) method in estimating the coefficients of the following model as analog to equation (1). 2 In the case of this study, agriculture production is potentially endogenous in explaining food consumption. CBMS-FAO | 23

Select target paragraph3

Connect to a paragraph
Connect to an entity
Disable highlights
Add to table of contents