ESTIMATING MAIZE PRODUCTION IN KENYA USING NDVI - SOME STATISTICAL CONSIDERATIONS

A regression model approach using a normalized difference vegetation i ndex (NDVI) has the potential for estimating crop production in East A frica. However, before production estimation can become a reality, the underlying model assumptions and statistical nature of the sample dat a (NDVI and crop production) must be examined rigorously. Annual maize production statistics from 1982-90 for 36 agricultural districts with in Kenya were used as the dependent variable; median area NDVI (indepe ndent variable) values from each agricultural district and year were e xtracted from the annual maximum NDVI data set. The input data and the statistical association of NDVI with maize production for Kenya were tested systematically for the following items: (1) homogeneity of the data when pooling the sample, (2) gross data errors and influence poin ts, (3) serial (time) correlation, (4) spatial autocorrelation and (5) stability of the regression coefficients. The results of using a simp le regression model with NDVI as the only independent variable are enc ouraging (r = 0.75, p = 0.05) and illustrate that NDVI can be a respon sive indicator of maize production, especially in areas of high NDVI s patial variability, which coincide with areas of production variabilit y in Kenya.