Faster agricultural development requires understanding whether the inverse land size-yield relationship exists or not. To verify the presence of this relationship, this study decomposes a yield index into separate components attributable to (1) efficiency, (2) soil quality, (3) land size, (4) variable inputs, (5) capital inputs, and (6) outputs. Nonparametric productivity accounting methods are used to decompose the inverse land size-yield relationship in a multi-output representation of the technology without specific assumptions on returns to scale. A strongly significant inverse (positively convex) land size-yield relationship is present in the Kenyan data, but vanishes in favor of a linear inverse relationship when accounting for the effect of outputs' diversification.