To the Editor: Ms Isanaka and colleagues1 conducted a cluster randomized trial to evaluate the effect of ready-to-use therapeutic foods on various measures of nutritional status, morbidity, and mortality in children in Niger. The cluster randomized trial design is a very useful one for this setting because of logistical constraints. However, such a design leads to analytic complications.
Ghosh D. Effect of Preventive Supplementation on Young Children in Niger. JAMA. 2009;301(21):2208-2209. doi:10.1001/jama.2009.740