A cluster-randomised controlled trial to compare the effectiveness of different knowledge-transfer interventions for rural working equid users in Ethiopia

There have been few studies evaluating the efficacy of knowledge-transfer methods for livestock owners in developing countries, and to the authors' knowledge no published work is available that evaluates the effect of knowledge-transfer interventions on the education of working equid users. A cluster-randomised controlled trial (c-RCT) was used to evaluate and compare the effectiveness of three knowledge-transfer interventions on knowledge-change about equid health amongst rural Ethiopian working equid users. Groups were exposed to either; an audio programme, a village meeting or a diagrammatic handout, all of which addressed identical learning objectives, and were compared to a control group which received no intervention. Thirty-two villages were randomly selected and interventions randomly assigned. All participants in a village received the same intervention. Knowledge levels were assessed by questionnaire administration. Data analysis included comparison of baseline data between intervention groups followed by multilevel linear regression models (allowing for clustering of individuals within village) to evaluate the change in knowledge between the different knowledge-transfer interventions. A total of 516 randomly selected participants completed the pre-intervention questionnaire, 504 of whom undertook the post-dissemination questionnaire, a follow up response rate of 98%. All interventions significantly improved the overall 'change in knowledge' score on the questionnaire compared to the control, with the diagrammatic handout (coefficient (coef) 9.5, S.E. = 0.6) and the village meeting (coef 9.7, S.E. = 0.6) having a significantly greater impact than the audio programme (coef 4.8, S.E. = 0.6). Covariates that were different at baseline, and which were also significant in the final model, were age and pre-intervention score. Although they had a minimal effect on the intervention coefficients there was a significant interaction between age and intervention. This study should aid the design of education materials for adult learning for working equid users and other groups in developing countries. (C) 2011 Elsevier B.V. All rights reserved.