No abstract

No abstract

This paper proposes an efficient adaptive realization of the Wiener model for the identification of complex-valued nonlinear systems. Using a two-dimensional simplicial canonical piecewise linear filter for the complex-valued nonlinear mapping, we derive a realization of the Wiener model requiring fewer parameters than previous approaches. An adaptive implementation of the proposed Wiener model is derived, and local convergence analysis for the updating algorithm is presented. The tradeoff between computational complexity and modeling performance is discussed. Simulations of a system identification example show that the proposed algorithm can provide similar or better performance than other approaches in terms of computational complexity, convergence speed, and final mean-squared error (MSE).

Behavioural change communication interventions have been shown to be effective at improving infant and young child nutrition knowledge and practices. However, evidence in humanitarian response contexts is scarce. Using data on secondary outcomes of breastfeeding, water treatment, and knowledge from a cluster randomized control trial of the Yemen Cash for Nutrition programme's impact on child nutritional status, this paper shows that the programme significantly improved knowledge and practices for poor women with young children in the pilot districts. The intervention consisted of cash transfers and monthly group nutrition education sessions led by locally recruited community health volunteers. Data are based on self‐reports by participants. Estimating impacts among all 1,945 women in 190 clusters randomly assigned to treatment versus control and controlling for baseline levels and community characteristic and adjusting for noncompliance with randomization, the programme increased the probability of breastfeeding initiation within the first hour after delivery by 15.6% points (p < .05; control = 74.4% and treatment = 83.6%), the probability of exclusive breastfeeding during the first 6 months by 14.4% points (control = 13.5% and treatment = 25.3%), the probability of households treating water consumed by adults by 16.7% points (p < .01; control = 13.9% and treatment = 23.4%), and treating water consumed by children under two by 10.3% points (p < .10; control = 31.2% and treatment = 37.9%). Impacts on knowledge and breastfeeding are similar for both literate and illiterate women, and water treatment impacts are significantly larger for literate women. This study was registered at 3ie (RIDIE‐STUDY‐ID‐5b4eff881b29a) and funded by the Nordic Trust Fund and Consultative Group on International Agricultural Research programme on Policies, Institutions, and Markets.