Necrotising enterocolitis is an oft-fatal disease of the in
testinal tract in neonates
born prematurely and with low birthweight. We study the vari
ation of its rates
across the neonatal networks (groups of hospital-based neo
natal care units) in
England. We illustrate the problematic nature of hypothesi
s testing for a key
decision which an analysis is meant to inform, and apply an ap
proach based on
decision theory. We emphasise the role of sensitivity analy
sis in dealing with
the ambiguity encountered in the process of eliciting infor
mation about the per-
spective of the client or sponsor for whom the analysis is con
ducted. In the
application based on a fiducial distribution, the likelihoo
d is approximated by a
linearising transformation of the score function.