The comparable effects of these nursing interventions
on both hospital costs and complication rates
were estimated by a path model using AMOS 7.0 software.
Because path modelling allows for a meaningful
interpretation of the estimates only when the model
fits the data, model trimming was completed using the
following modification indices: (i) the model chisquare,
(ii) the Steiger–Lind root mean square error of
approximation (RMSEA), (iii) the Bentler comparative
fit index (CFI) and (iv) the standardized root mean
square residual (SRMR). By convention, values less
than or equal to 0.05 are desirable for RMSEA (Schumacker
& Lomax 2004).