This paper presents some preliminary results of a study investigating the effect of telecare on the length of stay in hospital using linked administrative health and social care data in Scotland. We make various assumptions about the probability distribution of the outcome measure and formulate three Negative Binomial Models to that effect i.e. a basic Negative Binomial Model, a zero-inflated Negative Binomial Model and a zero-truncated Negative Binomial Model. We then bring the models to data and estimate them using a strategy that controls for the effects of confounding variables and unobservable factors. These models provide an alternative to the Propensity Score Matching technique used by the previous studies. The empirical results show that telecare users are expected to spend a shorter time in hospital than non-users, holding other factors constant. The results also show that older individuals, males, rural residents and individuals with comorbidities have a longer length of stay in hospital, on average, than their counterparts, all things equal. Future research will involve conducting a sub-group analysis, investigating the effectiveness of various telecare devices and determining the impact of telecare on admission to hospital.
Telecare Negative Binomial Models length of stay in hospital
C32 C36 C55 D13 I12
The paper is part of the 24-month assessment for a PhD.