Abstract
The interrupted time series analysis is a quasi-experimental design used to evaluate the effectiveness of an intervention. Segmented linear regression models have been the most used models to carry out this analysis. However, they assume a linear trend that may not be appropriate in many situations. In this paper, we show how generalized additive models (GAMs), a non-parametric regression-based method, can be useful to accommodate nonlinear trends. An analysis with simulated data is carried out to assess the performance of both models. Data were simulated from linear and non-linear (quadratic and cubic) functions. The results of this analysis show how GAMs improve on segmented linear regression models when the trend is non-linear, but they also show a good performance when the trend is linear. A real-life application where the impact of the 2012 Spanish cost-sharing reforms on pharmaceutical prescription is also analyzed. Seasonality and an indicator variable for the stockpiling effect are included as explanatory variables. The segmented linear regression model shows good fit of the data. However, the GAM concludes that the hypothesis of linear trend is rejected. The estimated level shift is similar for both models but the cumulative absolute effect on the number of prescriptions is lower in GAM.
Highlights
Well-conducted randomized control trial experiments (RCTs) provide the most reliable evidence on the effectiveness of interventions, these are not always feasible for policy intervention analysis
Results include the mean and standard deviation of the level change estimated for the 500 simulations, along with the mean squared error (MSE) and mean percentage error (MPE) obtained from the comparison with the expected level change for each simulation model
To illustrate the use of generalized additive models (GAMs) in a real-life application, we investigate the impact of the 2012 Spanish cost-sharing reforms on pharmaceutical prescription financed by the Spanish National Health Systems (SNHS) [13]
Summary
Well-conducted randomized control trial experiments (RCTs) provide the most reliable evidence on the effectiveness of interventions, these are not always feasible for policy intervention analysis. The differences between groups can be attributed to the intervention. When it comes to measuring the effect of policy interventions, there may be obstacled to the use of RCTS, such as economic obstacles (impact evaluation are costly) or political constraints (to give services to some groups and not to others can generate conflicts). As alternative to RCTs, the interrupted time series analysis (ITSA) offers a quasiexperimental research design to measure the effect of an intervention when randomization is not possible [1]. ITSA has been used in various fields, such as financial economics [2], health policies [3] and regulatory actions [4], to name but a few
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
