ABSTRACT
Interrupted time series (ITS) is a statistical method for the quasi-experimental design specific to the outcome of time series, in which the effectiveness of an intervening measure is evaluated by examining change in slope and immediate change in level. The key feature of ITS is that the secular trend of time series prior to the intervention can be effectively controlled so as to accurately estimate the intervention effect. The design principle and statistical method for ITS were illustrated by an example of evaluating halving policy for the expert registration fee in the general hospital of a city. The segmented linear regression was used to fit the above time series data and the results were explained in detail. Meanwhile, the study design and model fitting along with explanations of the results with respect to the effects of two types of successive interventions and on different time-points of an intervention were illustrated as well in this paper. The existed upward or downward trend should be taken into account in order to accurately estimate the intervention effect as it exists in most of the public health surveillance data. Two parameters, known as change in slope and immediate change in level, were employed to evaluate the effect of the intervention. The ITS analysis can be widely applied to the program evaluation as it could enrich methods of the evaluation compared to the traditional model of the program evaluation.