Bootstrap confidence intervals for multiple change points based on moving sum procedures

The problem of quantifying uncertainty about the locations multiple change points by means confidence intervals is addressed. asymptotic distribution point estimators obtained as local maximisers moving sum statistics derived, where limit distributions differ depending on whether corresponding size changes local, i.e. tends to zero sample increases, or fixed. A bootstrap procedure for interval generation proposed which adapts unknown magnitude and guarantees validity both fixed changes. Simulation studies show good performance procedure, some discussions how it can be extended serially dependent errors are provided.