Distribution-free changepoint detection tests based on the breaking of records

The analysis of record-breaking events is interest in fields such as climatology, hydrology or anthropology. In connection with the record occurrence, we propose three distribution-free statistics for changepoint detection problem. They are CUSUM-type based on upper and/or lower indicators observed a series. Using version functional central limit theorem, show that asymptotically Kolmogorov distributed. main results under null hypothesis series independent and identically distributed random variables, but statistic to deal seasonal component serial correlation also proposed. A Monte Carlo study size, power estimate has been performed. Finally, methods illustrated by analyzing time temperatures at Madrid, Spain. R package $\texttt{RecordTest}$ publicly available CRAN implements proposed methods.