Abstract
Ordinary time-series analysis operates on time-series data measured on interval or ratio scale. However we often encounter time-series data measured on nominal scale especially in humanity science. In such cases, it is an important research activity to find systematic trend in the qualitative data. In order to achieve this purpose, Time-Series Analysis of Qualitative Analysis was developed by Inagaki (1997). In this paper, we mathematically explain the method extended to data constrained, and discuss the relation to other methods.
