Nowadays, it is a common practice to protect various types of statistical data before publishing them for different researches. For instance, when conducting extensive demographic surveys such as national census, the collected data should be at least depersonalized to guarantee proper level of privacy preservation. In practice, even more complicated methods of data protection need to be used. All these methods can be generally divided into two classes. The first ones aim at providing individual data anonymity, whereas the other ones are focused on protecting information about a group of respondents. In this paper, we propose a novel technique of providing group anonymity in statistical data using singular spectrum analysis (SSA).Also, we apply SSA to defining hidden patterns in demographic data distribution.