6

What is the difference between sequence data and time series data?

My understanding is that sequence data is any data where the order matters and time series is a special type of sequence data ordered by the time stamps. Is this correct?

Is there a paper or book that defines it so I can cite it in a research paper?

user2840286
  • 169
  • 1
  • 1
  • 3

2 Answers2

5

Sequential Data is any kind of data where the order matters as you said. So we can assume that time series is a kind of sequential data, because the order matters. A time series is a sequence taken at successive equally spaced points in time and it is not the only case of sequential data. In the latter the order is defined by the dimension of time. There are other cases of sequential data as data from text documents, where you can take into account the order of the terms or biological data (DNA sequence etc.). The fact that you have sequential data is important for two reasons. First, you can into account for the representation of the data and also you can take it into account for the data modeling (e.g. Conditional Random Fields, Hidden Markov Models for text or genes and ARIMA Models for time series problems).

Christos Karatsalos
  • 830
  • 4
  • 12
  • "equally spaced points in time" -> It does not have to be equally spaced. – Mr. Panda Jun 16 '22 at 11:37
  • Well, it is like that in most cases. Moreover, there are cases like "unevenly spaced time series", which is actually a sequence of observation time and value pairs (tn, Xn) in which the spacing of observation times is not constant. – Christos Karatsalos Jun 16 '22 at 18:20
0

A time series is a series of data points indexed (or listed) in time order. Most commonly, a time series is a sequence taken at successive equally spaced points in time.

Sequential data looks at data problems where the ordering of data matters.

Nyasha Musanhu
  • 1