time series

(redirected from Univariate time series)
Also found in: Dictionary, Thesaurus, Encyclopedia.
Related to Univariate time series: Multivariate time series

Time Series

A comparison of a variable to itself over time. One of the most common time series, especially in technical analysis, is a comparison of prices over time. For example, one may compile a time series of a security over the course of a week or a month or a year, and then use it in the determination of future price movements.

time series

A set of variables with values related to the respective times the variables are measured. Thus, a weekly record of a stock's price throughout a period of years is a time series. Time series are often used to project future values by observing how the value of a variable has changed in the past.

time series

any statistical information recorded over successive time periods. See TIME-SERIES ANALYSIS.
References in periodicals archive ?
In order to evaluate forecasting performance of ANNs, we consider three univariate time series models.
Repeating the analysis in Section VA using this parsimonious multivariate time series model (as opposed to a univariate time series model), it is found that no breaks occur for any of the four series (FS, NFS, FH, and NFH).
Similar to the concept of the potential structural break in a unit root test for a univariate time series data, the structural break may also exist in the cointegration vector, by reflecting on the interrelationship of a multivariate time series.
Univariate Time series modeling analyses patterns in historic prices, and is particularly useful in short-term forecasts.
Table 3 shows results from constructing one-sided estimates using forecasts from univariate time series models with forecasts constructed from Vector Autoregressive (VAR) models.
Rothman (1998), and Johnes (1999) also formulated and tested various univariate time series models.