The following definitions are based on the textbooks (Woodward and Crawley) unless otherwise noted.
- Autocorrelation (\(\rho\))
-
- Autocovariance (\(\gamma\))
- covariance within the same time series
- Cauchy-Schwarz inequality
-
- Correlation
- the degree to which two variables are linearly related; see also Pearson correlation coefficient
- Covariance
- the measure of joint variability of two random variables; positive, negative or near zero
- Continuous parameter
- a numeric parameter that can take any value from a specified range of values, for example \(T = (-\infty, \infty)\); compare against a discrete parameter
- Deterministic
-
- Discrete parameter
- a numeric parameter that can take any value from a specified range of values, limited by a minimum permissible distance between each value, for example \(T = \{0, \pm1, \pm2, ...\}\); compare against a continuous parameter
- Ensemble
- the collection of all possible realizations
- Ergodic
- a process whose ensemble averages can be consistently estimated from a single observation (e.g., u(t) doesn’t depend on t)
- Gaussian (normal)
-
- Identically distributed
- a collection of random variables where each random variable has the same probability distribution as the others; if these random variables are also mutually independent, they may be given the shorthand notation IID
- Mean (\(\mu\))
- the expected value (E) or first raw moment of a real-valued random variable (e.g., \(X(t)\)), oftentimes denoted: \(E[X(t)]\)
- Observation
- a real number from a given random variable
- Probabilistic
-
- Random variable
- a variable whose values depend on outcomes of a random process; it can be thought of as a function that is defined in some sample space whose range is the real numbers
- Real number (\({\rm I\!R}\))
- a value from a continuous quantity that can represent a distance along a line (includes all positive and negative rational and irrational numbers)
- Realization
- a set of real-valued outcomes for a random variable at a fixed location in the random variable’s sample space; compare against an ensemble
- Stationary
- a process that is in a state of statistical equilibrium; examples include strict stationarity, covariance stationarity
- Stochastic process
- a collection of indexed random variables from the same sample space
- Time series
- a special type of stochastic process where the sample space represents time
- Univariate
- having or involving a single variable
- Variance (\(\sigma^2\))
- the expected value of the squared deviation from the mean; see also here and here
- White noise
-