Skip to main content
Glite Dictionary
autoregressive

autoregressive

1 9.1
A model that uses past values in a series to predict future values
  • adjective
  • /ˌɔːtəˈrɛɡrɪsɪv/
  • Specialized
: autoregresivo
  • Trend lines were fitted using linear autoregressive models.
  • autoregressive model
  • autoregressive coefficient
  • autoregressive specification

So does it make sense to you that autoregressive LLMS are able to be so damn good?

Examples

  • We estimated a first-order autoregressive model and performed various diagnostic tests to refine our specification.

    Academic text (2001)

  • By adding the weights matrix specification and temporal variables, the autoregressive variation explanation increases from 0.342 to 0.504.

    Academic text (2016)

  • So it's it's a very simple structure for the autoregressive process as a linear state space model.

  • All right, well, let's move on to vector autoregressive processes.

  • Study context may affect the autoregressive specification.

    Academic text (2016)

  • Also included in the equation are a constant term and an autoregressive correction.

    Academic text (1992)

  • Comparatively, that model fit better than the autoregressive or LGC specifications and provides more information as well.

    Academic text (2010)

  • To explain the mechanism, we consider a first-order autoregressive model used in the main smoothing literature as presented in equation (6):

    Academic text (2016)

  • Engle (1982) pioneered the autoregressive conditional heteroscedasticity model to capture this type of behavior in the variance.

    Academic text (2001)

  • The researchers used an autoregressive model to predict sales based on previous data.

Surface Forms

autoregressive positive

Morphology

autoregressive = regressive (semi-transparent) = auto + re + gress + ive

The word is built from a recognizable base adjective plus the prefix 'auto-', but the statistical meaning is specialized and not fully predictable for a general learner.

Etymology

Autoregressive comes from auto- meaning 'self' and regress meaning 'to go back', as in the words automatic and regress. So an autoregressive model predicts future values by looking back at its own past values.