Authors :
Peichun Feng
Volume/Issue :
Volume 7 - 2022, Issue 7 - July
Google Scholar :
https://bit.ly/3IIfn9N
Scribd :
https://bit.ly/3BqYVZF
DOI :
https://doi.org/10.5281/zenodo.7087975
Abstract :
One of the most critical roles of macroeconometricians is to provide advice to policymakers by
describing and summarizing macroeconomic data,
making macroeconomic forecasts, estimating how much
stakeholders understand concerning the macroeconomy's
underlying structure. Various methods were used in to
perform these activities in the 1900s. The most notable
ones were policy analysis, forecasting and inference
structure. Researchers investigated a wide scale of these
techniques, from vast frameworks with numerous
complex equations to simple one-variable time series
models and single-equation interactions models. However,
none of these methods proven to be particularly reliable
after the macroeconomic instability of the 1970s.
Christopher Sims (1980) introduced a novel macroeconometric paradigm, vector autoregressions (VARs),
two decades ago, and it was immediately well received. As
the name suggests, the current value of a single variable is
explained by the residual of that same variable, which is
known as a univariate autoregression. To put it another
way, it constitutes a linear regression of n-equation and
variable in which each component is described based on
its individual lagged numbers, as well as present and
previous values of the rest of the n - 1 additional variables.
The VAR statistical toolset proved to be effective for use
and analysis and it provided a systematic technique to
detect dynamics in many time series. In a series of
significant early works, Sims (1980) and others claimed
that VAR had the promise of providing a consistent and
plausible model for policy analysis, structural inferences,
and data description.
Keywords :
vector autoregressions; univariate autoregression; macro-econometric analysis.
One of the most critical roles of macroeconometricians is to provide advice to policymakers by
describing and summarizing macroeconomic data,
making macroeconomic forecasts, estimating how much
stakeholders understand concerning the macroeconomy's
underlying structure. Various methods were used in to
perform these activities in the 1900s. The most notable
ones were policy analysis, forecasting and inference
structure. Researchers investigated a wide scale of these
techniques, from vast frameworks with numerous
complex equations to simple one-variable time series
models and single-equation interactions models. However,
none of these methods proven to be particularly reliable
after the macroeconomic instability of the 1970s.
Christopher Sims (1980) introduced a novel macroeconometric paradigm, vector autoregressions (VARs),
two decades ago, and it was immediately well received. As
the name suggests, the current value of a single variable is
explained by the residual of that same variable, which is
known as a univariate autoregression. To put it another
way, it constitutes a linear regression of n-equation and
variable in which each component is described based on
its individual lagged numbers, as well as present and
previous values of the rest of the n - 1 additional variables.
The VAR statistical toolset proved to be effective for use
and analysis and it provided a systematic technique to
detect dynamics in many time series. In a series of
significant early works, Sims (1980) and others claimed
that VAR had the promise of providing a consistent and
plausible model for policy analysis, structural inferences,
and data description.
Keywords :
vector autoregressions; univariate autoregression; macro-econometric analysis.