Economic Forecasting Test 2

Moving Average is a calculation to analyze data points by creating a series of

averages of different subsets of the full data set.

In an autoregressive model, the preceding model is a _______ autoregression, written as _________.

first-order; AR(1)

The structure of vector autoregression is that each variable is a linear function of

past lags of itself and past lags of the other variables.

A moving average (MA) is a trend-following or lagging indicator because it is based on

past values.

A big difference between ARMA mdoels and ARIMA models is that

Integrated means the trend has been removed; if the series has no significant trend, the models are known as ARMA models.

The forecast accuracy measures are:

Root-Mean-Square-Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Deviation (MAPD), Theil's Inequality Coefficient

AR(1) - causes

a buildup of error always and eventually makes the variables endogenous.

Theil's Inequality Coefficient provides a measure of how well a time series of estimated values compares to

a corresponding time series of observed values.

The RMSE serves to aggregate the magnitudes of the errors in predictions for various times into

a single measure of predictive power.

How to present a forecast: (TEST QUESTION)

a.) Graphical explanation of key drivers affecting variable being predicted b.) Presentation of the equating being used to forecast c.) discussion of macroeconomic outlook d.) discussion of other key factors in equation e.) presentation of standard forecast f.) discussion of other variables that could be relevant g.)alternative scenarios and probabilities h.) presentation of alternative forecast

Auto-Regressive Moving Average model consists of two parts,

an autoregressive (AR) part and a moving average (MA) part

Root-Mean-Square-Error (RMSE) is a frequently used measure of the differences between values (sample and population values) predicted by a model or

an estimator and the values actually observed.

A stationary time series is one whose statistical properties such as mean, variance, autocorrelation, etc. are all ________ over time.

constant

Stationarity imposes a constant mean and variance on any given period of a time series so that it is

constant for a model to produce more accurate results.

RMSD is a good measure of accuracy, but only to

compare forecasting errors of different models for a particular variable and not between variables

A moving-average model is one in which the dependent variable is a function of

current and lagged exogenous shocks, as represented by the residual term.

Endogenous variables gain their interpretation from within a equation, while the exogenous variables

gain their meaning outside the equation.

Mean absolute error (MAE) is a quantity used to measure

how close forecasts or predictions are to the eventual outcomes.

Mean Absolute Percentage Deviation

is a measure of prediction accuracy of a forecasting method.

The Johansen test is more applicable than the Engle-Granger because

it permits more than one cointegrating relationship.

VAR models generalize the univariate autoregressive model (AR model) by allowing for

more than one evolving variable.

The vector autoregression (VAR) is an econometric model used to capture the linear interdependencies among

multiple time series.

It is necessary to use a system of equations when endogenous variables

need to be expressed in terms of exogenous variables.

An auto regressive model is

one which the dependent variable is a function of its lagged values.

An autoregressive model is when a value from a time series is regressed

on previous values from that same time series. for example,yt on yt−1:

(Buildup of forecast error) Increased distance from the mean value has two sources of error:

one because of the random nature of the parameters that are being estimated, and the other because of the error term.

Exogenous Preference --

one that comes from outside the model and is unexplained by the model.

In an auto regressive model, the response variable in the previous time period has become the

predictor

Endogenous Preference --

preferences that cannot be taken as given, but are affected by individual internal responses to the external state of affairs.

The difference between predicted values and observed values are

residuals.

The Engle-Granger two step method for cointegration states that a combination of both X and Y must be stationary thus X-Y=z , then

test z for stationarity using the augmented Dickey-Fuller test for a Unit Root.

The two primary tests for cointegration are:

the Engle-Granger two step method and the Johansen Test.

The mean absolute error is an average of

the absolute errors

A major source of error buildup in multi-period forecasting stems from

using the lagged dependent variable on the right-hand side of the equation.

Granger causality is a statistical hypothesis test for determining

whether one time series is useful in forecasting another

Mean Absolute Percentage Deviation (formula)

|(actual value - forecasted value)/ actual value| summation of each observation and divided by n.