The relationship between a variable and itself over various time intervals as a function of the delay

1 of 32

Trend

An underlying pattern of behaviour

2 of 32

Stochastic Process

A series of random variables indexed by time

3 of 32

Sample (time series)

The one realised path of the series out of the many possible paths that it could have taken

4 of 32

Contemporaneous Relation

The relationship occurs in one period

5 of 32

Impact Multiplier

The immediate effect of a one unit change in x on y

6 of 32

Long-run Multiplier

The total effect of a one unit change in x on y. The sum of multipliers on all x variables.

7 of 32

BLUE

The unbiased estimator with the lowest variance

8 of 32

Biasedness

The difference between the expected value of an estimator and its true value

9 of 32

Consistency

An estimator for which the estimate converges in probability to its true value as the number of data points increases indefinitely

10 of 32

Efficiency

The estimator that attains the true value of a parameter using the fewest observations

11 of 32

Asymptotic Normality

A parameter that is rescaled to be approximated by a Normal distribution

12 of 32

Homoskedastcity

The variance of the errors is the same and does not change with the independent variable

13 of 32

Time Trend

A variable equal to a time index in a given period. Used to control for exogenous increases in dependent variables, usually a proxy for technological progress.

14 of 32

Order (FDL Model)

The number of previous periods included in the regression

15 of 32

IID

Independent and Identically Distributed. Each random variable has the same probability distribution as the others and all are mutually independent

16 of 32

Stationary Process

A stochastic process whose joint probability distribution does not change when shifted in time.

17 of 32

Weakly Dependent (Time Series)

A time series for which the elements are less correlated the further they are from each other.

18 of 32

Endogeneity

When an explanatory variable is correlated with the error term.

19 of 32

Static Model

A model in which only contemporaneous explanatory variables affect the dependent variable.

20 of 32

Sequentially Exogenous

The error term in the current period has a zero mean, conditional on all current and past explanatory variables.

21 of 32

Contemporaneously Exogenous

The error term in the current period is uncorrelated with the explanatory variables in the current period.

22 of 32

Strictly Exogenous

The error term has zero expectation, conditional on the explanatory variables in all time periods.

23 of 32

Covariance Stationary

A process with constant mean and variance for which the covariance between an two random variables depends only on the distance between them.

24 of 32

Autoregressive Process Order 1

A process whose current value depends linearly on its most recent value plus a random disturbance.

25 of 32

Moving Average Process Order 1

A process generated as the linear function of the current value and one lagged value of a zero mean, constant variance uncorrelated process.

26 of 32

Unit Root Process

A highly persistent process where the current value is equal to the previous value, plus a weakly dependent disturbance.

27 of 32

Noise Process

A serially uncorrelated, zero-mean, constant variance process.

28 of 32

Trend-Stationary Process

A process that is stationary and usually weakly dependent once a time trend has been removed.

29 of 32

Integrated Process Order 0

A stationary, weakly dependent process that satisfies the law of large numbers and central limit theorem.

30 of 32

Integrated Process Order 1

A process that must be first-differenced in order to produce an I(0) process.

31 of 32

Asymptotically Uncorrelated

As the distance between two elements increases, their correlation tends to zero. They are almost independent.

## Comments

No comments have yet been made