term 2 week 1

Question 1

what is trend in time series?

Question 2

what is seasonal component of time series

Answer 2

fluctuations with a regular period

Question 3

what is cyclical component of time series

Answer 3

• part of the movement which can be explained by other cyclical movements (long-period; boom-bust effect)
• to get the cycles we need to detrend the data

Question 4

how to detrended data

Question 5

how to get deseasonalised data

Question 6

why are there lags in the time series?

Answer 6

dependent variable is sluggish in response to movements in x

Question 7

what is the contemporaneous coefficient?

Answer 7

it is existing at the same time as variable y => same time effect of an increase in x - no lags

Question 8

what is the total change over time?

Answer 8

it is the sum of all partial effects which sums up to infinite sum of geometric series

Question 9

CLRM assumptions in time series?

Answer 9

all the same apart from 1) => contemporaneous exogeniety: errors are uncorrelated to past values of yt. Assumptions of random sampling in cross-sectional data is replaced by two conditions: stationarity and weak dependence

Question 10

what is stationarity?

Answer 10

1) mean is constant at all points in time
2) variance is constant at all points in time
3) covariance depends on h and not t