Time Series Data Flashcards
How does time series data differ from cross-sectional data?
Time series data involves temporal ordering, whereas cross-sectional data does not.
What is a stochastic process or a time series process?
A sequence of random variables indexed by time.
Why do we only see a single realization of time series data?
Because we cannot go back in time and start the process again
What is a static model?
A model where a change in z at time t has an immediate effect on y.
When are static models useful?
When interested in the tradeoff between two contemporaneous variables.
What is the purpose of finite distributed lag models?
They allow one or more variables to affect y with a lag.
What is the impact propensity?
The coefficient δ_0, which measures the immediate impact of z on y.
What does the lag distribution summarize?
The dynamic effect that a temporary increase in z has on y.
What is the long-run propensity?
The sum of coefficients on z, representing the long-run change in y due to a permanent increase in z.
What is Assumption TS.1?
The model is linear in parameters.
What is Assumption TS.2?
No perfect collinearity among independent variables.
What is Assumption TS.3?
The error term has a zero conditional mean given all explanatory variables
What happens if Assumption TS.3 fails?
The explanatory variables become endogenous, leading to bias
What is Assumption TS.4?
Homoskedasticity: the variance of errors does not depend on X
What is Assumption TS.5?
No serial correlation: errors are not correlated over time.
What does the Gauss-Markov Theorem state?
Under TS.1-TS.5, OLS estimators are the Best Linear Unbiased Estimators (BLUE).
What does Assumption TS.6 state?
Errors are independent of X and are independently and identically distributed (i.i.d.).
Why is normality important in OLS?
It ensures valid inference using t-tests and confidence intervals.
What are the key components in an event study?
Binary explanatory variables representing the occurrence of an event.
What is the goal of an event study?
To determine if a particular event influences an outcome, such as stock prices.
Why is recognizing trends important in time series analysis?
Ignoring trends can lead to spurious relationships between variables.
What is an exponential trend?
A trend where a series has the same average growth rate from period to period.
What is the spurious regression problem?
Finding a relationship between trending variables that is due to common trends rather than causality.
How can spurious regression be avoided?
By including a time trend in the regression model.
What is the purpose of detrending in regression analysis?
To remove time trends from variables before analyzing relationships.
What is seasonality in time series data?
A pattern that repeats at regular intervals, such as monthly or quarterly.
How is seasonality accounted for in regression models?
By including seasonal dummy variables.
: What does seasonally adjusted data mean?
Data that has had seasonal factors removed to better identify trends and relationships.
