9. Time Series & Sequential Data Flashcards
What is a time series?
A sequence of observations recorded at regular time intervals.
What is stationarity in time series?
A time series is stationary if its statistical properties (mean, variance) do not change over time.
What is the difference between additive and multiplicative seasonality?
Additive seasonality means variations are constant over time, while multiplicative means they increase or decrease with the trend.
What is differencing in time series?
A technique used to remove trends by computing the difference between consecutive observations.
What is an autoregressive (AR) model?
A model where future values depend on previous values plus noise.
What is a moving average (MA) model?
A model where future values depend on past forecast errors.
What is an ARMA model?
A combination of autoregressive (AR) and moving average (MA) models.
What is an ARIMA model?
A model combining autoregression, differencing, and moving averages for forecasting.
What is a seasonal ARIMA (SARIMA) model?
An extension of ARIMA that includes seasonal components.
What is exponential smoothing?
A forecasting technique that applies weighted averages to past data points.
What is Holt-Winters method?
A time series forecasting technique that accounts for trend and seasonality.
What is a rolling window in time series analysis?
A method of computing statistics over a sliding window of past observations.
What is a lag variable?
A past value of a time series used as a predictor for the current value.
What is Granger causality?
A statistical hypothesis test to determine if one time series can predict another.
What is a cointegration test?
A test used to determine if two or more time series have a long-term relationship.
What is a structural break in time series?
A sudden change in the relationship between time series variables.
What is seasonality in time series?
A repeating pattern of fluctuations over a fixed period.
What is a trend in time series?
A long-term increase or decrease in data values over time.
What is forecasting?
The process of predicting future values based on historical data.
What is autocorrelation?
The correlation of a time series with its past values.
What is partial autocorrelation?
The correlation of a time series with its past values after removing intermediate dependencies.
What is the ACF (Autocorrelation Function)?
A function that measures how a time series is correlated with its past values.
What is the PACF (Partial Autocorrelation Function)?
A function that shows the direct relationship between a time series and its lags.
What is white noise in time series?
A sequence of random values with a constant mean and variance and no correlation between observations.
What is a random walk?
A time series model where each step is randomly determined, often used in financial markets.
What is a unit root?
A characteristic of non-stationary time series where shocks have a permanent effect.
What is the Augmented Dickey-Fuller (ADF) test?
A statistical test used to determine whether a time series is stationary.
What is a time series?
A sequence of observations recorded at regular time intervals.
What is stationarity in time series?
A time series is stationary if its statistical properties (mean, variance) do not change over time.
What is the difference between additive and multiplicative seasonality?
Additive seasonality means variations are constant over time, while multiplicative means they increase or decrease with the trend.
What is differencing in time series?
A technique used to remove trends by computing the difference between consecutive observations.
What is an autoregressive (AR) model?
A model where future values depend on previous values plus noise.
What is a moving average (MA) model?
A model where future values depend on past forecast errors.
What is an ARMA model?
A combination of autoregressive (AR) and moving average (MA) models.
What is an ARIMA model?
A model combining autoregression, differencing, and moving averages for forecasting.
What is a seasonal ARIMA (SARIMA) model?
An extension of ARIMA that includes seasonal components.
What is exponential smoothing?
A forecasting technique that applies weighted averages to past data points.
What is Holt-Winters method?
A time series forecasting technique that accounts for trend and seasonality.
What is a rolling window in time series analysis?
A method of computing statistics over a sliding window of past observations.
What is a lag variable?
A past value of a time series used as a predictor for the current value.
