Please enable JavaScript.
Coggle requires JavaScript to display documents.
Time Series Analysis for Finance, Augmented Dickey-Fuller - Coggle Diagram
Time Series Analysis for Finance
Time Series Data are
Non-Stationary Data which can be
Trends data can be transformed by
Seasonal can be transformed by
Differencing
By season to get
With N-order to get
Stationary Time Series
Time Series with pure cyclic behaviour
Time Series Analysis Models and Techniques
ETS Models
Consisting of
A trend component (T)
A seasonal component (S)
An error term (E)
ETS Decomposition Module can decompose Time Series into
EWMA Models
SMA Models
ARMA Models generalized by
ARIMA Models
can be
Seasonal ARIMA using
Non-seasonal ARIMA
decomposed into
Degree of first differencing
Moving average part
Autoregressive part
Time Series Examples
Asset prices
Exchange rates
Inflation
Python Statsmodels that includes
Augmented Dickey-Fuller
p-value < 0.05 shows strong evidence for
p-value > 0.05 shows strong evidence for