Augmented Dickey–Fuller test
Augmented Dickey-Fuller (ADF) Test is a way to check if a time series data (data that changes over time, like temperature or stock prices) is stationary or not.
So, what does stationary mean? Imagine you have a toy car on a bumpy road, if the car bounces up and down, it's hard to tell how fast it's moving. But, if the car is on a smooth road, you can easily tell how fast it's moving. Similarly, if a time series data is not stationary, it's hard to tell if the data is going up or down or just moving randomly.
ADF test checks if a time series data is stationary by comparing it with a random walk (which means the value is determined by its previous value plus a random error). If the data follows a random walk, it means it's not stationary.
Now, the "augmented" part of ADF test means it adds more variables to the test to make it more accurate. These variables take into account the possibility of a trend or seasonality in the data. A trend means the data is moving in a certain direction (like stock prices going up or down), while seasonality means the data follows a repeating pattern (like sales of Christmas trees going up during the winter season).
In summary, the ADF test is a way to check if a time series data is stationary by comparing it with a random walk and taking into account possible trends and seasonality in the data.
So, what does stationary mean? Imagine you have a toy car on a bumpy road, if the car bounces up and down, it's hard to tell how fast it's moving. But, if the car is on a smooth road, you can easily tell how fast it's moving. Similarly, if a time series data is not stationary, it's hard to tell if the data is going up or down or just moving randomly.
ADF test checks if a time series data is stationary by comparing it with a random walk (which means the value is determined by its previous value plus a random error). If the data follows a random walk, it means it's not stationary.
Now, the "augmented" part of ADF test means it adds more variables to the test to make it more accurate. These variables take into account the possibility of a trend or seasonality in the data. A trend means the data is moving in a certain direction (like stock prices going up or down), while seasonality means the data follows a repeating pattern (like sales of Christmas trees going up during the winter season).
In summary, the ADF test is a way to check if a time series data is stationary by comparing it with a random walk and taking into account possible trends and seasonality in the data.