Augmented Dickey-Fuller (ADF) tests the null hypothesis that a unit root is present in a time series. Each plot is labeled with an “ADF Statistic” and a “p-value,” which are used to determine whether a time series is stationary.
Here is the analysis:
ADF Test: Total Jobs
The plot shows the time series data for “total_jobs.”
The ADF statistic is positive, and the p-value is very high (0.9475), indicating strong evidence that the series is non-stationary.
ADF Test: Unemp Rate
This is the time series data for “unemp_rate.”
The ADF statistic is negative, but the p-value is not below the common threshold of 0.05 (0.4789), suggesting the series is likely non-stationary.
ADF Test: Logan Passengers
This plot represents “logan_passengers” over time.
The ADF statistic is positive, and the p-value is extremely high (0.9853), indicating that the series is non- stationary.
ADF Test: Logan Intl Flights
The time series data for “logan_intl_flights” is shown.
The ADF statistic is negative, and the p-value is 0.2306, which is above the 0.05 threshold, suggesting non- stationarity.
ADF Test: Hotel Occup Rate
The plot displays the “hotel_occup_rate” time series.
The ADF statistic is negative, with a p-value of 0.4359, again indicating non-stationarity as the p-value is above 0.05.
ADF Test: Hotel Avg Daily Rate
This plot shows the “hotel_avg_daily_rate” time series.
The ADF statistic is negative, and the p-value is very low (0.0058), suggesting that the series is stationary.
ADF Test: Labor Force Participation Rate
This plot shows the “Labor_Force_Part_Rate” time series.
The ADF statistic value is positive, with a p-value (0.9691). With a p-value significantly greater than the common threshold of 0.05, the test suggests that the series is non-stationary.
For the ADF test, a p-value below a threshold (commonly 0.05) indicates stationarity, meaning there is no unit root present in the time series. A non-stationary time series is characterized by a changing mean or variance over time, which can be problematic for many types of time series analysis, including forecasting.