Trends and cycles in unemployment¶
Here we consider three methods for separating a trend and cycle in economic data. Supposing we have a time series \(y_t\), the basic idea is to decompose it into these two components:
where \(\mu_t\) represents the trend or level and \(\eta_t\) represents the cyclical component. In this case, we consider a stochastic trend, so that \(\mu_t\) is a random variable and not a deterministic function of time. Two of methods fall under the heading of “unobserved components” models, and the third is the popular Hodrick-Prescott (HP) filter. Consistent with e.g. Harvey and Jaeger (1993), we find that these models all produce similar decompositions.
This notebook demonstrates applying these models to separate trend from cycle in the U.S. unemployment rate.
[1]:
%matplotlib inline
[2]:
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import statsmodels.api as sm
[3]:
from pandas_datareader.data import DataReader
endog = DataReader("UNRATE", "fred", start="1954-01-01")
endog.index.freq = endog.index.inferred_freq
Hodrick-Prescott (HP) filter¶
The first method is the Hodrick-Prescott filter, which can be applied to a data series in a very straightforward method. Here we specify the parameter \(\lambda=129600\) because the unemployment rate is observed monthly.
[4]:
hp_cycle, hp_trend = sm.tsa.filters.hpfilter(endog, lamb=129600)
Unobserved components and ARIMA model (UC-ARIMA)¶
The next method is an unobserved components model, where the trend is modeled as a random walk and the cycle is modeled with an ARIMA model - in particular, here we use an AR(4) model. The process for the time series can be written as:
where \(\phi(L)\) is the AR(4) lag polynomial and \(\epsilon_t\) and \(\nu_t\) are white noise.
[5]:
mod_ucarima = sm.tsa.UnobservedComponents(endog, "rwalk", autoregressive=4)
# Here the powell method is used, since it achieves a
# higher loglikelihood than the default L-BFGS method
res_ucarima = mod_ucarima.fit(method="powell", disp=False)
print(res_ucarima.summary())
Unobserved Components Results
==============================================================================
Dep. Variable: UNRATE No. Observations: 857
Model: random walk Log Likelihood -463.315
+ AR(4) AIC 938.630
Date: Sat, 14 Jun 2025 BIC 967.143
Time: 19:35:38 HQIC 949.548
Sample: 01-01-1954
- 05-01-2025
Covariance Type: opg
================================================================================
coef std err z P>|z| [0.025 0.975]
--------------------------------------------------------------------------------
sigma2.level 1.184e-05 0.012 0.001 0.999 -0.023 0.023
sigma2.ar 0.1735 0.016 11.081 0.000 0.143 0.204
ar.L1 1.0262 0.019 54.111 0.000 0.989 1.063
ar.L2 -0.1064 0.016 -6.573 0.000 -0.138 -0.075
ar.L3 0.0741 0.023 3.165 0.002 0.028 0.120
ar.L4 -0.0246 0.019 -1.292 0.196 -0.062 0.013
===================================================================================
Ljung-Box (L1) (Q): 0.00 Jarque-Bera (JB): 6932928.73
Prob(Q): 0.97 Prob(JB): 0.00
Heteroskedasticity (H): 9.06 Skew: 17.61
Prob(H) (two-sided): 0.00 Kurtosis: 442.48
===================================================================================
Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
Unobserved components with stochastic cycle (UC)¶
The final method is also an unobserved components model, but where the cycle is modeled explicitly.
[6]:
mod_uc = sm.tsa.UnobservedComponents(
endog,
"rwalk",
cycle=True,
stochastic_cycle=True,
damped_cycle=True,
)
# Here the powell method gets close to the optimum
res_uc = mod_uc.fit(method="powell", disp=False)
# but to get to the highest loglikelihood we do a
# second round using the L-BFGS method.
res_uc = mod_uc.fit(res_uc.params, disp=False)
print(res_uc.summary())
Unobserved Components Results
=====================================================================================
Dep. Variable: UNRATE No. Observations: 857
Model: random walk Log Likelihood -469.971
+ damped stochastic cycle AIC 947.943
Date: Sat, 14 Jun 2025 BIC 966.942
Time: 19:35:40 HQIC 955.219
Sample: 01-01-1954
- 05-01-2025
Covariance Type: opg
===================================================================================
coef std err z P>|z| [0.025 0.975]
-----------------------------------------------------------------------------------
sigma2.level 0.1760 0.004 46.897 0.000 0.169 0.183
sigma2.cycle 5.879e-11 0.002 2.66e-08 1.000 -0.004 0.004
frequency.cycle 0.3491 536.237 0.001 0.999 -1050.655 1051.353
damping.cycle 0.1106 33.903 0.003 0.997 -66.339 66.560
===================================================================================
Ljung-Box (L1) (Q): 1.17 Jarque-Bera (JB): 6975413.52
Prob(Q): 0.28 Prob(JB): 0.00
Heteroskedasticity (H): 9.68 Skew: 17.55
Prob(H) (two-sided): 0.00 Kurtosis: 444.36
===================================================================================
Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
Graphical comparison¶
The output of each of these models is an estimate of the trend component \(\mu_t\) and an estimate of the cyclical component \(\eta_t\). Qualitatively the estimates of trend and cycle are very similar, although the trend component from the HP filter is somewhat more variable than those from the unobserved components models. This means that relatively mode of the movement in the unemployment rate is attributed to changes in the underlying trend rather than to temporary cyclical movements.
[7]:
fig, axes = plt.subplots(2, figsize=(13, 5))
axes[0].set(title="Level/trend component")
axes[0].plot(endog.index, res_uc.level.smoothed, label="UC")
axes[0].plot(endog.index, res_ucarima.level.smoothed, label="UC-ARIMA(2,0)")
axes[0].plot(hp_trend, label="HP Filter")
axes[0].legend(loc="upper left")
axes[0].grid()
axes[1].set(title="Cycle component")
axes[1].plot(endog.index, res_uc.cycle.smoothed, label="UC")
axes[1].plot(endog.index, res_ucarima.autoregressive.smoothed, label="UC-ARIMA(2,0)")
axes[1].plot(hp_cycle, label="HP Filter")
axes[1].legend(loc="upper left")
axes[1].grid()
fig.tight_layout();
