Economic Policy Uncertainty Index (EPU)#

Uncertainty poses challenges to the stability and growth of economies. The Economic Policy Uncertainty Index (EPU) developed by Baker et al. [2016] emerges as a vital tool to measure both economic- and policy-related uncertainties. Sepcifically, a news needs to contain at least one keyword in each of the three criteria, namely (1) Economy, (2) Uncertainty, and (3) Policy. After counting the frequency of EPU news (in relative to all news), the EPU index can be produced by following steps:

• Let $X_{it}=\frac{\text{EPU news in newspaper }i\text{ at time }t}{\text{All scraped news in newspaper }i\text{ at time }t}$ and pre-defined $T_1$ to be the standardization and normalization period;

• Calculate the standard deviation ${\sigma }_i$ for each newspaper $i$ over $T_1$.

• Standardize $X_{it}$ by dividing by ${\sigma }_i$ for all time $t$, resulting in $Y_{it}=\frac{X_{it}}{{\sigma }_i}$

• Compute the mean of $Y_{it}$ over all newspapers in each month to obtain $Z_t=\text{mean}(Y_{it})\text{ at }t$

• Compute $M$, the mean value of $Z_t$ over the period $T_1$

• Normalize the EPU index by multiplying $Z_t$ by $\left(\frac{100}{M}\right)$ for $T_1$, resulting in the normalized EPU time-series index with a mean of 100 over $T_1$.

Beyond the $Z_t$ being arithmetic mean of $Y_{it}$, we develop a weighted scheme where $w_{it}=\frac{\text{news in newspaper }i\text{ at time }t}{\text{All scraped news at time }t}$ and $Z_t=\sum _{i=1}^n{w}_{it}{Y}_{it}$ for $n$ newspapers. The very rationale behind is to overcome the scenario where a single newspaper with a small number of both news and EPU news creates voltaility for the EPU index. The weighted EPU index is displayed as below with 2016 to 2021 being the standardization and normalization period, as represented by green dashed line.