The recent Covid crisis has actually underlined the requirement of high-frequency tools able to track in real-time financial activity (see for example the tool put forward by Lewis et al., 2020, at the New York Fed to carefully follow U.S. financial activity on a weekly basis).
Figure 2: Economic Weakness Index for the U.S.
Heiner Mikosch, with P. Kronenberg and S. Neuwirth (all ETH Zürich KOF), have created developed tool to track economic activity in many various European countries with alternative data sets and various numerous modelsDesigns Gabriel Perez Quiros (Banco de España), joint with S. Delle Chiaie (ECB), question the use of models that only include high-frequency alternative information, as those information have a weak signal-to-noise ratio and usually do have a little sample size, leading to complex estimate procedures. By utilizing a simulation exercise, they reveal that high-frequency alternative information alone lead to bad nowcasting performances and a great method for professionals would be to blend both high-frequency alternative data (i.e. weekly or daily) and low-frequency main data (i.e. regular monthly or quarterly). Real-time estimate of this design points out its capability to efficiently track U.S. economic activity consisting of the most recent duration.
Figure 1: Euro area GDP development (quarter-over-quarter) nowcast for 2022q4. Source: euronowcast.com
.
Notre Dame), have actually constructed a new tool able to track weekly U.S. financial conditions at the state level. They handled to gather a public database of financial signs at the state level, including labor market, mobility, real activity, expectations, financial conditions and homes. Evaluation of state-space models for each state leads to a dashboard of economic conditions for each state at different frequencies.
On Friday 21 October, we arranged with Catherine Doz at Paris School of Economics (PSE) a global workshop on macroeconomic nowcasting, with the assistance of the PSE Chair “Measurement in Economics”. In times of international unpredictabilities, it is of vital value to know where we presently are, before attempting to anticipate where we will enter the future. Macroeconomic nowcasting is a principle at first put forward by Giannone et al. (2008) with the idea of optimally using all the current readily available info to assess financial conditions of the present quarter, well in advance of main figures generally released with a lag by statistical workplaces around the world.
Many of the documents presented during this workshop focus on recent methods developed to nowcast crucial macro variables, by using either basic or alternative high-frequency variables. Alternative high-frequency variables are data that can be collected through different channels (website, satellites, social networks, tensors …). They are typically rather large databases, available daily, not structured and with a weak signal-to-noise ratio. Therefore, statistical/econometric strategies need to be executed to filter out the data and extract a readable signal. The recent Covid crisis has actually highlighted the need of high-frequency tools able to track in real-time economic activity (see for instance the tool advanced by Lewis et al., 2020, at the New York Fed to carefully follow U.S. economic activity on a weekly basis).
Modugno (Federal Reserve Board), joint with D. Cascaldi Garcia (Federal Reserve Board), T. Ferreira (Federal Reserve Board) and D. Giannone (Univ. of Washington & & Amazon), provided a brand-new tool established to track economic activity in the euro location through Dynamic Factor Models approximated for each of the primary euro area nations (Germany, France and Italy). The main idea is to represent leads and lags in between business cycles of the nations in order to improve nowcasting capability. Opinion surveys are proved to be extremely useful against this background. Weekly updates of euro location GDP are offered in real-time on the internet site euronowcast.com The last GDP price quote for 2022q4, calculated on October 28, stands at 0.2% (see Figure 1) and indicate a sharp downturn in euro area financial activity, in line with incredibly high inflationary pressures putting growth at danger.
Figure 2: Economic Weakness Index for the U.S.
Heiner Mikosch, with P. Kronenberg and S. Neuwirth (all ETH Zürich KOF), have actually a tool to track economic financial in many various European countries nations alternative data sets and various econometric modelsDesigns Remarkably all the nowcasting estimate stemming from all the numerous designs are available in a transparent method to users, making that each user can focus on its favourite design.
Figure 3: Current GDP growth nowcasts for 2022q4. Source: KOF, Nowcasting Lab.
The U.S. month-to-month retail trade index is one of the most watched financial indications by market individuals and financial experts as it reflects family intake, the most crucial component of U.S. GDP development. Scott Brave (Morning Consult) and associates from the Chicago Fed have actually developed a tool to track this index on a weekly basis: Chicago Fed Advance Retail Trade Summary (CARTS). The methodology counts on a mixed-frequency Dynamic Factor Model that includes both official information and high-frequency data from personal business that reflect credit and debit card deals, retail foot traffic, gas consumption or customer sentiment. Unfortunately, in April 2022 the Chicago Fed has momentarily stopped briefly the release of the CARTS index because of modifications in private information providers. The staff is presently dealing with a brand-new version to be quickly launched.
Gabriel Perez Quiros (Banco de España), joint with S. Delle Chiaie (ECB), question the usage of models that just contain high-frequency alternative data, as those information have a weak signal-to-noise ratio and usually do have a little sample size, leading to complicated evaluation treatments. By utilizing a simulation workout, they show that high-frequency alternative data alone lead to poor nowcasting efficiencies and an excellent technique for specialists would be to blend both high-frequency alternative information (i.e. day-to-day or weekly) and low-frequency official information (i.e. regular monthly or quarterly). Real-time estimation of this model points out its capability to effectively track U.S. economic activity including the most recent period.
This post composed by Laurent Ferrara.
Today, were happy to present a guest contribution by Laurent Ferrara (Teacher of Economics at Skema Service School and Board Member of the International Institute of Forecasters).
