Topics In Demand
Notification
New

No notification found.

There is no Corona Dip!
There is no Corona Dip!

July 6, 2020

7

0

Let’s talk about time series analysis and some of its more challenging aspects. Be careful with data right now. Look at it from various angles and re-think your own tools.

Ok, now that I have your attention.  Yes, of course there is a dip.  At ARC, we see that Q3 and Q4 will be the quarters hit the most, and we have published a series of reports for clients on Corona already.  Our research shows that for total automation we expect a dip somewhere around -15% to -20%, but this is highly dependent on the individual industries.  We will soon publish more reports for clients, so if you are a client, you can check here.

Corona dip

 

I actually want to use the current situation to talk a bit about time series analysis and some of its more challenging aspects.  Don’t worry, there will be no big theoretical discussion here, but I want to show you the implications, using the corona crisis as an example.

The chart shows ARC’s machinery based on 400+ publicly listed machinery builders, which are indexed using a Paasche Index to avoid jumps, when adding new data.

At ARC, we typically use seasonally adjusted data.  This has the advantage that smaller “jumps” are flattened, and we do not over-interpret certain findings.  Such as the “spike” we have in Q4 2019 or the dip in Q2 2019, while the market was more or less flat.  But now, in times of Corona Crisis, the seasonally adjusted line (blue) does not show any dip.  How can this be?

We use an optimized filter according to Baxter/King, which adopts along the time series, it can be considered as optimal, but it has challenges at the end of the time series, which is unfortunately the most interesting part of it.  At the end of the time series, the filter uses past data to calculate the current seasonally adjusted value.  But, in the past there was no corona!  We can use ARMA or ARIMA models to help us out here, but they also use past data to forecast the future.  And, in the past there was no corona!  So, we are at the beginning of a structural break, which cannot be smoothed or forecasted using past information or data, it does not work.

Corona dip

While this may sound nerdy, it has a very clear and simple implication (highlighted in red in first chart above):

  • Raw Data:                          Year over year: -4% and quarter of quarter -8%   Conclusion: CRISIS STARTS!
  • Seasonally Adjusted:       Year over year: -1.3% and quarter of quarter -0.2%           Conclusion: Nothing happens!

What does that mean?  Be careful with data right now.  Look at it from various angles and re-think your own tools in BI.  Worst case may be, as a strategist or manager, your tool may give you the wrong basis for decision making.

“Reprinted with permission, original blog was posted here”. You may also visit here for more such insights on the digital transformation of industry.

About ARC Advisory Group (www.arcweb.com): Founded in 1986, ARC Advisory Group is a Boston based leading technology research and advisory firm for industry and infrastructure.

For further information or to provide feedback on this article, please contact RPaira@arcweb.com

About the Author:

Florian Güldner

Florian’s focus areas are the discrete industries with a special focus on PLCs, AC drives, motion control, and discrete sensors.  At ARC, he specializes in economic modeling, time series and business cycle analysis, and forecasting.  He is also experienced in strategic marketing and mergers & acquisitions.  Florian’s experience in the automation industry includes Siemens and has a strong background in energy markets.  In particular, he worked for AREVA in Germany and the US, as well as for E.On Energy.


That the contents of third-party articles/blogs published here on the website, and the interpretation of all information in the article/blogs such as data, maps, numbers, opinions etc. displayed in the article/blogs and views or the opinions expressed within the content are solely of the author's; and do not reflect the opinions and beliefs of NASSCOM or its affiliates in any manner. NASSCOM does not take any liability w.r.t. content in any manner and will not be liable in any manner whatsoever for any kind of liability arising out of any act, error or omission. The contents of third-party article/blogs published, are provided solely as convenience; and the presence of these articles/blogs should not, under any circumstances, be considered as an endorsement of the contents by NASSCOM in any manner; and if you chose to access these articles/blogs , you do so at your own risk.


© Copyright nasscom. All Rights Reserved.