October 25: The slow upward trend continues. Locally, Vienna continues to concern me.


Daily Status, October 25

Reminder:  any sections that are unchanged since yesterday are grayed out.  

I try to update this every day between 11:00 and 12:00.  However, my updates are based on when the Virginia Department of Health updates; it takes some time in analyze and collate the data.  In addition, because I my own health issues, there will be days when the update is late or does not happen.  

The one thing to remember is the day-to-day changes are minor. Any trend takes several days to identify, and I will be looking at the data daily (that is easy), but may not update the blog.

One thing that is immensely personal to me is I need to avoid COVID-19.  Like, I do not know my mortality risk exactly, but last week, I thought my Infection mortality rate was 5-10%.  With active cancer, that doubles, to 10-20%.  So if you see me in town, wear a  mask.  I try to avoid challenging people, but maybe it is time. If I can see your nostrils, you are not wearing it right.  If I can see a gap to your mouth, you are not wearing it right.  I try to avoid confrontation with these people, because it goes south quickly, but I will not support any business that allows other customers to but me at risk.

Situational Awareness

Big picture:  There is little doubt that the increase in cases viewed in the commonwealth is real.  This may be the beginning of the fall COVID-19 surge we were warned about.

Local: Doubling of the case load in Vienna in the last month.  Be careful and wear your mask.

Yesterday,the VDH has reported 999 new cases of COVID-19.  The data is was reported by VDH on October 25 2020 (based on data collected on October 25th by 5 PM) is slightly above  the three week bias-adjusted average of 868 cases  (the bias is based on day of the week reporting, and is computed from the data; bias adjusted average is the the three week average x the day of week bias). We had been seeing a caseload increase, but there is some indication that the trend has flattened though it could also be reporting issues; based on prior experience, I am inclined to suspect the latter..  Viewed over the last seven days, Virginia reported 7233 cases, or 1033 cases per day on which works out to 12.4 cases/100K people.  This is a welcome decrease over the last several day (early to mid October), but it is up from 9 cases per 100K from late September .  It is worth noting that there was a dip in hospitalizations that coincided with the September dip, leading me to believe the september dip reflected case count and not reporting issues.  Furthermore, if we subtract the effect of the college outbreaks, there was a constant decrease from just before August 1 to Sept 25.  By October 3, there was a measurable increase.  

The trends over the last three weeks, now are showing a modest increase, at 1.1%/per day or  8% per week.  

By combining our current regional trends with the typical reporting for the day of the week, I expect about 816 cases tomorrow (Monday) with a 90% chance of the numbers falling between  586 - 1183 cases.  If tomorrow's numbers differer from that, we are having a very rare event.  This is useful to consider if I am unable to report tomorrow, as you can compare the state reported numbers with this.

Regionally, all of the commonwealth are showing flat to positive case growth. The testing numbers now show the percent positive to essentially at the 5% metric over the last week (5.01%) that is often used to indicate sufficient testing (e.g., is is safe to reopen schools).    Virginia is testing about 2.8% of the population every two weeks, which is about 1/4th the number of tests desired for random sampling, but most of the Commonwealth's testing is driven by medical needs and not surveillance. Surveillance would ideally test at least 5% of the population per week but the testing is somewhat invasive.

On one other front, over the last week, we well above 10 cases per 100,000 to enter states like NY without quarantine -- we are at nearly 12.3 cases per 100K.  We will remain on the NY Quarantine list for at least 1 more week, and probably longer.

When we look at the local/ZIPCode data, we see that the observed increases are almost universal across the Virginia.  For comparison, I am comparing the current estimated % positive to that one month ago.  Note that almost all is a warmer color (further from blue and closer to yellow).  This is an indication of the uniformity of the increase.  As a practice matter, it means to be safe and careful; no matter where in Virginia you, there is risk.


One Month ago:


In the spring, COVID-19 in Virginia was primarily a concern in the DC suburbs.  Over a 3-4 weeks, in late may to early June, NOVA recovered, and for about a month, the disease was under control, to the point where the restrictions were eased.  Unfortunately, in eastern VA/Hampton Roads, the easing of restrictions results in a surge in cases,  which peaked just before August 1 (and resulted in stricter restrictions in that area).  Since then, the the exception of growth on college campus, the disease has been stable, except for the rural parts of the state, where safeguards (social distancing and masks) are largely ignored.  Starting in October, our weekly case count has been increasing throughout the commonwealth, but particularly in NOVA, NWVA and SWVA and Central VA. 

Looking at the weekly case count, we see that the case numbers are more in line where we were at the beginning of August.  The numbers across the state are showing improvement, or stabilization mostly because SWVA, is showing less increase in the recent days -- though it is still increasing.
Regional growth rates are (in fraction per day) continue to to show degradation over three weeks.   It is worth noting that it is easier to show a decline when the prior numbers increased.

NOVA: 1.008- GMU

Central VA: 1.010--  VCU

Hampton Roads/Eastern VA:  1.001 -- W&M, CNU & ODU

SW VA:  1.022-- VT & Radford

NW VA:  0.991-- JMU & UVA

The state as a whole is is increasing with Rt=1.011

The following table shows the number per 100k for each region. Again, NOVA and Eastern VA are doing the best, and the mountainous regions in NW & SW continue having more cases.   The concerning aspect is in all regions, the numbers for last week are significantly higher than the prior 3 weeks.  What is most concerning is SW &NW VA, where it is hitting very high numbers, in spite of VT and Radford doing better.

Daily Cases/100,000 


Last month

Last week
















The following charts are for the 5 regions. in the chart that shows all regions,  The individual line charts show the unfiltered data per day, coupled with the trend lines.  The trend lines show the different periods of growth.    Early in the pandemic, the different parts of Virginia were functioning largely independently, with NOVA mimicking the northern states, and Hampton Roads mimicking the southern states. But, since September 1, the regions have trended with each other.  Starting in late Sept., NoVA and SWVA diverged from the rest of the state, a trend that continues today.

It is also critical to note that, currently SWVA has the most number of cases, even though they have 1/2 the population of Northern VA.  

Note that the effects at both ends of the chart are probably an artifact of the 7-day polynomial filtering I use.  For those not inclined, it means it does a bad job at the beginning and end of the data.  

For those technically inclined, the filter is called a Savitzky-Golay filter, basically is a moving window polynomial filter.  At the edge (first and last days of the time series), the filter will over compensate for the trend as it is unconstrained.  I recommend the Wikipedia article if anyone is interested in more information, or contact me.

Local/Northern VA:

After the early peak in May (~1000 cases per day), NOVA saw a sharp drop in all COVID metrics, reaching a broad valley in mid June(~200 cases/dat), which lasted until around August 1, when by Sept 1, we increased back to around three hundred. September showed notable caseload drops to about 150 by late in the month. Since then, we have have a steady increase to on average of about 250+ per day.


Currently, most jurisdictions are increasing, though slowly:

Fairfax Co.: 1.013
Arlington Co.: 1.022
City of Alexandria: 1.008
Prince William Co.: 1.001
Loudoun Co.: 1.006

The number above is Rt:  Rt is an exponential time constant, where the number of cases in a time segment is approximately, n=Ao Rt ^ t, where Ao is the number of cases at the start of the segment, Rt is the exponential growth rate, and t is the number of days since the start of the segment.  So, if Rt is greater than 1, it is growing exponentially, if it is less than one, it is decreasing each day.  \

Another way to look at it, todays number are approximately the growth rate times yesterday's numbers.  This is the exponential time constant.  Fortunately, the time constants are below 1 and our rate of cases is about 6/100,000 per day.  Ideally, we would be 0, but 6 is much better than our peak in which was around 30/100000K. 

Looking at the trends, the strong downward trend in daily case count we observed since around Sept. 1, has ended.  We now see significant jump in cases in every jurisdiction. The cause of that is unknown, but may relate to the cooler weather.  

The contrast in the Northern Virginia map is increasing. In addition the overall map is warming (as is happening throughout the commonwealth).  At this point, it seems likely that this is related to the fall surge others had predicted.

Most localities in Northern VA are case counts near or above 10/100K/day.  In Vienna, for example, a for a while, we were under 5 in late September, but are now at 9.1/100K/day.


Last month

Last week

Growth rate (%/day)

Fairfax Co









 So. Alexandria








 Annandale/Fall Church









 No. Arlington




 So. Arlington








Recently, the trends show two groups of rates for Fairfax county:  McLean is doing better better, and everywhere else is tightly grouped at a higher number.  It is worth noting that almost every region is seeing small upticks in the last few weeks. 

At the local level in Vienna, we see are seeing a very concerning trend October: the average daily case count has doubled.  I do not why; I have not been out and about.  I do know that youth sports are active (though I no reason to expect that is causing the increase).  

Local Safety/Risk

I am attempting a different means of discussing risk.  Risk is a very personal item.  Different people will respond to COVID differently.  However, we know how many people have died (and how many cases) for each age group in Virginia.  So, we can get a case fatality rate for age groups.  Also, based on serology studies, we know the case numbers are low by a factor of 2.4, so we can get a infection fatality rate (IFR).  We also know how comorbidities play in. 

So in the following tables, I have combined the current probability of person being infected around Vienna to compute the probability that a person in a specific crown is infected.  

Next, assuming one interacts with everyone in the crowd (big assumption), I assume if you interact with an infected person, you have a 50% chance of getting infected.  I do not know what that rate is:  it will be a function of how long you interact, how close, and if masks were used, etc.  This is the big unknown.

That gives me a probability of being infected based on the number of interactions.  I then combine that with the IFR to estimate the risk of dying by age and number of interactions for people with and without co-morbidities.  

For comparison, the risk of dying in a car accident in a given day is about 3 in 1 million. (3.1e-6).  That is a baseline as I know few people that will not get in a car because of the risk of dying.

No Co-morbidities
#exposure        0-9      10-19      20-29      30-39      40-49      50-59      60-69      70-79        80+ 
         1   0.00e+00   3.24e-08   2.59e-07   1.10e-06   2.95e-06   8.16e-06   1.85e-05   2.95e-05   5.53e-05 
         5   0.00e+00   1.62e-07   1.29e-06   5.49e-06   1.47e-05   4.07e-05   9.23e-05   1.47e-04   2.76e-04 
        15   0.00e+00   4.82e-07   3.86e-06   1.64e-05   4.39e-05   1.21e-04   2.75e-04   4.39e-04   8.22e-04 
        50   0.00e+00   1.57e-06   1.26e-05   5.35e-05   1.43e-04   3.97e-04   8.99e-04   1.44e-03   2.69e-03 
       100   0.00e+00   3.06e-06   2.45e-05   1.04e-04   2.78e-04   7.71e-04   1.75e-03   2.79e-03   5.22e-03 
       500   0.00e+00   1.23e-05   9.82e-05   4.17e-04   1.12e-03   3.09e-03   7.01e-03   1.12e-02   2.09e-02 
      1000   0.00e+00   1.91e-05   1.53e-04   6.50e-04   1.74e-03   4.82e-03   1.09e-02   1.74e-02   3.26e-02 
      2000   0.00e+00   2.51e-05   2.00e-04   8.52e-04   2.28e-03   6.32e-03   1.43e-02   2.29e-02   4.28e-02 

#exposure        0-9      10-19      20-29      30-39      40-49      50-59      60-69      70-79        80+ 
         1   0.00e+00   3.24e-07   2.59e-06   1.10e-05   2.36e-05   4.08e-05   5.55e-05   5.91e-05   1.11e-04 
         5   0.00e+00   1.62e-06   1.29e-05   5.49e-05   1.18e-04   2.04e-04   2.77e-04   2.95e-04   5.51e-04 
        15   0.00e+00   4.82e-06   3.86e-05   1.64e-04   3.51e-04   6.07e-04   8.26e-04   8.79e-04   1.64e-03 
        50   0.00e+00   1.57e-05   1.26e-04   5.35e-04   1.15e-03   1.98e-03   2.70e-03   2.87e-03   5.37e-03 
       100   0.00e+00   3.06e-05   2.45e-04   1.04e-03   2.23e-03   3.85e-03   5.24e-03   5.58e-03   1.04e-02 
       500   0.00e+00   1.23e-04   9.82e-04   4.17e-03   8.93e-03   1.55e-02   2.10e-02   2.24e-02   4.19e-02 
      1000   0.00e+00   1.91e-04   1.53e-03   6.50e-03   1.39e-02   2.41e-02   3.27e-02   3.49e-02   6.52e-02 
      2000   0.00e+00   2.51e-04   2.00e-03   8.52e-03   1.82e-02   3.16e-02   4.29e-02   4.57e-02   8.55e-02 

Age Distribution: 

I am not updating this section, except for the charts.  I will leave it present for a while longer, as at times, it can be very interesting.  In particular, when speific age groups to not follow other groups, it is an indication of something interest.  For example, teens and 20 somethings surged in early sept while the other age groups did not -- that was the outbreaks at colleges.

As expected, there was an increase in cases among Middle Aged (and young adults) delayed from when the JMU students returned home.  There are about about 150 cases from the JMU students. We are now back to the baseline number for that age group.  The JMU students infected their parents, resulting in an increase of The concern is that the JMU students will infect their families, and we saw an uptick in the middle aged population, which has since recovered; about 50-100 extra people were infected, which was less than I expected.

Note, I will talk about the age distribution in college communities under "college communities


Overview:  Things are improving at most colleges.  I have added the Lexington VA colleges (VMI/Washington and Lee) to the discussion.  My data mining by zip code requires I group them together, because they share a zip code.  Two schools have moved to good to watch:  CNU and ODU.

My process combines the VA Department of Health data and what is reported by the colleges.  The report is as of 11:00 ET.   I need to point out that the VDH cases may include cases not affiliated with the university as I am using geographic surveillance.  It is also worth noting that all assume that students feeling ill are going to health service; I have heard anecdotal reports of people not doing that because they did not want to quarantine.  The colleges usually update the dashboards after this post, or on Monday/Tuesdays.  Except for Radford, all weekly updates are complete at this time.  And the numbers are encouraging (except for UVA).

As the process has evolved, it was clear that I needed to show active cases (e.g., last 10 days) in addition to cumulative cases.

Also, I am assuming the colleges are promptly reporting there numbers to the Virginia Department of Health.  As it turns out, W&M is reporting the cases approximately 2 days after updating the dashboard.  It is probably a result of the phasing of the process.

Note: I have been tuning the following table to improve the estimated number of cases (the order of operations has changed a bit).  Also, I am adjusting the pre-student case olad:  to estimate the number of cases from students, I subtract out the average number of cases prior to the student arrivals from the reported cases.  If the numbers are large (UVA, VT, JMU & Radford), the impact is minimal.  This makes it harder, though, to identify cases in more urban settings, like ODU, VCU and CNU.

RED means there is clear evidence for community spread
YELLOW means there may be community spread; still ambiguous
GREEN means no evidence of community spread
BLACK means they went online.


% Positive


Last 10 days

Dashboard Cases

% that had COVID***

VDH Cases*



VDH Cases*



Va Tech
























































































* estimated from the number of cases in the zip codes associated with the university removing the pre-student arrival case rate
** estimated number of cases is an attempt to normalize for testing limitations. Specifically, I assume at 5% positive, 100% of the cases would be caught. so I normalize it to that value.  If the % positive is very high (>40%) I am likely overestimating the numbers.
*** Dashboard cases are only counted if I can find the dashboard.  In some cases, it is difficult to distinguish positive tests from cases (1 case may have multiple positive tests; that is mostly at VT).  I include active cases if reported, otherwise, I use total cases.
****% population uses the total reported number of students rather than just those on campus; it may be off when the percent positive is above >40%.
***** Old data, not updated for today.
****** Active cases, not total cases


Large Scale Community Spread:

Virginia Tech: Virginia Tech is finally getting a handle on COVID with only a few new cases a day.  Virginia Tech is more than a College...it is a football team.  And the football team has been decimated by COVID-19.  The real test is when VT can field a full team. On Sat, 10/17, they were down to 13 inactive players.  I may promote it to yellow.

W&L / VMIThere is clearly an outbreak occurring at these schools.  The numbers are low because the schools are small.  My surveillance approach is based on ZIPCodes, and they are in the same ZIPCode, so they are combined into a single entry.  This is just an artifact of how things are tracked, and not a judgement on either school.

Watch List:

JMUJMU returned to in-person class 10/5; here is their plan. So far so good with the return. The case count at JMU to rise, but slowly.  JMU has been fairly transparent with the situation, but could not get ahead of it initially.   As it stands now, case loads continue to smolder.  They are not increasing nor decreasing.  My one signficant concern is reporting:  there are a lot more cases in Harrisonburg than there are new cases at JMU.  This may be students failing to report, or it could be cases not associated with the university.  

CNU -- I am not really sure what is happening at CNU, because they are in a populated area, and their dashboard is not sufficient.  They are showing a significant increase in caseload.  I will be monitoring them more closely now.

ODU -- ODU is now showing a significant increase in the percent positive, which suggests there may not be a complete count.  But, the numbers remain relatively low for the size of the university.  It is difficult to track ODU because it is in a populated area and they only update the dashboard weekly.
UVAWith the students return, there has been a marked increase in cases.  Week over week.  It appears, that with the much stricter rule UVA imposed two weeks ago ago, the case load is abating.  As a Hokie, nothing saddens me more than having to move UVA on the watch list (down) before I do VT.  Oh well.  They still messed up COVID.  There is that.

RADFORDRadford was moved back upto the primarily because of the % positive.  Radford updates the dashboard once a week, which is not sufficient in my opinion, but fortunately they report to VDH regularly.  As such, the data on Radford's dashboard is now 7 days old.  While it is not how many students at Radford contracted COVID-19.  It would not surprise me to see enough that the community, when isolated effectively has herd immunity (meaning over 60-80% contracted COVID-19).  The only way to know would be antibody studies.  Hopefully, VDH will look into that.  But, currently, it seems that Radford has a manageable number of cases.  While only 57% of the cases in the last two months are attributed to students, there were so few cases prior to the students return, this means either the dashboard is undercounting, or there were a lot of non-students infected by students. 

Other schools:

William & Mary -- There is at least a small scale outbreak in the athletic department.  W&M tested all athletes, and stood down on athletics.  They had a total of 20 positives within the athletic program. However, W&M (and Williamsburg) has gone a full week without a positive case (and nearly 1000 tests).   Most of the active cases are among athletes. It is worth noting that W&M is quick to update the dashboard; they update prior to reporting the VDH.  W&M tested all students prior to arrival in town. With the current outbreak (albeit small), the college probably is a bigger threat to the town than the other way around, which is a reversal of the last several weeks

VCU seems to have the virus under control -- They have beaten back an outbreak, the % positive is good, and there are few new cases. It was promoted from RED to YELLOW. and now Green.  The numbers have shown no significant increase in the last several days; quarantine and isolation space is becoming more prevalent.   Being in an urban setting the zip-code and regional surveillance that works well at some of the other schools is not particularly helpful here.  So, I have to rely on the dashboard.   

UMW -- Nothing noteworthy.  A few cases but they just returned.  I am concerned because they did not test all students.

GMU -- Nothing noteworthy.  GMU tested all students.

College Communities:

When I started talking about communities, the  focus was on the safety for incoming students.  Unfortunately, that concept as changed.  Now, we are seeing the colleges impacting the surrounding communities.  If we look at the age distribution of cases in the communities of JMU, Radford and VT (New River, and Central Shenandoah health districts), we see that, starting about 4 week ago, number of cases for non-college age citizens is increasing -- about two weeks behind the college age curve.  This suggests the disease is infecting the general population.  So far, it looks like about an extra 372 middle aged and seniors have been infected were infected; we have gone from 12 cases to 24 cases per day in those groups.  Furthermore, in the 5 months from the beginning of the epidemic to early Sept, there was an average of 10 deaths per month; in the last 7 weeks there have been 35 deaths.  This is the concern, as the return of students has appeared to result in 21 extra deaths in the commonwealth today -- in just the New River and Central Shenandoah health districts.  Though none of the additional deaths were of student age.  This trend has been observed elsewhere in the country, where the college students infect the more vulnerable populations.


Since Donald Trump has been infected, or more accurately, with the infection of Trump, we have learned:
  1. People can test negative and still spread the disease.
  2. Even if everyone who interacts with you is tested immediately prior to the interaction, you can still get sick (see 1).
  3. If you have an event with hundreds of people, there is potential for it to be a super-spreader event, even if you test everyone at the event.
  4. If you do this frequently enough, you will get unlucky.
  5. A non-spaced, but outside event is still dangerous.
This has two impacts for us:  first, some of the attendees and support people live in our community. I have no information as to the impact this has had.   Second, we now know that any crowded situation is a potential spreading event, even if outside.  This includes sporting events, concerts, and worship.  Please think about this before planning activities.

There are safety concern with athletics, but those can be mitigated.  I am more concerned about the fans in the stands.

I have reason to believe about 100 or more of the last week's Virginia cases are a direct result of the combination of the Newport News Trump rally and the Whitehouse outbreak.  If we are placed back on the NY quarantine list, it is because of these political activities.  


1) You can repost / share in the entirety by forwarding the link, 2) If you want share partial content, you must receive my permission – I need to make sure you understand what I am saying. If anyone sees this work being used without attribution, please let me know as soon as possible. I am willing to have an informed discussion / debate on my approach, but I want to make sure the proper context is captured.


Source data is from the Virginia Dept of Health COVID Site

Why I did this:  About the blog
I have thoughts on the spread in college communities which can be seen here.  This is the same link at the top of the write-up.

Other Sites:  John's Hopkins

Kids can pass covid to parents: Pediatric SARS-CoV-2: Clinical Presentation, Infectivity, and Immune Responses

A fun video showing masks work, guy style:

How to wear a mask.

Politics:  Some lie.

Donald Trump yesterday said that without blue states, the death rate would be much better.  He needs to stop using alternate facts.  Red and blue are defined by who the state voted for in 2016.  47% of the deaths come from red states, which is about his percent of the popular vote.  But, more importantly, after June first, when states could use science to mitigate the virus, 65% of the deaths are from red states.  Facts matter.


  1. A couple of observations and questions on the analysis:
    1. Should the increase in cases be normalized to the increase in testing? Otherwise isn't the % increase in cases meaningless as a measure for rate of transmission.
    2. Risk is not personal, acceptance of risk is. I will agree the quantification of risk is specific to the individual.
    3. Most people don't make "risk" decisions which is a quantification of the occurrence of some phenomenon and its severity. Most people make uncertainty decisions based on ignorance, gut feel, or just what they want to do.
    4. I believe risk is additive, so to "compare" it to driving it not realistic because generally you don't make the decision to interact in public OR drive. You generally do both. So maybe a more accurate assessment would be to estimate the % increase of dying on any given day based on the overall risk of exposure to COVID and other activities throughout your day - such as walking on a busy street, climbing on ladders, driving (time and amount), lawn mowing, etc.
    5. Have you quantified the level of uncertainty in your calculations based on your assumptions made to establish # of exposures.

    1. 1) I did that early in the process, back until our testing positivity rate dropped below 5 %. If I put it back in it will impact the data primarily before July 1. After that, getting tested in va was not a problem with exceptions around college outbreaks.

      3) the risk is individual in stat every one has a different risk profile in terms out probable outcome from infection. I have a different risk than a healthy 56 yo, with probably 20-40x the mortality. My definition of rust is that of a bad outcome. I know there are other bad outcomes than death, but that has the best quantitative information

      3) absolutely agree. I am trying to give quantitative numbers to assess that risk.

      4). I have to think about this some more. But the issue is that there are a lot of non-linearities in the combinations.

      5) I do have uncertainties. I have addressed them in earlier posts. Communicating them is difficult. I do not have the time or energy to expand on that on a daily basis.

  2. David,
    Thank you for the reply! I am a risk management amateur, but do know that statistics don't often provide the final answer, just indications of where to direct our efforts to discover causality. In the interim they can help us to make marginally better decisions and mitigate point #3. We must always track the results of our decisions, question our assumptions, check the data, and re-run the calculations. Your blog really helps in this process! Thank you for the personal time you spend in this quests for the better answers. The starting point - when we are born, we all have a 100% chance of death. Our lives are a struggle in managing this probability, until it returns to 100% - instantly or hopefully over decades.


Post a Comment

Popular posts from this blog

Daily Status, August 29

Daily Status, Nov 8: Every trend I was tracking 10 days ago remains. Which is not good.

October 24: Vienna is not doing well, Virginia is not doing well, the USA is not doing well (but I will not talk about the latter)