Spurious Claims of Voter Fraud

Because of the absolute blizzard of misinformation and flat out lies being currently spread, it is essential to share the facts with regard to Trump's dangerous, authoritarian, and undemocratic claims of voter fraud. I have done my best to provide my followers with accurate, factual, and up to date information, based on data and evidence during this entire process. It is disappointing that I even have to address this issue, but I apparently do. 

I grew up hearing spurious claims about "dead people voting" etc. I heard these claims my entire life, and I often believed them, without actually looking into the evidence for them. We need to understand what constitutes good evidence, and the ways in which claims like these should be tested. The fact that things like this are said on talk radio, is not proof that they are accurate and reliable. Since then, I have actually taken an interest in voting, polling, statistics, and the data science behind it. In all that work, I have found that the evidence for these claims, beyond simple claims and hearsay, is practically non-existent. It always was. 

After intense claims of voter fraud in 2016, Trump initiated an investigation and task force to look into all those claims, the so called "Voter Integrity Commission". Pence was in charge of this commission/task force. It concluded with no concrete evidence having been found or presented to the American public. https://apnews.com/article/f5f6a73b2af546ee97816bb35e82c18d The burden of proof continues to be on those claiming fraud, and our courts of law are the places where such evidence should be weighed and evaluated. 

As Lyle Schofield, a dedicated (and frankly extreme) Republican and Trump supporter wrote: "if [Trump] understood world history and geopolitical reality he is playing right into Russia, China, and Iran's hands by creating distrust in our form of government and the outcome of the election." https://www.facebook.com/lyle.schofield.7/posts/3586941988015270 Even he sees it. 

Romney recently responded to Trump's claims by pointing out that Trump "has a relatively relaxed relationship with the truth." https://twitter.com/CNNPolitics/status/1325448775595339779?s=04 

The American people are well aware of the fact that Trump often says whatever he wants, and thinks that if he says it often enough, people will think it's true. Only 39% of those who voted said that they thought that Trump was "honest and trustworthy". https://www.npr.org/2020/11/03/929478378/understanding-the-2020-electorate-ap-votecast-survey

Republicans USED to care about these geopolitical issues. The collateral damage to our democratic institutions and international standing may be irreparable.  

For this reason, there should be a high bar of evidence for such claims... A bar that Trump and his team are clearly not crossing.

The Court Battles, Evidence of Fraud: 

Litigation regarding which votes should be counted, and how they should be counted, is common in elections like this. That part at least is somewhat normal, even if the rhetoric around it this year is not. This litigation leaves a paper trail of actual, reliable, confirmed evidence. 

The best way to assess the strength of the claims of fraud is to simply look at the results and arguments on his ongoing court battles. Unlike at a press conference, in court you have to have (and present) factual evidence. Press conferences, social media, network news anchors, are all irrelevant. Simply read the court filings, and follow the rulings of the various judges. Remember, the courts are largely packed with Republican judges, they are NOT somehow biased against Trump. Even if you believe that the media is biased against Trump, the courts are not. 

He has every opportunity to get a fair hearing there. And yet, none of these cases are actually going well for Trump.

Even more telling, most of the cases don't even allege what they are falsely claiming in their press conference, because in a court of law, you can't simply make things up like you can in a press conference... you need actual evidence, and they apparently have none. If they did, they would be presenting it to the courts. And they are not. 

Here is a useful summary of the current state of the various court cases, both those that are finished, and those still in play: https://www.washingtonpost.com/politics/trump-election-irregularities-claims/2020/11/08/8f704e6c-2141-11eb-ba21-f2f001f0554b_story.html 

As Chris Christie (Republican) has repeatedly said, Trump should now provide concrete and court worthy EVIDENCE for voter fraud, or move on. "That's why, to me, I think it was so important early on to say to the president: If your basis for not conceding is that there was voter fraud, then show us. Show us, because if you can't show us we can't do this. We can't back you blindly without evidence." https://nj1015.com/christie-on-trump-provide-proof-of-election-fraud-or-just-move-on/

Republicans like Christie understand the incredible damage that will come to our democracy if Trump eventually concedes that the election was "stolen" rather than that he simply lost. 

If there is actual, concrete, and actionable evidence of fraud, it should be heard by the courts, and the vote counts corrected appropriately. But so far, none has been found. If any is found, I will be the first to call for the correction of the vote counts. 

The Red/Blue Mirage, Evidence for Fraud? 

Another very VERY essential point is that the most intuitive argument for fraud being put forward is that Trump was INCREDIBLY far ahead, and then fell behind as the slower mail in votes were counted. 

Here I can say something relatively concrete, because we are back in my area of expertise (polling, uncertainty quantification, and data analysis). 

Before the election began, I pointed out that this year we should expect wild swings depending on when each state counted the different TYPES of votes. I reminded people of this on November 3rt, ad 8:33pm Mountain:

"Reminder, we expect a late red shift in Arizona, but a blue shift in Wisconsin, Michigan, and Pennsylvania... The difference has to do with whether mail-in votes are counted and reported first... or after..." https://www.facebook.com/jlcarroll/posts/10160290376544018: 

We knew this going in. For example, Ohio looked VERY good for Biden, but then swung hard towards Trump. Why? Because Ohio counted the mail in ballots first BEFORE election night even began.

Pennsylvania wanted to do the same, but they were blocked from doing this, and could not begin processing mail in ballots until election night. The result was that in person votes were reported FIRST, while mail in votes were counted second. 

Here's what the AP Votecast "alternative" to exit polls shows about mail in voting:

​

https://www.npr.org/2020/11/03/929478378/understanding-the-2020-electorate-ap-votecast-survey 

The reliability of exit polling this year, given the errors in the pre-election polls, and (more significantly for exit polls) the amount of mail in voting this year, is another topic of discussion that I hope to write about soon. 

But for now, it's enough to say that our best guess is that Biden won mail in voting by 36 points, more in other regions. This is not surprising given that one candidate discouraged his followers from voting by mail, and given that the COVID-19 outbreak has been politicized such that one party is more concerned about it than the other. 

I KNEW this late shift in counts was a likely thing, and I did my best to warn everyone before the election began. And yet, even I was confused about it twice during election night, once when I started to think that Biden had a shot at Ohio, and again when I started to think that Trump was more likely than Biden to win Pennsylvania. In both cases, I KNEW the late shift red in Ohio, and blue in Pennsylvania was coming, but I questioned whether it would be enough.  During the course of the election, I NEVER thought that Trump was the inevitable winner, but I did think he was up.

In contrast, fiveThirtyEight's conditional probability model (taking the called states into account) kept telling me that Biden was a large favorite to win Michigan and Wisconsin, and that Pennsylvania would be close. I should have trusted it more. It's also true that there were election experts who were looking at which types of votes were still out in Pennsylvania, and where those votes were from, who were telling me at the time that Biden was actually up in Pennsylvania the entire time, even when I was saying that Trump was likely a small favorite. This was simply a matter of lacking information on my part. In retrospect, I can look at the raw data, and see that a Biden victory in Pennsylvania was almost assured from very early on on election night. Trump was NEVER actually ahead there, given which votes were in, where they came from, and what kind they were.

The point of all of this is to say that there is no evidence of voter fraud in a late blue, or red shift in these states. It was expected, we understand the mechanism, and it is not at all surprising, or nefarious.

The math simply doesn't support that claim, so if there is actual evidence of fraud, it will need to come from another source... But as I said above, so far, the court battles haven't provided it. 

COVID-19 Daily Updates Moved:

New Blog for COVID-19 Daily Updates:

I have been posting my daily COVID-19 updates here, on my personal blog. But it now makes sense for this to have its own space. So I will be posting all future daily updates there. If you have been following me here for those updates, I recommend subscribing over there: 

https://covid-19watch.blogspot.com/

COVID-19 Daily Update for Yesterday, Sunday, 8/30/2020

World Wide Trends, How Many People Have Been or Currently Are Infected? 

There have now been 25,417,886 confirmed cases of COVID-19 world wide.  That's 0.33% of the world population. According to WorldOMeter, 6,840,933 of those cases are "active". However, as we discussed in the last update, WorldOMeter's recovery estimate is too low. I estimate that there are currently 4,395,451 confirmed cases that are still "active'. 

However, how many people have actually been infected? Many people who are infected are never tested, and never become a "confirmed" case. 

One way to estimate infections that I have used before, is to use the number of deaths, and the range of possible infection fatality rates to get a range of possible true infections (and assuming an average 20 day lag between infection and death).

This estimate will only be as good as the approximations to the Infection Fatality Rate (IFR), and the reliability of the death data used. I am currently using the range of IFR estimates given by the CDC. 

If we apply this to the World-Wide data, these are the results: 

We can see that the number of true infections inferred in this way is significantly larger than the number of confirmed infections. But it's also worth pointing out that this is possibly an under estimate, because it is highly likely that the true death tole world wide is under-reported, especially in less developed regions. 

We can then apply the same formula we used last week for estimating recoveries to turn the cumulative number infected into an estimate of the number of active cases, those currently infected: 

By this estimate somewhere between 0.15% and 0.3% of the world's population are currently infected with SARS-CoV-2, the virus that causes COVID-19. 

Both of these estimates seem unreasonably low. Certainly it is significantly lower than we see in Europe or the US (although the US should hardly be held up as a model of success). Certainly a large portion of the world's population live in China, and they have done remarkably well at limiting the virus' spread. 

Nevertheless, it seems likely to me that the true death tole from COVID-19 is significantly under-reported world wide. 

Deaths By Day, Estimating the Reporting Lag from Florida:

It can be very helpful when locations report either cases by date of symptom onset, or deaths by date of death, rather than by the date the case or death was reported/recorded. This can give us a better idea of the true shape of the curve... but it also has a lag to it, that always makes it look like cases/deaths are going down while we wait for these cases/deaths to be reported. 

When modeling this lag, it's important to have good data on what the lag has been historically. For Florida, there is an excellent archive of historical information showing how the data has come in over time, available here: 

https://github.com/mbevand/florida-covid19-deaths-by-day 

This is what that delay looks like for Florida: 

The proposed fit is 1-e^(-0.1513x).

COVID-19 Daily Update for Yesterday, Friday, 8/28/2020

World Wide Trends, Updated Methodology:

I have been using WorldOMeter to get world wide recovery data. They had the best estimates, because many places simply don't report recoveries, and in that case, WorldOMeter seemed to be estimating them. 

Sometimes. 

But after staring at this figure for weeks now, I'm coming to the conclusion that they are missing a lot of recoveries. 

It's been over a month since peak cases back in mid July, but the recoveries have not yet caught up. But they should have by now. And if this was wrong, it would be impacting everything I did with global trends... the % growth rate, doubling times, etc.

So just as a sanity check, I implemented a common "recovery estimation" algorithm (used for a while by Texas). That is, I took the number of cases-deaths, and I assumed that 80% of those will have a mild case, and will recover in 14 days, while 20% of those will have a more severe case and recover in 32 days. 

(Note, I am not looking for "long haulers" who seem to have a lingering immune over-reaction that persists and causes sometimes debilitating problems long aver the virus itself has left their system. Rather, I am looking for the number of people who have cleared the virus and are therefore no longer contagious, regardless of long term impacts.) 

As you can see, this approach paints a far more optimistic picture of what is happening. I also think that it is more likely to be correct. 

If we use these estimates of recoveries to estimate the daily change in active cases, we get the following: 

Again we see that my estimates look very different from those of WorldOMeter, and, they paint a much more optimistic picture of what is happening. Right now, my estimate shows that the number of active cases is declining (the change is below 0) while WoM's estimate for recoveries has the number of active infections still growing (above 0).

If we use these new recovery estimates to calculate the % growth (in active cases) this is the result: 

And if we zoom in on the y axis we see that the trend has been a negative % growth for just over a week: 

I highly suspect that right now more people are recovering each day than are being newly infected each day. Which we would not suspect if we just naively used WoM's recovery data.

Some good news. 

CODID-19 Daily Update for Yesterday, Thursday, 8/27/2020

World Wide Trends in Brief:

The world wide daily change in new cases now appears to be roughly flat in both the 7 and the 14 day averages: 

The reason for this can be seen in the daily cases and recoveries chart below: 

However, since the daily cases are also in VERY gradual decline, eventually the daily recoveries should catch up, and the daily change in active cases should go negative. Unless there is a new increase in the number of daily cases.

Second Wave Watch:

For the last month we have been watching three countries that initially did very well in responding to the virus, namely South Korea, New Zealand, and China. They each used a different approach, but all three initially succeeded in handling the pandemic in a way that most of the rest of the world has failed to do. New Zealand even completely eliminated all local transmission for over 100 days, and completely reopened. 

However, near the end of July/start of August, all three have seen a second resurgence of cases. It will be important to watch and see if they are capable of controlling the virus again, if so, it will demonstrate that their initial success was not a 'fluke', and that it was something the rest of us COULD have done, had we chosen to. 

Cases in South Korea are still rising. Their contact tracing system has yet to catch up with the viral spread. Nevertheless, most countries would be ecstatic if they could keep cases below 400/day. Whether this remains a "success" will depend on whether cases continue to climb. 

Cases in New Zealand appear to be declining. Their response to this failure at their boarder which allowed the virus back in has been phenomenal so far. If this continues, it seems likely that New Zealand will soon be virus free again, and can again reopen. 

When they do, they will show the world that the best response both economically and from the perspective of public health is to "go early, and go hard."

China is also seeing a steep decline in the number of daily cases, which is now well below 100/day. 

While their authoritarian tactics are neither desirable nor something we would want to emulate, they are a second case study demonstrating that local lockdowns coupled with contact tracing can successfully eliminate viral spread, and keep the rest of the country open, and thus minimizing economic impact. 

And New Zealand demonstrates that this can be done without the authoritarian overtones. 

The US's halfhearted response, with a "lockdown" that never actually locked things down, is the absolute worst of both worlds, with extreme economic impact, but without any meaningful control of the virus. 

COVID-19 Daily Update for Yesterday, 8/26/2020

Automation Update, Available Figures:

I am now automatically generating several figures each day and pushing them to an online "git" repository. I have had two volunteers offer to work on creating a web page that will provide a more useful interface to the figures/data. But for now, you can browse the figures with this link. 

There are several things available so far. 

First, I am running the rt.live algorithm on the US as a whole (which they don't do). There are some good reasons they don't do that (the US is a diverse place, and some areas are doing better than others). But for those interested in what their algorithm has to say about the US as a whole, I now provide that visual updated every day.

As I have previously discussed, I disagree with the conclusions of rt.live's algorithm. I believe they are FAR too aggressive in adjusting for testing rates, which causes them to assume that the first peak(in April) was much higher than the second (in July). I believe they were of roughly the same size. So I hope to eventually provide a modified version of this analysis that more accurately adjusts for testing rates. 

We are providing tests and cases for each state. As an example, here's New Mexico: 

For these figures, the scale is set such that the tests are at a scale 10 times that of the cases, therefore, if the cases are above the tests in the figure, then the percent of tests that are positive is over the danger zone of 10%. The goal is to keep the cases (orange line) well below the tests (blue line).

 

And finally, we are providing the % of tests that are positive information directly in its own figure. As an example, here is New Mexico again: 

Again, the goal is to keep the % positive rate below the danger zone of 10%. 

Because I am now producing these figures for each state every day, you can check your own state, without waiting for me to do one of my "daily updates" on the state you care about. 

This is all a work in progress, so hopefully the user interface for viewing all this data will improve substantially in the future. 

COVID-19 Daily Update for Yesterday, Tuesday, 8/25/2020

Is it Signal, or Is it Noise? (World Wide Trends Update)

We discussed these two charts a few days ago. But here's the update: 

The question at the time was whether the seeming uptick in the 7 day average of the daily change in new cases seen in the 7 day average was signal or noise, given that the 14 day average was still going down. 

As of today, the 14 day average is also going up. So for now at least, it appears that this metric is getting worse. 

However, it appears that much of this is driven by the change in recovery rates. The number of daily new cases appears to be slowly declining:

First Confirmed Case of Reinfection (Is that as Scary as it Sounds?): 

The first truly confirmed case of reinfection has now been reported from Hong Kong. Previous reports of reinfection may have been due to false positives, or to a test picking up on dead viral material, or from a resurgence of the previous infection. 

However, in this case, we know it's real. The RNA of the virus was sequenced from both infections, and it is clear that the second infection was both real, and different from the first. 

I have seen quite a few news stories, and/or posts on social media with people freaking out. 

What does this really mean? And should we be panicking? 

First, it doesn't mean that the virus has mutated enough to reinfect people. The mutations were enough to use RNA tests to show this was a different strain, but we have been tracking mutations of the virus, and using those to track the family tree of the pandemic from the start. There is no evidence (yet) that the virus is mutating in ways that help it to avoid immunity (like the flu does).

Instead, it would appear that the man's natural immunity simply decreased to the point where he could be reinfected. This is how most other corona viruses (like the corona virus versions of the common cold) end up re-infecting us. Meaning this was expected. The reinfection took place after four and a half months from the time of initial infection, meaning immunity likely lasts at least that long, and most likely longer on average, since this was the FIRST confirmed case like this so far. 

That we lasted this long is GOOD news. 

What is even more exciting was that his second case was completely asymptomatic. Meaning, that his immunity wasn't actually gone. While it didn't prevent him from being reinfected, it DID prevent him from getting ill with ANY symptoms the second time through. 

This is also good news, this is VERY good news. 

We also know that many of the vaccines currently in development appear to be producing a stronger, and longer lasting immune response than the disease itself. 

While this does mean that natural herd immunity is a losing strategy, we already knew that. By the time we could conceivably anything close to herd immunity levels of population immunity... that immunity would be going away for many, and things would just start over. Although the disease would likely be less deadly to may the second time around, this would make it impossible to prevent the elderly and/or vulnerable from catching the disease at least once, and that would mean an unacceptably large death tole. 

However, with a vaccine, things look very different. 

While this case of reinfection may mean that we will need a booster at 6 months, it does not mean that a vaccine would not work. And, with a vaccine, we could actually reach (and maintain) herd immunity levels such that we could allow people who are elderly and/or vulnerable to go back out into society with minimal risk of getting infected. 

The news articles sound scary... but I believe that this isn't actually bad news. 

COVID-19 Daily Update: Automation Progress Update:

Today is a model discussion day. I will give a pandemic status update tomorrow. 

I have been working recently on automating the process of gathering data every morning. Frankly, I'm surprised it took me this long. 

Previously I had been moving data to my spreadsheet from various sources by hand. For those interested, here's a link to my spreadsheet, with all my old data. 

As nice as it was to have all the data (and figures) in one place, where everyone could look at it, and intuitively see how I did any calculation... as I began to track (and correlate) a larger set of data, this became unwieldy, and simply took too much of my time. 

I spent yesterday and this morning writing python code to automate this process. 

For those interested, the code is available on github: https://github.com/jlc42/JLC-COVID-19-Tools

This is a very preliminary work in progress. Currently, it has scripts to gather data which I ca run each day. I still need to write some code to automatically parse some of the web pages I scrape. But at least the data is saved. (Some date, notably from Georgia and Texas goes away if you don't scrape it daily. Some of that data is saved each day by CovidTracking, but other bits are simply lost if I don't scrape it myself daily, namely the testing data on antigen tests or serology tests. Texas puts that in their spreadsheet, but only has the "daily" value for the antigen and serology tests there... so yesterday's numbers are 'wiped out' by tomorrow's numbers.)

I can now put that on a chron job, and have it run every night while I am sleeping, and the data will all be saved. 

Next I need to write some code to go through all the saved data, and organize it into the useful fields I track... that's a larger task, that will take a LOT of time. For NOW, I have it pulling down (and organizing) the US state data from CovidDTracking... and then building a single plot... 

So... after two days of work... drum roll please.... here's my single plot, automatically generated for me this morning: 

And there it is, in all its glory. Here's the same figure plotted from my spreadsheet: 

I happen to think the scripted python version looks better. 

Side note: things ARE improving in New Mexico, yes Tests are down along with cases, but that is because the DEMAND for tests is falling, as true infections fall... you can tell because the % of the tests that are positive is also falling. 

Back to automation... 

This single figure may not look like much, HOWEVER, with a simple loop, tomorrow I will be ready to produce this figure for EVERY state in the US. 

And with a little bit of additional work, some parsing and gathering of data from my other sources, combined into a single data-file, I will be able to do this for every country as well. 

The case data and testing data is already available from other sources, but the next step will be to do some of the unique calculations I sometimes do, like my estimates of the % infected, and % currently infected, etc. And that's where the real potential lies. At that point, I may want to think about hosting this somewhere where people can see updated estimates for all these quantities for whatever location they are in. 

COVID-19 Daily Update for Yesterday, Sunday, 8/23/2020:

World Wide Trends in Brief: 

In today's installment of "is it signal or is it noise", let's look at the World Wide daily change in the number of active cases. 

Active Cases are defined as the number of cases - number recovered. So the daily change in active cases, is the number of new cases that day, minus the number of people who have recovered that day. In other words, it's the orange line, minus the green line below:

When it's positive (when the orange line is above the green line) the number of active cases world wide are growing. When it's negative (when the green line is above the orange line) the number of active cases world wide is shrinking. 

When we plot that difference, we see that with a 7 day trend, the daily change in the number of active cases shrank for a while, but is now starting to grow again: 

However, with a 14 day average, the daily change in the number of active cases is still smoothly falling:

Remember that even if this line is heading downward, as long as it is positive, things are getting worse. It needs to be negative before things are getting better. That being said, are things getting worse at a decreasing rate (14 day average)? Or... are things starting to get worse at an accelerating rate (7 day average)? 

This question (is it signal, or is it noise) is one of the KEY questions of statistics. And it is not at all easy to answer. 

Given that there are strong "weekend" effects, we know we should be taking moving averages of the data in increments of 7. (With less than that you start to see weekly fluctuations that make the interpretation even more difficult). However, a 7 day average is potentially too small of a chunk, and it can be impacted by noise which makes you think you are seeing a new "trend" when you aren't. However, the 14 day average is too large, because it can hide trends that are, in fact, real, and you have to wait at least two weeks to be sure that something real has changed. Neither is ideal... and I would prefer something like a 10 day average. But the weekend effects make that even more problematic than either the 7 or the 14 day averages. 

This is a BAD idea, but I will show you what it looks like anyway: 

It is POSSIBLE that the right thing to do would be to create a complicated model of the weekend effect, then take it out of the data, correcting for it... then take a 10 day average, and see what the trend says. But the strength of the weekend effect depends on which country is reporting the most cases at the time (some have a stronger weekend effect than others) so correcting for this is a moving target! It's potentially impossible to really get right. 

So instead... we are just going to have to wait... watch... and see where this trend goes in the next week or so. 

Did I mention that I hate waiting?

via GIPHY

COVID-19 Daily Update for Yesterday, Thursday, 8/20/2020:

World Wide Trends in Brief:

Major world wide trends from my last update are largely continuing. 

Percent daily growth in active cases has been falling, but is now holding at around 0.25%/day:

There have been two days with large outlier reporting spikes that make interpreting the daily deaths difficult, but the trend seems to be down since late July:

Compilation of Data Sources: 

I am in the process of compiling some of the best computer readable data sources for COVID-19 modeling out there. This is a work in progress, but for those interested, here's a link to the document which will likely grow through time. Eventually I hope to wrote code to auto-scrape many of these resources, and I will provide a link to that code once it's available. 

If you are aware of a good data source that I have missed, leave it in the comments here, or feel free to send me an email, or yell at me on FB or Twitter. 

Mis: 

I apologize that today's update is short, I have both a paper deadline, and a deadline for a presentation both due tonight. 

Data: https://docs.google.com/spreadsheets/d/1qVOdkuQ1IQb8McLNoe3oiSrnU1gVj7X916dvpyZ-zZY/edit#gid=0 

COVID-19 Daily Update for Yesterday, Wednesday, 8/19/2020:

Yesterday's update was a "model talk" discussion about problems with rt.live's approach to estimating Rt.

Today is a more traditional status update. 

World Wide Trends in Brief: 

World wide we are starting to see minor signs of improvement. 

Daily cases peaked at the end of July, and have been falling VERY slowly since then. Because recoveries lag, they have continued to climb over the same period:

However, the number of new infections is still larger than the number of new recoveries, which means that the change in the number of active cases is still positive, meaning that more people are sick today than yesterday. But that trend has been moving down over time:

For the world to recover, this trend needs to be negative, and then stay negative. But there are still signs of improvement. 

We can also see improvement in the daily deaths, which have also been trending down since the end of July: 

Can it be Done, Watching China, New Zealand, and South Korea:

We have been especially watching three countries: China, South Korea, and New Zealand to see if their strategies for dealing with the virus is viable. China used a totalitarian lockdown, South Korea used extensive contact tracing with only minor restrictions, and New Zealand "went hard and went early" (without China's totalitarian bent) to stamp out all local transmission before reopening completely. 

All three were initially successful. All three are now facing local outbreaks that are challenging their strategies. If we wanted to prove to the rest of the world that there were alternatives to our failed approaches, these are some important places to watch. 

China's approach of local lockdowns of the affected regions appears to be working: 

New Zealand's second lockdown with contact tracing also now appears to be producing improvements:  

South Korea is still struggling to get its most recent Fundamentalist Church Based outbreak back under control. But they did it once. Now we need to see if they can do it again. It's currently too soon to tell: 

Source, Data, and Graphs:

https://docs.google.com/spreadsheets/d/1qVOdkuQ1IQb8McLNoe3oiSrnU1gVj7X916dvpyZ-zZY/edit#gid=737858658

COVID 19 MODEL TALK, RT.LIVE IS WRONG:

I've been doing daily COVID-19 updates on facebook for a while now, and decided to move them to my blog. 

Today is a statistics and modeling thing, so if that is not your "thing" I promise to do a "status update" tomorrow. And I'll start putting in the title which I am doing each day. 

So... rt.live is wrong: 

https://rt.live runs their algorithm on individual states, but never gives an average for the entire USA. It makes sense that they might not choose to do this, the outbreak in the US is quite diverse, and differs from place to place. But I think it's still a good idea to get the average over-all picture. 

Now that I have their code running on my local machine, I modified the code to run on the average for the US. The first two figures show my results. Remember, this is rt.live's algorithm, but run on data they don't normally show. 

The current estimate of Rt for the US is 0.96, with 80% intervals of 0.73 - 1.13. That seems reasonable. 

HOWEVER, their adjustment for testing rates is VERY aggressive. They estimate that cases were more than TWICE as high in April's peak as they were in July's second peak. 

I don't believe this is right. And if they get the case adjustment wrong, they will get their estimate of Rt wrong in general. I suspect that their CURRENT Rt is right, but their RT back in July is FAR too low. 

If you ONLY look at the daily death curve, you might suspect something like what rt.live is saying. BUT, if you look at the hospitalization curve, it is obvious that this isn't right. 

Instead... the case fatality rate has to be dropping. And that means that the second peak has to be at least as high as the first. I used to claim that the first was larger, because more people were being turned away at the hospitals, but after a conversation with  Youyang Gu over on twitter, I have changed my mind... a falling average age of infection means a lower fatality rate, but ALSO a lower hospitalization rate. And THAT would imply that the second peak should be LARGER than the first! 

Rt.live's second peak is not only not as large or larger than the first, it's MUCH smaller! This just CAN'T be correct. And that means that EVERYTHING else they are doing is also wrong. 

The last figure shows the range of ways that the case data (in blue) can be adjusted for tests. The red curve is Youyang Gu's adjustment (with the second peak much higher than the first). The Yellow curve is my adjustment, with the two peaks roughly equal in size based on the hospitalization data. (I now believe that Youyang Gu's estimate is likely better than mine). The green curve is from rt.live. Not only is it an outlier... it makes NO sense. 

Conclusion: rt.live is wrong. The way they adjust cases for testing rates seems to be FAR too aggressive. For their curve to be right, the Infection Hospitalization Rate (IHR) would have to be RISING DRAMATICALLY, while the Infection Fatality Rate would have to be staying the same. 

The reality is that both the IFR and IHR should be falling as the median age of infection falls, while the IFR should be falling faster than the IHR as treatments improve. 

To get a good and reliable estimate of Rt, I'm going to need to re-write the part of their code that adjusts for testing rates. 

(Here's a link to Youyang Ug's discussion of how he adjusts for testing rates: https://covid19-projections.com/estimating-true-infections/)