choropleth – Page 3 – Coffee Spoons

Choose Your Own FiveThirtyEight Adventure

In case you weren’t aware, the US election is in less than a week, five days. I had written a long list of issues on the ballot, but it kept getting longer and longer so I cut it. Suffice it to say, Americans are voting on a lot of issues this year. But a US presidential election is not like many other countries’ elections in that we use the Electoral College.

For my non-American readers, the Electoral College, very briefly, was created by the country’s founding fathers (Washington, Jefferson, Adams, Franklin, et al.) to do two things. One, restrict selection of the American president to a class of individuals who theoretically had a broader/deeper understanding of the issues—but who also had vested interests in the outcome. The founders did not intend for the American people to elect the president. The second feature of the Electoral College was to prevent the largest states from dominating smaller states in elections. Why else would Delaware and Rhode Island surrender their sovereignty to join the new United States if Virginia, Pennsylvania, and New York make all the decisions? (The founders went a step further and added the infamous 3/5 clause, but that’s another post.)

So Americans don’t elect the president directly and larger states like California, New York, and Texas, have slightly less impact than smaller states like Wyoming, Vermont, and Delaware. Each state is allotted a number of Electoral College votes and the key is to reach 270. (Maybe another time I’ll get into the details of what happens in a 269–269 tie.) Many Americans are probably familiar with sites like 270 To Win, where you can determine the outcome of the election by saying who won each state. But, even though the US election is really 50 different state elections, common threads and themes run through all those states and if one candidate or another wins one state, it makes winning or losing other states more or less likely. FiveThirtyEight released a piece that attempts to link those probabilities and help reveal how decisions voters in one state make may reflect on how other voters decide.

The interface is fairly straightforward—I’m looking at this on a desktop, though it does work on mobile—with a bunch of choices at the top and a choropleth map below. There we have a continually divergent gradient, meaning the states aren’t grouped into like bins but we have incredibly subtle differences between similar states. (I should also point out that Maine and Nebraska are the two exceptions to my above description of the Electoral College. They divide their votes by congressional district, whoever wins the district gets that Electoral College vote and then the state overall winner receives the remaining two votes.)

Below that we have a bar chart, showing each state, its more/less likely winner state and the 270 threshold. Below that, we have what I’ve read/heard described as a ball plot. It represents runs of the simulation. As of Thursday morning, the current FiveThirtyEight model says Trump has an 11 in 100 chance of winning, Biden, conversely, an 89-in-100 chance.

But what happens when we start determining the winners of states?

Well, for my non-American readers, this election will feature a large number of voters casting their ballots early. (I voted early by mail, and dropped my ballot off at the county election office.) That’s not normal. And I cannot emphasise this next point enough. We may not know who wins the election Tuesday night or by the time Americans wake up on Wednesday. (Assuming they’re not like me and up until Alaska and Hawaii close their polls. Pro-tip, there’s a potentially competitive Senate race in Alaska, though it’s definitely leaning Republican.)

But, some states vote early and/or by mail every year and have built the infrastructure to count those votes, or the vast majority of them, on or even before Election Day. Three battleground states are in that group: Arizona, Florida, and North Carolina. We could well know the result in those states by midnight on Election Day—though Florida is probably going to Florida.

So what happens with this FiveThirtyEight model if we determine the winners of those three states? All three voted for Trump in 2016, so let’s say he wins them again next week.

We see that the states we’ve decided are now outlined in black. The remainder of the states have seen their colours change as their odds reflect the set electoral choice of our three states. We also now have a rest button that appears only once we’ve modified the map. I’m also thinking that I like FiveyFox, the site’s new mascot? He provides a succinct, plain language summary of what the user is looking at. At the bottom we see what the model projects if Arizona, Florida, and North Caroline vote for Trump. And in that scenario, Trump wins in 58 out of 100 elections, Biden in only 41. Still, it’s a fairly competitive election.

So what happens if by midnight we have results from those three states that Biden has managed to flip them? And as of Thursday morning, he’s leading very narrowly in the opinion polls.

Well, the interface hasn’t really changed. Though I should add below this screenshot there is a button to copy the link to this outcome to your clipboard if, like me, you want to share it with the world or my readers.

As to the results, if Biden wins those three states, Trump has less than a 1-in-100 chance of winning and Biden a greater than 99-in-100.

This is a really strong piece from FiveThirtyEight and it does a great job to show how states are subtly linked in terms of their likelihood to vote one way or the other.

Credit for the piece goes to Ryan Best, Jay Boice, Aaron Bycoffe and Nate Silver.

Where Are the Votes?

I’m not working for a good chunk of the next few days. But, I did want to share with my readers an analysis of Pennsylvania’s missing votes. Broadly, Trump needs to win the Commonwealth of Pennsylvania next week—yes, the US election is now one week away. Though, Pennsylvania allows mail-in ballots postmarked on Election Day to arrive within a few days and still be counted. So we may not have final tallies for the state until the weekend or Monday after Election Day.

Pennsylvania, of course, narrowly voted for Donald Trump over Hillary Clinton in 2016 with 44,000+ votes making the difference. In 2020, polling has consistently placed Joe Biden above Donald Trump by 5+ points. But, can Trump again pull off an upset victory?

I argue that yes, he can. And fairly easily too. (If you want to see why I think Pennsylvania is really Trumpsylvania, I recommend checking out my longer, more in-depth analysis.) So where would the votes come from? I mapped the 2016 difference between votes cast and registered voters, i.e. people who could have voted, but did not for whatever reason. I then coloured the map by the county’s winner in 2016. Red counties voted for Trump by more than 10 points and blue for Clinton by more than 10 points. The purple counties are those that were competitive, plus or minus 10 points for either candidate.

In the purple counties, both candidates will want to drive out as many voters as possible. But in the blue counties, Biden has reliably Democratic votes and in red Trump has reliably Republican votes. So why on Monday did Trump visit Allentown, Lititz, and Martinsburg? Because that’s where those votes are.

Allentown, in Lehigh County, is competitive. In fact, neighbouring Northampton Co. will be a key swing county next week and one I will be following closely as the returns come in. But Lititz, Lancaster Co., and Martinsburg, Blair Co., are in reliably red counties. (Though in my Trumpsylvania piece I argue Lancaster Co. is undergoing a transition to a competitive, albeit lean Republican county.)

In Lancaster Co., which went to Trump by nearly 20 percentage points in 2016, there were still just short of 100,000 voters who didn’t vote in 2016. Not all of those voters would have voted for Trump, but for sake of argument, just say 50% would have. That makes just short of 50,000 potential Trump votes—more than Trump’s entire state margin.

Blair Co. is in the Pennsyltucky region of the state, relatively rural, but in Blair’s case, its county seat Altoona is the state’s 10th largest city. While the total number of votes—and the total number of non-voting voters—are smaller than in Lancaster Co., add up all the available votes and it’s a large number.

If you add up all those red counties’ missing votes, you get a total of just shy of 840,000 missing votes. Far more than enough to drastically swing the Commonwealth to Trump in 2020.

Of course, Biden’s counting on driving out turnout in Philadelphia and Pittsburgh and their suburbs, along with other cities in the state, like Allentown, Scranton, Harrisburg, and Erie. In those blue counties, there were 927,000 missing votes, so the potential for a Biden win is also there.

But, if Democratic voters don’t vote again in 2016, Trump has plenty of potential votes to pick up across the state.

Credit for the piece is mine.

Covid Migration

Yep, Covid-19 remains a thing. About a month or so ago, an article in City Lab (now owned by Bloomburg), looked at the data to see if there was any truth in the notion that people are fleeing urban areas. Spoiler: they’re not, except in a few places. The entire article is well worth a read, as it looks at what is actually happening in migration and why some cities like New York and San Francisco are outliers.

But I want to look at some of the graphics going on inside the article, because those are what struck me more than the content itself. Let’s start with this map titled “Change in Moves”, which examines “the percentage drop in moves between March 11 and June 30 compared to last year”.

Conventionally, what would we expect from this kind of choropleth map. We have a sequential stepped gradient headed in one direction, from dark to light. Presumably we are looking at one metric, change in movement, in one direction, the drop or negative.

But look at that legend. Note the presence of the positive 4—there is an entire positive range within this stepped gradient. Conventionally we would expect to see some kind of red equals drop, blue equals gain split at the zero point. Others might create a grey bin to cover a negative one to positive one slight-to-no change set of states. Here, though, we don’t have that. Nor do we even get a natural split, instead the dark bin goes to a slightly less dark bin at positive four, so everything less than four through -16 is in the darker bin.

Look at the language, too, because that’s where it becomes potentially more confusing. If the choropleth largely focuses on the “percentage drop” and has negative numbers, a negative of a negative would be…a positive. A -25% drop in Texas could easily be mistaken with its use of double negatives. Compare Texas to Nebraska, which had a 2% drop. Does that mean Nebraska actually declined by 2%, or does it mean it rose by 2%?

A clean up in the data definition to, say, “Percentage change in moves from…” could clear up a lot of this ambiguity. Changing the colour scheme from a single gradient to a divergent one, with a split around zero (perhaps with a bin for little-to-no change), would make it clearer which states were in the positive and which were in the negative.

The article continues with another peculiar choice in its bar charts when it explores the data on specific cities.

Here we see the destinations of people moving out of San Francisco, using, as a note explains, requests for quotes as a proxy for the numbers of actual moves. What interests me here is the minimalist take on the bar charts. Note the absence of an axis, which leaves the bars almost groundless for comparison, except that the designer attached data labels to the ends of the bars.

Normally data labels are redundant. The point of a visualisation is to visualise the comparison of data sets. If hyper precise differences to the decimal point are required, tables often are a better choice. But here, there are no axis labels to inform the user as to what the length of a bar means.

It’s a peculiar design decision. If we think of labelling as data ink, is this a more efficient use with data labels than just axis labels? I would venture to say no. You would probably have five axis labels (0–4) and then a line to connect them. That’s probably less ink/pixels than the data labels here. I prefer axis lines to help guide the user from labels up (in this case) through the bars. Maybe the axis lines make for more data ink than the labels? It’s hard to say.

Regardless, this is a peculiar decision. Though, I should note it’s eminently more defensible than the choropleth map, which needs a rethink in both design and language.

Credit for the piece goes to Marie Patino.

Trumpsylvania

After working pretty much non-stop all spring and summer, your humble author finally took a few days off and throw in a bank holiday and you are looking at a five-day weekend. But, because this is 2020 travelling was out of the question and so instead I hunkered down to finish writing/designing an article I have been working on for the last several weeks/few months.

The main write-up—it is a lengthy-ish read so you may want to brew a cup of tea—is over at my data projects site. This is the first project I have really written about for that since spring/summer 2016. Some of my longer-listening readers may recall that the penultimate piece there I wrote about Pennsyltucky was inspired by work I did here at Coffeespoons.

To an extent, so is this piece. I wrote about Trumpsylvania, the political realignment of the state of Pennsylvania. 2016 and the state’s vote for Donald Trump was less an aberration than many think. It was the near-end result of a decades-long transformation of the state’s political geography. And so I looked at the data underlying the shift and how and where it occurred.

And originally, I had a slightly different conclusion as to how this related to Pennsylvania in the upcoming 2020 election. But, the whole 2020 thing made me shift my thinking slightly. But you’ll have to read the whole thing to understand what I’m talking about. I will leave you with one of the graphics I made for the piece. It looks at who won each county in the state, but also whether or not the candidate was able to flip the county. In other words, was Clinton able to flip a Republican county? Was Trump able to flip a Democratic county?

Let me know what you think.

And of course, many, many thanks to all the people who suffered my ideas, thoughts, and early drafts over the last several weeks. And even more thanks to those who edited it. Any and all mistakes or errors in the piece are all mine and not theirs.

Credit for the piece is mine.

African Descent in African Americans

A study published last week explores the long-lasting impact of the Atlantic triangle trade of slaves on the genetic makeup of present day African Americans. Genetic genealogy can break down many of what we genealogists call brick walls, where paper records and official documentation prevent researchers from moving any further back in time. In American research, slavery and its lack of records identifying specific individuals by name, birth, and place of origin prevents many descendants from tracing their ancestry beyond the 1860s or 50s.

But DNA doesn’t lie. And by comparing the source populations of present day African countries to the DNA of present day Americans (and others living in the Western hemisphere), we can glean a bit more insight into at least the rough places of origin for individual’s ancestors. And so the BBC, which wrote an article about the survey, created this map to show the average amount of African ancestry in people today.

Average amount of African genetic ancestry in present day populations of African descent

There is a lot to unpack from the study, and for those interested, you should read the full article. But what this graphic shows is that there is significant variation in the amount of African descent in African-[insert country here] ethnic groups. African-Brazilians, on average, have somewhere between 10–35% African DNA, whereas in Mexico that figures falls to 0–10%, but in parts of the United States it climbs upwards of 70–95%.

In a critique of the graphic itself, when I look at some of the data tables, I’m not sure the map’s borders are the best fit. For example, the data says “northern states” for the United States, but the map clearly shows outlines for individual states like New York, Pennsylvania, and New Jersey. In this case, a more accurate approach would be to lump those states into a single shape that doesn’t break down into the constituent polities. Otherwise, as in this case, it implies the value for that particular state falls within the range, when the data itself does not—and cannot because of the way the study was designed—support that conclusion.

Credit for the piece goes to the BBC graphics department.

Wednesday’s Covid-19 Data

Here we have the data from Wednesday for Covid-19.

Pennsylvania saw continued spread of the virus. Notably, Monroe County in eastern Pennsylvania passed 1000 cases. It was one of the state’s earliest hotspots. That appears to have been because it was advertised as a corona respite for people from New York, not too far to the east and by then in the grips of their own outbreak.

New Jersey grimly passed 5000 deaths Wednesday. And it is on track to pass 100,000 total cases likely Friday or Saturday. Almost 2/3 of these cases are located in North Jersey, with some South Jersey counties still reporting just a few hundred cases and a handful of deaths.

Delaware passed 3000 cases and Kent Co. passed 500. While those don’t read like large numbers, keep in mind the relatively small population of the state.

Virginia has restarted reporting deaths, this time at the county level and not the health district level. What we see is deaths being reported all over the eastern third of the state from DC through Richmond down to Virginia Beach. In the interior counties we are beginning to see the first deaths appear. And in western counties, we still see that the virus has yet to reach some locations, but counties are beginning to report their first cases.

Illinois continues to suffer greatly in the Chicago area, and at levels that dwarf the remainder of the state. However, the downstate counties are beginning to see spikes of their own. Macon and Jefferson Counties each saw increases of 30–40 cases in just 24 hours.

Preview(opens in a new tab)

A longer-term look at the states shows how the states diverge in their outbreaks. Pennsylvania looks like it might be forcing the curve downward whereas New Jersey appears to have more plateaued. Earlier I expressed concern about Virginia, which does now appear to have not peaked and continues to see an increasing rate of spread. Then we have Illinois, which may have plateaued, but we need to see if yesterday’s record amount of new cases was a blip or an inflection point. And in Delaware a missing day of records makes it tricker to see what exactly the trend is.

Credit for the piece is mine.

Comparing Covid-19 to Influenza

I want to share a small graphic I made yesterday evening. And I am being charitable with the term graphic. Really it is nothing more than a collection of organised factettes. But I have seen the footage of those protesting the lockdowns in various states, including Pennsylvania.

To be clear, people can have different policy prescriptions to solve the pandemic. For example, the governor of Pennsylvania is considering lifting the lockdown piecemeal once the state overall has sufficient testing and tracing capabilities. Look at the state.

He rightly said that Cameron County, one of the little light purple shapes in the upper left, with its one case for the last 25 days is in a different situation than Philadelphia where cases continue to grow, albeit at a slowing rate. And in the future it is possible that Cameron County could open before Philadelphia. That is a different policy prescription than, say, opening the state all at once.

I don’t think most people enjoy lockdown—I haven’t left my building in 38 days and I cannot wait to leave and go do something. But I recognise that spreading outside these walls we have a deadly pandemic for which we have no vaccine. But then I see people protesting—protesting in a manner that contradicts the guidelines put out by the health officials—and claiming that we should open up because this is nothing worse than the flu.

Well, Covid-19 is not the flu. It is much worse.

This isn't your grandmother's flu. Or anyone else's flu. Because this isn't the flu. — This isn’t your grandmother’s flu. Or anyone else’s flu. Because this isn’t the flu.

Now, those numbers will change because the pandemic is ongoing. But, let’s spitball. Let’s assume those numbers hold. The idea of the shutdowns, lockdowns, and quarantines is to prevent the spread of the virus. For the sake of this thought experiment, let’s just assume, however, that it infects 56 million people, the upper end of the range for this most recent influenza season.

Influenza this year killed as many as 62,000 people after infecting 56 million. Hypothetically, with a mortality rate of 5%, Covid-19 would kill 2,800,000 people.

With a 4% rate that drops to 2,240,000

With a 3% rate that drops to 1,680,000

With a 2% rate that drops to 1,120,000

With a a 1% rate that drops to 560,000

With a 0.5% rate that drops to 280,000

And even at 0.5% that is still far greater than the flu. And so that is why it is so important to keep the number of people infected as low as possible. (And I won’t even get into the surge problems overwhelming hospitals that acts as a force multiplier and is the proximate reason for the lockdowns.)

This is not the flu.

Credit for the piece is mine.

Covid-19 Data from Monday

Monday’s Covid-19 data for Pennsylvania, New Jersey, Delaware, Virginia, and Illinois provided a glimmer of good news, most notably in Pennsylvania. That, however, occurred on the same day as a protest in Harrisburg that could set the state back days if not weeks. More on that below.

Pennsylvania saw fewer than 1000 new cases for the first time since 1 April. The curve here may be doing more than flattening, but it might actually be falling. That is to say the infection rate is decreasing rather than stabilising and holding steady, as it appears to be doing in New Jersey. That said, new cases are appearing sporadically in the rural and less dense areas of the state. Problematically, protestors arrived in Harrisburg to let it be known they are unhappy with the quarantine. Because the rest of us are.

The problem is that it appears a significant percentage of those infected with the virus are asymptomatic carrier, i.e. they are sick, but do not show any symptoms like fever, coughing, difficulty breathing. Critically, they may not appear sick, but they can spread the sickness. And so a gathering of several hundred people in close quarters? Not ideal.

Compare that to a Christian cultish church in Daegu, South Korea. There, an infected parishioner did not heed government calls to isolate and instead attended a church service. The average infected person spreads this virus to two or three people. This congregant? They infected 43 people who then went on to infect other people.

It is quite possible that someone in that Harrisburg protest was an asymptomatic carrier. And given the lack of social distancing, the lack of masks, and the general reckless behaviour, it is quite possible that the rally could be a super-spreading event. But we won’t know for 5–10 days, the apparent incubation period of the virus. Hopefully we dodge the proverbial bullet. But it is quite easy to see how these kinds of protests could lead to surges in infections. And those surges would then force the government to extend its quarantine by weeks thereby defeating the entire point of the protestors.

We get it. Quarantine sucks. But we all have to suck it up.

Moving on to New Jersey, where we see continuing evidence of the plateauing of cases. The bulk of the cases remain in the north in the New York suburban counties with the fewest numbers in the counties in South Jersey. However, averages of nearly 3500 new cases daily remains quite high and the death toll of 4377 is likely to continue to climb higher, even if Monday’s 175 new deaths was lower than most days in recent weeks.

Delaware is back to reporting its figures. And in that release, we had Sussex County in the south climb above 1000 total cases. The levels or curves chart at the end will also show how the state might be flattening and stabilising its infection rate, but we will need several days of uninterrupted reporting to make that determination.

Virginia might be worrying. Or it might not be. Cases continue to increase in the big metropolitan counties like Fairfax and Henrico. But, there are still several counties out in the west that remain unaffected. And the curves chart at the end shows how there has not yet been any sort of even a near-exponential growth curve. Instead we just see a steady, slow increase in the number of cases. That in its own way makes it more difficult to see when the curve flattens, because it was already a relatively flat curve.

Illinois continues to be the tale of two states: Chicago vs. everywhere else. The combined Chicago and Cook County have over 20,000 total cases and the surrounding counties add a few thousand more, which gets you over 2/3 of the state’s 31,000 cases. That said, new cases and new fatalities are beginning to pop up in downstate counties.

Lastly a look at the curves. As I noted above when talking about Pennsylvania, you can clearly see the downward slope of the state’s new cases curve. Compare that to the plateau-like shape of New Jersey. Delaware and Illinois might be approaching a New Jersey-like curves. But I would want to see more data and in Delaware less volatility. But like I said, Virginia is a tricky one to read.

Credit for the pieces is mine.

Sunday’s Covid-19 Data

Here is a look at the data from Sunday’s releases on the COVID-19 outbreak in Pennsylvania, New Jersey, Virginia, and Illinois. I’ve omitted Delaware because they paused reporting on Sunday to move to a noontime release instead of their previous end-of-day.

I’m not exactly certain what that means for the data on Delaware and reporting time series. But, my guess is that will be more like a hole in the time series. I need to spend some time looking at that. But, anyways, on to the states for which we did have data on Sunday.

Pennsylvania continues to see growth in cases, but as we’ll get to with the levels, that appears to at least be stabilising. But in the spread of the outbreak, we are beginning to see the T of the state, that more rural and less densely populated area, beginning to fill in with cases. These are of course the areas of concern, the areas with shuttered rural hospitals, lack of comparatively developed infrastructure, where the impacts could be proportionately more severe than in the bigger cities. In terms of deaths, they have now spread almost across the state from east to west. I am still waiting until two adjacent counties connect before I make that final pronouncement.

For New Jersey, I have removed the orange outlines around each county. The initial idea was to show where deaths had occurred. But now that they have been reported in every county, they don’t seem to be as helpful as the small number I provide in the graphic. Regardless, 4200 deaths is a lot. But the approximately 200 new deaths is the lowest number reported in several days.

Virginia is a weird state. When we see the levels chart below, you will see how its uptick has been far more gradual, and to this point it does not yet appear to have peaked or begun to stabilise. Most of the reported cases continue to be in and around the state’s big cities, notably the DC metro area, but also Richmond.

Illinois has now seen cases from north at the Wisconsin border all the way south to Cairo. Most cases remain, however, concentrated in the Chicago metropolitan area, with lesser scale outbreaks occurring in the Quad Cities area and the suburban counties of Illinois this side of the Mississippi. Deaths continue to rise, and while most area again in the Chicago area, they are appearing increasingly at low levels in downstate counties.

But what about those curves? Excepting Delaware, which hasn’t reported new data, we can see that some states like Virginia continue to see increasing rates of infection. Others like New Jersey and Pennsylvania clearly have flattened and have entered a new phase. In New Jersey’s case it appears to be more of a stabilised plateau. In Pennsylvania, there was some evidence it was entering a declining rate phase, but that may now have begun to become more of a steady rate of infection like in New Jersey. Illinois is tough to read because of the variability of its data. It might be more of a pause in the rate of increase, or it may have begun to stabilise. We need more data.

Credit for the pieces is mine.

Monday Covid-19 Data

The data from Monday provided yet more evidence that the outbreak is flattening in several states. However, in some, the outbreak continues to pick up steam. Does this runs contrary to the idea that as a country is flattening? Not necessarily, but it is important to remember that a country that spans a continent and holds 330 million people will experience the pandemic differently at different times. So some states like Washington will be first, and others will be last.

Our five states cover the range of worsening to stabilising. We hope that those stabilising states soon enter the improving phase. Though to beat the dead horse, I would add that just because a state is improving doesn’t mean we can all go back to life like we knew it two months ago. That would likely result in us being right back here shortly thereafter.

Pennsylvania continues to be a state where the pandemic is spreading within the denser metropolitan areas of Philadelphia and Pittsburgh, leaving the central T to see fewer cases that spread more slowly.

Delaware might be approaching an inflection point, given that its most populous county, New Castle, is about to reach 1000 cases. (By the end of today it likely will if its new case trend holds.) We know that deaths lag new cases, and so the worry is that the number of deaths will begin to increase rapidly. The hope is that the slow initial growth of the outbreak will have left hospitals able to better cope over the longer time frame than if everyone had gotten sick all at once.

Virginia is a state that we will contrast to New Jersey, which I will write about last. Because Virginia is a state where it appears the outbreak is beginning to pick up steam and accelerate, rather than flatten. There was the significant drop in cases on Sunday, but that was due to the state’s enhancement of reporting data. (Their website now includes many new statistics.) But just like that the Monday data showed over 450 new cases on Monday. The question will be whether or not over the remainder of the week those new case numbers fall from over 450 to less than 400 to show that the state can flatten the curve before the outbreak becomes especially severe.

Illinois has shown a lot of variability in its day-to-day numbers, hence the advantage of the rolling average. But even that has appeared a wee bit jagged. It’s tough to see the curve flattening just yet, but if we receive updates today and over the next few days that cases are consistently lower, than we might just be able to say the curve is flattening.

And of course in New Jersey we have a state where the curve really and truly has flattened. We have yet to see sustained evidence of a decline in the number of new daily cases. As I said before, this might be more a situation where the outbreak has stabilised and roughly the same number of new cases is being reported daily. Of course the hope is that whatever that rate is falls below the excess capacity threshold of the state’s hospitals.

But I also want to take a look at the state of New Jersey with a degree of granularity. Because, as I noted with Virginia above, not all states are at the same point in their outbreak. And the same can hold true within states. We know that the outbreak in New Jersey began in the north and was very late in reaching some parts of South Jersey. So the same metrics we run for the state, we can run for the counties—though the data I have been collecting from the states only goes back as far as St. Patrick’s Day.

New Jersey's curves — New Jersey’s curves

The northern counties, where the state has been hardest hit, have clearly begun to see the curve bend. But in the south the story is a bit more mixed. Some, like Burlington and Ocean, have seen the curve noticeably flatten. But in Camden and Mercer Counties, home to Camden and Trenton, respectively, the evidence is not quite there. Instead, in these populous counties there exists the very real possibility that the outbreak will continue accelerating for hopefully a very short while.

Credit for the pieces is mine.