As an NFL fan, (and a fan of the Seattle Seahawks in particular) I occasionally find myself watching football with my dad, and whenever I do, the accusation inevitably creeps in that the referees are biased in the way that they make penalty calls – specifically that for a given illegal action, a penalty flag will be thrown against the Seahawks much more frequently than against the opposing team, even when the offending action is performed at a similar rate by both teams. Personally, I’m not good enough at spotting every penalty on the field to say with confidence whether or not this is the case, and to be honest, my suspicion is that this feeling of one’s own team being unfairly persecuted is one harbored by most sports fans regardless of the team they root for. It occurs to me though, that as a data scientist, this sports fan is uniquely qualified to actually grab some data and attempt to vet this theory as it applies to my own team and be able to say with some objective numbers how well founded these suspicions may be.
The accusation at the heart of this study really has to do with penalties that are not called, for which there is no record, which makes this claim very hard to definitively confirm or refute. However, data on called penalties is published and publicly available, and through thoughtful analysis of the penalties that were called, we can at least see if there is any evidence of a bias towards calling penalties against certain teams more often than others.
Yesterday at a town hall style forum the president of the United States once again asserted an opinion regarding Covid 19; that the virus would just go away on its own, an opinion that the president has voiced repeatedly since the start of the pandemic. This time however he specified that the mechanism by which the virus would cease to be a concern was through herd immunity, or the idea that eventually a large enough percentage of the population would have contracted the virus and through exposure built a natural immunity to it, to stop the virus from being able to effectively spread through the population. While herd immunity is an actual phenomena and could prevent the virus from being able to effectively spread, according to the Mayo Clinic in order to have effective herd immunity, at least 70% of the population would have to have contracted and become immune to the virus. So, the question to evaluate this statement becomes; are we close enough to that threshold right now to justify the head of the current administration’s position of unconcern and inaction?
Several months ago I published my rough estimates for how many people in the U.S. may have likely contracted Covid at that time given our comprehensive lack of random testing, and the assumption that most of those who have been tested did so out of a need for medical help. I was able Continue reading →
Several days ago I caught the tail end of a television interview with a doctor who was being asked if there is a way to estimate the number of people in the U.S. who have contracted Covid-19 given that only 0.6% of the total population has been tested (at the time of this publication that number is around 1%). The doctor being interviewed didn’t really have an answer to this question, but the answer is yes; it is possible to say something about the actual number even if we can’t say what that number is. Providing this answer isn’t quite within the range of what most medical doctors would normally be expected to do, but as a data scientist, answering this question is the sort of things that does fall within my wheel-house. Today I’ll be going over two approaches I take to provide some hopefully useful insight on this question, one approach that provides a broad answer that reflects the uncertainty of how much we don’t know without widespread testing, and then another that may help provide some direction for where to narrow down a more specific answer to.
To provide some context, the discussion at large within this interview was regarding the potential risks involved in lifting the shelter in place policies currently in place across the country to get the economy back on more stable footing. The heart of the question was really this; has enough of the population been exposed to the virus, and thus developed immunities to it, that any second wave of outbreaks would be significantly slowed by the amount of people that are now already effectively immune through exposure? While I don’t have the medical knowledge to say how much of the population would have to develop immunities in order to significantly slow a viral spread, I can say something about how far the spread has gone, even if only to give a window of likely infection counts.
The tricky part about this question is that only a proportion of those who have Continue reading →
I have recently been taking a look at the electric vehicle industry and in so doing have been giving some thought to a solution to one of the biggest drawbacks to choosing an electric vehicle over a traditional one; the time it takes to recharge a battery. As it currently stands an electric vehicle can take up to 8 hours to charge when the battery is depleted. This means large downtimes for the driver which not only put a limit on the driver’s mobility, but also necessitate that the driver take long charge times into consideration when planning one’s travel. Much discussion has taken place revolving around the investment in fast charge stations which could provide a fast enough charge to travel roughly 40 miles off of 10 minutes of charging, but the drawback to this solution is that it is expensive and would still require a downtime of 10 minutes or more depending on how depleted the battery is.
An alternative to this that I take a look at today is the possibility of simply swapping out a depleted battery altogether in favor of a fully charged one at a battery swap station; sort of the electric vehicle equivalent of the gas station that traditional vehicles utilize. Some basic research tells me that this method is in fact already being utilized by a taxi business in China as well as being taken into consideration by Tesla, Inc. It has been reported that the battery swap done in China can be done in as little as four minutes. This is comparable to the downtime from driving one takes for fueling up a gas powered car that most drivers are familiar with now. Continue reading →
Having taken off the summer from writing and by and large researching as well, it has been since the start of the year since I have posted a forecast for the U.S. economy, too long (since my last forecast only extended to June of this year). So today I post my predictions for the rest of the year and beyond, as well as talk a little bit about the background work that went into the formulation of said forecast as I’ve tweaked the statistical model and mathematical formulas that culminate in this particular set of predictions about the near future of the economic environment in which we live and conduct business.
I’ll start with my predictions and then move to a discussion of the behind the scenes stuff. I predict that for the final quarter of the year we will see the economy grow by between Continue reading →
In April of 2015 the city of Seattle enacted an unprecedentedly large increase to the city’s minimum wage and as an empirical analyst in the general vicinity I couldn’t help but go out and make some data driven predictions regarding some of the effects of this groundbreaking bit of public policy. The results of said research are of course published on this site for any who are interested.
Today, after roughly a year and a half it seems almost overdue time for me to take a look at what has actually taken place since then and evaluate both the preliminary effects of the policy and also the accuracy of my own predictions. While the total effects of the new policy won’t be completely measurable for several years to come thanks to the 3 year phase in of the total wage increase, a preliminary look will provide policymakers and the generally curious both with at least some indication of the potential effectiveness of enacting significant upward increases in wages.
In order to properly evaluate the effectiveness of the change to wage policy I take a look at a number of different statistics that would potentially be influenced by the dramatically higher wages in an attempt to get a holistic look at the effects of the policy. Continue reading →
Since roughly the beginning of the year I have been loosely following the course of the U.S. presidential primaries and have noticed a trend towards candidates falling towards the extremes of the political spectrum as far as their stances on policy and governance. This is a strategic move in order to capture the vote of a given candidates party base to win the primary elections, and can be expected to reverse to an extent during the general elections where swing voters will likely be the target audience of rhetoric rather than those already deeply entrenched in the candidates own party. It has got me thinking though as to whether or not anyone has developed any sort of partisanship index in order to actually provide some sort of quantifiable measure of a given politician’s partisanship that could be used as a point of comparison between candidates. Continue reading →
With the start of a new year comes a new short term forecast for the U.S. economy (a little later than expected, but here none the less), with a few new visual depictions of my results as I start to experiment with Tableau’s data visualization software.
To get right to business, my models predict a rather slow and steady rate of GDP growth around 0.2% over the first few months of 2016 with a slight jump in March followed by a return to a rate of around 0.2% until June, where we could see some slowdown to around 0.14% To put this in perspective, if we were to see a 0.2% steady growth rate throughout the year, we would see yearly growth of close to 2.5%, compared to an average growth rate of around 3%, this is a little below average but not alarmingly so, and is a good sign given the fears of recession that have risen in the face of the recent shock to oil prices. My exact predictions for percentage growth of GDP along with the 95% confidence interval range can be viewed in the following table. Continue reading →
Today I bring you the results of a research project that I have been excited to do for some time now, as the question is one that I find personally interesting and has plagued me for almost as long as I’ve been a sports fan. Specifically this issue is the return on the ownership of naming rights of professional sports stadiums. More and more it seems like pro sports stadiums are named after businesses rather than either sports teams or the region that the team represents. I first remember noticing this trend as a kid growing up in the Seattle area when the Seattle Mariners’ Kingdome was replaced with a new park named Safeco Field. The average annual cost of retaining the naming rights to a pro sports stadium in North America is roughly $2.7 million and can range from $600 thousand to $10 million. This is no small amount, and brings the value of the benefits of owning these rights into question. A question punctuated by instances such as that of Portland Trail Blazers’ Moda Center. The Center was renamed from the Rose Garden back in 2013 at a cost of $40 million for 10 years, or $4 million annually, by a local insurance company that is now in financial trouble, and being forced to pull out of business in two states to cut operating costs.
With such a high cost to retain the naming rights of major league sports venues my questions are these: does the added name exposure add enough sales revenue to at least cover the cost to the firm of renting the naming rights, and in the case of publicly traded firms, does this expensive advertising practice have a noticeable effect on a firms bottom line therefore making a difference to investors? A third question that I found it necessary to ask in order to fully explore the issue is what effect does the addition of payments for naming rights have on a companies expenses? Or do firms that spend money on naming rights spend more on advertising or just shift away from other forms of advertisement expenses? Continue reading →
My movie viewing for this week was The Big Short, it wasn’t quite what I thought going into the movie (it was billed as some sort of financial heist movie), but I thought it was very well done. For anyone who is interested, it came off as a witty documentary about the financial collapse that caused the Great Recession with A-list actors portraying the key players that the film follows through the collapse. It does a fairly good job of explaining how the collapse came about in a non-technical way, and without losing audience attention in the process. I recommend the film to anyone who is curious to learn more about the causes of the recession, or even just looking to see an entertaining film and learn something in the process.
As an economist who was learning his trade during the later years of the recession and the period following it, I am somewhat familiar with the causes of the collapse and therefore didn’t learn anything too new myself, although the film did offer some insights on the events as they unfolded by way of viewing them through the eyes of the key characters of the film who were investigating the legitimacy of the real estate market in order to ascertain whether there was in fact a bubble in the market. The biggest take away for me was an issue regarding the credit rating agencies, whose complete failure to accurately report the riskiness of mortgage backed securities as well as derivatives of those securities was a big factor in the crisis. I had been familiar with this failure in reporting being a key factor that allowed the crisis to form the way it had prior to viewing the film, but the film presents an alternate explanation as to why this failure may have come to pass than what I had previously heard. Continue reading →