My Interest In The New Goldman Sachs CEO Goes Pretty Much Exactly As You Would Expect…

In learning about the music industry, I often think about how what behavioral experiments I would want to run if I had the proper resources/infrastructure/etc. Along these lines, one thing I’m curious about is how people’s willingness to pay for music is affected by the financial situation of the people creating the music- in other words, are people more willing to pay for music (as opposed to download illegally, stream, whatever) when they know the money matters to the musicians? I’ve actually brainstormed with people about how to implement such a thing, and…it’s harder than you might think. See, one feature of economic experiments is that we’re not supposed to use deception- in this case, it means I would actually have to find musicians with differing levels of income rather than just tell hypothetical background stories. Obviously such people exist, but I’m going to go out on a limb and hypothesize that the music created by the high-income musicians is different from the music created by the low-income musicians in a way that is related to willingness to pay.

In a perfect world, I guess I would find a band where the members have day jobs that differ widely in income, since then I could present the same music with different backstories without having to make anything up. (If you know any such unicorn bands please do drop me a line!) I guess something like this would be a decent backup plan:

Goldman Sachs’ president has gigs as a DJ around the world

Goldman Sachs’ president has gigs as a DJ around the world

His Fleetwood Mac remix was recently featured on SiriusXM.

Source: www.cnbc.com/2018/03/14/goldman-sachs-david-solomon-has-gigs-as-a-dj-around-the-world.html

I like this on principle, since I feel pretty strongly that people should have hobbies and interests and whatnot, but I also can’t help but think “hmmm, now if I find an equivalently popular DJ who isn’t a CEO as my control group”…

Turns out the story gets more interesting…apparently the Sirius exposure that D-Sol (yep, that’s David Solomon’s stage name) get ended up getting him a spot on the Billboard charts:

I mean come on, this is #goals…in case you can’t see the chart itself, here’s the description:

Dance/Mix Show Airplay

This week’s most popular current songs ranked by total weekly plays on full-time dance-formatted stations as well as mix show plays on mainstream top 40 and select rhythmic and adult top 40 stations that have submitted their hours of mix show programming, as monitored by Nielsen Music, to Billboard. Songs are defined as current if they are newly-released titles, or songs receiving widespread airplay and/or sales activity for the first time.

Obviously I’m curious as to the effect that such airplay has on streaming and sales behavior…unfortunately, I don’t have data on streaming, but here’s the sales trajectory:

Let’s unpack this, since the chart timing is a little complicated…the Billboard chart date is July 28, 2018, which means it was published on July 24 and covers the period July 16-22. The song didn’t remain on the chart the next week (boo), so we can think of this as the period over which the song got the bulk of its airplay attention. That’s a little weird but interesting, since it suggests a couple of things: one, that the sales interest preceded the airplay interest rather than the other way around, and two, that the airplay and chart recognition didn’t lead to a huge spike in sales. (Granted, we don’t know that we wouldn’t have seen more of a decline if the airplay hadn’t happened, but the magnitude of the effect is still limited by the fact that sales couldn’t have been less than zero in the “counterfactual” situation.)

As a related matter, I have an idea…so I’m going to make a song, and enough of you are going to buy it so that I can get on the Billboard charts, since from what I can tell the bar is a lot lower than it used to be. (The chart above is an airplay chart, so the sales data I showed here doesn’t speak to this point directly, but this is the pattern that I see more generally.) Wait, now I’m wondering if David Solomon just had 1,000 of his closest friends do him a solid… 🙂

In case you’re curious, here’s the song in question (there’s also an extended version if you’re super into it):

Since you’ve read this far, I figured I’d pass along another relevant item I came across in my research:

Yes, I’m trying to not be annoyed by the misspelling because it’s just too funny. I’m also trying to not take issue with the following headline:

Calvin Harris Tops the ‘Forbes’ Highest-Paid DJ List For Sixth Straight Year

Calvin Harris Tops the ‘Forbes’ Highest-Paid DJ List For Sixth Straight Year

Calvin Harris has been named Forbes’ highest-paid DJ in the world for a sixth year in a row. Check the full list of Forbes’ top 15 paid DJs here.

Source: www.billboard.com/articles/news/dance/8467942/calvin-harris-top-paid-dj-forbes

I mean, technically…though looking at the numbers, I think the article might actually be correct as stated, at least for the top spot for the time being.

Causal Friday: The Dumbest Differences-in-Differences Ever, Viral Video Edition…

It’s causal Friday, so I’m poking around in some data trying to make a case for cause and effect. More specifically, I’m drowning in a differences-in-differences analysis trying to construct a proper control group. (In this case, identifying a control group isn’t conceptually difficult, it’s just really annoying to pull the data.)

So what is a differences-in-differences analysis? It’s…well, pretty much exactly what it sounds like- it’s kind of nice when that happens. Here’s a little thing I wrote up a while ago for my team at work (who had more of a data science than social science background), or you can consult Wikipedia. (note: you will never convince me it’s “difference-in-differences” and not “differences-in-differences”) The general principle behind differences-in-differences is that you can’t just do a before-after comparison to identify the effect of an event, since you’d also need to know what the before-afters look like for stuff that wasn’t subjected to the event. For example, consider the following hypothetical question:

Fairlife milk initiated a new marketing campaign at the beginning of 2018, and so far sales of Fairlife milk are 5 percent higher than for the same portion of 2017. Should the marketing campaign be considered a success?

Hopefully it’s at least somewhat intuitive that the answer should be “I dunno, how do the sales of non-Fairlife milk compare to last year?” If milk sales more generally are, say, also up 5 percent, it’s not particularly likely that the marketing campaign is doing much. On the other hand, if sales for the milk industry were generally down compared to last year, the marketing campaign should be viewed much more favorably.

So this is what I was trying to do, but with music sales. Remember this?

Is this the best way ever to quit your job? Marina Shifrin resigns with Kanye West dance video

Is this the best way ever to quit your job? Marina Shifrin resigns with Kanye West dance video

Ever wanted to quit your job? Why don’t you take a leaf out of video producer Marina Shifrin’s book and do it through the medium of “interpretive dance”?

Source: www.telegraph.co.uk/news/newsvideo/viral-video/10344179/Is-this-the-best-way-ever-to-quit-your-job-Marina-Shifrin-resigns-with-Kanye-West-dance-video.html

For context, I’m using this as a motivating example for a larger analysis on music sampling. So I dutifully went through and identified two other songs from the same Kanye album that were about as popular as ‘Gone” before the video above went viral, and then I looked up the sales of all three songs (this is way more annoying than you’d think it should be) before and after the video’s posting date so I could do a very careful and nuanced analysis. Clearly I didn’t think things through, since, well…

This is only for the song used in the viral video, so I don’t technically have a comparison group (yet), but I mean COME ON…nonetheless, I persisted and added my control group:

(I changed the scale of the graph so it looked just wonky rather than useless.) You’ll be pleased to know that my confidence in the video causing a sales bump has not decreased…but let’s calculate some differences in differences anyway (it’s not really possible to run a regression here). So here are the numbers for 4 weeks before and 4 weeks after:

These numbers are pretty easy to interpret- an effect is positive if the differences-in-differences numbers are positive and vice versa. (An effect is nonexistent if the difference is close to zero.) Now I guess technically I should run a test to see whether the differences are *statistically* different from zero, but 1. that’s kind of hard with 3 data points, and 2. I mean come on.

The real punch line in all of this is the fact that the video has been taken down on copyright grounds…I’m, um, not sure you’re doing it right, record label…