I’ve been thinking about smoothing time series data. I tweeted out a bite size bit of code. To fit it into a tweet, I had to squeeze things down a bit. Slightly more verbose, and using fredr to get data from FRED using their API. You’ll need an API key from FRED. These data happen to be for New Private Housing Units Authorized by Building Permits - in Structures with 1 Unit.
Early last Friday morning I was sitting in Palm Springs International Airport waiting to catch a flight back to Virginia. I had traveled out west to speak at the 2019 NAGLREP Conference. This Friday happened to be jobs Friday, when the U.S. Bureau of Labor Statistics releases the employment situation. Jobs Fridays are busy on Twitter. Everybody seems eager to offer a perspective on what the latest jobs numbers mean for the U.
Over the summer I spent a few weeks in Asia. One of the places I visited was Fushimi Inari-taisha in Kyoto, Japan. This shrine is situated on a beautiful mountain. What really struck me about this place was the vibrant colors used in the Torii gates and to decorate some of the fox statues like these: The color got stuck in my head, so I decided to look up the hex code here and created a modified ggplot2 theme using the color.
Found in Translation On a hill in Kyoto, Japan there is a most delightful sign. Near the Kiyomizu Temple temple in the Higashiyama District there are several picturesque streets. The presevered historic district is a favorite place for tourist shopping, tasty snacks, photo opportunities with majestic temples in the background. Many folks like to rent Kimonos (mostly women, but also a few men) and snap photos in the street. On my way through the district I happened across this wonderful sign attached to a private residence:
Earlier today I tweeted out some yield curve charts. I won’t go into great detail into the why, but here I will share some R code to make the charts. My Thread: hope you all are ready for some crazy yield curve charts, cuz you're about to get some crazy yield curve charts — 📈 𝙻𝚎𝚗 𝙺𝚒𝚎𝚏𝚎𝚛 📊 (@lenkiefer) August 7, 2019 We can get Treasury yield curve data from the U.
I have been exploring some visualizations for housing seasonality. In recent days I’ve tried out various ways of using tile plots to display seasonal patterns in home sales and other related data. In this post I want to share some of the R code I used to wrangle data and generate those plots. You can see some for example, in this thread (and others): though outside there's blistering heat
On intrinsic irreducible uncertainty of economic outcomes (forecasting is hard) Here’s a picture of me and some bears. Don’t worry, I didn’t get hurt. Those bears couldn’t hurt anybody. First, because they are behind some glass. And second, because they are stuffed. There are a lot of stuffed bears out there. They’ve grown aggressive lately. Maybe because they haven’t eaten much. This current economic expansion is over 10 years old now.
Let us take a look at house price trends in the United States and across states and metro areas. Earlier this week I tweeted out a few charts on housing market trends. In most of the middle part of the country over the past 44 years there has been little growth in real (inflation-adjusted) house prices. In coastal states, a very different story. pic.twitter.com/PLbiNftha3 — 📈 𝙻𝚎𝚗 𝙺𝚒𝚎𝚏𝚎𝚛 📊 (@lenkiefer) July 10, 2019 In this post we’ll analyze real house prices since 1975, and per usual use R to wrangle data and make plots.
If I cannot send Adam Ozimek (at Modeled Behavior ) a Diet Pepsi, then the next best thing might be a chart about epop. epop is the term economists use to describe the employment-to-population ratio, a useful summary statistic about the labor market. Perhaps the summary statistic. Adam (and others) has been talking about epop as a key labor market statistic for years. It seems the Federal Reserve is catching on to the usage of the term epop (though many economists over there have been looking at the statistic for a long while too).
Last week I posted a long thread comparing trends in various housing market indicators over on Twitter: Assuming we aren't in recession right now, the current expansion will tie the 1990s expansion for longest in U.S. history. Let's take a look at how housing markets have behaved in this expansion relative to earlier ones a thread... pic.twitter.com/ovaiq3lsA8 — 📈 𝙻𝚎𝚗 𝙺𝚒𝚎𝚏𝚎𝚛 📊 (@lenkiefer) June 12, 2019 I followed it up with an article on LinkedIn with some more commentary The U.