LET’S PICK BACK UP where we left off and think about communicating forecast results. To help guide our thinking, let’s set up a little game. Basic setup Like last time we’re going to focus on a situation where a forecaster observes some information about the world and makes an announcement about a future binary outcome. A decision maker observes the forecaster’s announcement and takes a binary action. Then the outcome is realized and the forecaster receives a payoff.
LAST FRIDAY WAS JOBS FRIDAY, the day when the U.S. Bureau of Labor Statistics (BLS) releases its monthly employment situation report. This report is blanketed with media coverage and economist and financial analysts all over the world pay close attention to the report. The employment situation gives a read on trends in the world’s largest economy’s labor market. It also provides a clue about how monetary policy might unfold, affecting bond yields around the world.
LAST WEEK IN THE WALL STREET JOURNAL an article LINK talked about how pundits can strategically make probabilistic forecasts. It seems 40% is a sort of magic number, where it’s high enough that if the event comes true you can claim credit as a forecaster, but if it doesn’t happen, you still gave it less than 50/50 odds. Since I’m often asked to make forecasts I’m interested in this problem. Under what conditions is a 40 percent probability an optimal forecast?
Spring is nearly upon us, or at least we can hope. Let’s examine how housing activity typically rounds into shape as the weather warms up. We’ll make some fun plots with R. Seasonality in housing data Housing market activity in the United States is highly seasonal. Consider this animated plot. This plot shows U.S. new home sales. Often the data are presented seasonally adjusted, but this plot is for non seasonally adjusted data.
LET US TAKE A LOOK AT HOUSE PRICE AND EMPLOYMENT TRENDS. House prices in the Unitest States have been increasing at a rapid pace, about 7 percent on an annual basis. How does that relate to employment growth? And how do those trends vary by geography. Let’s take a look. Per usual, I will post R code and you can follow along. Data Following recent posts (see here and here for example), we will use the Freddie Mac House Price Index an Excel spreadsheet can be downloaded here.
SO TODAY I SPENT SOME TIME WITH THE KIDDOS and contemplated the Enlightenment, so I didn’t have time to write up some code. But I will post a couple images that I think are interesting. I’ve got two plots for you, both using geofacets. See this post on using the geofacet package in R to make plots like these. The first plot shows U.S. house price trends by metro area from January 2015 to December 2017.
LAST YEAR WE TOURED recent house price trends Post. Let’s update the data visualizations with data through December 2017. We are going to show house price trends using data from the publicly available Freddie Mac House Price Index. Animation: Here’s an updated animation showing trends in the top 20 metro areas, based on population. Below, I’ll plot stills for each of the 20 metro areas. Later I’ll follow up with some additional visualizations and some commentary.
EARLIER THIS WEEK I TWEETED out a poll asking whether or not folks wanted to see a thread/tweetstorm with slides from an upcoming presentation on the economy and housing markets that I’m giving. Over 90 percent voted for a thread. So I shared it. In this post let me add a little more commentary on the individual slides. Here’s the thread I ended up posting: Thread (0/5). I'm giving an update on economy, #housing and #mortgage market trends.
THIS MORNING I SAW AN INTERESTING CHART OVER ON BLOOMBERG. In this post they compared recent 10-year Treasury yield movements with the Taper Tantrum in 2013. The chart you can see here was an area chart with overlapping line plots. I thought it would be a fun exercise to remix a similar chart with R. Eventually it will look like this: Let’s make our remix and try out a few alternative plots.
Hey check it out! Me on a podcast: https://policyviz.com/podcast/episode-111-len-kiefer/. We talk about data visualization and how I use it at work. A bit about using R too. I got the opportunity to talk with Jon Schwabish on the Policyviz podcast. Jon’s PolicyViz blog has a lot of cool data visualization stuff, including chart remakes and thoughtful discussion. There’s a bunch of other neat stuff on the page too. So check out the podcast and take a look around the page, there’s a lot of useful stuff there.