Len Kiefer

Forecasting with logs

As an economist and all-around friend of strictly positive numbers I often use the log function. The natural logarithm of course, need I specify it? Apparently in certain spreadsheet software you do. In this note I just wanted to write down a couple of observations about how to generate mean or median forecasts of a variable $$y$$ given the model is fit in $$log(y)$$. Of course, I am going to borrow heavily from Rob Hyndman’s blog, where he coverse this.

Killing it while shilling it

Economist Play-in Round Bracket madness is about the descend on us. Before we get to March Madness we’ll have to suffer through a different kind of madness: the Neoliberal Shill Bracket. This year the Neoliberal project has succumbed to inflation and has expanded the field. This year features a play-in round. In this post we analyze the Economist Play-in: Economist Play-in (8) ---@mioana @imbernomics @stanveuger @jodiecongirl @cblatts @jonathaneyer @R_Thaler @florianederer pic.

Phoning it in with R

Recently I have been running R from my Android phone. There are some apps on the Google Play Store that seem to let you emulate R, or connect to a remote version. Instead of doing that, I have been running R directly off my phone using the terminal. Rocking now Writing, running #rstats scripts from the terminal with Emacs, pulling data from Fred, making chartz, All from my oh so very smart phone https://t.

Double Trouble Hazard of Dual Axis Charts

In a blog post the dual y-axis chart just say no Tim Duy asks analysts to give up dual y-axis charts for a new year’s resolution. Like with many resolutions, I predict most will fail at this challenge. I also predict few will take it up. Dual y-axis charts are super popular, especially in finance/economics. As you all know, I care a lot about data visualization. And I have been fighting a losing battle against dual y-axis charts for about a decade.

I shared a chart recently on Twitter that got some attention: static version pic.twitter.com/vtD54nXGio — 📈 𝙻𝚎𝚗 𝙺𝚒𝚎𝚏𝚎𝚛 📊 (@lenkiefer) November 14, 2019 But not just any attention (though I do appreciate all your likes and retweets). This was special. Robert Allison [at]RobertAllison__ at SAS replicated the chart with SAS software and wrote a blog about it. These mortgage rates look shady to me. I worked on a lot of SAS stuff early in my days working at Freddie Mac, and Robert’s SAS graph examples were a resource I often used.

Write Anything

This could have been a tweet. Sometimes it is a tweet. After I have taken a break from social media, blogging, etc and I try to get back in the swing I find it incredibly difficult to get restarted. I feel enormous pressure to say something insightful, something funny, something grand. An effective strategy is not to shoot for the stars. Rather than writing something great, I set my sights lower.

Lower Mortgage Rates Bolster the Housing Market

Mortgage interest rates have moved about a percentage point lower from where they were a year ago. The housing market seems to have responded favorably. On my way into D.C. the other day to do some business, I joined a Twitter exchange originally between [at]Graykimbrough and Adam Ozimek, [at]ModeledBehavior about the effects of Federal Reserve interest policy on the housing market. Seems unlikely housing market was slowed by trade war.

Forecasts from a bivariate VECM conditional on one of the variables

This post is for me and future me, though if you get something out of that, that’s great too. Here I will jot down some notes on something I’ve been thinking about. Because reasons, I have been interested in Vector Error Correction Models (VECM). I’ve been thinking of the case where you estimate an error correction model, and have available external forecasts for one of the variables. How can you easily construct the conditional forecasts for the VECM in R?

Visualizing consumer price inflation and mortgage rates

Today I tweeted something that turned out to be pretty popular: US consumer prices pic.twitter.com/LxIxvEnGFe — 📈 𝙻𝚎𝚗 𝙺𝚒𝚎𝚏𝚎𝚛 📊 (@lenkiefer) October 10, 2019 This was an update to a visualization we have talked about here. In this post I want to provide some updated R code to make this visualization taking advantage of the new gganimate api. I’ll also share some code for mortgage rate plots. The code for the inflation plot is pretty simple.

E-Poster using Flexdashboards and SlickR

I’m hearing that folks have been invited to speak at the upcoming Rstudio conference. Congratulations to the folks who got accepted this year. I am not sure if I’m going to go to the conference this year, but I recommend you consider it if you love R. I spoke there last year, giving an E-Poster. It was a lot of fun. The best part was getting a chance to meet other R enthusiasts.