Other than housing, the market seems quite unlike a recession, which jibes with what I'm seeing anecdotally, as business outside of housing seems at full speed. Ed Leamer notes that three indices — payroll employment, the unemployment rate and industrial production — “nearly perfectly reproduce the NBER official peak and trough dates.” and that "things have to get much worse to pass the recession threshold.”...
Leamers model includes the following thresholds:
falling industrial production for six months at a rate of at least 6% per year;
declining payroll employment for six months at a minimum 1% rate per year;
and a six-month rise in the unemployment rate of at least 0.8 percentage point.
“Every recession since World War II has included months that satisfied all three of these limits. And there has never been a time in the expansions during which all three of these limits were satisfied.”
This would be very reassuring, but we must remember he is a macroeconomist.
I remember the Stock-Watson model that was to replace the old Leading Economic Indicators. While highly rigorous--it used a Kalman filter, just like real rocket scientists--the model failed to predict the 1990-1991 recession, and an updated version of the model then failed to predict the 2001 recession. Stock and Watson (download here) discuss, with admirable honesty and clarity, this failure and argue that it is hard to predict recessions because each is caused by a unique set of factors. For instance, housing and durable goods consumption was strong proceeding and throughout the 2001 recession, as the decline was focused on IT manufacturing. By contrast, in the 1990-1991 recessions, housing and durable goods spending slowed considerably. As Stock and Watson say, "without knowing these shocks in advance, it is unclear how a forecaster would have decided in 1999 which of the many promising leading indicators would perform well over the next few years and which would not". Indeed.
I remember asking Watson about what he learned about macro from this venture, as he also does lots of pure theory, and he said, 'stick to seasonals' (ie, you can predict unadjusted monthly output).