![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEioaXb6rw7b3NUXwmOHNePWAdjL2ABo-0j0x2NMqirmvnhy7xnNBTnfScNBREd05f_cMhyrMIkRw5gvm1nUOjfHzgr2oufSI_S8EklqXzoe5zcXNmEq-Qj7lJnISQ9PjNw8auaPohCL190Z/s320/levels.png)
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhxkRC57emPTXvM5lTqJX6P-gXdQFMxZ_ESGUNrMLNy9PqHYgw5JBwFgBFLU7c1xJpb7qGqLC_9DgoPtnGMLQ7wkt5YcAtkwOAqCQusaJFXrdMZ12XTfFR-3BAauWRJ3xU0i9aumro13sj3/s320/household.png)
But let's not be too hasty. Following the same approach as for last month's employment report, I looked at the 12-month growth rates in unadjusted establishment employment (see the third chart).
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgADq_WAMH39EClbmQcev0jOjavvcFlf-hN4oA4jCvHU4W_JfbUPJkd6gsR7Xy9UWpM6Ny1cXfFBxELrCbOkrC7lgPShnZ9kDH_Aw_DJa_ETE0r93fVegAMfDcLm6r6id088FJaSNPXH2J3/s320/empgrowth.png)
Conclusion: How you filter the data matters a lot. There is no reason you should trust my year-over-year filter more than what the BLS uses (X11, X12, or some variant) to do seasonal adjustment, but at least the year-over-year filter is simple enough for a simpleton like me to understand exactly what it is doing. The more I think about seasonal adjustment, the less I trust it, particularly at times like this when all the unusual shocks hitting the economy are likely to confuse X11 (X12, or whatever). The reason we use seasonal adjustment is so that we can conveniently eyeball time series. If we could train ourselves to eyeball the unadjusted series, that would be great. I actually tried with the unadjusted employment series and just gave myself a headache. Maybe Jeff Miron can do this, but I can't.
Check out Brad DeLong's comment on this analysis.
ReplyDeleteIt's located here:
ReplyDeletehttp://delong.typepad.com/sdj/2010/07/department-of-huh-stephen-williamson-doesnt-know-what-he-is-doing-department.html
Well, negative attention is better than none. As I've said before, I've never claimed to be an expert on anything, or to know what I'm doing. I'm glad Brad is reading my stuff.
Another thing to look at is initial claims. The improvement in the 4-week moving average of initial claims has virtually stalled since mid-December. You can see the charts here: http://globaleconomicanalysis.blogspot.com/2010/06/four-week-moving-average-of-weekly.html
ReplyDelete-- Dave