Seasonally adjusted unemployment?

Seasonally adjusted unemployment?

There is this growing trend in the world of macroeconomic statistics, to seasonally adjust data.  Computation is cheap and easy, so why not compute?  Back in the days of the adding machine, it would have taken a lot more time and effort to seasonally adjust the data.  But think of what it is doing.  Was just reading in RGE Monitor about Hong Kong’s seasonally adjusted unemployment rate.  By having seasonally adjusted data quoted at me, I have lost the information that was there in the seasonal cycle.  Were I to do a univariate time series forecast, I would end up forecasting seasonally adjusted unemployment with the data at hand.  I would have lost the information in the cycle, which I need for a forecast.

And the point is, do I want to know how this December’s unemployment compares with other Decembers before it?  Not really.  What I want is an absolute number of the poor unemployed souls in the state of Hong Kong.  Each soul is dear to me.  And that I cannot get from seasonally adjusted data.

So there is and isn’t a place for seasonal adjustment, and I wish that in the future statistical agencies have the nous to give both seasonally adjusted and unadjusted data.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: