Zillow expects existing home sales for October to fall 0.5 percent to a seasonally adjusted annual rate (SAAR) of 5.14 million units, down from 5.17 million units in August. But the models we use and the assumptions that underlie them are not always as definitive as we would like. Below we provide greater detail about the assumptions that went into our October 2014 forecast.

Zillow’s existing home sales forecast uses two models:

• A “structural” model than estimates home sales as a function of other economic data. More information about this model can be found here.

• A “historical” model that estimates home sales as a function of past movements in existing home sales as well as recent pending home sales data. More information about this model can be found here.

The historical model considers past values of pending and existing home sales when estimating existing home sales for the current month. When pending home sales increase, existing home sales tend to rise during the subsequent four months. But when existing home sales increase in one month, they are expected to decline during the next two months.

For October, our historical model suggests that existing home sales will fall 0.5 percent to 5.14 million units (SAAR). The decline is driven, in part, by September’s unexpectedly strong existing home sales report.

The structural model typically provides greater insight than the historical model into the broader economic forces that drive existing home sales. But depending on the month, it can rely heavily on forecasts of explanatory variables. In particular, our forecasts of the homeownership rate and the homeowner vacancy rate—which we must forecast anywhere from one to four months ahead because they are only released quarterly—can have large effects on the model estimates. For October, we only need to forecast these variables one month ahead.

The homeownership rate has been steadily declining. Holding all else constant, if it continues to decline through October at its recent pace of anywhere between 0.1 percentage points and 0.3 percentage points per month, then existing home sales would fall between 8.3 percent and 10.2 percent, to between 4.74 million units (SAAR) and 4.62 million units (SAAR).

The homeowner vacancy rate had been falling steadily throughout the recovery, but the most recent data show a small uptick, in line with Zillow’s for-sale inventory series. If nothing else were to change, but the homeowner vacancy rate were to rise in October (in line with recent months) from 1.75 to 1.80, then existing home sales would decline by 8.7 percent to 4.72 million units (SAAR).

Our model is less sensitive to other assumptions, including the following:

• We estimate that the median sales price of existing homes sold in October will increase to $211,000 from $209,000 in September, the result of a best-fit ARIMA model—an ARIMA(2,1,3) process in this instance.
• We estimate that median family income will increase to $66,500 from $66,300 in June, in line with the change in the Consumer Price Index (CPI) for Services.
• We estimate that the number of households will increase to 115.9 million in October, up from 115.8 million in September, the result of a best-fit ARIMA model—an ARIMA(3,1,0) process in this instance.