What Is Seasonal Adjustment?

A seasonal adjustment is a statistical technique designed to even out periodic swings in statistics or movements in supply and demand related to changing seasons. It can, therefore, eliminate misleading seasonal components of an economic time series. Seasonal adjustment is a method of data-smoothing that is used to predict economic performance or company sales for a given period.

Seasonal adjustments provide a clearer view of nonseasonal trends and cyclical data that would otherwise be overshadowed by the seasonal differences. This adjustment allows economists and statisticians to better understand the underlying, base trends in a given time series.


Key Takeaways

  • Seasonal adjustments are a statistical method to smooth out aberrations in time series of certain types of economic activity that occur on a regular or cyclical basis.
  • These adjustments provide a clearer view of net trends and non-seasonal changes in data.
  • Seasonal estimates are based on the effect sizes of the previous years' fixed event.

Seasonal Adjustment Explained

Seasonality is a characteristic of a time series in which the data experiences regular and predictable changes that recur every calendar year. Any predictable fluctuation or pattern that recurs or repeats over a one-year period is said to be seasonal.

Seasonal adjustments are intended to smooth out aberrations in certain types of financial activity. For example, the U.S. Bureau of Labor Statistics (BLS) uses seasonal adjustment to achieve a more accurate portrait of employment and unemployment levels in the United States. They do this by removing the influence of seasonal events, such as the holidays, weather events, school schedules, and even the harvest period. These adjustments are estimates based on seasonal activity in previous years.

Seasonal events are relatively temporary, usually with a known duration, and they tend to follow a generally predictable pattern each year, at the same time of year. As a result, seasonal adjustments can remove their influence on statistical trends. Adjustments allow statisticians to more easily observe non-seasonal and underlying trends and cycles and get an accurate and useful view of the labor market and buying habits.

Adjusting Data for Seasonality

Adjusting data for seasonality evens out periodic swings in statistics or movements in supply and demand related to changing seasons. By using a tool known as Seasonally Adjusted Annual Rate (SAAR), seasonal variations in the data can be removed. Analysts start with a full year of data, and then they find the average number for each month or quarter. The ratio between the actual number and the average determines the seasonal factor for that time period. To calculate SAAR, take the un-adjusted monthly estimate, divide by its seasonality factor, and multiply by 12. If quarterly data are being used instead, multiply by four.

For example, homes tend to sell more quickly and at higher prices in the summer than in the winter. As a result, if a person compares summer real estate sales prices to median prices from the previous year, he may get a false impression that prices are rising. However, if he adjusts the initial data based on the season, he can see whether values are truly rising or just momentarily increasing by the warm weather.


Seasonal effects are different from cyclical effects, as seasonal cycles are observed within one calendar year, while cyclical effects, such as boosted sales due to low unemployment rates, can span time periods shorter or longer than one calendar year.

Seasonal Adjustments Expose Underlying Trends

Seasonal movements can be substantial, so much so that they can often obscure other traits and trends in the data. If seasonal adjustments are not made, analyses of the data cannot yield accurate results. If each period in a time series—for example, each month in the fiscal year—has a different tendency toward low or high seasonal values, it can be difficult to detect the true direction of the underlying trends of the time series. Difficulties include increases or decreases in economic activity, turning points, and other economic indicators.

Seasonality also affects industries—called seasonal industries—which typically make most of their money during small, predictable parts of the calendar year. For instance, companies that rely on a particular rush of holiday sales will appear to have abnormal earnings compared to non-seasonal businesses.

How the Consumer Price Index Uses Seasonal Adjustment

The consumer price index (CPI) uses X-13ARIMA-SEATS seasonal adjustment software to perform seasonal adjustments of pricing data that is deemed subject to seasonal adjustments such as motor fuels, food and beverage items, vehicles, and some utilities.

CPI economists re-evaluate the seasonal status of each data series each year. To do this, they calculate new seasonal factors each January and apply them to the last five years of index data. Indexes older than five years old are considered final and are no longer revised. The Bureau of Labor Statistics reevaluates whether each series should remain seasonally adjusted or not, based upon specific statistical criteria. Intervention analysis seasonal adjustment is used when a single, non-seasonal event influences seasonally-adjusted data.

For example, when the global recession in 2008 affected fuel prices, intervention analysis seasonal adjustment was used to offset its effects on fuel pricing in that year. Using these methods, the CPI can formulate more accurate price indexes for components and indexes that aren't subject to seasonal adjustment.

Real World Example of a Seasonal Adjustment

As an example, say that the sales of running shoes bought in the summer exceed the amount bought in the winter. This increase is due to the seasonal factor that more people run, or participate in other outdoor activities requiring similar footwear, in the summer.

The seasonal spike in running shoe sales can obscure the general trends in athletic footwear sales across the whole time series. A seasonal adjustment is therefore made to obtain a clear picture of the general trend.