This is our Friday rubric: every week a new Science Page from the **Bob Morrison’s Swine Health Monitoring Project**. The previous editions of the science page are available on our website.

This week, we are sharing a report by the MSHMP team regarding the EMWA analysis for years 2009-2018.

### Key points:

- The EWMA chart is a smoothed chart of the percentage of farms that are breaking.
- Newly added farms to MSHMP increase the denominator therefore diluting the estimate which affects the EWMA chart giving the impression that PRRS season has changed.

### Reminder: What is the EWMA?

The Exponential Weighted Moving Average (EMWA) is a statistical method that averages data over time, continually decreasing the weight of data as it moves further back in time. An EWMA chart is particularly good at monitoring processes that drift over time and is used to detect small shifts in a trend.

In our project, EWMA is used to follow the evolution of the % of farms at risk that broke with PRRSV every week. EWMA incorporates all the weekly percentages recorded since the beginning of the project and gives less and less weight to the results as they are more removed in time. Therefore, the % of farms at risk that broke with PRRSV last week will have much more influence on the EMWA than the % of farms at risk that broke with PRRSV during the same week last year.

MSHMP report chart 4 depicts: 1)the number of new cases (green dots – secondary Y axis) during a specific week and 2)the percentage of farms that broke during that week of the total in the MSHMP project in a smoothed way (blue line/Y axis). The red horizontal line indicates the threshold (upper confidence limit – UCL). This UCL is calculated based on the average of cases during the lowest PRRS months in the year, June, July and August and is recalculated every two years.

When there are more cases than expected, the blue line crosses the threshold (red line) indicating there is an epidemic.

The formula used in the EWMA chart is the following:

where E is the smoothed % of infected herds, *lambda* the constant smoothing the curve, I the % of infected herds during that week and Et-1 is the smoothed % of infected herds during the previous week.

If different smoothing factors are applied to the MSHMP data this would generate different trends and then we would place the threshold based on the sensitivity

that we consider that signals an epidemic.

### Has the incidence of PRRS changed?

One possible reason the EWMA % of cases decreasing might be that the number of farms that are breaking expressed as a percentage is less. This can be due to the fact that the total number of farms sharing PRRS status has been increasing and these new farms might have a lower underlying incidence.