This is a three-week, group project. During the first two weeks you will spend a few minutes each day gathering information from the web. (Information on finding appropriate web sites is available on the Guidance page.) If an Internet connection isn’t available, you can gather information from the newspaper and from TV. Each member of your group will be responsible for gathering information for one or two forecasters. You will analyze your data and prepare your reports during the third week.

1. You will start by finding data sources for the forecasters you will be evaluating. These forecasters could be the weather reports provided by local television stations (such as NBC, FOX, ABC and CBS), The Weather Channel, the local newspapers, Weather Underground (National Weather Service), or other potential forecasters. [See the Information Resources page for suggestions and examples.]
2. On Monday through Friday of each week, record each forecaster’s high temperature forecast for the following day. Do this for a two week period.
3. At the beginning of the third week, use the Weather Underground (National Weather Service) web site to collect the high temperature that actually occurred for your forecasted dates (this is called verification). The procedure for verifying high temperatures is described on the Guidance page.
4. For each forecaster, determine the average relative forecast error. The average relative forecast error gives you the average error, including whether the forecasts are too high or too low. (The term ‘average’ is the same as the term ‘mean’.)
5. For each forecaster, determine the average absolute forecasting error. The average absolute forecast error gives you the average error, regardless of whether the forecasts are too high or too low. (The term ‘average’ is the same as the term ‘mean’.)
6. Prepare individual and group reports.
• The individual report should list the forecaster(s) for which the individual collected data, the web sites (or other data sources) used, the average relative and absolute errors for each forecaster, and a paragraph for each forecaster, evaluating their ability to accurately predict high temperatures. The paragraph should also include the range of errors found.
• The group report should include a table listing the following information for each forecaster: the data sources used, the average relative and absolute errors, and an accuracy ranking. The report should also issue awards to the best, the worst, the most biased and the least biased forecaster. Each award citation should include a paragraph describing the reasons why the award is being given to that particular forecaster.