The two articles we were assigned to read focused on how to effectively use data, and which data you should actually trust. Kelly McGuire asks some key questions like: What is data? How is data collected? and How often is the data updated and how? Another step she highlights is determining if additional resources are needed to interpret the information provided, such as Plotyly that we have used in class. She also warns against using multicolinearity. This happens in a multiple regression analysis when two or more predictor variables are highly correlated, and thus do not provide any unique or independent information to the model. The article by U of Saskatchewan mainly focuses on how to determine what sources are reliable or not. They talk about primary, secondary, and tertiary sources, and Scholarly Vs. Popular sources. It goes through an in-depth summary of how to find data and how to determine if it is reliable or not.
The data I found was the the US Fish and Wildlife Service. They studied the decline in nesting sites in Alaska. It gives multiple different species, the numbers of nests, and the percentage of the decline over 22 years. I chose this data set because I am a pretty big outdoorsman and I do have a concern for their decline in numbers.
- Source: Data.gov
- Who made it: The US Fish and Wildlife Service researched and created the data
- How it was collected: An independent study by Peter Shepern of the Alaska Dpt. of Fish and Game
- How old it is: It is quite old. It was released when the study was finished which was in 1964 and has not been updated.
- The format: The format is a PDF of a data set just like you would find in an excel document (probably didn’t have excel in the 60’s)
- The type: It is a time series because it gives the number of nests recorded over the 22 years
- How I would use the data: I would use the data to back up my statement that waterfowl populations are on the decline. The decline in nests being recorded is a direct correlation to the population density because it means there is less offspring being produced.