Databases Reference
In-Depth Information
A base dataset
is created with the combined name of “Zip3Pop_join_
PraiaSales”.
View the summary statistics for Zip3Pop_join_PraiaSales.
The new dataset contains three columns: Population from the Zip3Pop
dataset, RowCount (total sales) from the PraiaSales dataset, and Zip3 which
was common to both. Before viewing the dataset, an additional column is
needed: SalesPerCapita.
Right-click on Zip3Pop_join_PraiaSales.csv; select “Create derived dataset”.
Name the new dataset “PraiaPerCapita”.
Click “Select All” to include all existing rows.
Click “New” to define a new computed column.
Name the new column “SalesPerCapita”.
Enter a formula of “RowCount/Population”.
Click “Create” to create the new column.
Click “Create” to create the new derived dataset.
View the new dataset “PraiaPerCapita” using a Boundary Plot.
In the “Show data for” drop-down, select “RowCount (total sales)”; review
the results.
Switch to SalesPerCapita. Again, review the results.
In SalesPerCapita, we see a more accurate picture of areas where the Praia
shoe line is selling well. High sales rates exist in all of coastal southern
California as well as southern Nevada, southern Arizona, and southern New
Mexico. We even see a high sales rate in Oregon around the Eugene area. This
could not have been done without first joining the private Zapata sales data with
the publicly available census data.
Exercise 3.4
In the same way that a new dataset was created to evaluate Praia sales per capita,
evaluate sales for the Fazenda and Montanha lines.
a. Where are Montanha shoes selling best?
b. Where are Fazenda shoes selling best?
c.
In which regions do multiple lines sell best?
