Week 9 Truth Flashcards
What Excel feature can help reduce manual data entry errors?
The data validation tool, which controls what a user can enter into a cell.
When should outliers be removed from a dataset?
Only after careful consideration of their cause and their effect on insights drawn from the data.
What should be done if an outlier is caused by an obvious data error?
It can be removed or replaced by a corrected value.
What must you do if outliers are removed but not due to data errors?
Note the removal in the data visualization or documentation so the audience is informed of the step.
What is biased data?
Data that attempts to represent an intended population using a non-random sample.
What is selection bias?
When data drawn from a non-random or unrepresentative sample is used to describe a larger population.
What is Simpson’s Paradox?
When a trend in individual data subsets disappears or reverses when the subsets are combined.
What is survivor bias?
When sample data overrepresents successful outcomes by excluding entities that failed or dropped out.
What is a price index?
The aggregated price of a basket of products and services.
What is the formula for adjusting for inflation?
base year x (calculating year/base year)
What does “aspect ratio” refer to in charts?
The width-to-height ratio of a chart.
What is a dual-axis chart used for?
To show two variables with different vertical ranges on the same chart using a secondary axis.
Why can dual-axis charts be misleading?
They may cause the viewer to misinterpret data by making unrelated lines appear to intersect or correlate.
What is a clearer alternative to using dual-axis charts?
Using two separate charts, each displaying one variable individually.
