Flashcards in Introduction: Obtaining and Displaying Data Deck (25):
What is an observational study?
A study that observes individuals and measure variables of interest but does not attempt to influence responses.
What is a controlled experiment?
An experiment which deliberately imposes some treatment on individuals in order to observe their responses.
What is a population?
The entire group of people or objects about which information is wanted.
What is a sample?
The part of the population that is actually being examined, in order to gather information.
When is the design of a statistical study said to be biased?
If it systematically favours certain outcomes.
What are two simple but biased sampling designs?
Voluntary response sample
What are the two major divisions of variables?
What two categories are categorical variables divided into?
What two categories are measured variables divided into?
What are three ways to display categorical data?
What are three ways to display numerical data?
What two things should a good data display do?
Serve a clear purpose
Get the viewer to focus on the substance
In what three ways can you ensure your data display serves a clear purpose?
Show the data
Simplify complex information
Highlight particular figures and situations
In what two ways can you get the viewer to focus on the substance of your data?
Avoid "chart junk" (distracting features)
Avoid distortion - reveal the true nature of the data.
In what three ways can you describe the overall pattern of a histogram?
If the Mode is in the middle, what is the skewing of the data said to be?
If the Mode is to the left, what is the skewing of the data said to be?
If the Mode is to the right, what is the skewing of the data said to be?
What is the difference between anecdotes and data?
Anecdotes don't prove anything, while data does.
An anecdote is getting information about a drug from your friends, whereas a scientist would give data.
What does "beware the lurking variable" mean?
Be careful you're considering every variable that may affect your results.
What is an example of observational studies?
What are controlled experiments limited by?
The fact that they are hard to do and they're expensive.
What is it important to remember when creating a sample?
You want it to be representative of the whole population.
How does allowing people the choice of whether they want to respond or not reduce the quality of your data?
It will create bias as only people who care will answer.