Study that involves the collection, organization, description, analysis, and interpretation of data
Statistics
Variables that are typically integers representing a count of objects or abstract amounts
Discrete (variables)
Type of sample that involves surveying the people you have easiest access to, such as an online poll, or surveying the people near you right now.
Convenience sample
Can you use your notes on the Chapter 1 exam Thursday?
No
Data in its original form
Raw Data
If I were to ask people their T Shirt sizes, what type of variable is that? (be specific)
Ordinal (variables)
Type of sample that involves separating population into groups and selecting random members from each group
Stratified random sample
The type of sample where every single person in the population is sampled.
Census
When raw data is organized into a table with rows and columns
Structured Data
The weight of a newborn baby (in ounces)
Continuous (variables)
The type of sample that is the ideal, where each member of the population has an equal likelihood of being selected
Simple random sample
A researcher wants to know on average how much an insurance salesman makes in commission. He surveys a large sample of people who work in insurance, but forgets to include people who tried out the profession and quit. What type of bias is this?
Survivorship Bias
Name a way raw data can be transformed into a statistic
Counting, ordering, or finding the average
The rankings of the top 10 movies on IMDB
Ordinal (variables)
You survey 50 seniors asking about what theme they'd like for prom this year.
Your friend surveyed 50 seniors as well, and got different results.
This is an example of:
Sampling error
A researcher surveying TV viewers collected the ages of every viewer in the survey. If he wanted to convert this numerical data into ordinal data, how could he do it?
He could set age ranges, such as:
(0-17, 18-39, 40-59, 60+)
(Children, Young adults, middle aged, elderly)
An attempt to make a prediction or conclusion based on the data we collect and analyze
Inference
The names of the top 10 movies on IMDB are why type of variable?
Nominal (variables)
You survey 50 seniors asking about what theme they'd like for prom this year. Explain the difference between parameter of interest and statistic with this example.
Parameter of interest = proportion of whole senior population that want a particular theme
Statistic = proportion of sample of 50 seniors who want a particular theme
How many total chapters are there in OnRamps Stats?
There are 8 Chapters
In structured data, what does each row and column represent?
Each row is a single record or entry
Each Column is a variable
Both ordinal and discrete data can be ordered with numbers. Name the difference between these two types of data
Discrete data represents objects that have been counted, ordinal data numbers are just assigned and don't represent counts. You also cannot calculate statistics on ordinal data.
A student creates an online poll on the RPHS website asking if the school should offer pizza every day in the cafeteria.
Explain the type of bias this would cause, and which side of the question (in favor or opposed) this would likely be biased towards.
Volunteer Bias.
People who like pizza and care about it being offered are far more likely to answer the poll, so there would be a bias toward being in favor of this.
Studies show a link between use of sunscreen and skin cancer. People who use sunscreen are more likely to have skin cancer in the future. We know the sunscreen is not causing higher cancer rates.
What variable is causing this, and what is this type of variable called?
The variable actually causing this is exposure to sunlight. This is a confounding (or lurking) variable.