Unit 1
What two types of quantitative data can we collect?
Discrete and Continuous
What do we call the strength of a linear regression model between two quantitative variables?
Correlation
Instead of observing multiple instances of a certain scenario, we can save time by using randomly generated numbers to represent a situation. What do we call this practice?
Simulation
What should all probabilities in a given event add up to?
1
What measure of spread do we use when we use the median for the center?
Interquartile Range (IQR)
Fill in the blank: An ___________ variable is a variable whose values are used to explain or predict corresponding values for the ____________ variable.
Explanatory; Response
An experiment may separate a population into certain groups with shared characteristics to control variability. From there, a random sample is taken. What kind of experimental design is this?
Stratified Random Sampling
What is the probability of flipping a heads for times in a row with a fair coin?
1/16
What conditions should be met in order to use the mean and standard deviation for a set of data?
What does it mean for a point to have a negative residual in a linear regression model?
The value of the point is below what is expected from the line of best fit.
What conclusion can we make using a controlled experiment?
That any statistically significant finding has a causal relationship.
What condition must be met for the addition rule to be used concerning probability?
The events must be disjoint.
Name two charts we used to display categorical data
Bar chart, pie chart, segmented bar chart
What are the four things we can describe of a scatterplot?
Form, Direction, Strength, and Unusual Features
What are the three important attributes for a well-designed experiment?
Randomization, Control, and Replication
Finish the statement: Events A and B are independent if and only if...
You may use an explanation or an equation.
Knowing whether event A has occurred (or will occur) does not change the probability that event B will occur.
What are the four things we describe when analyzing distribution of numerical data? Think about the acronym we learned.
Center, Unusual Features, Spread, Shape
It may be tempting to predict any value using a linear model, but choosing an x-value outside of the range of the given points may make the prediction less reliable. This potential error is called what?
Extrapolation
What does it mean for data to be "statistically significant?"
The observed relationship/outcome is so large that it cannot be attributed to chance.
Suppose we have 20 high school students randomly chosen. If there is a 35% chance that a high school student has taken an AP course, what is the probability that 5 of the 20 have taken an AP class?
12.7% chance