Unit 1: Univariate Data
This type of variable takes values that are category names or labels
What is a categorical variable?
True or false: r never has units.
What is true?
This type of survey is when you split the population into homogenous groups, and then complete a simple random sample within each group.
What is a stratified random sample?
There are 10 marbles in a bag. Four of them are red. What is the probability of the complement of pulling a red marble from the bag? Include correct notation.
What is P(RedC) = 0.6?
This type of variable takes numerical values for a measured or counted quantity.
What is a quantitative variable?
It's the median of this data set of ages:
68, 69, 70, 70, 44, 45, 43, 42
What is 56.5 years?
This is what we must describe when asked to describe a scatterplot.
What are form (linear or non-linear), direction (positive or negative), strength (weak, moderate, or strong), and unusual features (outliers, high leverage points, clusters, etc.)?
This type of bias occurs when something in the survey influences participants' responses.
What is response bias?
These two terms indicate that events cannot happen at the same time.
What are disjoint and mutually exclusive?
With a skewed data set, this is the appropriate measure of center.
What is median?
This tells us the average distance data values are from the mean
What is standard deviation?
This statistic is described by the following equation:
____________ = actual - predicted
What is residual?
This is something that can only be determined from experiments, and NOT from observational studies.
What is causation/cause-and-effect/a causal relationship?
The following equation describes this statistical concept:
P(A) = P(A|B)
What is independence?
This is how we determine if there are outliers in a quantitative data set.
What is the 1.5*IQR rule? OR What is finding values more than three standard deviations away from the mean?
Lengths of Labrador Retrievers are normally distributed with a mean of 39 inches and a standard deviation of 3 inches. This is the percentage of labs that are shorter than 32 inches long.
What is 0.98%?
These points have unusually high or low x-values (x-values that are far from x-bar in either direction).
What are high-leverage points?
When both the subject and evaluator do not know which treatment was applied, we call an experiment this.
What is double-blind?
This type of random variable takes a fixed number of values with gaps between values.
What is a discrete random variable?
This is how we know if a linear regression model is appropriate.
What are the following:
-quantitative variables
-straight enough scatterplot
-no outliers
-no pattern in residual plot
?
These are the conditions that must be met before using the normal distribution.
What are having a quantitative, symmetric, and unimodal data set?
This statistic is interpreted in the following way:
___% of the variation in [insert response variable] is explained by the [explanatory variable].
What is r2 (the coefficient of determination)?
These are the four principles of experimental design.
What are control, randomization, replication, and blocking (if appropriate)?
P(A and B) = 0.075 and P(B) = 0.2. This is P(A|B).
What is 0.375?
Lengths of Labrador Retrievers are normally distributed with a mean of 39 inches and a standard deviation of 3 inches. This is how long a lab at the 15th percentile would be.
What is 35.892 inches?