Unit 1
What is the difference between categorical data and quantitative data?
Categorical is groups or labels, quantitative is numerical or amounts.
What are some tools to determine a relationship between categorical data?
Bar graphs, two-way tables, conditional relative frequencies
What is a sample
A grpup of people selected from the whole observed population
What is a sample space?
The collection of all possible outcomes.
What is a sampling distribution?
The collection of all possible samples from a population
How can we tell which way data is skewing?
The side with the slope that looks like something a skier would go down is how it skews. EX: _|\_ skews right
Explain the how the r-value visually connects to a scatterplot
when r is closer to 1, it has a stronger positive correlation. The closer to 0 it becomes a weaker correlation. And the closer to -1, it becomes a stronger negative correlation.
What are all the sampling types?
Census - measuring the entire population. Random sample - choosing a group of people at random. SRS - using a random number generator to create the sample size. CRS - Divide population into clusters and randomly select some clusters and use the data within the cluster. Stratified RS - Taking clusters but clusters with similar data and taking an SRS from every cluster. Systematic RS - Choosing a random starting place and moving through the data with a fixed interval.
What makes an event mutually exclusive or not?
Mutually exclusive events can never occur at the same time, when they can happen at the same time then they are not.
How do we know if an estimator is biased or not?
An estimator is unbiased if it is typically equal to the population parameter
What is standard deviation?
Standard deviation is on average how much the data varies from the mean.
What is a residual?
The actual response value - the predicted response value
Why are there so many sample types?
All data is different and must be differently measured, so a variety allows for people to choose the exact perfect sampling type.
What makes an event independent?
If the previous trials have no effect on the future trials and each trial has the same probability.
How do you interpret the mean?
For all random samples of size ___, from the (POPULATION), the mean of the distribution of all possible samples of (WHAT IS BEING MEASURED) will have a value of (MEAN)
What is IQR
IQR is the interquartile range, the range between Q1 and Q3. Q1 is the median of the first half of the data and Q3 is the median of the second half of the data.
How is the least squares regression model used?
To find the best line on a scatterplot based on squared residuals.
What is a confounding variable
A third variable that isn't accounted for that affects the outcome of the data which could create a false idea of a correlation.
What is a binomial distribution?
The amount of successes after a set number of trials, with each trial being independent.
How do you interpret the standard deviation?
For all random samples of size ___, from the (POPULATION), the sample mean of the distribution of all possible samples of (WHAT IS BEING MEASURED) will typically vary by about (STANARD DEVIATION) from the population mean of (MEAN).
Explain Z-score
Z score is how much each data point is, in terms of standard deviation, from the mean. It's also called the standard score or standardized score. It can be found through the formula: Z = (X-mean)/std dev
What are high leverage points and outliers?
Why is a randomized experiment good?
It can help cut out confounding variables.
What is a geometric distribution
The amount of trials it takes to get a success with each trial being independent.
What is the central limit theorum?
When the sample of a population is large enough, the distribution of the sample is approximately normal. This works for all distributions of populations.