Surveying the Scene
Experimental
Proposing
(do in order!)
Probability something we should practice
So scattered...
100

In this foundational sampling method, every group of n individuals in the population has an equal chance of being selected.

SRS

100

This is the specific condition applied to the individuals in an experiment.

Treatment

100

Dan wants to investigate the relationship between caffeine consumption and the amount of sleep high school students get. Dan proposes to randomly selects 200 high school students. For one month, the students are asked to keep a daily log recording the exact milligrams of caffeine they consume and the number of hours they sleep each night. At the end of the month, Dan analyzes the data to see if higher caffeine intake is linked to fewer hours of sleep. The proposal is this type of investigation:

Observational Study (survey)

100

If P(A) = 0.6 and P(B) = 0.4 this must be the value of P(A and B) in order for events A and B to be considered independent.

P(A and B) = 0.24

100

Jan investigates the amount of caffine consumed and total hours of sleep. A scatterplot and linear regression output table determines that the correlation coefficient  is 0.7. This is the label for the correlation coefficient.

There is no label

200

An example of this survey method is described here: A principal divides the student body by grade level, then takes a random sample of 25 freshmen, 25 sophomores, 25 juniors, and 25 seniors to ask about prom themes. 

Stratified Sample

200

This describes the phenomenon where some subjects in an experiment respond favorably to any treatment, even when an inactive treatment is given.

Placebo effect

200

Sally also wants to investigate the relationship between caffeine consumption and the amount of sleep high school students get. Sally uses two groups of volunteers and assigns one group to take a 200mg caffeine pill every afternoon, while the other group is given a daily placebo pill. For one month, the students record the number of hours they sleep each night. At the end of the month, Sally compares the average sleep duration between the two groups. This part of her proposal makes this an experiment:  

Assignment into two treatment groups (caffine pill and placebo)

200

If P(A) = 0.6, P(B) = 0.4, and P(A and B) = 0.2, this is the P(A or B).

P(A or B) = 0.8

200

The slope of the LSRL is -0.03. This is the correct interpretation of slope: 

For each additional mg of caffiene, nightly sleep hours is predicted to decrease by 0.03 hours.

300

An example of this sampling technique is: A quality control inspector at a factory tests the 3rd item off the assembly line, and then tests every 20th item after that for defects.

Systematic Random Sample

300

In this type of experiment, neither the subjects nor those who interact with them and measure the response variable know which treatment a subject received. The COVID 19 vaccine trials were an example of this.

Double Blind

300

A student's heavy homework load might cause them to both consume more caffeine and sleep fewer hours. In Sally's proposal, "homework load" acts as an example of this.

Confounding Variable

300

If P(A) = 0.6, P(B) = 0.4, and P(A and B) = 0.12, this is the P(A given B).

P(A given B) = 0.3

300

If r=0.7 for this scatterplot, this is the value and interpretation of R-squared, the coefficient of determination:

49% of the variability in sleep hours can be explained by a linear association between caffeine intake and sleep hours.

400

This type of bias occurs when some members of the population are less likely to be chosen or cannot be chosen in a sample.

Undercoverage Bias

400

This occurs when two variables are associated in such a way that their effects on a response variable cannot be distinguished from each other.

Confounding

400

Sally decides to have students measure their sleep before and after the treatments have been assigned. Using the change in sleep hours is called this and it has this advantage in analyzing the experiments results: (2 responses)

Matched Pairs will reduce the natural variability between experimental units.

400

92% of people support George in the next election. If you find a survey of 10 people, what is the probability that all of them will support George?

.92^10 = 43.4%

400

A reaction time study found the following results between people under 30 and over 30.This percent of people under 30 have times between 5 and 20.  

 75%

500

What is the statistical advantage to using a stratefied sample over a SRS?

It reduces the variability between samples.

500

This is a group of experimental units that are known before the experiment to be similar in some way that is expected to affect the response to the treatments.

Block

500

If Sally could first group the students by their baseline caffeine tolerance (high vs. low) before randomly assigning them caffeine pills or placebos. This experimental design technique is known as this.

Blocking

500

70% of people have detached earlobes. If you take a random sample of 6 people, what is the probability that at least one of them will not have detached earlobes?

1-.7^10 = 88.2%

500

A reaction time study found the following results between people under 30 and over 30. This is the approximate percent of people in this study that are over 30 who are slower than the slowest person under 30.

More than 25% and less than 50%.