Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

AP Statistics > AP Exam Review > Flashcards

AP Exam Review Flashcards

1
Q

What are two ways to increase power?

A
  1. Increase sample size

2. Increase significance level (alpha)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

To get the largest power, look for the distribution with the _______p-value

A

Smallest

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is power?

A

The probability of rejecting a false Ho

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

When the p-value is low…

A

…reject the Ho.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What 4 graphs can display univariate numerical data?

A

Dot plot
Histogram
Stem plot
Box plot

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

r

A

Correlation coefficient

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Interpret r

A

There is a strong/weak, pos/neg, linear association between _____ and ______.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

R squared

A

Coefficient of determination

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Interpret R squared

A

___% of the variation in y can be explained by x

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Three characteristics of a binomial

A
  1. 2 outcomes
  2. Constant probability
  3. Fixed number of trials
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is InvNorm for?

A

To find the z score if you know the probability (use the area to the left)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

How do you use normalcdf?

A

Put in the lowest z score and the highest z score

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is the formula for outliers?

A

Q3+1.5IQR

Q1-1.5IQR

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What kind of tests can you use with numerical data/means?

A

One sample t test
Two sample t test
Matches pairs t test

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What type of tests can you use with categorical data/proportions?

A

One proportion z test
Two proportion z test
Chi square test

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What are 2 measures of center?

A

Mean

Median

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What are 2 measures of spread?

A

Range
IQR
Standard deviation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What is a Type I error?

A

Ho is true, but we think Ha is true.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What is a Type II error?

A

Ha is true but we think Ho is true.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What is the difference between a binomial and a geometric distribution?

A 
Geometric = count the number of trials until you get a success
Binomial = count the number of successes in a fixed number of trials
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

What are the 3 principles you should incorporate when you design an experiment?

A 
Control = Treat all subjects the same except for the treatment
Randomization = Assign subjects to treatment groups randomly
Replication = Assign multiple subjects to each treatment group
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What are three types of experiments?

A

Completely Randomized Design
Randomized Block Design
Matched Pairs

23
Q

What is another name for subjects?

A

Experimental units

24
Q

The x variable or independent variable is called…

A

Explantory Variable

25
Q

The y variable or dependent variable is called…

A

Response Variable

26
Q

What are 4 ways to randomly sample people?

A

Simple Random Sample
Cluster
Stratified
Systematic

27
Q

What is a block?

A

A group of subjects that are similar in some way (gender, age, etc). The subjects in each block are split apart and randomly assigned to each treatment group.

28
Q

What is the difference between stratified and cluster sampling?

A

Stratified = groups are made so they are similar based on a characteristic (age, race, etc.). Then survey some from EVERY group.

Cluster = Groups are usually naturally occurring and are mixed. Survey a few of the groups, not all of them.

29
Q

What is systematic sampling?

A

Start with the ___th person. Sample every ___th person.

30
Q

What is Ms. Fortune’s favorite Starbucks drink?

A

Java Chip Frappachino :)

31
Q

What are 4 types of bias?

A

Response Bias
Non Response Bias
Voluntary Bias
Undercoverage

32
Q

A badly worded question or an embarrassing survey topic might result in _______ bias.

33
Q

A survey conducted by a police officer, teacher, or other authority figure might result in _____ bias.

34
Q

A survey in which people choose to participate might result in _________ bias. To avoid this type of bias, the researcher should randomly choose people to participate.

35
Q

A survey conducted during homeroom or first period might miss the opinions of students who are chronically late to school. This is an example of ________________.

A

Undercoverage

36
Q

What happens to the standard deviation of a sampling distribution as n increases?

37
Q

For the LSRL given, interpret the slope:

Predicted Exam Grade = 50 + 15 hrs studied

A

For every increase in 1 hour studied, on average your exam grades increases by 15 points.

38
Q

For the LSRL given, interpret the y-intercept:

Predicted Exam Grade = 50 + 15 hrs studied

A

When you study 0 hours, your predicted exam grade is 50.

39
Q

If a linear model is appropriate for a scatterplot, the residual plot shows ________________

A

no pattern

40
Q

How do you calculate a residual?

A

e = actual y - predicted y

41
Q

What is a residual?

A

The distance between a point on the scatterplot and the Least Squares Regression Line.

42
Q

What is extrapolation?

A

Using a LSRL to make a prediction for an x value outside the range of your data. Extrapolation is not a good idea because the pattern may not continue.

43
Q

What is an influential point?

A

A point whose removal significantly changes the LSRL.

44
Q

True or False: If you add a constant to every piece of data in your data set, measures of spread do NOT change.

45
Q

True or False: If you multiply every piece of data in your data set by n, measures of spread are also changed by a factor of n.

46
Q

Name two statistics that are resistant to outliers and skew.

A

Median

IQR

47
Q

Name three statistics that are non-resistant.

A

Mean
Standard Deviation
Range

48
Q

What kind of distribution has a mean and a median that are approximately equal?

A

A distribution that is symmetrical

49
Q

What are the 3 conditions for a one sample z test?

A 
Random
Independence (n 10)
50
Q

What are the 3 conditions for a one sample t test?

A

Random
Independence (n30 OR
2. Original pop is normal OR
3. Graph of sample is approx normal

51
Q

What are the 3 conditions for a Chi Square test?

A
  1. Random
  2. Categorical data
  3. Expected values >5
52
Q

What are the 4 conditions for a Linear Regression t test?

A
  1. Random
  2. Linear Model is appropriate because the scatterplot shows a linear trend.
  3. The y-values are approx normal because a graph of the residuals is approx normal.
  4. Sigma of y is approx the same for all x values since the points are evenly spaced around the regression line.
53
Q

As you increase the confidence level, what happens to the confidence interval?

A

It gets wider.

54
Q

How do you calculate degrees of freedom for…

  1. t-test
  2. Chi Square GOF
  3. Chi Square
  4. LinReg t test
A

t test = n-1
Chi Square GOF= categories -1
Chi Square = (rows -1)(columns - 1)
LinReg t test = n-2

AP Statistics (1 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2025 Bold Learning Solutions. Terms and Conditions