stud
bud
Sign up
Log in
Home
Library
Explore
SAT
More
AP Stats Final Exam Project Flashcards | StudBud
Explore
/
AP Stats Final Exam Project
AP Stats Final Exam Project
70 terms
·
StudBud Administration
·
14 plays
WHHS Period 2 AP Stats Final Project 2024-2025. By Owen Yang
Flashcards
70 cards
F
Practice quiz
P
Host live
L
Questions
70
Answers
1
Which graphs display quantitative data?
Bar Graph, Histogram, Two-Way Table,
Dot Plot, Pie Chart, Stem Plot, Scatter Plot
Dot Plot, Box Plot, Stem Plot, Histogram, and Scatter Plot
Bar Graph, Pie Chart, Two-Way Table
2
How is the stratified random sampling method different from the block?
Both are the same
Stratified assigns treatments into groups of similar characteristics
Stratified randomly selects treatments into groups
Stratified takes a random sample of all treatments in one go
3
If a distribution fails to state normality or pass the CLT, the last option is to:
Do not assume normality, and proceed with caution
Assume normality and proceed with the inference test
Look at the graph for a symmetric distribution without any outliers
Reject the checks and drop the inference test
4
What happens if a significance test produces a p-value greater than the significance level?
You reject the null hypothesis
You fail to reject the null hypothesis
There is statistical evidence for the alternate hypothesis
You raise the significance level to reject the null hypothesis
5
For mean confidence intervals and tests you can use normcdf?
True
False
6
What are the difference types of chi-squared tests?
Goodness of Fit Test, Test for Homogenize, Test for Independence
Goodness of Health Test, Test for Homogeneity, Test for Independence
Goodness of Fit Test, Test for Homogeneity, Test for Forestall
Goodness of Fit Test, Test for Homogeneity, Test for Independence
7
If a confidence interval for a difference of mean distribution is bounded by both negative values, then
There is reason to assume the feasibility of both means being equal
There is convincing evidence that the 1st mean is less than the 2nd
There is not convincing evidence of a difference in means
It is impossible as you cannot get negative values
8
What are the 4 conditions for a binomial distribution?
Center, Unusual Features, Shape, Spread
Median, Mean, IQR, Standard Deveiation
Binary, Independent, Number, Success
Context, Unusual Features, Form, Strength
9
If a residual plot shows no apparent pattern in the distribution of residuals, then that means the distribution of data:
Has a positive distribution
Has a quadratic distribution
Has a non-linear distribution
Has a linear distribution
10
For a difference of means significance test, the null hypothesis claims:
The mean difference is 0
There is a difference between the two population means
The mean difference is not 0
There is no difference between the two population means
11
What does a correlation of -1 (r = -1) imply about a linear distribution?
There is a weak, negative, linear correlation between the two variables
There is a strong, positive, linear correlation between the two variables
There is a strong, negative, linear correlation between the two variables
There is a weak, positive, quadratic correlation between the two variables
12
How are all statistics affected when multiplying or dividing all values of a distribution by a value?
Only IQR and SD shift
Increases(multiplied/divided) all statistics by the factor
All statistics remain the same
Mean, median, Q1, and Q3 shifts by the factor. IQR and SD stay the same
13
How do you find the value of a residual?
Residual = Actual - Predicted
Residual = (Predicted - Actual)^2
Residual = Predicted - Actual
Residual = (Actual - Predicted)^2
14
What 5 components does a box plot reveal (Also known as a 5 number summary)?
Direction, Unusual Features, Form, Strength, Context
Context, Center, Unusual Features, Shape, Spread
Median, Mean, Mode, Range, Standard Deviation
Minimum, First Quartile, Median, Third Quartile, Maximum
15
The general formula for slope inferences tests is the same as Z and T-tests being Point estimate +/- Margin or Error
True
False
16
Which best describes a confidence interval
A test used to find the probability of getting an precise interval
The interval of p-values for getting the observed extreme value
An interval of plausible values for the true value of a population at a %
A test used to find the probability of getting an extreme value
17
What does it mean for two events to be "independent" of each other?
One event's results influences the other
Both events belong to different populations
One event's result doesn't affect the result of the other
Both events must occur at differing times
18
What does the Law of Large Numbers claim?
Increasing the # of trials increases the accuracy of the sample mean
The bigger the sample value, the bigger the expected value
By the CLT, the sample size must be equal to or greater than 30
For any inference test, your sample size must be greater than 10
19
What does the 10% condition check?
If a distribution can be considered normal
If the distribution has random input to lower the likelihood of bias
If it is safe to determine the results of a distribution to be independent
If there is a large enough sample size to pass the Law of Large Counts
20
Correlation only implies the existence of a relationship between the explanatory and response variables, meaning:
There is a linear association between the two variables
Correlation does not mean causation
The two variables are independent of each other
It is reasonable to conclude an association that relies on causation
21
Increasing the sample size of a confidence interval does what?
Increases the confidence level of the interval
Decreases the margin of error
Raises the width of the interval of plausible values
Decreases the precision and accuracy of the interval
22
What is true about all geometric distributions?
Their distributions are always skewed right
They solve for the probability of an event occurring X amount of times
The mean is equal to the proportion of the event occuring
They have the same exact check conditions as a binomial distribution
23
What do we use a Least Square Regression Line for?
To derive a quadratic equation to a linear one
To predict a "y" value for a given "x" value
To determine the probability of outliers
To find the true mean of a data distribution
24
What happens to correlation if units change?
You need to convert LSRL to the right units
Nothing. Correlation does not have units in the first place
It will change the results of the correlation
You cannot proceed as the units must remain the same
25
What is the best interpretation of a Z-score of -1.5?
The selected value is in the 1.5th percentile
The selected value is 1.5 units below the mean
The selected value is 1.5 standard deviations below the mean
The selected value is 1.5 standard deviations above the mean
26
What is the purpose of a control group?
To increase the sample size, which increases the precision
To create more groups for more trials, leading to more accuracy
To compare the results of a placebo group to another placebo group
To compare the results of a placebo group to an altered group.
27
A sample standard deviation will always be larger than a population standard deviation
False
True
28
What is the difference between the parameter and statistic of a distribution?
The parameter describes the statistic with the population for the sample
The parameter describes the sample with the statistic for the population
The parameter describes population with the statistic for the population
The parameter describes the population with the statistic for the sample
29
Which center is most resistant to outliers?
Mode
Median
Mean
Range
30
What are the 4 parts to a significance test?
Correlate, Check, Calculate Conclude
Choose, Check, Calculate, Conform
Choose, Check, Calculate, Confirm
Choose, Check, Calculate, Conclude
31
How do you find the lower and upper bounds of expected values for a distribution?
LB: Q1 + 1.5(IQR) HB: Q3 - 1.5(IQR)
LB: Q1 - 1.5(IQR) UB: Q3 - 1.5(IQR)
LB: Q1 + 1.5(IQR) HB: Q3 + 1.5(IQR)
LB: Q1 - 1.5(IQR) UB: Q3 + 1.5(IQR)
32
If a distribution is symmetric, you use the Mean and Standard Deviation, not Median and IQR
False
True
33
What does it mean for two variables to be "mutually exclusive?"
Both events cannot happen at the same time, thus share no common outcomes
They influence each other's responses
There is an association between both variables
Both share similar outcomes that can happen at the same time
34
How do you describe a scatterplot distribution?
Parameter, Null Hyp, Alt Hyp, Some Evidence, Significance Level
Linear, Independence, Normality, Equal Variance, Random
Direction, Unusual Features, Form, Strength, Context
Context, Center, Unusual Features, Shape, Spread
35
Which of these statements about random trials are true?
Randomly assigning treatments increases the likelihood of bias
You are always guaranteed to find the true proportion
You can easily determine a probability in a short amount of trials
Randomness is only predictable in the long run
36
What is the empirical rule?
About 68%, 95%, 99% of all the data falls within 1, 2, 3 SD
A graph must can be not normal to follow the 3 SD rule
Data is distributed between 3 SD in both directions
100% of the data falls within the 3 SD limit
37
Raising the significance level does what?
Decreases the chance of rejecting the alternate hypothesis
Increases the accuracy and precision of the test
Increases the chance of proving the null hypothesis not true
Decreases the likelihood of encountering type 1 errors
38
If the Central Limit Theorem is passed, we can assume a distribution to:
To be considered independent
Not be reasonable to use for a inference test
To have some degree of randomness
Have a sampling distribution with an approx normal distribution
39
Raising the % confidence for a confidence interval increases what?
The percent of intervals constructed that will capture the true pop mean
The sample size, increasing the the interval width
The p-value, which makes it more difficult to reject the null hypothesis
The accuracy and precision of the interval for narrowing down the pop value
40
What do the three "P's" in stats represent?
Probability, Percent, Plausibility
Probability, Percent, Proportion
Probability, Perchance, Proportion
Persistence, Percent, Proportion
41
Degree of freedom (df) for chi-squared test is (row - 1)(column - 1)
False
True
42
If a distribution is skewed left, what scenario would always happen?
The mode would be lower than the mean
The mean is larger than the median
The median is larger than the mean
The mode would be lower than the median
43
What is the main difference between mean and proportion confidence intervals and significance tests?
Mean is given the population size
For mean, the sample standard deviation is not given
Proportion is given the population standard deveiation
Proportion can have negative values
44
To calculate a mean inference, we change what from a proportion inference?
We use normcdf instead of tcdf
We use T-score instead of Z-score
We use proportion values instead of values
We use standard error instead of standard deviation
45
The degree of freedom for a slope inference is
Check the T - table
Sample size - 1
Sample size - 2
(Row - 1)(Column - 1)
46
If a distribution appears symmetrical, it is just to immediately assume normality?
True
False
47
How is an experiment different from an observational study?
It has no input from the observer
It has a controlled input by the observer
It is not independent
It has a higher likelihood for potential bias
48
What are some examples of simple random sampling methods?
Shirt method, random name generator, Table or random digits
Hat method, Lucky Key method, Screw method
Checkered Box, Random Number Generator, Bag Method
Hat method, Random number generator, Table or random digits
49
How do you describe linear distributions?
Linear, Independence, Normality, Equal Variance, Random
Minimum, Q1, Median, Q3, Maximum
Center, Unusual Features, Shape, Spread
Direction, Unusual Features, Form, Strength
50
If our sample value is close to what we expect, what would our chi-square value be near?
It would be near 1
It would be a very high magnitude negative number
It would be near 0
It would be a very high number
51
A greater correlation coefficient "r" for a linear distribution means:
A greater y-intercept value
The data is more condensed and linear
A higher proportion of variance that can be explained by the LSRL
A steeper slope
52
What are the check conditions for a slope inference?
Linear, Independence, Normality
Linear, Independent, Normal, Equal Variance, Random
Random, Independence, Normality
Random, 10%, Large Counts
53
What is true about chi-squared distributions?
They are always skewed right
They are always skewed left
They need to have normal distributions to solve for
They can be skewed either way and solved for
54
What is the difference between a "difference of means" and "mean difference" inference?
"Difference of means" analyzes one population's response
"Difference of means" compares two samples from the same population
"Difference of means" compares two separate populations unlike "mean diff"
"Difference of means" has the sample standard deviation
55
How do Chi-Squared test hypothesis' differ from the other significance tests?
They seek to prove or disprove a stated claim rather than a specific value
They assume a set value for the true mean
They assume a set value for the true proportion
Their hypotheses do not differ
56
If a sample is given random assignment, it is not necessary to check for independence
False
True
57
What is the best way to describe bias in stats?
The probability of getting outliers in a set of data
Sampling that consistently under or overestimates the true target value
The chance of getting a value way off from the true value for the center
Someone's outside, personal beliefs that come into factor of a decision
58
If the alternate hypothesis claims inequality, then is the distribution is to be considered two-sided it two-tailed?
True
False
59
What does it mean for two events to be "complementary?"
Their proportions add up to 50%
The response of one does effect the response the other
They are mutually exclusive and thus opposite results of each other
They occur at the same time sharing commonality in their responses
60
Slope confidence intervals and significance tests aim to find:
The true slope for a linear distribution
If two variables are independent
The true mean population
The true proportion population
61
What are the percentiles for Q1, Median, Q3?
They are all in the 50th percentile
1st percentile, 50th percentile, 99th percentile
33rd percentile, 66th percentile, 99th percentile
25th percentile, 50th percentile, 75th percentile
62
Larger sample sizes causes smaller standard deviations
False
True
63
What is the main goal of any sampling method?
To produce a sample that is a "good" representation of the population
To provide a range of numbers of plausible values for the true proportion
To find the chance for an event to occur for differing scenarios
To find the proportion of scenarios that fit the observed one
64
What is a null hypothesis?
An assumed to be false hypothesis that goes with the seeked claim
The hypothesis aimed to be proven correct to dispute a stated claim
An assumed to be correct hypothesis that goes against the seeked claim
The hypothesis aimed to be proven wrong to support the assumed claim
65
What is the p-value of a significance test?
The proportion of intervals that are to capture the true proportion
The probability of getting the observed extreme value
The proportion of tests that will correctly calculate the probability
The percent of intervals that will contain the extreme value observed
66
A mean diff inference will likely have what type of sampling method?
Cluster Random Sample
Simple Random Sample
Stratified Random Sample
Matched-Pairs Random Sample
67
What best describes the standard deviation of a distribution?
The probability of being further away from the mean
The likelihood of a distribution being normal
The typical spread of values from the mean
A random value used to determine the probability of an event occurring
68
If the null hypothesis value is contained within an interval, then what is to be concluded?
The null hypothesis is a plausible value, thus we reject it
The alternate hypothesis is a plausible value, thus we fail to reject it
The alternate hypothesis is a plausible value, thus we reject it
The null hypothesis is a plausible value, thus we fail to reject it
69
How do you find the degrees of freedom (df) for a mean inference?
Sample size -2
Check the table for T*
(Row - 1)(Column - 1)
Sample size - 1
70
What is a type I error?
Accepting the null hypothesis when it is true
Rejecting the null hypothesis when it is not true
Accepting the null hypothesis when it is in fact not true
Rejecting the null hypothesis when it is in fact true