stud
bud
Sign up
Log in
Home
Library
Explore
SAT
More
MATH 221 Exam 2 Review Flashcards | StudBud
Explore
/
MATH 221 Exam 2 Review
MATH 221 Exam 2 Review
59 terms
·
StudBud Administration
·
171 plays
Imported from external platform
Flashcards
59 cards
F
Practice quiz
P
Host live
L
Questions
59
Answers
1
What is the standardized measures of the size of an effect?
standard effect
effect size
z-score
statistical power
2
If our model is a good fit, then we'd expect it to be able to explain...
the null & alternative hypotheses
more variance than it can't explain
the probability it occurred by chance alone
more error
3
What is the probability of earning $95,000 or less if $95,000 has a z-score of 1.72?
95.728%
4.272%
95.637%
9.09%
4
If we picked a number other than the mean to be our model, what value (calculated w/ our new number) would change & how?
variance would increase
error would decrease
deviance scores would decrease
standard deviation would increase
5
Why do we use 0.05?
b/c of convention
it's arbitrary
it's a simple benchmark
all of the above
6
When you increase the sample size to create the illusion that something is significant, this is called...
hypothesis testing
p-hacking
statistical power
effect size
7
The larger the test statistic is, ...
the more likely it is incorrect
the less likely it is incorrect
the more likely it is to occur by chance
the less likely it is to occur by chance
8
We calculate the probability that our model would fit the data if...
the null hypothesis is true
the alternative hypothesis is true
the standard error were small
the null hypothesis was rejected
9
99.9% of z-scores lie between...
+/- 2.58
+/- 2.34
+/- 1.96
+/- 3.29
10
The frequency distribution of the sample means from the same population is the...
normal distribution
probability distribution
sampling distribution
frequency distribution
11
Which of the following is a Type II error?
false negative
you say someone is ill, but they are not
rejection of a true null hypothesis
false positive
12
What z-scores cut off the top 0.5% and bottom 0.5% of the distribution?
+/- 1.96
+/- 2.58
+/- 3.29
+/- 2.34
13
99% of z-scores lie between...
+/- 3.29
+/- 2.58
+/- 1.96
+/- 2.34
14
What doe we call the boundaries within which we believe the true value of the mean will fall?
min/max
confidence intervals
interquartile range
standard error
15
What 2 ways have we learned to assess if the sample mean is representative of the population mean?
standard deviation & confidence intervals
confidence intervals & effect size
standard error & confidence intervals
standard error & test statistics
16
What value is the difference between each score in a dataset and the mean?
mean
standard deviation
deviance score
range
17
How do we visually represent the deviance scores on a scatter plot of points when using the mean as the model?
vertical line
a vertical line for each point
horizontal line
a single point
18
What z-scores cut off the top 0.05% and bottom 0.05% of the distribution?
+/- 1.96
+/- 3.29
+/- 2.58
+/- 2.34
19
Does the mean have to be in our data set?
No
Yes
20
When samples vary because they contain different members of the population, this is known as
random sampling
sampling variation
sample mean
stratified sampling
21
Confidence intervals are another way to assess the accuracy of the sample mean as an estimate of the population mean.
False
True
22
Which of the following is non-directional hypothesis?
computer science majors have longer hair than data science majors
computer science & data science majors have different hair lengths
computer science & data science majors have the same hair length
23
If we take multiple samples from a population the means of each sample will be the same.
True
False
24
The Central Limit Theorem tells us that as samples get large enough...
the sample is representative of the population
the standard error gets large
the sampling distribution will be normally distributed
the error goes to 0
25
Why do we need to compute the z-score?
b/c we need our distribution to be normal
b/c we like z-scores
b/c they tell us something about the sample size
b/c we want to compute more values using the z-scores
26
The statistical model that we fit to our data represents...
the test statistic
the null hypothesis
the alternative hypothesis
the variance
27
Since we want to say something about our population from our sample, we care if the sample is representative.
True
False
28
Which of the following is directional hypothesis?
computer science majors have longer hair than data science majors
computer science & data science majors have different hair lengths
computer science & data science majors have the same hair length
29
What does large standard error tell us?
the sample mean is not representative of the population mean
the sample mean is representative of the population mean
the mean is not a good fit as a model for our data
the mean is a good fit as a model for our data
30
The Central Limit Theorem tells us that as samples get large enough...
the sampling distribution will have a mean equal to the population mean
the standard devation gets large
the confidence interval gets large
the sample is not representative of the population
31
What threshold are we usually using (also called the significance level)?
0.02
0.10
0.05
0.01
32
Which of the following is a Type I error?
failure to reject a false null hypothesis
false negative
rejection of a true null hypothesis
someone is ill, but you tell them they're not
33
A positive deviance score tells us...
the mean is a good fit as a model
the mean is overestimating
the mean is equal to the score
the mean is underestimating
34
How do we visually represent the mean as a model on a scatter plot of points?
vertical line
horizontal line
a vertical line for each point
a single point
35
If we're looking for the probability of a certain z-score or higher, which portion of the graph do we look at?
smaller portion
larger portion
36
If we took the mean of thousands of sample means from the same population, what would we get?
one of the sample means
the sampling distribution
the standard error
the population mean
37
The Central Limit Theorem tells us that as samples get large enough...
sampling distribution will have standard deviation equal to standard error
sampling distribution is skewed to the right
the error is large
sampling distribution is skewed to the left
38
If the probability of obtaining the value of our test statistic by chance is less than 0.05, ...
we reject the alternative hypothesis
we have support for the null hypothesis
we reject the null hypothesis
we have support for the alternative hypothesis
39
A statistical model that tests a non-directional hypothesis is called a...
Type I error
Type II error
two-tailed test
one-tailed test
40
If the mean is 4.5 & the outcome for score #3 is 2, what is the error for score #3? outcome_i=\left(model\right)+error_i
6.5
-2.5
2.25
2.5
41
A negative deviance score tells us...
the mean is overestimating
the mean is a good fit as a model
the mean is equal to the score
the mean is underestimating
42
If we use the mean as a model for a dataset on income & our mean is $50,000 how much would we predict someone makes?
$60,000
$25,000
$50,000
$100,000
43
When considering the mean as a model, what value can be thought of as the average error between the mean & the scores?
standard error
variance
range
deviance score
44
What equation do we use to construct the upper & lower bound of the 99% confidence interval?
X=\overline{X}\pm1.96\left(SE\right)
Z=\frac{X-\overline{X}}{s}
\sigma_{\overline{X}}=\frac{s}{\sqrt{n}}
X=\overline{X}\pm2.58\left(SE\right)
45
If dataset 1 has a SD of 1.73 and dataset 2 has a SD of 4.12, what does this tell us?
the mean is a good model for both datasets
the mean is a better model for dataset 2
the mean is a bad model for both datasets
the mean is a better model for dataset 1
46
We build statistical models from our data to...
make predictions
find the mean
compute deviance scores
47
It doesn't matter if our model is accurate.
False
True
48
The more variation our model explains compared to what it can't, ...
the smaller the model will be
the larger the test statistic will be
the smaller the test statistic will be
the larger the model will be
49
As the probability decreases (from the previous question), we gain greater confidence in...
our confidence interval
the null hypothesis
the sample mean being representative of the population mean
the alternative hypothesis
50
The degree to which a statistical model represents the data collected is known as the...
standard error
statistical significance
confidence interval
fit of the model
51
Which of the following can be used to assess if the mean as the model is a good fit for our data?
mean
T-scores
standard deviation
confidence intervals
52
We can use the same probabilities for the tails of the distribution for a one- and two-tailed test.
False
True
53
95% of z-scores lie between...
+/- 2.58
+/- 1.96
+/- 2.34
+/- 3.29
54
A statistical model that tests a directional hypothesis is called a...
Type II error
one-tailed test
two-tailed test
Type I error
55
The mean is the value that is closest to each of the scores (in a dataset) combined.
False
True
56
The standard deviation of sample means compared to the population mean is known as...
central limit theorem
confidence intervals
standard error
population mean
57
What z-scores cut off the top 2.5% and bottom 2.5% of the distribution?
+/- 3.29
+/- 1.96
+/- 2.58
+/- 2.34
58
Test statistics are comparisons of...
variance explained to variance not explained
standard error to confidence intervals
effect to error
null hypothesis to alternative hypothesis
59
What value do we need to calculate to find the probability of a particular score occuring in our distribution?
confidence interval
probability
z-score
standard error
