ILRST 2100 Prelim 2

0.0(0)
Studied by 0 people
call kaiCall Kai
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
GameKnowt Play
Card Sorting

1/65

encourage image

There's no tags or description

Looks like no tags are added yet.

66 Terms

1
New cards

When you _______ the population standard deviation you should use the z-test, when you _________ the sample standard deviation you should use the t-test.

know; estimate

2
New cards

Chapter 7, 7.4 - Checking for Normality and Normalizing Distributions

3
New cards

One way to see whether an assumption of the population normality is possible is to construct a _________ _________ plot of the data

normal probability

4
New cards

a normal probability/quantile plot is a scatterplot of the ( __________ _______, _________ ____________) pairs

normal score, observed value

<p>normal score, observed value</p>
5
New cards

a strong _________ pattern in a normal probability plot suggests that population normality is plausible

linear

6
New cards

systemic departure from a straight-line pattern such as curvature in the plot indicates that it is ____ _______ to assume that the population distribution is normal

not reasonable

7
New cards

correlation coefficient formula

(Cov of X and Y) / [(STD of X) x (STD of Y)

8
New cards

the correlation coefficient r is used as a quantitative measure of the extent to which the points in a scatterplot fall close to a straight line. a value of r close to 1 indicates a _________ linear relationship in the normal probability plot. If r is too much _________ than 1, normality of the underlying distribution is questionable

strong; smaller

9
New cards

if sample size n is small, an r value somewhat below 1 is _____ __________ even when the population distribution is normal; but if n is __________, only an r value very close to 1 supports the assumption of normality

not surprising; large

10
New cards

if r __ critical r for corresponding n, it is not reasonable to assume that the population distribution is normal

<

11
New cards

Chapter 8.1 - Statistics and Sampling Variability

12
New cards

statistic

any numerical measure computed from a random sample

13
New cards

the observed value of a statistic depends on the particular sample selected from the population and it will _______ from sample to sample. This __________ is called sampling __________

vary; variability; variability

14
New cards

a density histogram visually conveys information about the sampling variability in the statistic x bar, or __________ ________ . It provides an approximation to the distribution of x bar values that would have been observed if we had considered every different sample of size 5 in this population

sample mean

<p>sample mean</p>
15
New cards

The actual sampling distribution comes from considering ____ possible samples of size n

all

16
New cards

the distribution that would be formed by considering the value of a sample statistic for every possible different sample of a given size from a population is called its ________ _________

sampling distribution

17
New cards

Chapter 10: Hypothesis testing

knowt flashcard image
18
New cards

a hypothesis test has 5 key steps

1. specifying a null hypothesis (Ho)

2. specifying an alternative hypothesis (Ha)

3. calculating a test statistic (z or t test (use either x bar/mu or p hat/p)

4. Finding the p-value of the test

5. making a decision about the null hypothesis

19
New cards

The null hypothesis has p-value of

0.10

20
New cards

The normal distribution is a symmetric, bell-shaped distribution for _________ random variables with mu = _______ as the mean of the distribution

sigma^2 = __________ is the variance of the distribution

continuous

E(x)

Var(x)

21
New cards

Normal random variables (X) can be standardized through the z formula: z = ?

(X (value) - mu (mean))/sigma(st deviation)

22
New cards

p(a < x < b) =

P((a - mu)/sigma < z < (b-mu)/sigma

= P(a* < z < b*)

23
New cards

given a percentile that corresponds to a particular z-score z*, the corresponding value of the unstandardized normal is...

x* = mu + sigma(z*)

24
New cards

in a normal quantile plot, data that are skewed to the right will have a curvilinear pattern with points at the tails ________ this line

data that are skewed to the left will have a curvilinear pattern with points at the tails _________ this line

below; above

25
New cards

a random sample of size n...

is a sequence of n independent random variables X1, X2, ..., Xn that follow the same probability distribution that has mean mu and variance sigma^2

26
New cards

statistics are...

numerical measures computed from a random sample

27
New cards

parameters are...

corresponding numerical measures computed from a population

<p>corresponding numerical measures computed from a population</p>
28
New cards

while values of a statistic are _______ from the sample, population parameters....

known; remain unknown

29
New cards

review page 4 of review sheet

30
New cards

2 rules for a random sample X1, X2, ... where each X is normally distributed with mean mu and variance sigma^2

1. the sampling distribution of X bar is also normal with

2. mean mu and variance sigma^2/n

31
New cards

central limit theorem tells us that a sufficiently large sample size is _______,

n is greater than or equal to 30

32
New cards

central limit theorem also tells us that (two things)

1. sampling distribution of X bar is normal with

2. mean mu and variance sigma^2/n

33
New cards

we can standardize the sampling distribution of x bar so that the standardized variable Z is

(x bar - mu)/(sigma/sqrt(n))

34
New cards

Sampling distribution of a proportion:

the sample proportion of successes p hat can be viewed as the sample average number of successes in the n trials, or p =

X/n

<p>X/n</p>
35
New cards

in a sample mean, it will follow a normal distribution with E(p hat) =

p

36
New cards

because trials are independent:

Var(p hat) =

(p(1-p))/n

37
New cards

Chapter 9: single sample estimation

38
New cards

estimation of parameters include

point estimation

interval estimation

39
New cards

sample statistics are _________ for the population parameters. The standard deviation of an estimator is called the ________ _______

estimators; standard error

40
New cards

we prefer estimators that are...

unbiased and have small sampling variability

41
New cards

statistics that are biased have a bias given by REVIEW

B(theta hat) = E(theta hat) - theta

42
New cards

the bound on error of estimation (margin of error) is given by...

B = z(alpha/2) * (sigma/sqrt(n))

<p>B = z(alpha/2) * (sigma/sqrt(n))</p>
43
New cards

Confidence interval formula

P(mean +- z*(sigma/sqrt(n)))

44
New cards

confidence interval is simplified to

x hat +- z(sigma/sqrt(n))

45
New cards

margin of error is given by

b = z(sigma/sqrt(n))

<p>b = z(sigma/sqrt(n))</p>
46
New cards

when sigma is not known, the 100(1-a)% confidence interval for mu is...

x hat +- t(sigma/sqrt(n))

47
New cards

Interval estimation for the population proportion, p

48
New cards

standard deviation(p hat) is

sqrt((p(1-p))/n)

<p>sqrt((p(1-p))/n)</p>
49
New cards

z score for an interval estimation for the population proportion p

z = P hat - p/sqrt((p(1-p)/n)

- this follows the standard normal distribution

<p>z = P hat - p/sqrt((p(1-p)/n)</p><p>- this follows the standard normal distribution</p>
50
New cards

the Wald (1-alpha)% confidence interval is

p hat +- z(sqrt(p(1-p)/n)

<p>p hat +- z(sqrt(p(1-p)/n)</p>
51
New cards

the sample size needed to estimate the population proportion WITH a desired margin of error B is...

n = p(1-p)* (z alpha/2)^2)/(B)^2

<p>n = p(1-p)* (z alpha/2)^2)/(B)^2</p>
52
New cards

we can choose p = 0.5 to get...

n = 1/4*((z)^2)/(B)^2

<p>n = 1/4*((z)^2)/(B)^2</p>
53
New cards

for finding the test statistic t when sigma is not known, we have

t = (x bar - mu)/(S/sqrt(n))

t = p hat - po/ (sqrt(po(1-po)/n)

<p>t = (x bar - mu)/(S/sqrt(n))</p><p>t = p hat - po/ (sqrt(po(1-po)/n)</p>
54
New cards

when the stated alternative hypothesis has the test statistic as not equal to the value actually observed, the p-value is

2 * P(T > (x bar - mu)/(s/sqrt(n))

<p>2 * P(T > (x bar - mu)/(s/sqrt(n))</p>
55
New cards

reject the null hypothesis when...

the p-value is less than or equal to the significance level (alpha)

56
New cards

for a one sample t-test for a population mean, a random sample of size n comes from a _________ random variable X

continuous

57
New cards

for a large sample hypothesis test for a population proportion, a random sample of size n comes from a _______ categorical variable X

binary

58
New cards

a sample size must be sufficiently large so that...

np is greater than or equal to 10

n(1-p) is greater than or equal to 10

if sampling without replacement, the sample size is not larger than 10% of the population

59
New cards

when we do not reject Ho and the Ha is true, what kind of error is it?

type ii error

60
New cards

when we reject Ho and Ho is true, what kind of error is it?

type i error

61
New cards

to control Type II error, we should increase sample size so that we have sufficient power, where power =

1 - B

62
New cards

critical value of the test is c =

mu + z(sigma/sqrt(n))

63
New cards

the difference in the sample mean and mu is "statistically significant" when

the confidence interval does not contain mu

64
New cards

practical significance is a statement that the difference between the sample mean and mu is of large enough strength that one would be willing to make...

an economic decision as a result

65
New cards

does statistical significance imply practical significance/vice versa?

No

66
New cards

When the sample size is small (n

similar