ISDS exam 2

A

which one of the following is NOT a step we use when formulating the null and alternative hypotheses? A) calculate the value of the sample statistic B) determine whether it is a one- r a two-tailed test C) include some form of the equality sign in the null hypothesis D) Identify the population parameter of interest

steps in the p-value approach

1. specify the null and alternative hypotheses 2. calculate the value of the test statistic and its p-value 3. state the conclusion and interpret results

C

A Type I error occurs when we: A) reject the null hypothesis when it is actually false B) do not reject the null hypothesis when it is actually false C) reject the null hypothesis when it is actually true D) do not reject the null hypothesis when it is actually true

B

Bias can occur in sampling. Bias refers to: A) the division of the population into overlapping groups B) the tendency of a sample statistic to systematically over- or under-estimate a population parameter C) the creation of strata which are proportional to the stratum's size D) the use of cluster sampling instead of stratified random sampling

D

We use _________ tests to address conflicts between two competing views on a particular population parameter. A) confidence B) alternative C) null D) hypothesis

one-tailed test

a hypothesis test for which only one tail of the sampling distribution is used

time and cost

a sample can provide results more quickly and for a lower cost

non probability sample

a sample in which the items have unknown probabilities of being selected

A

a simple random sample is a sample of observations that is: A) representative of the population from which it was chosen B) obtained randomly from a group of volunteers C) obtained from randomly selected groups called strata

sample

a subset of the population selected for analysis

statistic

a summary measure that is computed to describe a characteristic from only a sample of the population

parameter

a summary measure that is computed to describe a characteristic of an entire population

A

an alternative hypothesis: A) contradicts the status quo B) is true 95% of the time C) states the status quo

C

an important final conclusion to a statistical test is to: A) fail to reject the null hypothesis wen it is false B) reject the null hypothesis when it is true C) clearly interpret the results in terms of the initial claim D) publish the results

A

cluster sampling works best: A) when most of the variation in a population is between groups and not within groups B) when most of the variation in a population is between groups and not within groups C)when there is a variation in a population both within groups and between groups

nonresponse error/bias

error incurred when some subjects refuse to respond to a survey

example of measurement error

ex: CDC Hepatitis Survey, Teacher Evaluation requiring you to fill in your name, order of surgery questions, etc.

example of feasibility

ex: assessing the quality of wine, determining the life time of light bulbs, determining the winner of an election

example of non probability sample

ex: convenience sample

example of nonresponse error/bias

ex: estimating percentage of car crashes that involve alcohol. drunk drivers usually refuse the BAC test

example of time and cost

ex: long version of the Census Form

example of probability sample

ex: simple random sample

hypothesis testing

helps to resolve two competing opinions about the parameter of interest

D

hypothesis testing enables us to determine if the collected _____________ data is inconsistent with that is stated in the null hypothesis. A) parameter B) population C) alternative D) sample

central limit theorem

if the population is not normal (or unknown), then the shape of the sampling distribution is normal for large samples

D

if we were to sample repeatedly from a given population, the average value of the sample means will equal: A) the sample mean minus the population mean, divided by the standard error of the mean B) the population mean divided by the square root of n C) the sample mean D) the population mean

D

in hypothesis testing, if the sample data provides significant evidence that the null hypothesis is incorrect, then we: A) do not reject the null hypothesis B) do not reject the alternative hypothesis C) reject the alternative hypothesis D) reject the null hypothesis

B, D

in hypothesis testing, two incorrect decisions are possible: (2 answers) A) rejecting the null hypothesis when it is false B) not rejecting the null hypothesis when it is false C) not rejecting the null hypothesis when it is true D) rejecting the null hypothesis when it is true

B

in inferential statistics, we use _______________ information to make inferences about an unknown ____________ parameter. A) population, sample B) sample, population C) population, sample D) sample, sample

feasibility

in some cases, taking the population is not a viable option, so decision makers can only rely on information obtained from a sample

yes

is sampling distribution symmetric?

probability sampling

necessary when making conclusions about the population, that is, for statistical inference

A

nonresponse bias occurs when: A) those responding to a survey or poll differ systematically from the non-respondents B) cluster sampling is used instead of stratified random sampling C) portions of the population are excluded from the consideration for the sample D) the population has been divided into strata

coverage error (selection bias)

occurs when certain items are excluded from the sampling frame

B

random samples of size 400 are taken from a population whose population proportion is 0.25. The expected value of the sample proportion is: A) 400 B) 0.25 C) 0.02 D) 0.75

bias

refers to the tendency of the sample statistic t systematically over- or under- estimate a population parameter

probability sample

sample in which items are selected based upon known probabilities

C

stratified sampling is preferred to cluster sampling when the objective is: A) to reduce costs B) to access every possible individual in the population C) to increase precision

null hypothesis

tentatively believed to be true unless overwhelming refuted by data

C

the basic principle of hypothesis testing is to first assume that the __________ hypothesis is true and then determine if the sample data ______________ this assumption. A) alternative, contradicts B) null, requires C) null, contradicts D) alternative, requires

C

the basic principle of the hypothesis testing is to assume that: A) the null hypothesis is true and see if the population data contradicts this assumption B) the null hypothesis is false and see if the population data contradicts this assumption C) the null hypothesis is true and see if the sample data contradicts this assumption D) the null hypothesis is false and see if the sample data contradicts with this assumption

D

the central limit theorem states that, for any distribution, as n gets larger, the sampling distribution of the sample mean becomes: A) smaller B) more spread out than a normal distribution C) larger D) closer to a normal distribution

D

the critical value approach specifies a region of values, called the __________. If the test statistic falls into this region, we reject the __________. A) rejection region, alternative hypothesis B) error area, null hypothesis C) error area, alternative hypothesis D) rejection region, null hypothesis

A

the critical value of a hypothesis test is: A) the value that separates the rejection region from the non-rejection region B) equivalent to p-value C) the value of the test statistic D) not dependent on the significance level of the hypothesis test

critical value

the difference measured by the z-score

sampling distribution

the distribution of all possible sample means is called the _______________ of the mean.

sampling error

the error incurred by taking a sample instead of a census

null hypothesis

the initial statement about population and ordinarily represents a commonly accepted state of affairs, a general position, or the status quo

B

the normal distribution approximation for a binomial distribution is valid when: A) n<30 B) np is greater than or equal to 5 and n(1-p) is less than or equal to 5 C) n is greater than or equal to 30 D) np < 5 and n(1-p) < 5

the alternative hypothesis

the opposite of the null hypothesis and corresponds to what the researcher wants to prove.

C

the sample size required to approximate the normal distribution depends on: A) the magnitude of the standard deviation B) the magnitude of the mean C) how much the population varies from normality

population

the set of all items in a particular study

sampling distribution

the set of all possible sample statistics could be represented by a histogram or distribution

B

the significance level is the probability of making: A) a type II error B) a Type I error C) both Type I and Type II errors D) either a Type I or Type II error

critical value approach and p-value approach

the two equivalent methods to solve a hypothesis test are....

major goal of inferential statistics

to make conclusions about the population based upon a single ample

true

true or false: if the original population is NOT normally distributed, the sampling distribution will be approx. normal large samples ( the shape will approach a normal distribution as sample size increases)

true

true or false: if the original population is normally distributed (bell shaped), the sampling distribution of the mean will be normal, bell shaped

true

true or false: if we had access to data that included the entire population, then the values of the parameter would be known and no statistical inference would be required.

true

true or false: for a given sample size n, a Type I error can only be reduced at the expense of a higher Type II error

true

true or false: the optimal values of Type I and Type II errors require a compromise in balancing the costs of each type of error

A

unlike the mean and standard deviation, the population proportion is a descriptive summary measure that can be used for data that is: A) qualitative B) discrete C) quantitative D continuous

A

we can generally reduce Type I and Type II errors by: A) increasing the sample size B) decreasing the sample size C) increasing the standard deviation D) changing the hypothesized parameter value while keeping the sample size constant

D

we use hypothesis testing to: A) resolve conflicts between two statisticians B) determine the best business plan C) prove a theory D) resolve conflicts between 2 competing opinions

A

what is a primary requirement for a "good" sample? A) it is representative of the population we are trying to describe B) it proves our hypothesis about the population C) it is easy to analyze

B

when a sample statistic is used to make inferences about a population parameter, it is referred to as a/an: A) constant B) estimator C) explanatory variable D) response variable

measurement error

when data collected do not reflect the true measures

A

when testing "u", the p-value is the probability of obtaining a sample mean at least as large or at least as small as the one derived from a given sample, assuming the __________ hypothesis is true. A) null B) pessimistic C) alternative D) optimistic

C

which of the following statements is NOT correct concerning the p-value and critical value approaches to hypothesis testing? A) both approaches state the null and alternative hypotheses B) both approaches lead to the same conclusion C) both approaches use the same decision rule concerning when to reject H_o D) both approaches specify and compute the test statistic

C

which of these is a characteristic of a "bad" sample? A) the statistic computed from the sample has no selection bias B) the statistic computed from sample has no nonresponse bias C) the sample is not representative of the population we are trying to describe D) the sample is typical of information in the population in a systematic way