## Statistics for People Who Think They Hate Statistics 3rd Edition By Salkind – Test Bank

**CHAPTER 9**

**Significantly Significant: What It Means for You and Me**

__Part I. Multiple-Choice Questions (20 items)__

- Which of the following is the term associated with identifying differences between groups that are not due to chance?
- Probability
- Meaningfulness
- Significance
- Statistics

Ans: c

- An error that cannot be controlled is called a?
- Type I error
- Chance
- Type II error
- Probability

Ans: b

- The level of chance you are willing to take is called the?
- Beta level
- Power level
- Significance level
- Chance level

Ans: c

- Which of the following is a statement of equality?
- Research hypothesis
- Directional hypothesis
- Nondirectional hypothesis
- Null hypothesis

Ans: d

- The degree of risk you are willing to take that you will reject the null hypothesis when it is actually true is known as a:
- Significance level
- Type III error
- Type II error
- Power

Ans: a

- Which of the following occurs when you accept the null hypothesis when it is really true?
- Type I error
- Correct decision
- Type II error
- Power

Ans: b

- Which of the following occurs when you accept the null hypothesis when it is really false?
- Type I error
- Correct decision
- Type II error
- Power

Ans: c

- Which of the following occurs when you reject the null hypothesis when it is really true?
- Type I error
- Correct decision
- Type II error
- Power

Ans: a

- Which of the following occurs when you reject the null hypothesis when it is really false?
- Type I error
- Incorrect decision
- Type II error
- Power

Ans: d

- What Greek letter is associated with Type I error?
- a
- b
- S
- h

Ans: a

- What Greek letter is associated with Type II error?
- a
- b
- S
- h

Ans: b

- What does 1 – b represent?
- Alpha level
- Type I error
- Type II error
- Power

Ans: d

- When reporting statistical significance, how is this usually represented?
*p*= .05*p*> .05*p*< .05*p*= .01

Ans: c

- If you want to examine the difference between the average scores of two unrelated groups, which of the following statistical techniques should you select?
- Regression
*t*test for dependent samples- Analysis of variance
*t*test for independent samples

Ans: d

- If you want to examine the difference between the average scores of three unrelated groups, which of the following statistical techniques should you select?
- Regression
*t*test for dependent samples- Analysis of variance
*t*test for independent samples

Ans: c

- If you want to examine the difference between the average scores for students on a pretest/posttest measure, which of the statistical techniques should you select?
- Regression
*t*test for dependent samples- Analysis of variance
*t*test for independent samples

Ans: b

- What is the test statistic that is calculated by the statistical procedure known as?
- Critical value
- Significance level
- Obtained value
*p*value

Ans: c

- In order to determine whether or not you will reject the null hypothesis, what must the test statistic be compared against?
- Critical value
- Significance level
- Obtained value
*p*value

Ans: a

- If the obtained value is greater than the critical value, what should you do?
- Reject the null hypothesis
- Accept the null hypothesis
- Set a higher
*p*value - Increase your sample

Ans: a

- If the obtained value is less than the critical value, what should you do?
- Reject the null hypothesis
- Accept the null hypothesis
- Reduce the
*p*value - Decrease your sample

Ans: b

__Part II. Short-Answer Questions (10 items)__

- What is the definition for significance level?

Ans: The significance level is the degree of risk associated with not being 100% confident that what you observe in an experiment is due to what is being tested.

- Complete the following table:

“null” True

“null” False

Reject “null”

Retain “null”

Ans:

“null” True

“null” False

Reject “null”

Type I Error

Power!

Retain “null”

Correct Decision

Type II Error

- What is the formula for calculating power?

Ans: The formula for calculating power is 1 – b

- If you conclude that your findings yield a 1-in-20 chance that differences were not due to the hypothesized reason, what is the corresponding p value?

Ans: If you conclude that your findings yield a 1-in-20 chance that differences were not due to the hypothesized reason, .05 is the corresponding *p* value.

- If you conclude that your findings yield a 1-in-100 chance that differences were not due to the hypothesized reason, what is the corresponding p value?

Ans: If you conclude that your findings yield a 1-in-100 chance that differences were not due to the hypothesized reason, .01 is the corresponding *p* value.

- What are the Greek letters associated with Type I and Type II error?

Ans: Type I error = a and Type II error = b

- List the steps to take when applying a statistical test to the null hypothesis.

Ans: The steps could be stated as follows:

- A statement of null hypothesis
- Set the level of risk associated with the null hypothesis
- Select the appropriate test statistic
- Compute the test statistic (obtained) value
- Determine the value needed to reject the null hypothesis using appropriate table of critical values
- Compare the obtained value to the critical value
- If obtained value is more extreme, reject null hypothesis
- If obtained value is not more extreme, accept null hypothesis

- What is the difference between the obtained value and the critical value?

Ans: The obtained value is the value produced by the test statistic while the critical value is the value against which the test statistic is compared to determine whether to reject or retain the null hypothesis.

- Under the normal curve, if the obtained value falls to the left of the critical value, under what percent of the normal curve did it fall?

Ans: Under the normal curve, if the obtained value falls to the left of a critical value of .05, it falls under 95 percent of the normal curve.

- Under the normal curve, if the obtained value falls to the right of the critical value, under what percent of the normal curve did it fall?

Ans: Under the normal curve, if the obtained value falls to the right of a critical value of .05, it falls under 5 percent of the normal curve.

**CHAPTER 10**

**Only the Lonely**

__Part I. Multiple-Choice Questions (20 items)__

- A good reason to use a one sample Z-test is to know if the sample values are different from a given?
- sample
- value
- collection
- population

Ans: d

- Excel differentiates z-scores and z-values by identifying one sample test by using what function?
- FTEST
- CHITEST
- TTEST
- ZTEST

Ans: d

- The primary purpose of a Z TEST is?
- To provide sample values
- To return the one-tailed probability value
- To return a significance level
- To return a chance level

Ans: b

- The symbol in the Z Test equation is defined as?
- The range of data
- The standard error
- The mean of the sample
- The standard deviation

Ans: c

- What Greek letter represents the population average in a Z Test equation?
- a
- n
- h
- m

Ans: d

- Given that it is impossible to compute
*all*the possible means, what is the best*estimate*that can be used? - ANOVA
- SEM
- Xbar
- T Test

Ans: b

- The formula to compute the standard error of the mean requires the standard deviation for the population divided by the square root of?
- The population average
- The mean of the sample
- The size of the sample
- The standard deviation

Ans: c

- If the obtained z value is more extreme than the critical value, then?
- The hypothesis is non-directional
- The null hypothesis can be accepted
- The null hypothesis cannot be accepted
- The hypothesis is directional

Ans: c

- When you reject the null hypothesis when it is really true, then you have made a?
- Incorrect decision
- Correct decision
- Type II error
- Type I error

Ans: b

- When you reject the null hypothesis when it is really false, then you have made a?
- Type I error
- Incorrect decision
- Type II error
- Correct decision

Ans: a

- If
*z*represents the test statistic used which results in*z*=2.05,*p*<.05 what does this result indicate? - That 2.05 is the critical value
- That 2.05 is not the critical value
- The probability is less than 5% that on any one test of the null hypothesis, the sample and the population averages differ
- The probability is less than 5% that on any one test of the null hypothesis, the sample and the population averages agree

Ans: c

- Using the standard error of the mean allows the researchers to use the table of
*z*scores to: - Reach a decision as to the probability of an outcome
- Determine the mean of the population
- Determine the value of the scores is by chance
- Reach a decision as to the probability of the z value

Ans: a

- In Excel, what are the three components of the ZTEST function?
- Array, m
_{0}, sigma - Array, Xbar, sigma
- Array, n, sigma
- Array, SEM, sigma

Ans: a

- The Array is also known as the?
- Sigma
- Mean score
- AVERAGE
- Mu

Ans: c

- The observed sample mean?
- Array
- Mean score
- Sigma
- Mu

Ans: a

- Given the symmetry of the normal distribution, if AVERAGE(array) < μ
_{0}, then the ZTEST will return a value greater than? - 0.10
- .001
- 0.5
- 0.05

Ans: c

- A Z Test is preferred when the population (n) is?
- >30
- <30
- =30
- ¹30

Ans: a

- Degrees of freedom for the Z Test are not required given that
*z*-scores of 1.96 and 2.58 are used for 5% and 1% respectively. - False
- True

Ans: b

- Excel can apply the Z tests to data arranged in rows or in columns, but the statistical packages present the results typically by.
- Rows
- Columns

Ans: b

- Because these compare between two means to suggest whether both samples come from the same population the Z Test is similar to.
- ANOVA
- Chi-Test
- F-Tests
- T- Tests

Ans: d

__Part II. Short-Answer Questions (10 items)__

- What can be said about data points and Z Tests?

Ans: Data points should be independent from each other.

- If the
*n*is less than 30, what should the distribution be?

Ans: The distributions should be normal if *n* is low.

- If
*n*> 30, what should the distribution be?

Ans: The distribution does not have to be normal if n > 30.

- When analyzing data types what type of chance should each individual have for being selected?

Ans: All individuals must have equal chance of being selected.

- Write the formula used for computing the value for a one sample Z-Z-test and define each of the three components.

Ans: where Xbar is equal to the mean of the sample; m is equal to the population average and SEM is equal to the standard error of the mean.

- A test is conducted for H
_{0}: μ = 34, with σ = 5. A sample size of 100 is selected. Calculate the standard error of the sampling distribution.

Ans: The calculated standard error of the sampling distribution is 0.5.

- A test is conducted for H
_{0}: μ = 20, with σ = 4. A sample of size 36 has = 21.4. Calculate the Z Test.

Ans: Test result is 2.1 if for H_{0}: μ = 20, with σ = 4. A sample of size 36 has = 21.4.

- If you have designed a 99% confidence interval to estimate the population average (μ) with a known standard deviation for the populationstandard deviation for the populationstandard deviation for the population (σ), what is supposed to be the correct critical values range for
*z*?

Ans: The critical values are to be ±2.58 because *z*-scores of 1.96 and 2.58 are used for the confidence level of 95% and 99% respectively.

- If you have a sample of size 60 and a sample mean of 8.3 was selected from a population where σ = 1.2 (the standard deviation for the population), determine the interval for the population average (μ) at the 95% confidence interval.

Ans: 8.3 ± 1.96 __1.2__

√60

- You have a sample of 45 male teens ages 15-19 have with a mean height of 70.8 inches and assume you have a σ = 1.5 inches. What is the equation that will determine the standard error of the mean?

Ans: SEM = __1.5__

√45

**CHAPTER 11**

*t*(ea) for Two (Again): Tests Between the Means of Related Groups

__Part I. Multiple-Choice Questions (20 items)__

- Examining one group of subjects under two different conditions would require what statistical technique?
- Regression
*t*test for dependent samples- Analysis of variance
*t*test for independent samples

Ans: d

- When comparing two groups the term independent explains that:
- One group is compared to other similar groups
- One group is compared to dissimilar groups
- Two groups are related
- Two groups are not related in any way

Ans: d

- In the formula that computes a
*t*value, what does*n*S*D*represent? - Sum of the difference between groups
- Sum of the means for Group 1
- Sum of the means for Group 2
- Sum of the differences squared

Ans: b

- In a
*t*test for dependent samples that examine the difference between a pretest and posttest, what type of hypothesis is used? - Nondirectional
- Directional
- Null
- Research

Ans: c

- In order to be 99% confident you have not committed a Type I error, at what level should you set your
*p*value? - .01
- .10
- .05
- .15

Ans: d

- In order to compute the test statistic or
*t*value, you must first approximate the sample size through calculating which of the following? - Pooled variance
- Standard deviation
- Degrees of freedom
- Mean score

Ans: c

- What is the test statistic calculated by the statistical procedure selected known as?
- Critical value
- Significance level
- Obtained value
*p*value

Ans: c

- To determine whether you will reject the null hypothesis, the test statistic must be compared against the:
- Critical value
- Significance level
- Obtained value
*p*value

Ans: b

- If the obtained value is greater than the critical value, what should you do?
- Reject the null hypothesis
- Accept the null hypothesis
- Set a higher
*p*value - Increase your sample

Ans: a

- If the obtained value is less than the critical value, what should you do?
- Reject the null hypothesis
- Accept the null hypothesis
- Reduce the
*p*value - Decrease your sample

Ans: c

- What is the formula used to calculate degrees of freedom for a
*t*test for dependent groups? *n*_{1}– 1*n*_{1}+*n*_{2}– 1*n*_{1}– 1 +*n*_{2}*n*_{1}+*n*_{2}

Ans: a

- How many subjects were examined based on the following:
*t*_{(29)}= 2.001,*p*< .05? - 29
- 30
- 31
- 32

Ans: a

- In the following, what are the degrees of freedom:
*t*_{(29)}= 2.001,*p*< .05? - 29
- 30
- 31
- 32

Ans: a

- What does the Excel function TTEST compute?
*t*value- Probability of the
*t*value occurring - Critical
*t*value - Obtained
*t*value

Ans: c

- What Excel function requires that you enter the
*t*value, degrees of freedom, and the number of tails? - TTEST
- TEST2
- TDIST
- TDIST2

Ans: a

- What is another name for a dependent samples
*t*test? - Paired sample
- Two sample
- Independent sample
- Freed sample

Ans: c

- What is used to examine the degree of relationship between variables?
- Hypothesized mean difference
- Pearson correlation
- Observations
- Variance

Ans: a

- Which of the following relates to the difference you expect?
- Hypothesized mean difference
- Pearson correlation
- Observations
- Variance

Ans: b

- How many observations are there for each case in a
*t*test for dependent samples? - One
- Two
- Three
- Four

Ans: b

- Which of the following represents degrees of freedom?
*fd**df**d**f*

Ans: d

__Part II. Short-Answer Questions (10 items)__

- What does the
*t*test for dependent samples allow you to examine?

Ans: A *t* test for independent samples allows you to examine the difference between the means of two groups that are related in some way. For example, you can examine the means from a pretest and posttest for a group of students.

- Given the following, what should you conclude?
*t*_{(24)}= 2.001 and*t*_{critical}= 1.94

Ans: Conclusion: Reject the null hypothesis and accept the research hypothesis.

- What is the formula for calculating a
*t*value for a dependent samples test?

Ans:

- What does P(T<=t) two-tail represent?

Ans: The probability of *t* occurring by chance for a one-tailed test

- What does
*t*critical one-tail represent?

Ans: The crucial value one needs to exceed for a one-tailed test

- What does
*t*stat represent?

Ans: The value of the *t* statistic

- What is another term that statisticians use when talking of dependent tests? Explain.

Ans: Statisticians talk of dependent tests as repeated measures because the measures are repeated across time, conditions, or some factor, and they are repeated across the same cases, be the case a person, place, or thing.

- Explain the difference between a test of dependent and independent means.

Ans: A test for dependent means tests one group of subjects and each subject is tested twice while a test for independent means tests two different groups of subjects and each group is tested once.

- When using the Amazing Analysis ToolPak to compute t value for dependent samples, which test should you select?

Ans: Select the *t* Test: Paired Two Sample for Means option when computing the t value for dependent samples.

- Consider the following set of conditions: The focus is the difference between scores on a pretest and a posttest, the participants are being tested more than once, and there are two groups. Which test should you use?

Ans: Under these conditions, the appropriate test statistic is the t test for dependent means.

## Reviews

There are no reviews yet.