Deck 19: Inferential Statistics

Question 1

Which of the following symbols represents a sample statistic?

A) ρ
B) μ
C) SD
D) σ

Answer 1

C

Question 2

Explain how confidence intervals work over repeated sampling.

Answer 2

not answered

Question 3

List and explain the steps in hypothesis testing.

Answer 3

not answered

Question 4

Explain the basic logic of significance testing.

Question 5

Explain the difference between the null hypothesis and the alternative hypothesis.

Question 6

Recognize the symbols used for the mean, variance, standard deviation, correlation coefficient, proportion, and regression coefficient.

Question 7

Which of the following symbols represents a population parameter?

A) SD
B) σ
C) r
D) 0

Question 8

Define inferential statistics.

Question 9

State how to decrease the probability of Type I and Type II errors.

Question 10

Explain the different significance tests discussed in the chapter.

Question 11

Explain the difference between statistical and practical significance.

Question 12

Explain the difference between a probability value and the significance level.

Question 13

Explain the purpose of hypothesis testing.

Question 14

Provide the definition of sampling distribution.

Question 15

Explain the difference between a statistic and a parameter.

Question 16

Draw the hypothesis-testing decision matrix and explain the contents.

Question 17

Explain what an effect size indicator is.

Question 18

Explain the difference between a nondirectional and a directional alternative hypothesis.

Question 19

Explain the difference between a sample and a population.

Question 20

Compare and contrast point estimation and interval estimation.

Question 21

What is the standard deviation of a sampling distribution called?

A) Sampling deviation
B) Standard deviation
C) Standard error
D) Standard variance

Question 22

The "probability of the result of your research study, or a more extreme result, assuming that the null hypothesis is true" is known as the:

A) Alternative hypothesis
B) Research hypothesis
C) Null hypothesis
D) Probability value

Question 23

What significance level do most educational researchers use?

A) .5
B) .1
C) .01
D) .05

Question 24

Which of the following is a directional alternative hypothesis?

A) m₁=m₂
B) 0₂ ≠ 0₂
C) m₁ > m₂
D) m₁ ≠ m₂

Question 25

If you drew all possible samples from some population, calculated the mean for each of the samples, and constructed a line graph (showing the shape of the distribution) based on all of those means, what would you have?

A) A population distribution
B) A sample distribution
C) A sampling distribution
D) A parameter distribution

Question 26

Which of the following best characterizes a sampling distribution?

A) The average value is equal to the true population parameter
B) The standard error is always less than 1
C) It is based on 50 samples
D) The sampling error is the same as the standard error

Question 27

What would happen (all other things being equal) to a confidence interval if you were able to increase the sample size?

A) It will become narrower
B) It will not change
C) It will become wider
D) The sample size has no effect of the width of a confidence interval

Question 28

Which of the following is not true?

A) You can use the "sampling distribution of the mean" in significance testing
B) You can use the "sampling distribution of the difference between two means" in significance testing
C) You can use the "sampling distribution of the correlation coefficient" in significance testing
D) Large sampling error is associated with a small sampling error in a sampling distribution

Question 29

Which of the following symbols stands for the population mean?

A) ρ
B) μ
C) SD
D) σ

Question 30

In statistical hypothesis testing, the hypothesis that is tested is the:

A) Alternative hypothesis
B) Null hypothesis
C) Research hypothesis
D) Probability hypothesis

Question 31

Which of the following statements is a null hypothesis?

A) The coin is not fair
B) There is a correlation in the population
C) There is no difference between the incomes of men and women in the population
D) The defendant is guilty

Question 32

Which hypothesis is viewed as the "status quo" or the "nothing new" hypothesis?

A) Null hypothesis
B) Inferential hypothesis
C) Alternative hypothesis
D) Research hypothesis

Question 33

If a researcher concludes that the confidence interval is 55% plus or minus 5%, then which of the following is true?

A) The level of confidence is 5%
B) The margin of error is 5%
C) The margin of error is 10%
D) The level of confidence is 10%

Question 34

An index (e.g., a mean or a correlation) calculated with sample data is called a ______ whereas an index calculated with the complete set of population data (i.e., everyone in the population) is called a _______.

A) Statistic, Parameter
B) Parameter, Statistic
C) Sample, Population
D) Population, Sample

Question 35

In what type of statistics do you use the value of your sample statistic as your best guess of the unknown population parameter?

A) Descriptive statistics
B) Hypothesis testing
C) Point estimation
D) Interval estimation

Question 36

Compared to a 95% confidence interval, a 99% confidence interval is:

A) Narrower
B) The same
C) Something that cannot be calculated
D) Wider

Question 37

A researcher has calculated the 95% confidence interval. What does that mean?

A) The process she used captures the true population statistic 95% of the time in the long run
B) She can be "95% confident" that her interval will include the population parameter
C) She can be "5% confident" that her interval will includes the population parameter
D) She can reject the null hypothesis.

Question 38

A researcher reports in a mainstream educational research journal that the statistic she calculated had a p >.05. What does this statement mean?

A) The outcome was very unlikely assuming the null is true
B) The research finding is statistically significant
C) The research finding is not statistically significant
D) The probability of this outcome or one more extreme is less than .05

Question 39

What is the difference between a sample statistic and the corresponding population parameter called?

A) Sampling error
B) Sampling deviation
C) Standard error
D) Confidence error

Question 40

A researcher does a study and reports that the statistic she calculated has a p <.05. What does this statement mean?

A) Her outcome was very likely assuming the null is true
B) The probability of this outcome was high
C) The probability of this outcome or one more extreme was .95
D) The probability of this outcome or one more extreme is less than .05 if the null hypothesis is true

Question 41

If you reject the null hypothesis, which of the following should you avoid?

A) Tentatively accepting the alternative hypothesis
B) Claiming that your finding is statistically significant
C) Claiming that you have proven the alternative hypothesis to be true
D) Making sure that your result also is practically significant

Question 42

An effect size indicator tells the researcher:

A) How big of an effect is present
B) If a result is statistically significant
C) about the strength of statistical significance
D) about the strength of the null hypothesis

Question 43

If you claim that your evidence suggests that the observed result was not due to chance, what are you doing?

A) You are claiming that your finding is practically significant
B) You are claiming that your finding must be theoretically important
C) You are claiming that finding was due to sampling error
D) You are claiming that your finding is statistically significant

Question 44

You can use the analysis of variance test for statistical significance when you have how many means to compare?

A) 1 mean
B) 2 or more means
C) 3 or more means
D) 4 or more means

Question 45

Post hoc tests in the analysis of variance are generally required when the independent variable:

A) Has one level
B) Has two levels
C) Has three or more levels
D) Is quantitative

Question 46

When should you set the significance level for your research study?

A) Before the research data have been analyzed
B) After the research data have been analyzed
C) After looking at the probability values
D) The computer sets the significance level

Question 47

Which of the following is not an effect size indicator?

A) Probability value
B) Eta squared
C) Omega squared
D) Correlation coefficient squared

Question 48

If you use a significance level of .01 rather than a significance level of .05 then which of the following will be true (assuming other things equal, such as sample size)?

A) You are more likely to fail to reject your null hypothesis
B) You are more likely to reject your null hypothesis
C) You are more likely to reject a true null hypothesis
D) You are more likely to retain your alternative hypothesis

Question 49

What type of error would you make if you rejected a true null hypothesis (i.e., a false positive)?

A) Type I
B) Type II
C) Type III
D) Type IV

Question 50

Which of the following is the null hypothesis for testing a regression coefficient for statistical significance?

A) H₀: µ_GRE-V = 476
B) H₀: µ_M = µ_F
C) H₀: β_YX1.X2 = 0
D) H₀: ρ_XY = 0

Question 51

Assume that the null hypothesis says a person is "innocent." What is the problem when an innocent person is found guilty?

A) A Type I error was made
B) A Type II error was made
C) A Type III error was made
D) A Type IV error was made

Question 52

How can you minimize the risk of both Type I and Type II errors?

A) Use a smaller alpha level
B) Use a smaller relationship
C) Decrease the sample size
D) Increase the sample size

Question 53

Which of the following steps occurs first in hypothesis testing?

A) Obtain the probability value
B) Determine practical significance
C) Set the significance level
D) Compare the probability value with the significance level

Question 54

If you failed to reject a false null hypothesis (i.e., a false negative), you are making a:

A) Type I error
B) Type II error
C) Type III error
D) Type IV error

Question 55

Assume that the null hypothesis says a person is "innocent." What is the problem when a guilty person is found to be innocent?

A) A Type I error was made
B) A Type II error was made
C) A Type III error was made
D) A Type IV error was made

Question 56

Which of the following is based on your empirical data and is obtained from the computer printout?

A) Significance level
B) Alpha level
C) Probability value
D) Beta level

Question 57

Which of the following significance levels provides the greatest protection against making a Type I error?

A) .5
B) .1
C) .01
D) .05

Question 58

Which of the following is the null hypothesis for testing the difference between two means for statistical significance?

A) H₀: µ_GRE-V = 476
B) H₀: µ_M = µ_F
C) H₀: β_YX1X2 = 0
D) H₀: ρ_XY = 0

Question 59

Which of the following is the null hypothesis for testing a correlation coefficient for statistical significance?

A) H₀: µ_GRE-V = 476
B) H₀: µ_M = µ_F
C) H₀: β_YX1.X2 = 0
D) H₀: ρ_XY = 0

Question 60

What does the researcher usually hope to do in hypothesis testing?

A) Retain the null hypothesis
B) Reject the null hypothesis
C) The researcher usually does not care which hypothesis is supported
D) The researcher hopes not to obtain statistical significance

Question 61

If we drew all possible samples from a population, calculated the correlation coefficient for each of the samples, and constructed a line graph (showing the shape of the distribution) based on all of those sample correlation coefficients, what would we have?

A) The population distribution
B) A sample distribution
C) A sampling distribution
D) A parameter distribution

Question 62

What sampling distribution is used for one-way analysis of variance?

A) The t distribution
B) The F distribution
C) The chi-square distribution
D) The Z distribution

Question 63

If a research finding is statistically significant, what else should you determine?

A) The strength of significance
B) The practical significance
C) The probability value
D) The alpha level

Question 64

Roger's hypothesis states that the two groups are not equal. He has a:

A) Directional null hypothesis
B) Null hypothesis
C) Directional alternative hypothesis
D) nondirectional alternative hypothesis

Question 65

The _____ is a statement that the population parameter is some value other than the value stated by the null hypothesis.

A) Alternative hypothesis
B) Null hypothesis
C) Probability value
D) Significance level

Question 66

Bree hypothesized that members of the experimental group would score differently than the control group. Her hypothesis was a:

A) Nondirectional alternative hypothesis
B) Directional alternative hypothesis
C) Null hypothesis
D) Type 1 hypothesis

Question 67

What sampling distribution is used for the t test for correlation coefficients?

A) The t distribution
B) The F distribution
C) The chi-square distribution
D) The Z distribution

Question 68

The likelihood of rejecting the null hypothesis when it is false is known as:

A) Power
B) Strength
C) Direction
D) Force

Question 69

When a researcher wants to investigate the differences between two independent groups he can analyze the data using techniques. He can use the t Test for independent samples and:

A) One-way analysis of variance
B) t test for correlation coefficients
C) Chi-square test for a contingency table
D) t test for regression coefficients

Question 70

A statement that there is no difference between population means or no relationship between variables in the population is known as the:

A) Alternative hypothesis
B) Null hypothesis
C) Probability value
D) Significance level

Question 71

A researcher is interested in doing a study comparing the effectiveness of two different approaches to teaching spelling. One approach is phonics-based, and the other is not. She randomly assigns 30 first grade children to the phonics-based approach and 30 children to the other approach. Her dependent variable is the number of words the children spell correctly on a 100-word spelling test. In order to compare the groups, what inferential test should she use?

A) Chi-square test for contingency tables
B) Partial correlation coefficient
C) t test for independent groups
D) Post hoc analysis of variance

Question 72

The cut-off that a researcher uses to decide when to reject a null hypothesis is the:

A) Alternative hypothesis
B) Null hypothesis
C) Probability value
D) Significance level

Question 73

In his research, William proposed that his treatment would be so effective that the experimental group would have a higher mean than the control group. He has made a:

A) Nondirectional alternative hypothesis
B) Directional alternative hypothesis
C) Null hypothesis
D) Type 1 hypothesis

Question 74

During significance testing, Dr. Gray looked at his data to see if the relationship between his independent and dependent variables was large enough to be meaningful. In doing so, he was investigating:

A) Statistical significance
B) Practical significance
C) Probability significance
D) Effect size significance

Question 75

What hypothesis do we directly test in statistical hypothesis testing?

A) The null hypothesis
B) The alternative hypothesis
C) The primary hypothesis
D) The directional hypothesis

Question 76

If one has two categorical variables and constructs a contingency table, then what statistical test would be appropriate?

A) t test
B) Normality test
C) Omega-square test
D) Chi-square test

Question 77

In a directional alternative hypothesis,

A) the two groups are equal on the dependent variable.
B) one group scores higher or lower on the dependent variable than the other.
C) the two groups do not differ on the dependent variable.
D) the two groups' scores on the dependent variable are not equal.

Question 78

The _____ is defined as the probability or your finding or a more extreme finding under the assumption that the null hypothesis is true.

A) Alternative hypothesis
B) Null hypothesis
C) Probability value
D) Significance level

Question 79

Jean has conducted a study with an experimental and control group. She conducted an analysis of variance and found that there was a significant difference between the groups. How will she conduct post hoc tests?

A) She will use the Bonferroni procedure
B) She will look at the two group means and see which group scored higher
C) She will calculate a correlation coefficient between the two groups
D) She will conduct a independent samples t test

Question 80

As shown in your book, what kind of test is used to determine whether a correlation coefficient is statistically significant?

A) It is a type of t test because it is based on the t probability distribution
B) It is a normality test because it uses the normal distribution
C) Beta test because it uses the beta distribution
D) Alpha test because it uses the alpha distribution