Practice Question 8.1

What null hypothesis is appropriate for both two-sample t-tests and for ANOVA?

A.  H(0): The population means are equal.
B. H(0): The population means are zero (0).
C. H(0): The population means are not equal.
D. H(0): One population mean is less than, or greater than, the other population mean.

What one alternative hypothesis is appropriate for both two-sample t-tests and for ANOVA?

A. H(1): One population mean is less than, or greater than, the other population mean.
B. H(1): The population means are equal.
C. H(1): The population means are not zero (0).
D. H(1): The population means are not equal.

The ANOVA table tell if one population mean is less than another population mean?

True
False
True False

What is the appropriate situation for the ANOVA method?

A. When the question is about the equality of two or less population means.
B. When the question is about do three or more population means equal zero (0).
C. When the question is about the difference between two or more population means.
D.  When the question is about the equality of three or more population means.

What is the main reason why three two-sample t-tests are not used to find out if three population means are equal?

A.  Losing control of the Type I error rate (α).
B. Two-sample t-tests are not appropriate when the question is about more than two population means.
C. Two-sample z-tests should be used instead.
D. Two-sample t-tests are more laborious to do.

In the ANOVA table, why are two variances analyzed when the question is about the equality of three population means?

A. Variances are the only other sample statistic available to use.
B. Three variances need to be analyzed to answer a question about the equality of three population means.
C. Analyzing variances takes one hypothesis test, giving control of the Type I error rate (α).
D. Two sample variances contain enough information about the population means.

What two variances are analyzed in the ANOVA table.

A. The theoretical variance of the sample averages coming from probability information.
B. The actual variance of the sample averages coming from sample information.
C. The difference variance coming from subtracting the largest and smallest sample variances.
D. The estimated variance coming from the researcher's estimation of the variance.

What two equations express the main logic of the ANOVA table.

A. Does: the sample averages = each other?
B. Does: s²_x = (s²/m) ?
C. Does: the Actual Variance of the sample averages = the Theoretical Variance?
D. Does: the spread of the sample averages = the spread of the population means.

In the ANOVA table, what information does the Theoretical Variance give?

A. The spread of the sample averages if they all came from one population.
B. The spread of the sample averages if they came from different populations.
C. The spread of the sample averages.
D.  ~The spread of the population means.

In the ANOVA table, what information does the Actual Variance give?

A. The spread of the sample variances.
B. The spread of one population mean.
C. The spread of the sample averages.
D. The spread of the population means.

In the ANOVA table, how are the two variances actually analyzed?

A. By subtracting the two variances and seeing if the value is close to zero (0).
B.  By dividing the two variances and seeing if the value is close to one (1).
C. By adding the two variances and seeing if the value is close to one (1).
D. By converting the two variances into F-values and using the F-table to get probability.

Select the two tables that make up the ANOVA method, as discussed in this class?

A. The Levene's table.
B. The Reference table.
C. The ANOVA table.
D. The Tukey table

Please match the two tables below with the appropriate question they answer.

A.  Tukey Table
B.  ANOVA Table

__ An overall test to learn if the population means differ.
__ A series of pairwise tests to learn how the population means differ.

Please match the two views below with how the data values are arranged.

A. Long View
B. Wide View

__ The data values are arranged in several columns, one column per population.
__ The data values are arranged in one column, all populations together.

What part of a dataset is the focus when converting a data set from a wide view to a long view of the data values?

A. The number of columns.
B. The variable names.
C. The data values.
D. The population names.

What part of a dataset is the focus when converting a data set from a long view to a wide view of the data values?

A. The number of columns.
B.  The population names.
C. The variable names.
D. The data values.

When is a wide view of the data values most useful?

A.  When using hand calculations to statistically analyze the data values.
B. When using a computer to statistically analyze the data values.
C. When a lot of populations in the study make it hard to statistically analyze the data values.
D. When a lot of individuals in the study make it hard to statistically analyze the data values.

When is a long view of the data values most useful?

A. When using hand calculations to statistically analyze the data values.
B. When a lot of individuals in the study make it hard to statistically analyze the data values.
C. When a lot of populations in the study make it hard to statistically analyze the data values.
D.  When using a computer to statistically analyze the data values.

In a long view of the data values, what is the column containing the data values called?

A. The factor variable.
B. The continuous variable.
C. The number of populations in the factor variable.
D.  The response variable.

In a long view of the data values, what is the column containing the population names called?

A.  The factor variable.
B. The number of populations in the factor variable.
C. The response variable.
D. The continuous variable.

In a long view of the data values, what does levels mean?

A. The number of data values in the response variable.
B. The number of factor variables in the data set.
C. The number of columns in the data set.
D.  The number of populations in the factor variable.

In the method of ANOVA, what does the assumption of Normality mean?

A. The shape of the response variable is normal.
B.  The shape of each population, by itself, is normal.
C. The shape of each data value is normal.
D. The shape of the factor variable is normal.

In the method of ANOVA, what does the assumption of Equal Variance mean?

A. All data values have the same variance.
B.  All populations have the same variance.
C. The mathematical sign in H(1) is not equal (#).
D. All variables, response and factor, have the same variance.