Question 1

A claim about a population based on statistics from a sample of this population is most commonly called

Accepted Answer

An inference is a conclusion or prediction about a population based on statistics from a sample of that population. It involves using the information from the sample to draw general conclusions about the larger group (the population).

Question 2

Which of the following is a likely sample size for the General Social Survey?

Accepted Answer

The General Social Survey is a nationally representative survey of adults in the United States. A sample size of 2,500 is a common sample size for large national surveys. Choices A and C are too small and choice D is far too large for a survey like the General Social Survey.

Question 3

You want to select a random sample from a large class you are in, so you get a class roster from your instructor. This roster is called:

Accepted Answer

The roster provided by the instructor is a list of all the individuals in the class, which is the sampling frame. The sampling frame serves as the basis for selecting the random sample. The other choices, such as sample population and sampling cluster, are not accurate terminology in this context.

Question 4

In order to assess the attitudes of Buddhists adequately, a researcher ensures that this group is sampled at a much higher rate than the rest of the population. This process is called:

Accepted Answer

Oversampling is the process of purposely selecting more individuals from a particular group or population than would be randomly selected in order to increase the representation of that group in the sample. This is often done to ensure that the attitudes or behaviors of a particular group can be studied in greater detail and precision. In this case, the researcher is oversampling the Buddhist population in order to obtain meaningful conclusions about their attitudes.

Question 5

In a sample of 100 men and 100 women, we find that 75 of the men own dogs and 25 of the women own dogs. In the table of expected frequencies, how many women would we expect to own dogs?

Accepted Answer

All of the marginals would be 100, so 50% of the total sample has dogs, therefore we want 50% of the 100 women to have dogs, so the expected frequency would be 50.

Question 6

In a sample of 100 men and 200 women, we find that 75 of the men own dogs and 175 of the women own dogs. In the table of expected frequencies, how many men would we expect to own dogs?

Accepted Answer

100 x 250 / 300 = 83.33

Question 7

If our research question is "Do blacks and whites differ in their overall health?" Health is measured by a single self-assessment question with the possible responses being: excellent, good, fair, and poor. What is the most likely statistical procedure to use here?

Accepted Answer

This is the best choice, since we have one dichotomy and one ordinal-level variable.

Question 8

When you go to the chi-square table, the goal is to see how _____ _______ you can get with your chi-square value, in order to find your p-conclusion.

Accepted Answer

When you go to the chi-square table, the goal is to see how far to the right you can get with your chi-square value, in order to find your p-conclusion. This is because the area to the right of the chi-square value represents the probability of obtaining a result as extreme or more extreme than the one observed, assuming the null hypothesis is true. The smaller this probability (i.e., the farther to the right the chi-square value is), the stronger the evidence against the null hypothesis and in favor of the alternative hypothesis.

Question 9

To achieve statistical significance, the textbook's key p-value is that p must be below:

Accepted Answer

The normal standard in most fields is to set the significance level at 0.05, indicating a 5% chance that the results were due to chance rather than the actual variable being tested. Therefore, a p-value below 0.05 would achieve statistical significance.

Question 10

A researcher claims based on sample results that men's and women's abortion attitudes differ in the population, but in reality, in the population, they do not differ. This researcher has made:

Accepted Answer

A Type One Error occurs when the null hypothesis is rejected when it is actually true. In this case, the researcher has incorrectly concluded that there is a difference in abortion attitudes between men and women when there is actually no difference in the population.

Question 11

A researcher claims based on sample results that men's and women's abortion attitudes do not differ in the population, but in reality, in the population, they do differ. This researcher has made:

Accepted Answer

This researcher has made a Type Two Error because they have incorrectly failed to reject the null hypothesis that there is no difference in men's and women's abortion attitudes, when in fact there is a difference in the population.

Question 12

Using a crosstab, we are investigating the relationship between sex (M,F) and health (excellent, good, fair, poor). In this crosstab, how many degrees of freedom are there?

Accepted Answer

The number of degrees of freedom in a crosstab is calculated using the formula (r-1) x (c-1), where r is the number of rows and c is the number of columns. In this case, there are 2 rows (one for each sex) and 4 columns (one for each health category), so the number of degrees of freedom is (2-1) x (4-1) = 3. Therefore, the best choice is B.

Question 13

What is the minimum number of degrees of freedom in a crosstab?

Accepted Answer

The minimum number of degrees of freedom in a crosstab is 1, which occurs when you have a 2x2 table. Degrees of freedom for a crosstab are calculated as (R-1)*(C-1), where R is the number of rows and C is the number of columns.

Question 14

Using a crosstab, we are investigating the relationship between educational degree (less than high school diploma, high school diploma, associate's degree, bachelor's degree, graduate degree) and agreement on a Likert-scale survey item (strongly agree, agree, neither agree nor disagree, disagree, strongly disagree). In this crosstab, how many degrees of freedom are there?

Accepted Answer

The degrees of freedom for a crosstab (contingency table) are calculated using the formula (r-1)(c-1), where r is the number of rows and c is the number of columns. Here, we have 5 educational degrees and 5 Likert-scale responses, so the degrees of freedom are (5-1)(5-1) = 4*4 = 16.

Question 15

A researcher thinks that attitudes toward the death penalty vary by sex. What is his likely Null Hypothesis?

Accepted Answer

The null hypothesis is always the assumption that there is no significant difference or relationship between the variables being studied. In this case, the null hypothesis is that there is no significant difference between the attitudes of men and women toward the death penalty. Therefore, choice A is the best answer.

Question 16

In the chi-square distribution for a two-by-two crosstab, only a few of the values are above:

Accepted Answer

In a chi-square distribution for a two-by-two crosstab, most of the values are small, and only a few values are above 4, indicating a significant difference between observed and expected frequencies.

Question 17

The values in a chi-square distribution for a 3x3 crosstab are typically _____ than the values in a chi-square distribution for a 2x2 crosstab.

Accepted Answer

The values in a chi-square distribution for a 3x3 crosstab are typically higher than the values in a chi-square distribution for a 2x2 crosstab because there are more cells in a 3x3 table, which means more degrees of freedom for the chi-square test. This increased complexity can lead to higher chi-square values.

Question 18

What behavior did Weinberg and Williams study in order to provide insight into gender differences?

Accepted Answer

The answer of What behavior did Weinberg and Williams study...

Question 19

In Weinberg and Williams' study of bodily behaviors, their sample can best be described as:

Accepted Answer

The study's sample was not random, as the researchers specifically recruited participants who reported experiencing specific bodily behaviors.

Question 20

According to the Weinberg and Williams research on bodily behaviors, which group was most similar to heterosexual women?

Accepted Answer

The Weinberg and Williams research found that the bodily behaviors of non-heterosexual men were most similar to heterosexual women.

Quiz 4: Using Sample Crosstabs to Talk About Populations: the Chi-Square Test