Stats Final Quiz Review

When to use ANOVA

-You are comparing more than 2 groups. - You have an interval level variable (rank order) - You also have a categorical variable

One-Tail Single Mean Test (t)

- Hypothesis is less than or greater than - Only one sample - you do NOT know the population SD

One-Tail Single Mean Test (z)

- Hypothesis is less than or greater than - Only one sample - you know the population SD

One-Tail Two Mean Test (different n)

- Hypothesis is less than or greater than - Two samples - you do NOT know the population SD - both samples have different number of cases

One-Tail Two Mean test (same n)

- Hypothesis is less than or greater than - Two samples - you do NOT know the population SD - both samples have same number of cases

When to use Chi-square test?

- You have 2 categorical variables (nominal or ordinal - crosstab and frequency

Two-Tail Single Mean (t)

-Hypothesis is just different - Only one sample - you do NOT know the population SD

Two- Tail Single Mean (z)

-Hypothesis is just different - Only one sample - you know the population SD

Statistics students believe that the mean score on the first statistics test is 65. The instructor thinks the mean score is higher than 65. She samples ten statistics students and calculates a mean score of 67. Assume that she knows that the population standard deviation is 3. She performs a hypothesis test with an alpha level of .05. What is the value of the test statistic (Z) (approximately)? A. 2.108 B. -.667 C. .667 D. -2.108

A. 2.108

Statistics students believe that the mean score on the first statistics test is 65. The instructor thinks the mean score is higher than 65. She samples ten statistics students and calculates a mean score of 67. Assume that she knows that the population standard deviation is 3. She performs a hypothesis test with an alpha level of .05. What is the critical value of Z? A. 1.65 B. -1.96 C. 1.96 D. -1.65

A. 1.65

You are conducting a hypothesis test of the association between race/ethnicity (measured as black, white, or Hispanic) and income using a sample of 15 adults (5 black adults, 5 white adults, and 5 Hispanic adults). What is the within group degrees of freedom? A. 12 B. 14 C. 13 D. 2

A. 12

What is the critical value of Chi-square for the hypothesis test described in questions 8 and 9 (and restated below), using an alpha of .05? The city council is considering a law that would ban smoking in all public facilities. A sample has been selected from the community and tested for support of the ordinance (yes or no). You want to determine if there is a statistically significant relationship between age (IV) measured in two categories (under 40 years old; vs. 40 years or older) and support for the anti-smoking law (DV), measured in two categories (yes or no). A. 3.84 B. 9.39 C. 5.55 D. 3.19

A. 3.84

The city council is considering a law that would ban smoking in all public facilities. A sample has been selected from the community and tested for support of the ordinance (yes or no). You want to determine if there is a statistically significant relationship between age (IV) measured in two categories (under 40 years old; vs. 40 years or older) and support for the anti-smoking law (DV), measured in two categories (yes or no). How many cells will the crosstabulation have? A. 4 B. 2 C. 5 D. 9

A. 4

Use the F-table for an alpha level of .01 to determine the critical value of F in an ANOVA that uses a sample of n=80 to test the association between race/ethnicity (black, white, hispanic, other) and health measured on an interval level scale. A. 4.05 B. 2.49 C. 3.58 D. 2.73

A. 4.05

In an ANOVA test your IV is______ and your DV is ______ A. Categorical/Interval B. Interval/ Categorical C. Dichotomous/ Interval

A. Categorical/Interval

Cell frequencies computed under the assumption that the null hypothesis is true are called: A. Expected Frequencies B. Sum of Squares (SS) C. Observed Frequencies D. Relative Frequencies

A. Expected Frequencies

Statistics students believe that the mean score on the first statistics test is 65. The instructor thinks the mean score is higher than 65. She samples ten statistics students and calculates a mean score of 67. Assume that she knows that the population standard deviation is 3. She performs a hypothesis test with an alpha level of .05. This is an example of a __________ test. A. One-tailed single mean test B. Two-tailed single mean test C. Two mean test

A. One-tailed single mean test

A hypothesis test that tests whether the population mean is greater to or lesser than some predetermined value is called ______________. A. Single Mean Test B. Type II error C. Two Mean Test D. Type I error

A. Single Mean Test

Statistics students believe that the mean score on the first statistics test is 65. The instructor thinks the mean score is higher than 65. She samples ten statistics students and calculates a mean score of 67. Assume that she knows that the population standard deviation is 3. She performs a hypothesis test with an alpha level of .05. What is the null hypothesis (H0)? A. The population mean test score is less than or equal to 65 B. The population mean exam score is greater than or less than 65 C. The population mean exam score is greater than 65

A. The population mean test score is less than or equal to 65

The chi-square test is appropriate for testing associations between variables with which of the following levels of measurement? A. Two nominal level variables B. An ordinal and interval variable C. A nominal level variable and an interval level variable D. Two interval level variables

A. Two nominal variables

In a two-tailed single mean hypothesis test, alpha is: A. distributed in both tails of the distribution B. distributed in only one tail of the distribution C. The probability of rejecting a false null hypothesis

A. distributed in both tails of the distribution

Given the same alpha level, the one-tailed test A. makes it more likely that H0 will be rejected. B. Does not affect the probability of rejecting H0 C. is less dependable than the two-tailed test D. makes it harder to reject H0

A. makes it more likely that H0 will be rejected.

When the null hypothesis in a chi-square test is true, there should be: A. no difference between the row and column marginals B. little or no difference between the observed frequencies and the expected frequencies C. no difference between the observed frequencies and the marginals D. large differences between the observed frequencies and the expected frequencies

B

In a research study conducted to determine if convictions (yes/no) were related to the socioeconomic class of the offender (upper, middle, lower), the chi square critical score was 9.488 and the chi square test statistic was 12.2. We can conclude that: A. We have insufficient evidence to conclude that socioeconomic class is associated with convictions in the population B. Socioeconomic class is associated with convictions in the population C. the probability of getting these results by random chance alone is .5 D. the variation in convictions between categories of socioeconomic class is greater than the variation within.

B.

In the Chi-square test, degrees of freedom are: A. N1+N2-2 B. (R-1)(C-1) C. N-1 D. (R+1)/(C+1)

B. (r-1)(c-1)

How many degrees of freedom does a 2 X 3 crosstabulation have? A. 5 B.2 C.3 D. 4

B. 2

If you reject the null hypothesis in a chi-square test, which statistic should you use to test the strength of the association between your independent and dependent variable? A. Mean Squares B. Cramer's V C. Eta-squared D. ANOVA

B. Cramer's V

In deciding which type of hypothesis test to use, you base your decision on: A. The SD B. The level of measurement of IV and DV C. The alpha level D. The SE

B. Level of measurement of IV and DV

Statistics students believe that the mean score on the first statistics test is 65. The instructor thinks the mean score is higher than 65. She samples ten statistics students and calculates a mean score of 67. Assume that she knows that the population standard deviation is 3. She performs a hypothesis test with an alpha level of .05. What is the result of this hypothesis test? A. reject the null hypothesis and conclude that the population mean score is different from 65. B. Reject the null hypothesis and conclude that the population mean score is greater than 65. C. Retain the null hypothesis and conclude that the population mean score is less than or equal to 65. D. retain the null hypothesis and conclude that the population mean score is not different from 65.

B. Reject the null hypothesis and conclude that the population mean score is greater than 65

As alpha decreases: A. The chance of making a Type 2 error decreases B. The chance of making a Type 1 error decreases C. The chance of rejecting the null hypothesis increases D. The chance of retaining the null hypothesis decreases

B. The chance of making a type 1 error decreases

In hypothesis testing, which hypothesis do directly test in order to draw our conclusions about our research question? A. The hypothesis of statistical dependence B. H0: the null hypothesis C. H1: The research hypothesis D. There is only one hypothesis

B. The null hypothesis

The probability of making a Type I error is __________. A. Very Low B. Alpha C. Beta D. Very high

B. alpha

You are testing the association between parental status (no children, one child, two or more children) and income (measured on an interval scale as the number of dollars earned per year). You collect a sample of 10 people in each of the three parental status groups and obtain their income. If there is a perfect relationship between parental status and income, you should observe that: A. The no children group would have a different mean income than the group with 2 or more children but the same mean income as the group with one child B. the three parental status groups have different mean incomes and the 10 individuals within each parental status group would have the same incomes. C. All parental status groups would have the same mean income and the 10 individuals within each parental status group would all have different incomes D. none of these options would be observed

B. the three parental status groups have different mean incomes and the 10 individuals within each parental status group would have the same incomes.

In hypothesis testing, the _________ variable is the variable that is presumed to exert an effect on the ____________ variable. A. DV ; IV B. Continuous; nominal C. IV ; DV D. Interval; categorical

C. IV; DV

ANOVA is used to test hypotheses about the association between which two types of variables? A. Interval level; categorical with two categories B. Two categorical variables C. Interval level; categorical with more than two categories D. Interval level; dichotomous

C. Interval level; categorical with more than two categories

You have developed a research/alternative hypothesis (H1) that married people are happier than unmarried people. What is the null hypothesis (H0)? A. There is no difference in the happiness levels of married and unmarried people B. Unmarried people are happier than married people C. Married people are equally or less happy than unmarried people D. Happy people are less likely to get married than unhappy people

C. Married people are equally or less happy than unmarried people

For a given alpha level, the one-tailed critical value will be ________ the two-tailed critical value A. Smaller or larger depending on the question B. Equal to C. Smaller than D. Larger than

C. Smaller than

In testing the following hypotheses, what does an alpha level of .01 indicate? H0: People with cats have levels of self-esteem that are equal to or lower than those of women. H0: μ1(dogs) ≤ μ2(cats) H1: People with dogs are happier than people with cats. H1: μ1(dogs)> μ2(cats) A. none of these answer choices is correct B. There will be a 99% chance of concluding that people with dogs are happier than people with cats when they really aren't C. There will be a 1% chance of concluding that people with dogs are happier than people with cats when they really aren't. D. There is a 1% chance of rejecting a false null hypothesis

C. There will be a 1% chance of concluding that people with dogs are happier than people with cats when they really aren't.

A single mean test in which H1 is that the population mean is DIFFERENT than some predetermined value of interest is called: A. Two mean test B. One-tailed single mean test C. Two-tailed single mean test D. Type 1 error

C. Two-tailed single mean test

____________ is a measure of variation while __________ is a measure of variance A. mean squares; sum of squares B. eta squared; mean squares C. sum of squares; mean squares D. sum of squares; eta squared

C. sum of squares; mean squares

We hypothesize that marital status influences opinions on abortion. Marital status is measured in four categories (never-married, married, divorced, widowed). Opinion on abortion is measured in two categories (pro-choice, pro-life). We would test our hypothesis with: A. T-test B. Chi Square C. z-test D. ANOVA

Chi Square

You have a research/alternative hypothesis (H1) that men have more sex partners (measured on a scale of 0 to 30) than women using a sample of 20 men and 20 women and you have no information about the distribution of sex partners in the population. What type of hypothesis test will you use? A. 2 tailed 2 mean test B. 1 tail single mean test C. ANOVA D. 1 tail two mean test

D. 1 tailed two mean test

In the ANOVA summarized below, how many categories does the independent variable have? df between groups: k-1=2 df within groups: n-k: 21 Total: 23 A. 21 B. 2 C. 24 D. 3

D. 3

In an ANOVA with a perfect association between two variables, which of the following would be true? A. one of the group means would differ from the grand mean B. All of the variation in the dependent variable occurs within categories of the independent variable C. the group means would all be equal D. All of the variation in the dependent variable occurs between categories of the independent variable

D. All of the variation in the dependent variable occurs between categories of the independent variable

You are interested in determining whether age (measured in three categories--child, adolescent, and adult) is associated with health (measured in two categories--healthy and unhealthy). Which type of hypothesis test would you use? A. Single mean t-test B: ANOVA C. two mean t-test D. Chi-square

D. Chi-square

Your friend claims that his mean golf score is 63. You have a hypothesis that it is higher than that. What type of test would you use?

D. One-tailed single mean test

In conducting a two mean hypothesis test using t, which part of the test differs depending on whether both samples are the same size or different sizes? A. The alpha level B. The sample means C. The critical value of t D. The calculation of the standard error of the difference

D. The calculation of the standard error of the difference

Rejecting (or failing to retain/accept) a null hypothesis that is true results in _________ error. A. Type II error B. inductive reasoning C. falsifiability D. Type I error

D. Type I error

________________ is a measure of the strength of the association between two variables in an ANOVA. A. F B. Sum of squares C. mean squares D. eta squared

D. eta squared

You are conducting a two mean t-test of the following hypothesis (H1): Older adults (group 1) have higher happiness scores than younger adults (group 2). You calculate an observed t-statistic by subtracting the mean happiness of older adults (group 1) from the mean happiness of younger adults (group 2) and dividing by the standard error of the difference. In order for you to reject the null hypothesis this t-statistic must be _______ A. equal to the critical value of t B. greater than the positive critical value of t or less than the negative critical value of t C. less than the critical value of t D. greater than the critical value of t

D. greater than the critical value of t

Determining Which type of tail test to do

Do you know the population SD? - If yes: z table -If no: t table Is the hypothesis just different or </> - If just different: two tail - if </>: one tail Is there only one sample or is there two? - One: One mean - Two: Two mean

True or False: In an ANOVA hypothesis test that city type influences income level you find that the following group mean income levels: (a) big cities = $55,000 (b) small city = $30,000 and (c) rural town = = $25,000). If you reject the null hypothesis, you can conclude that income in big cities is significantly greater than income in small cities.

False

True of false:: you reject the null hypothesis in an ANOVA hypothesis test when the observed value of F is greater than the critical F

True

True, False, or Other: In an ANOVA hypothesis test, you reject the null hypothesis if the observed value of F is greater than the critical value of V

True

Failing to reject (or retaining) a null hypothesis that is false results in ________ error. Type I error Solar flares (I'm kind of tired of writing distractors) :)) Type II error Failing this class

Type II Error

No association

Variation is within the categories but between categories the same

perfect association

Variation that is between categories not within. Perfect association would be if 3 categories all had different means but within the each individual category each case has the same mean

You want to determine if kids today spend more hours watching television than they did in 1995. From an older study you know that the population mean number of hours of television watched per child was 3 hours per day but you do not know the population standard deviation. You take a random sample of children today and find that, on average, they watch 5 hours per day. What kind of test should you perform? A. Single mean t-test B. Two-mean z-test C. Two mean t-test D. single mean z-test

single mean t-test

In a one-tailed single mean test, H1 states that: A. the population means on a variable differs between two different groups. B. the population mean is different than some predetermined value. C. the population mean can't be determined D. the population mean is greater than some predetermined value or the population mean is less than some predetermined value

the population mean is greater than some predetermined value or the population mean is less than some predetermined value