Deck 16: Hypothesis Testing With Measures of Association and Regression

Question 1

Your research hypothesis is that there is a negative association (as indicated by Kendall's tau-b) between social class and happiness with life. Based on the following output, the sample results are consistent with the _____, the significance level is _____, and the null hypothesis is _____.
Symmetric Measures
$\begin{array}{|l|r|r|r|r|}\hline & \text { Value } & {\begin{array}{c}\text { Asymp. Std. } \\\text { Error? }\end{array}} & \text { Approx. T? } & \text { Approx, Sig. } \\\hline \text { Ordinal by Ordinal Kendall's tau-b } & .199 & .088 & 2.210 & .027 \\\text { N of Valid Cases } & 122 & & & \\\hline\end{array}$
a. Not assuming the null hypothesis.
b. Using the asymptotic standard error assuming the null hypothesis.

A) null hypothesis … skipped … not rejected
B) null hypothesis … .0135 … rejected
C) research hypothesis … .0135 … rejected
D) research hypothesis … .027 … not rejected

Answer 1

null hypothesis … .0135 … rejected

Question 2

What kinds of questions can you answer using tests of significance for measures of association?

Answer 2

Is the association between these two variables statistically significant? Is there a significant positive association between these two variables? A significant negative association?

Question 3

For which of the following inferential statistics must you identify hypotheses as one-tailed or two-tailed?

A) chi-square
B) F ratio
C) t statistic
D) all of the above

Answer 3

t statistic

Question 4

In SPSS output the significance levels for regression coefficients are not marked as one- or two-tailed. That means they are

A) one-tailed significance levels
B) two-tailed significance levels
C) universal significance levels (the same value for one- and two-tailed tests)

Question 5

Which SPSS procedure would you use to answer the question "Is there a significant relationship between nationality and religious affiliation?"

A) Bivariate Correlation
B) Chi-square
C) Linear Regression
D) One-way ANOVA

Question 6

Which SPSS procedure would you use to answer the question "Does gender have a significant net effect on amount given to charity after controlling for age and personal earnings?"

A) Bivariate Correlation
B) Chi-square
C) Linear Regression
D) One-way ANOVA

Question 7

Based on this correlation matrix, which of the following is true?
Correlations $\begin{array}{|ll|r|r|r|r|}\hline & \text { AGE } & \text { EDUC } & \text { HOURS } & \text { TVHOURS } \\\hline \text { AGE } & \text { Pearson Correlation } & 1 & .112^{\circ} &{.226^{\circ}} & -.079 \\& \text { Sig. (2-tailed) } & & .038 & .001 & .220 \\& \mathrm{~N} & 341 & 341 & 211 & 240 \\\hline \text { EDUC } & \text { Pearson Correlation } & .112^{\circ} & 1 & .037 & -.240^{\prime \prime} \\& \text { Sig. (2-tailed) } & .038 & & .593 & .000 \\& \mathrm{~N} & 341 & 341 & 211 & 240 \\\hline \text { HOURS } & \text { Pearson Correlation } & .226^{\circ} & .037 & 1 & -.049 \\& \text { Sig. (2-tailed) } & .001 & .593 & & .560 \\& \mathrm{~N} & 211 & 211 & 211 & 146 \\\hline \text { TVHOURS } & \text { Pearson Correlation } & .079 & -.240^{\prime \prime} & -.049 & 1 \\& \text { Sig. (2-tailed) } & .220 & .000 & .560 & \\& \mathrm{~N} & 240 & 240 & 146 & 240 \\\hline\end{array}$
*. Correlation is significant at the 0.05 level (2-tailed).
*. Correlation is significant at the 0.01 level (2-tailed).

A) There is a significant negative correlation between AGE and EDUC.
B) There is a significant negative correlation between AGE and TVHOURS.
C) There is a significant negative correlation between EDUC and TVHOURS.
D) There is a significant negative correlation between HOURS and TVHOURS.

Question 8

Your research hypothesis is that there is a positive correlation between AGE and years of schooling (EDUC) . Based on the following output, the sample results are consistent with the _____, the significance level is _____, and the null hypothesis is _____.
Correlations
$\begin{array}{|ll|r|r|}\hline & & {\text { AGE }} & \text { EDUC } \\\hline \text { AGE } & \text { Pearson Correlation } & 1 & .190^{\circ} \\& \text { Sig-(2-tailed) } & & .036 \\& \mathrm{~N} & 122 & 122 \\\hline \text { EDUC } & \text { Pearson Correlation } & -190^{\circ} & 1 \\& \text { Sig-(2-tailed) } & .036 & \\& \mathrm{~N} & 122 & 122 \\\hline\end{array}$
*. Correlation is significant at the $0.05$ level (2tailed).

A) null hypothesis … skipped … not rejected
B) research hypothesis … .018 … rejected
C) research hypothesis … .036 … not rejected
D) research hypothesis … .036 … rejected

Question 9

Which of the following conclusions is supported by these regression results?
$\begin{array}{|l|l|r|r|r|r|r|}\hline & \text { Unstandardized Coefficients }&&\text { Standardized Coefficients} \\\hline \text { Model } & {\text { B }} & \text { Std. Error } & {\text { Beta }} &{t} & \text { Sig. } \\\hline 1 & 1.873 & 2.512 & & .746 & .456 \\& \text { (Constant) } & -.018 & .045 & -.021 & -388 & .698 \\\text { AGE } & .030 & .088 & .018 & 337 & .737 \\\text { CHILDREN } & .396 & .051 & .420 & 7.688 & .000 \\\text { EDUC } & -294 & .112 & -139 & -2.623 & .009 \\\hline\end{array}$

A) AGE has a significant positive net effect on SCIFACTS.
B) CHILDREN has a significant positive net effect on SCIFACTS.
C) EDUC has a significant positive net effect on SCIFACTS.
D) RELINTEN has a significant positive net effect on SCIFACTS.

Question 10

Which variable has a significant net effect on willingness to allow legal abortion (ABORTOK)?
Coefficients"
$\begin{array}{|ll|r|r|r|r|r|}\hline &&\text { Unstandardized Coefficients}&&\text {Standardized Coeficients}\\ \text { Model } &&{\text { B }} & \text { Std. Error } & {\text { Beta }} & {\mathrm{t}} & {\text { Sig. }} \\\hline 1 & \text { (Constant) } & 2.327 & 1.648 & & 1.412 & .160 \\& \text { AGE } & .034 & .058 & .042 & .584 & 560 \\& \text { EDUC } & .100 & .064 & .117 & 1.560 & .120 \\& \text { RELINTEN } & -.729 & .202 & -.257 & -3.606 & .000 \\& \text { SIBLINGS } & -.036 & .078 & -.034 & -.461 & .646 \\\hline\end{array}$
a. Dependent Variable: ABORTOK

A) AGE
B) EDUC
C) RELINTEN
D) SIBLINGS

Question 11

Which SPSS procedure would you use to answer the question "Is there a significant positive correlation between strength of attachment to a religion and amount given to charity?"

A) Bivariate Correlation
B) Chi-square
C) One-Sample T Test
D) One-way ANOVA

Question 12

Your research hypothesis is that there is an association (as indicated by Cramer's V) between race and highest educational degree. Based on the following output, the sample results are consistent with the _____, the significance level is _____, and the null hypothesis is _____.
$$\begin{array}{l}\text { Symmetric Measures }\\\begin{array} { | l l | r | r | } \hline & & \text { Value } & \text { Approx, Sig. } \\\hline \text { Nominal by Nominal } & \text { Phi } & .278 & .000 \\& \text { Cramer's V } & .196 & .000 \\ { \mathrm { N } \text { of Valid Cases } } & & 450 & \\\hline\end{array}\end{array}$$

A) null hypothesis … .000 … not rejected
B) null hypothesis … skipped … rejected
C) research hypothesis … .000 … rejected
D) research hypothesis … skipped … not rejected

Question 13

Which SPSS procedure would you use to answer the question "Do the countries of North America, South America, Europe, and Oceania significantly differ in average national life expectancy?"

A) Bivariate Correlation
B) Independent-Sample T Test
C) One-way ANOVA
D) Two-way ANOVA

Question 14

Which SPSS procedure would you use to answer the question "Does a nation's level of economic development have a significant negative net effect on its population growth rate after controlling for climate and religion?"

A) Bivariate Correlation
B) Independent-Sample T Test
C) Linear Regression
D) One-way ANOVA

Question 15

Which SPSS procedure would you use to answer the question "Is there a significant difference between the average national population growth rates of South American and North American countries?"

A) Bivariate Correlation
B) Independent-Sample T Test
C) Linear Regression
D) One-way ANOVA

Question 16

Which SPSS procedure would you use to answer the question "Is there a significant difference in the average amount given to charity by Americans, Germans, Japanese, and Swedes?"

A) Bivariate Correlation
B) Chi-square
C) Linear Regression
D) One-way ANOVA

Question 17

Which SPSS procedure would you use to answer the question "Is there a significant negative correlation between a nation's level of economic development and its population growth rate?"

A) Bivariate Correlation
B) Independent-Sample T Test
C) One-Sample T Test
D) One-way ANOVA

Question 18

Your research hypothesis is that there is an association (as indicated by Cramer's V) between race and highest educational degree. Based on the following output, the sample results are consistent with the _____, the significance level is _____, and the null hypothesis is _____.
$$\begin{array}{l}\text { Symmetric Measures }\\\begin{array} { | l l | r | r | } \hline & & \text { Value } & \text { Approx. Sig. } \\\hline \text { Nominal by Nominal } & \text { Phi } & .217 & .382 \\& \text { Cramer's V } & .154 & .382 \\\text { N of Valid Cases } & & 135 & \\\hline\end{array}\end{array}$$

A) null hypothesis … skipped … not rejected
B) research hypothesis … skipped … rejected
C) research hypothesis … .154 … not rejected
D) research hypothesis … .382 … not rejected

Question 19

Your research hypothesis is that there is a positive correlation between a person's years of schooling (EDUC) and their mother's years of schooling (MAEDUC). Based on the following output, the sample results are consistent with the _____, the significance level is _____, and the null hypothesis is _____.
Correlations
$\begin{array}{|ll|r|r|r|r|}\hline & &{\text { EDUC }} & \text { MAEDUC } & \text { PAEDUC } & \text { SPEDUC } \\\hline \text { EDUC } & \text { Pearson Correlation } & 1 & -.111 & .261^{*} & .120 \\& \text { Sig. (2-tailed) } & & .234 & .007 & 433 \\& \mathrm{~N} & 122 & 116 & 107 & 45 \\\hline \text { MAEDUC } & \text { Pearson Correlation } & -.111 & 1 & .356^{*} & .013 \\& \text { Sig. (2-tailed) } & .234 & & .000 & .931 \\& \mathrm{~N} & 116 & 116 & 104 & 44 \\\hline \text { PAEDUC } & \text { Pearson Correlation } & .261^{*} & .356^{*} & 1 & .030 \\& \text { Sig. (2-tailed) } & .007 & .000 & & .847 \\& \mathrm{~N} & 107 & 104 & 107 & 43 \\\hline \text { SPEDUC } & \text { Pearson Correlation } & .120 & .013 & .030 & 1 \\& \text { Sig. (2-tailed) } & .433 & .931 & .847 & \\& \mathrm{~N} & 45 & 44 & 43 & 45 \\\hline\end{array}$
**. Correlation is significant at the $0.01$ level (2-tailed).

A) null hypothesis … skipped … not rejected
B) null hypothesis … .117 … not rejected
C) research hypothesis … .117 … not rejected
D) research hypothesis … .234 … not rejected

Question 20

Your research hypothesis is that there is an association (as indicated by Kendall's tau-b) between social class and political orientation. Based on the following output, the sample results are consistent with the _____, the significance level is _____, and the null hypothesis is _____.
Symmetric Measures
$\begin{array}{|l|r|r|r|r|}\hline & \text { Value } & {\begin{array}{c}\text { Asymp. Std. } \\\text { Error? }\end{array}} & \text { Approx. T? } & \text { Approx, Sig. } \\\hline \text { Ordinal by Ordinal Kendall's tau-b } & -.031 & .082 & -.385 & .700 \\\text { N of Valid Cases } & 119 & & & \\\hline\end{array}$
a. Not assuming the null hypothesis.
b. Using the asymptotic standard error assuming the null hypothesis.

A) null hypothesis … skipped … not rejected
B) null hypothesis … .350 … not rejected
C) research hypothesis … .skipped … not rejected
D) research hypothesis … .700 … not rejected

Question 21

Answer the questions that follow this SPSS output:

A) Is the regression model as a whole statistically significant? (yes / no)
B) Which of the independent variables, if any, have statistically significant coefficients? (If this step in hypothesis testing can be skipped, write the word "SKIP".)

Question 22

Before checking the significance levels of the net effects of the independent variables in a multiple regression, the significance of what should be checked?

Question 23

Hypothesis tests for which measures of association must be identified as one-tailed or two-tailed?

Question 24

Answer the questions that follow this SPSS output:

Your research hypothesis is "In the population, AGE has a positive net effect on INCOME after controlling for SEX and years of schooling (EDUC)." ()

A) What is your null hypothesis?
B) Are the sample results consistent with the research hypothesis or with the null hypothesis?
C) What is the probability of getting the sample results you got if the null hypothesis is true? (If this step in hypothesis testing can be skipped, write the word "SKIP".)
D) What is your conclusion? (In other words, do you "reject" or "not reject" the null hypothesis based on these results?)
E) Are your results statistically significant? (yes / no)

Question 25

Are weak associations between variables always nonsignificant? Are strong associations always significant?

Question 26

What kinds of questions can you answer using tests of significance for regression coefficients?

Question 27

Answer the questions that follow this SPSS output:

Your research hypothesis is "In the population, there is an association (as indicated by Kendall's tau-b) between number of children and marital happiness." (〖tau-b〗_(CHILDREN*HAPMAR)≠.00))

A) What is your null hypothesis?
B) Are the sample results consistent with the research hypothesis or with the null hypothesis?
C) What is the probability of getting the sample results you got if the null hypothesis is true? (If this step in hypothesis testing can be skipped, write the word "SKIP".)
D) What is your conclusion? (In other words, do you "reject" or "not reject" the null hypothesis based on these results?)
E) Are your results statistically significant? (yes / no)

Question 28

Answer the questions that follow this SPSS output:

Your research hypothesis is "In the population, there is an association (as indicated by Cramer's V) between type of family in which raised and marital happiness." ()

A) What is your null hypothesis?
B) Are the sample results consistent with the research hypothesis or with the null hypothesis?
C) What is the probability of getting the sample results you got if the null hypothesis is true? (If this step in hypothesis testing can be skipped, write the word "SKIP".)
D) What is your conclusion? (In other words, do you "reject" or "not reject" the null hypothesis based on these results?)
E) Are your results statistically significant? (yes / no)

Question 29

Answer the questions that follow this SPSS output:

Your research hypothesis is "In the population, there is a positive association (as indicated by Kendall's tau-b) between highest educational degree and marital happiness." ()

A) What is your null hypothesis?
B) Are the sample results consistent with the research hypothesis or with the null hypothesis?
C) What is the probability of getting the sample results you got if the null hypothesis is true? (If this step in hypothesis testing can be skipped, write the word "SKIP".)
D) What is your conclusion? (In other words, do you "reject" or "not reject" the null hypothesis based on these results?)
E) Are your results statistically significant? (yes / no)

Question 30

Answer the questions that follow this SPSS output:
Your research hypothesis is "In the population, there is a correlation between age (AGE) and willingness to allow legal abortion (ABORTOK)." ()

A) What is your null hypothesis?
B) Are the sample results consistent with the research hypothesis or with the null hypothesis?
C) What is the probability of getting the sample results you got if the null hypothesis is true? (If this step in hypothesis testing can be skipped, write the word "SKIP".)
D) What is your conclusion? (In other words, do you "reject" or "not reject" the null hypothesis based on these results?)
E) Are your results statistically significant? (yes / no)

Question 31

Answer the questions that follow this SPSS output:

Your research hypothesis is "In the population, there is a positive correlation between age (AGE) and education (EDUC)." ()

A) What is your null hypothesis?
B) Are the sample results consistent with the research hypothesis or with the null hypothesis?
C) What is the probability of getting the sample results you got if the null hypothesis is true? (If this step in hypothesis testing can be skipped, write the word "SKIP".)
D) What is your conclusion? (In other words, do you "reject" or "not reject" the null hypothesis based on these results?)
E) Are your results statistically significant? (yes / no)

Question 32

Are the significance levels that appear in the output for the net effects of the independent variables in regression one-tailed or two-tailed significance levels?