MaizePrepSTATS 250

Exam 3 Mock: Part II

Exam 3 Mock: Part II
Answered0/5
1
Part II · Lec 15 · 6 pts

Study. A county library system takes a random sample of 20 visits at each of its three branches (Campus, Downtown, Northside), 60 visits in all. For each visit it records the minutes spent in the branch (minutes), the number of items checked out (items), and whether the visitor used self-checkout (selfcheck). Branch is observed, not assigned.

Research Question A: Is branch associated with mean minutes per visit? (ANOVA, then Tukey) Research Question B: Is the number of items checked out associated with minutes per visit? (simple regression) Research Question C: Is branch associated with self-checkout use? (chi-square test)

For Research Question A, define μDowntown\mu_{Downtown} in context and write the hypotheses in notation.

# Research Question A: minutes per visit by branch (20 random visits per branch)
> summary(aov(minutes ~ branch, data = visits))
            Df Sum Sq Mean Sq F value  Pr(>F)   
branch       2    520     260   7.222 0.0016 **
Residuals   57   2052      36

> TukeyHSD(aov(minutes ~ branch, data = visits))
  Tukey multiple comparisons of means
    95% family-wise confidence level

$branch
                    diff        lwr        upr   p adj
Downtown-Campus       -5 -9.5658574 -0.4341426 0.0287
Northside-Campus       2 -2.5658574  6.5658574 0.5462
Northside-Downtown     7  2.4341426 11.5658574 0.0014

# Sample means (minutes): Campus 29, Downtown 24, Northside 31

# Research Question B: minutes per visit by items checked out (all 60 visits)
> summary(lm(minutes ~ items, data = visits))
Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  20.0000     2.3542   8.495  9.1e-12 ***
items         1.8000     0.5000   3.600  0.00066 ***

Residual standard error: 6.02 on 58 degrees of freedom
Multiple R-squared:  0.1826,	Adjusted R-squared:  0.1685
> confint(lm(minutes ~ items, data = visits))
               2.5 %   97.5 %
(Intercept) 15.287510 24.71249
items        0.799141  2.80086

# Research Question C: self-checkout use by branch
           Used  DidNotUse  Total
Campus        9         11     20
Downtown     14          6     20
Northside     8         12     20
> chisq.test(table(visits$branch, visits$selfcheck))

	Pearson's Chi-squared test

X-squared = 4.1379, df = 2, p-value = 0.1263
# Expected counts: 10.33 (Used) and 9.67 (Did not use) in every branch
Math shortcuts are on for STATS 250. Type ^ then digits for powers, _ then digits for subscripts.
2
Part II · Lec 15 · 6 pts

Define the F statistic for Research Question A in context, then write a complete conclusion for the ANOVA.

# Research Question A: minutes per visit by branch (20 random visits per branch)
> summary(aov(minutes ~ branch, data = visits))
            Df Sum Sq Mean Sq F value  Pr(>F)   
branch       2    520     260   7.222 0.0016 **
Residuals   57   2052      36

> TukeyHSD(aov(minutes ~ branch, data = visits))
  Tukey multiple comparisons of means
    95% family-wise confidence level

$branch
                    diff        lwr        upr   p adj
Downtown-Campus       -5 -9.5658574 -0.4341426 0.0287
Northside-Campus       2 -2.5658574  6.5658574 0.5462
Northside-Downtown     7  2.4341426 11.5658574 0.0014

# Sample means (minutes): Campus 29, Downtown 24, Northside 31

# Research Question B: minutes per visit by items checked out (all 60 visits)
> summary(lm(minutes ~ items, data = visits))
Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  20.0000     2.3542   8.495  9.1e-12 ***
items         1.8000     0.5000   3.600  0.00066 ***

Residual standard error: 6.02 on 58 degrees of freedom
Multiple R-squared:  0.1826,	Adjusted R-squared:  0.1685
> confint(lm(minutes ~ items, data = visits))
               2.5 %   97.5 %
(Intercept) 15.287510 24.71249
items        0.799141  2.80086

# Research Question C: self-checkout use by branch
           Used  DidNotUse  Total
Campus        9         11     20
Downtown     14          6     20
Northside     8         12     20
> chisq.test(table(visits$branch, visits$selfcheck))

	Pearson's Chi-squared test

X-squared = 4.1379, df = 2, p-value = 0.1263
# Expected counts: 10.33 (Used) and 9.67 (Did not use) in every branch
Math shortcuts are on for STATS 250. Type ^ then digits for powers, _ then digits for subscripts.
3
Part II · Lec 15 · 6 pts

Use the Tukey output to say which branches appear to differ in population mean minutes per visit, and in which direction. What can you say about Northside versus Campus?

# Research Question A: minutes per visit by branch (20 random visits per branch)
> summary(aov(minutes ~ branch, data = visits))
            Df Sum Sq Mean Sq F value  Pr(>F)   
branch       2    520     260   7.222 0.0016 **
Residuals   57   2052      36

> TukeyHSD(aov(minutes ~ branch, data = visits))
  Tukey multiple comparisons of means
    95% family-wise confidence level

$branch
                    diff        lwr        upr   p adj
Downtown-Campus       -5 -9.5658574 -0.4341426 0.0287
Northside-Campus       2 -2.5658574  6.5658574 0.5462
Northside-Downtown     7  2.4341426 11.5658574 0.0014

# Sample means (minutes): Campus 29, Downtown 24, Northside 31

# Research Question B: minutes per visit by items checked out (all 60 visits)
> summary(lm(minutes ~ items, data = visits))
Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  20.0000     2.3542   8.495  9.1e-12 ***
items         1.8000     0.5000   3.600  0.00066 ***

Residual standard error: 6.02 on 58 degrees of freedom
Multiple R-squared:  0.1826,	Adjusted R-squared:  0.1685
> confint(lm(minutes ~ items, data = visits))
               2.5 %   97.5 %
(Intercept) 15.287510 24.71249
items        0.799141  2.80086

# Research Question C: self-checkout use by branch
           Used  DidNotUse  Total
Campus        9         11     20
Downtown     14          6     20
Northside     8         12     20
> chisq.test(table(visits$branch, visits$selfcheck))

	Pearson's Chi-squared test

X-squared = 4.1379, df = 2, p-value = 0.1263
# Expected counts: 10.33 (Used) and 9.67 (Did not use) in every branch
Math shortcuts are on for STATS 250. Type ^ then digits for powers, _ then digits for subscripts.
4
Part II · Lec 17 · 6 pts

Interpret the items slope and its 95% confidence interval in context. Can the library conclude that checking out more items makes visits longer?

# Research Question A: minutes per visit by branch (20 random visits per branch)
> summary(aov(minutes ~ branch, data = visits))
            Df Sum Sq Mean Sq F value  Pr(>F)   
branch       2    520     260   7.222 0.0016 **
Residuals   57   2052      36

> TukeyHSD(aov(minutes ~ branch, data = visits))
  Tukey multiple comparisons of means
    95% family-wise confidence level

$branch
                    diff        lwr        upr   p adj
Downtown-Campus       -5 -9.5658574 -0.4341426 0.0287
Northside-Campus       2 -2.5658574  6.5658574 0.5462
Northside-Downtown     7  2.4341426 11.5658574 0.0014

# Sample means (minutes): Campus 29, Downtown 24, Northside 31

# Research Question B: minutes per visit by items checked out (all 60 visits)
> summary(lm(minutes ~ items, data = visits))
Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  20.0000     2.3542   8.495  9.1e-12 ***
items         1.8000     0.5000   3.600  0.00066 ***

Residual standard error: 6.02 on 58 degrees of freedom
Multiple R-squared:  0.1826,	Adjusted R-squared:  0.1685
> confint(lm(minutes ~ items, data = visits))
               2.5 %   97.5 %
(Intercept) 15.287510 24.71249
items        0.799141  2.80086

# Research Question C: self-checkout use by branch
           Used  DidNotUse  Total
Campus        9         11     20
Downtown     14          6     20
Northside     8         12     20
> chisq.test(table(visits$branch, visits$selfcheck))

	Pearson's Chi-squared test

X-squared = 4.1379, df = 2, p-value = 0.1263
# Expected counts: 10.33 (Used) and 9.67 (Did not use) in every branch
Math shortcuts are on for STATS 250. Type ^ then digits for powers, _ then digits for subscripts.
5
Part II · Lec 22 · 6 pts

The Downtown manager writes: "70% of our visitors used self-checkout, versus 45% at Campus and 40% at Northside. Our layout makes people use self-checkout, and the other branches should copy it." Take a position on this claim and support it with at least two aspects of the results and the design.

# Research Question A: minutes per visit by branch (20 random visits per branch)
> summary(aov(minutes ~ branch, data = visits))
            Df Sum Sq Mean Sq F value  Pr(>F)   
branch       2    520     260   7.222 0.0016 **
Residuals   57   2052      36

> TukeyHSD(aov(minutes ~ branch, data = visits))
  Tukey multiple comparisons of means
    95% family-wise confidence level

$branch
                    diff        lwr        upr   p adj
Downtown-Campus       -5 -9.5658574 -0.4341426 0.0287
Northside-Campus       2 -2.5658574  6.5658574 0.5462
Northside-Downtown     7  2.4341426 11.5658574 0.0014

# Sample means (minutes): Campus 29, Downtown 24, Northside 31

# Research Question B: minutes per visit by items checked out (all 60 visits)
> summary(lm(minutes ~ items, data = visits))
Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  20.0000     2.3542   8.495  9.1e-12 ***
items         1.8000     0.5000   3.600  0.00066 ***

Residual standard error: 6.02 on 58 degrees of freedom
Multiple R-squared:  0.1826,	Adjusted R-squared:  0.1685
> confint(lm(minutes ~ items, data = visits))
               2.5 %   97.5 %
(Intercept) 15.287510 24.71249
items        0.799141  2.80086

# Research Question C: self-checkout use by branch
           Used  DidNotUse  Total
Campus        9         11     20
Downtown     14          6     20
Northside     8         12     20
> chisq.test(table(visits$branch, visits$selfcheck))

	Pearson's Chi-squared test

X-squared = 4.1379, df = 2, p-value = 0.1263
# Expected counts: 10.33 (Used) and 9.67 (Did not use) in every branch
Math shortcuts are on for STATS 250. Type ^ then digits for powers, _ then digits for subscripts.

One composed observational study with new R output for an ANOVA with Tukey intervals, a simple regression and a chi-square test, and five written prompts graded by rubric elements, in the format Exams 1 and 2 used for Part II (40 minutes: about 10 to read, 30 to write). No Exam 3 Part II practice is posted yet; Case Study 3 in lab (week of Dec 7) will show the real one. Lec 16–22 prompts follow the course pack until those lectures happen. Not an official exam. Original questions written in the style of this course. Not official exam content.

MaizePrep is an independent study resource. It is not affiliated with, sponsored by, or endorsed by the University of Michigan. Course names and numbers are used only to describe which class the material covers. Every practice question is original, written in the style of the course.