Description

For multiple choice questions, circle only one answer, unless otherwise directed.  Show work for partial credit.  If R is required, insert the annotated code with the solution after the question for full credit. (Putting all R code at the end of the document will not get full credit)

Section 1:  R is not required for this section, but it may be used for calculations and to show work.

1. A Harris Interactive survey of 502 senior human resource executives in the Mid-Atlantic Region asked for the best method of finding the best candidates from a list of methods (e.g. referrals, LinkedIn, etc.).  Fifty-eight percent responded that referrals were one of the methods for finding the best candidates.

1. What is the population?

                                                        i.            502 senior human resource executives in Mid-Atlantic Region

                                                      ii.            Senior human resources executives in the Mid-Atlantic Region

                                                    iii.            The methods for finding the best candidates

                                                     iv.            Fifty-eight percent responding that referrals were one of the methods used

2. What is the sample?

                                                        i.            502 senior human resource executives in Mid-Atlantic Region

                                                      ii.            Senior human resources executives in the Mid-Atlantic Region

                                                    iii.            The methods for finding the best candidates

                                                     iv.            Fifty-eight percent responding that referrals were one of the methods used

2. All highway bridges in the U.S. are inspected periodically for structural deficiency by the Federal Highway Administration.  Data from the inspections are compiled into the National Bridge Inventory.  Several of the nearly 100 variables maintained are listed: (1)Whether the bridge has a structural deficiency (yes/no) (2) Width (3) Overall bridge rating (categories: Poor (scoring 1-3), Average (scoring 3-6), Excellent (scoring 4-10)) (4) Average number of days under construction per year.

a.      Variable (1) is: 

                                                              i.      Quantitative, discrete

                                                            ii.      Quantitative, continuous

                                                          iii.      Qualitative, nominal

                                                           iv.      Qualitative, ordinal

b.      Variable (2) is: 

                                                              i.      Quantitative, discrete

                                                            ii.      Quantitative, continuous

                                                          iii.      Qualitative, nominal

                                                           iv.      Qualitative, ordinal

c.       Variable (3) is:

                                                              i.      Quantitative, discrete

                                                            ii.      Quantitative, continuous

                                                          iii.      Qualitative, nominal

                                                           iv.      Qualitative, ordinal

d.      Variable (4) is:

                                                              i.      Quantitative, discrete

                                                            ii.      Quantitative, continuous

                                                          iii.      Qualitative, nominal

                                                           iv.      Qualitative, ordinal

3.      A researcher at a university in the U.S. collected estimates from 153 different studies about calorie consumption.  He conducted a meta-analysis using the estimates gathered from the studies.  What type of study is this?

e.      Observational Study

f.        Designed Experiment

g.      Secondary Source

4.      A study was conducted to determine the efficacy of a new tutoring method, method A.  Half of the participants were given tutoring method A, and the other half of the participants were given the standard tutoring method.  What type of study is this? 

h.      Observational Study

i.        Designed Experiment

j.        Secondary Source

5.      A study of the spending habits of Americans was conducted.  Participants were selected and mailed a survey to complete and return to the researchers of the study.  What type of study is this? 

k.       Observational Study

l.        Designed Experiment

m.    Secondary Source

6.      You are interested in finding the probability of at least 5 people showing up at a queue in an hour.  An average rate of people showing up at the queue is provided.  To find this probability, you should use:

a.      Binomial Distribution

b.      Poisson Distribution

c.       Bernoulli Distribution

d.      Normal Distribution

7.      You are interested in the probability of observing at least 8 heads when flipping a standard coin 10 times.  To find this probability, you should use:

a.      Binomial Distribution

b.      Poisson Distribution

c.       Bernoulli Distribution

d.      Normal Distribution

8.      Match the letter of the term below with the correct definition.

a.      Predictive Value Positive

b.      Predictive Value Negative

c.       False Negative

d.      False Positive

e.      Sensitivity

f.        Specificity

g.      Prevalence

_____________The rate at which a disease/characteristic is present in the population.

_____________The probability of a negative test result given that the disease is not present.

_____________The probability of a positive test result given that the disease is present.

_____________A test result indicating a positive status when the disease is not present.

_____________A test result indicating a negative status when the disease is present.

_____________The probability of a disease being present given that the test result was positive.

____________The probability of a disease not being present given that the test result was negative.

9.      A study of 5000 adults with known status for a type of cancer were screened using a newly developed cancer screening test.   A positive result indicates that the test determined that the person has this type of cancer.  Use the contingency table to answer the questions on the next page.

a.      If a random participant in this study is selected, what is the probability that he or she tests negative for Cancer?

            i.  0.23

            ii. 0.49

iv. 0.76

            iii. 0.52

b.   If a random participant in this study is selected, what is the probability that her or she tests negative and does NOT have cancer?

                                                              i.            0.7554

                                                            ii.            0.237

                                                          iii.            0.9659

                                                           iv.            0.3982

c.   Estimate the sensitivity of the test.

i.        0.170

ii.      0.710

iii.    0.084

iv.     0.974

d.   Estimate the specificity of the test.

i.   0.916

ii.  0.710

iii.   0.084

iv.    0.974

10.  The prevalence of a disease is known to be 0.2.  The sensitivity of a test for the disease is 0.85; the specificity is 0.98.

        a.   Calculate the predictive value positive.

                                                              i.      0.963

                                                            ii.       0.751

                                                          iii.       0.914

                                                           iv.      0.869

b.   Calculate the predictive value negative.

i.    0.963

ii.   0.751

iii.   0.914

iv. 0.869

Section 2:  For this section, use the dataset called iris (available in base R – you do not need to install anything else).  You must use R to find the answers in this section.  Remember to insert code and any plots you are required to produce.

       1. Find the mean of the variable Petal.Length