Epidemiology and Biostatistics Questions

Q1. Which of the following best describes the design where subjects are sampled by disease status and is often used when the investigator is interested in rare diseases? (Choose one best answer and provide rationale). (ONE POINT)

A. intervention trial

B. casecontrolstudy

C. retrospectivecohort

D. ecologic study

E. none of the above

 

Q2. The evidence supporting obesity as a risk factor for colon cancer remains inconclusive, especially among women. A study reported the association between obesity (measured at baseline) and colon cancer morbidity as determined from review of medical records and death certificates in a nationally representative cohort of men and women age 25-74 years who participated in the First National Health and Nutrition Examination Survey from 1971 to 1975 and were subsequently followed up through 1992. The following table 1 is from this study for men and women combined.

Table 1. Incidence of colon cancer, First National Health and Nutrition Examination Survey from 1971 to 1975 with follow-up 1992.

Baseline body mass index* <22 22 – <24 24 – <26 26 – <28 28 – <30 30+ Number of incident cases of colon cancer 40 54 25 66 38 Person-years of follow up 51,470 35,910 35,610 30,630 20,120 30,900 69

* kg body weight per height in meters squared

a. Which of the following best describes the research design used in this study? (Choose one best answer).

A. Cross-sectional survey

B. Cohortstudy

C. Ecologicalstudy

D. Population based case control study

E. None of the above

b. Calculate the relative risk (RR) of colon cancer associated with a BMI of 28 – <30 using the lowest BMI category (i.e., BMI <22) as reference category. In one sentence, interpret your answer.

 

Q3. Ŷ represents the predicted value of y (diastolic blood pressure [DBP]) calculated using the equation Ŷ = a + b X.

In the formula, DBP = 72 + 1.2 X; where X = value of age (years) for adult person.

a. What is the value of the intercept (a)?

b. Interpret the value of the intercept (a)

c. What is the value of the slope (b)?

d. Interpret the value of the slope (b)?

 

Q4. The strength of an association is one of the criteria for evaluating the cause and effect relationship between an exposure and outcome. Which of the following is a measure of the strength of association?

A. odds of disease among exposed relative to the prevalence of exposure in the source population

B. cumulativeincidenceamongtheexposed

C. the ratio of odds of exposure among cases to the odds of exposure among the non-cases

D. incidence rate among the exposed

E. none of the above

 

Q5. What is the independent variable(s) in the research question “Is the quality of life of elderly population affected by their functional ability”?

A. Quality of life

B. Functionalability

C. Hearingacuity

D. Nursing home residents

 

Q6. Among 500 persons with positive screening tests for HIV antibody, 400 are positive with HIV virus.

A. The most appropriate measure is:

a. sensitivity

b. specificity

c. predictive value positive

d. predictive value negative

B. Estimate the value of this measure and interpret it:

 

Q7. Tell whether the following statement is true or false:

A. Outcome research examines the quality and effectiveness of health care and nursing services. [True] [False]

B. Researchersusuallysamplefromthetargetpopulation.[True] [False]

C. Internalconsistencyreliabilityistheextenttowhichthedifferentitemsofthe scale are not reliably and consistently measuring attribute [True] [False]

 

Q8. Discuss the difference between efficacy, effectiveness, and efficiency. Give examples.

 

Q9. What are the criteria for a successful screening program?

 

Q10. The overall odds ratio for the association between breast cancer and smoking status is 2.8 (95% confidence interval=1.9-4.0).

a- Interpret the odds ratio and the 95% confidence interval

b- What do you conclude about smoking – is it a possible risk or preventive factor? Provide rationale

 

Q11. A distribution of data values can be described in terms of all of the following characteristics except:

a. Central tendency

b. Shape

c. Relative standing

d. Variability

 

Q12. What is the best measure to estimate the percent of children with no otitis media that have normal otoscope examination? Please explain.

a. Predicted value negative

b. Specificity

c. Sensitivity

d. Predicted value positive

e. Risk

 

Q13. Which of the following statements about R2 is not true?

a. It is sometimes called the coefficient of determination.

b. Its values can range from -1.00 to +1.00.

c. Its value indicates percentage of variation of Y explained by all predictors as a set.

d. It is a measure of magnitude but not direction of relationships.

 

Q14. Which of the following approaches can be used to compare the relative benefits of two alternative pharmacologic treatments for chest disease?

a. screening

b. cohort study

c. case-control study

d. randomized controlled clinical trial

e. randomized controlled clinical trial

 

Q15. Regression is used to:

a. Corroborate results from a correlation analysis

b. Make predictions about values for a variable based on known values for another

c. Estimate sample size needs when planning a study involving correlation

d. Determine the magnitude of effects of correlations among variables

 

Q16. A researcher found a correlation of -.28 between scores on a self-esteem scale and number of alcoholic drinks consumed in the prior month. What does this mean?

a. People who drank more alcohol had a slight tendency to have higher self-esteem.

b. People who drank more alcohol had a slight tendency to have lower self-esteem.

c. Drinking more alcohol tended to cause lower self-esteem.

d. Having lower self-esteem tended to cause people to drink more alcohol.

Table 2. Odds Ratios for Late Extubationa after Cardiac Surgery, by Patient Characteristics (N = 673) Female patient Extubation < 5 Hours (%)

 

Q17. Refer to Table 2 above. Which of the following numbers is a point estimate for a risk index for delayed extubation?

a. 19.2

b. 29.8

c. 2.03

d. 1.58

e. None of the above

 

Q18. Refer to Table 2 above. Which patient characteristic was most associated with a higher risk of delayed extubation?

a. Sex

b. Race

c. Hypertensive status

d. Prior experience with CABG 19.2 89.6 62.7 9.4 Extubation > 5 OR Hours (%) 29.8 1.66 91.3 1.09 73.9 1.58 16.0 2.03 95% CI 1.14 – 2.60 0.80 – 1.21 1.09 – 2.24 1.22 – 3.65

 

White patient Hypertensive Prior CABG aLate extubation = More than 5 hours of mechanical ventilation

 

Q19. What is a multiple regression equation? (Select all that apply.)

A. One that represents the mathematical effect that several independent variables have on the dependent variable

B. One in which the x-values are multiplied by one another

C. One that explains more of the variance in y than does a single linear regression equation

D. An experimental model for determining best practices

E. One that uses more than one predictor variable to predict the value of the outcome variable

F. One that explains all of the variance in the dependent variable, in terms of several independent variables

 

Q20. Which of the following items is different when comparing probability sampling and non-probability sampling?

a.The type of descriptive statistics applied to the sample

b.The size of the sample

c.The relative chance of being selected as a study participant

d.Whether or not the findings can be generalized

Table 3. Physiologic Outcomes for Patients with Emphysema during Exercise Performance Under Three Different Conditions (N = 50) Physiologic Outcome Control Condition Mean + SD With Admin- istration of Oxygen Mean + SD With Compressed Air Mean + SD F p Dyspnea rating (1-10) Heart rate (bpm) Oxygen saturation, SPO2 (%) Breaths per minute 4.70± 2.3 121.1 ± 13.6 91.0 ± 3.9 24.1 ± 4.8 4.77 ± 2.6 126.9 ± 19.9 94.4 ± 4.0 24.3 ± 5.9 5.09 ± 2.6 4.99 .008 126.0 ± 21.1 12.54 89.9 ± 4.1 9.80 28.8 ± 6.5 1.86 <.001 <.001 .22

 

Q21. Refer to Table 3 above. For which outcome would the researcher need to accept the null hypothesis?

a. Dyspnea rating

b. Breaths per minute

c. Heart rate

d. Oxygen saturatio

 

Q22. The chi-square test is used to test the null hypothesis that:

a. The medians of groups being compared are equal

b. Two categorical variables are independent (not related)

c. The expected cell sizes are zero

d. The odds ratio is zero

 

Q23. The death rates from various conditions are often compared across geographic areas. These comparisons are usually based on directly age-standardized mortality rates. Which of the following best describes what is meant by an age-standardized rate created by the direct method?

A. The number of events in each age stratum of a standard population is used to create a weighted average rate.

B. Theeventratesineachagestratuminthestandardpopulationareusedtocreatea weighted average rate.

C. Theeventratesinthegeographicareaofinterestareappliedtotheage-stratum sizes of a standard population to create a rate that is a weighted average.

D. The event rates in the geographic area of interest are compared to the event rates of a standard population to create a summary rate that is a weighted average.

 

Q24. Calculate the percentage of variance explained for correlation (r) = 0.90 [i.e., the coefficient of determination]. Is this correlation clinically important? Provide a rationale for your answer

 

Q25. Discuss the uses of factor analysis? Give examples

 

Q26. A researcher identifies three variables and formulates a hypothesis that links them. That hypothesis is testable. What does it mean that the hypothesis is testable?

a. All the variables in the hypothesis are measurable.

b. The hypothesis must be replaced by a research question.

c. The value of the hypothesis is low.

d. The hypothesis is causational.

 

Q27. Based on the data on table 4 below:

A. Howmanyfactorswillbeextracted?Providejustifications.

B. Whatpercentofthevariancetheextractedfactor(s)willexplain?Provide justifications.

Table 4. Factor analysis FACTORS Eigen V alue 2.10 2.00 1.74 1.43 0.38 0.12 Percent of Variance 37.8 34.3 12.3 7.2 6.4 2.0 1 2 3 4 5 6 Q28. Why is selection of an appropriate design for a research study important?

a. If the design is an incorrect one, the researcher will examine variables and their interactions in a way that does not answer the research question.

b. The design provides a blueprint or diagram that appears in the concept map.

c. If there is no design, critique is impossible.

d. If the design is appropriate, the researcher can eliminate error.

 

Q29. A researcher conducts research and uses a small sample that is not randomly selected. When he replicates the study, twice, he again uses the same site and another small sample that is not randomly selected. This is a threat to which type of validity?

a. Statistical conclusion validity

b. Internal validity

c. Construct validity

d. External validity

 

Q30. Consider two values, correlation ((r) = 0.2 and (r) = –0.75).

A. Describe the clinical importance of both (r) values

 

Q31. An instrument with 12 questions [i.e., a scale of 12 variables] was evaluated for internal consistency (reliability). The following is the result: Cronbach’s Alpha N of Items 0.590 12

A. Is the scale internally consistent? Provide rational.

B. How can you improve the internal consistency? Provide rationale.

 

SECTION 2: Please use the SPSS data set “sample_data_FINAL_EXAM_FALL_2018.sav” (Attached) and analyze the data using SPSS software to answer the following questions: (You need to complete the tables and interpret all the results) Our objective is to determine among stroke patients admitted to the hospital, what are the variables (predictors) that are associated with the following dependent variables:

1- In-hospital mortality

2. Length of hospital stay for rehabilitation

Methods: analysis of a secondary data from the Office of Statewide Health Planning and Development (OSHPD) [hospital discharge data] for the State of California.

Q1. Describe the population characteristics. “Do frequency distribution” of the following variables and interpret the findings: – Gender, Age in years (age), Physically Active [active], History of Diabetes [diabetes], Smoking Status [smoker], Cat Scan Result [catscan], and Died in Hospital [dhosp] – Develop one table in Microsoft word that includes name of the variable, number and percent (see example below).

Table 1. Population characteristics Variables name Number Percent …..

 

Q2. Determine which of the following variable is associated with the in-hospital mortality [dhosp] after adjusting for the other variables (i.e., significant predictors): Gender, Age in years [age], Physically Active [active], History of Diabetes [diabetes], Smoking Status [smoker], Cat Scan Result [catscan].

a. Select the appropriate type of regression analysis and determine if there are statistically significant relation or not. Specify which variable is a significant predictor and interpret the results. – Develop one table in Microsoft word that includes name of the variable, adjusted regression coefficient and 95% confidence interval, and p-value (see example below). Table 2. ….. …..

 

Q3. Do frequency distribution and descriptive statistics with histogram for the following variable and interpret the findings: [LOS_rehab = length of stay for rehabilitation]. Interpret the results and the histogram Gender Male Female V ariables name Adjusted Regression coefficient (95% Confidence Interval) P-value Gender Male Female

 

Q4. Which of the following variables is a predictor of the length of stay for rehabilitation [LOS_rehab]: age in years [age], gender, Physically Active [active], History of Diabetes [diabetes], Smoking Status [smoker], Cat Scan Result [catscan] a. Select the appropriate type of regression analysis and determine the statistically significant predictor(s). Specify which variable and interpret the results. – Develop one table in Microsoft word that includes name of the variable, adjusted regression coefficient and 95% confidence interval and p-value (see example below). Table 3. …… …..

 

Q5. Write a one-page report of the study and its implications on nursing practice. – The summary should include the following: – Objectives: – Methods: – Results: – Conclusions and implications on nursing practice V ariables name Adjusted Regression Coefficient (95% Confidence Interval) P-value Gender Male Female