Assignment:
SECTION 1: Below is the list of QUESTIONS.
Use the space assigned after each question for your answer. All the questions must be answered and show your calculations and write your justifications for full credit.
1. Which of the following statements describes the analytic studies?
A. They help lead to the prevention of disease, create quantitative evaluations of intervention programs as well as determine safe and effective new drugs, and other procedures.
B. This is something that describes the negative because you cannot always take the findings from group data and apply it to individuals.
C. the units of analysis are groups. This can be referred to as an Ecological Comparison Study.
2. What is the drawback of the ecologic study?
A. Are used very commonly in environmental epidemiologic research. An example may be possible health effects of exposure to electromagnetic fields.
B. Mass screening is defined as the standards of care, anyone that could at risks should be screened for exposure.
C. The ecologic fallacy and imprecise measurement of exposure.
3. Which of the following describe the disadvantages of the case control study?
A. A cohort is different because an entire cohort of exposed individuals is examined. A case study makes use of limited number of cases and controls who usually do not represent an entire cohort of exposed individuals.
B. The measurement of exposure may be inaccurate. Representativeness of cases and controls may be unknown and may provide indirect estimates of risk. The temporal relationship between exposure factor and outcome cannot always be determined.
C. For an observational designed study, the observer does not have control over the exposure factor. Mostly, cannot assign subjects by random to certain study conditions. For an experimentally designed study the observer can control who is exposed to certain factors and is able to assign subjects by random to certain study groups.
4. Which of the following is an example of a case control study?
A. Are used very commonly in environmental epidemiologic research. An example may be possible health effects of exposure to electromagnetic fields.
B. Allowance of the direct observation of risk. The exposure factor is well defined and can study exposures that are uncommon in the population. The temporal relationship between factor and outcome is known.
C. the units of analysis are groups. This can be referred to as an Ecological Comparison Study.
5. An outbreak of gastritis occurred on a cruise ship. The data in the following table were obtained shortly after the outbreak, from a questionnaire completed by everyone on board the ship.
A. What is the relative risk for developing gastritis from all the food listed in the table?
B. What are the most likely food(s) that cause this outbreak? Justify your answer
![454_P 2.jpg](https://secure.tutorsglobe.com/CMSImages/454_P 2.jpg)
6. In 1945, there were 1,000 women who worked in a factory painting radium dials on watches. The incidence of bone cancer in these women up to 1975 was compared to that of 1,000 women who worked as telephone operators in 1945. Twenty of the radium dial painters and four of the telephone operators developed bone cancer between 1945 and 1975. This is an example of a:
A. Cohort study
B. Experimental study
C. Clinical trial
D. Cross-sectional study
E. Case-control study
7. The following table gives the results of a screening test for diabetes compared to a confirmatory evaluation (oral glucose tolerance test).
|
True diagnosis
|
|
|
Test results
|
Diabetics
|
Non diabetics
|
Total
|
Positive
|
40
|
30
|
70
|
Negative
|
110
|
9820
|
9930
|
Total
|
150
|
9850
|
10000
|
A. The sensitivity of this screening test for diagnosing diabetes is:
B. The specificity of this screening test for diagnosing diabetes is:
C. The overall assessment of the test is:
8. Which of the following statements indicate the use of descriptive study?
A. Used in the comparison between a new SSRI drug and Venlafaxine
B. To compare the difference between random sampling and alternate sampling methods for assessing the efficacy of [CT and psychotherapy as a treatment for depression patients with psychotic depression
C. To document a cluster of Wegener's granulomatosis cases that has recently appeared in your area
D. To evaluate the effects of Team Based Learning (TBL) versus didactic lecture
E. None of the above
9. California highway patrol statistics revealed that more accidents occurred to blue cars than to cars of any other color. The inference that while driving a blue care, one is at higher risk of an accident than while driving a care of another color is:
A. Correct
B. Incorrect, because the comparison is not based on rates
C. Incorrect, because no control or comparison group is used
D. Incorrect, because no test of statistical significance has been made
E. Incorrect, because prevalence is used instead of incidence
10. The students t-test is used to:
A. Test the difference between 2 means
B. Test for differences between 3 or more means
C. Differences between two frequency distributions
D. Whether two distributions are independent or dependent
11. As income level declines, tooth decay increases. This is an example of what:
A. Positive correlation
B. Negative correlation
C. Internal Validity
D. External Validity
12. Retrospective and Prospective are what types of Epidemiological Studies?
A. Analytical
B. Descriptive
13. The sampling method where each member in the population has an equal chance of being selected is:
A. Random Sampling
B. Stratified Sampling
C. Systematic Sampling
D. Convenience Sampling
14. Systemic water fluoridation will reduce caries in school children by 30%.
a. What is the independent variable?
b. What is the dependent variable?
15. Correlation coefficient implies causation.
A. True
B. False
16. What type of sample has the least bias?
A. Random
B. Stratified
C. Systematic
D. Judgment
E. Convenience
17. Which of the following statements is correct?
a.) The attributable risk is the excess risk of disease in the exposed compared to the non-exposed during a defined period of time
b.) The attributable risk is a ratio of the disease risk in the exposed compared to the non-exposed during a defined period of time
c.) The attributable risk is a ratio of the disease risk in the non-exposed compared to the exposed during a defined period of time
d.) The attributable risk is the prevalence of disease in the exposed minus the prevalence of disease in the non-exposed
e.) The attributable risk is the disease risk in a defined group at a specific point in time
18. Which of the following statements is correct?
a) A study result is more generalizable if it is statistically significant vs. not statistically significant
b) A study result is clinically important if it is statistically significant
c) Failure to blind subjects and investigators is a potential threat to external validity
d) Failure to consider the cost of treatment is a potential threat to internal validity
e) A study result with a p-value less than 0.0000001 might have no clinical importance
19. Investigators feel it is important to reduce the probability of a Type I error so they set alpha at 0.01. The resulting p-value from their study is 0.02. Select the correct answer:
a.) The study result might be a Type II error
b.) The study result is statistically significant
c.) The study result is not important to patient care
d.) The study's power is 99%
e.) Under the assumption that the null hypothesis is true, the probability of getting a result as large or larger than 0.01 is 2%
20. The main benefit of a randomized controlled trial (RCT) compared to all other epidemiology study designs is that the RCT:
a) is prospective thereby eliminating the need for historical data
b) has better external validity
c) guarantees that confounding bias will not occur
d) tends to equally distribute into the study arms characteristics which may be independent risk factors for the outcome of interest
e) tends to avoid random misclassification of the outcome of interest
21. A researcher follows 200 women who exercise regularly and 300 women who do not exercise regularly. After 30 years of follow-up, 20 of the women in the exercise group are diagnosed with osteoporosis while 30 women in the non-exercise group are diagnosed with osteoporosis.
a) What type of design is this study? Calculate the measure of association for this study.
22. Researchers determine in a case control study that 20 of 100 patients with bladder cancer smoke cigarettes while 40 of 600 patients without bladder cancer smoke cigarettes.
A. Calculate the appropriate measure of association for developing bladder cancer in smokers vs. non-smokers. Interpret the measure of association you calculated.
23. It is known that having a high HDL level is protective of having a fatal myocardial infarction (MI). It is also known that cigarette smoking is an independent risk factor of having a fatal MI. In a randomized controlled trial comparing Medicine A to Medicine B in the prevention of fatal MIs in men older than 60, the following Table 1 was noted
Medicine A Medicine B
n = 600 n = 580
% Cigarette Smokers 25 25
% With High HDL Levels 15 5
The authors compare the outcomes of patients on Medicine A vs. Medicine B and report a relative risk of 0.4 The authors then report a relative risk of 0.9 after adjusting for high HDL levels.
a. Why did the relative risk change from 0.4 to 0.9? Interpret the relative risk of 0.9.
24. Which of the following statements is the best statement related to screening?
a. Screening women over the age of 40 to detect breast cancer with mammography is an example of a secondary level of prevention.
b. When considering a disease appropriate for screening, treatment begun after patients develop symptoms should be more beneficial than treatment begun before patients get symptoms.
c. An ideal screening test to be used in a group of patients with a low disease prevalence is a test with a very high sensitivity and a very low specificity.
d. An ideal screening test to be used in a group of patients with a high disease prevalence is a test with a very high sensitivity and a very low specificity.
e. Screening programs are conducted on patients with signs and symptoms of a disease.
25. Which of the following statements is the best statement related to a normal (Gaussian) distribution: [Select all that apply]
a.) The variance equals the standard deviation.
b.) The probability of randomly selecting a variable higher than two standard deviations above the mean is 5%.
c.) The probability of randomly selecting a variable higher than one standard deviation above the mean is 16%.
d.) The total area under the curve cannot be calculated unless the mean, median and standard deviation are known.
e.) The distribution is symmetric about each standard deviation.
26. Which of the following statements is the best statement related to correlation: [select all that apply]
a. The correlation coefficient, r, is dependent on the units of measurement.
b. In correlation, it matters which variable is put on the x-axis and which variable is put on the y-axis.
c. The coefficient of determination can be negative or positive.
d. The correlation coefficient, r, is sensitive to extreme values (outliers).
e. Correlation is a measure of the relationship between the population mean and the sample mean.
27. Researchers conduct a randomized controlled trial to determine if Medicine A is better than Medicine B in preventing MIs in women with heart disease over the age of 60. The researchers determined that a sample size of 100 would be necessary to have an 80% probability of detecting a true difference of 10% or larger between the two groups. Alpha was set at 0.05. The study results showed that 10% of the women on Medicine A had an MI and 5% of the women on Medicine B had an MI, with P = 0.30. Select the best statement:
a. Given the null hypothesis is true, there is a 30% chance of obtaining a difference of 5% or larger between the two groups.
b. Given the null hypothesis is true, there is a 30% chance of obtaining a difference of 10% or larger between the two groups.
c. The study's power is 20% to detect a true difference of 10% or larger.
d. The probability that a Type II error occurred is 30%.
e. The probability that a Type I error occurred is 30%.
28. The Table below represents the Relative Risk for Venous Embolism for each Med A dose as Compared with Placebo. (CI denotes confidence interval.)
Outcome 20 mg of Med A 40 mg of Med A
Relative Risk Relative Risk
(95% CI) (95% CI)
Venous Embolism 1.02 (0.70 - 1.51) 0.37 (0.22 - 0.63)
Interpret the 0.37 (0.22 - 0.63) appearing under 40 mg of Med A. Your interpretation must contain the three "values", i.e. 0.37. 0.22 and 0.63.
29. Researchers recorded data on diastolic blood pressure and height on 70 subjects with a mean age of 70 and a median age of 70. These 70 subjects had a mean diastolic blood pressure of 70 mm Hg and a mean height of 70 inches. The researchers considered height as the independent variable and diastolic blood pressure as the dependent variable when they performed simple linear regression. They reported that R Squared was 0.70. Interpret this R Squared of 0.70.
30. The average height of 100 students is 68 inches and the standard deviation is five inches. Calculate the 95% confidence interval around the mean.
31. Standard deviation is : [select all that apply]
A. is the square root of variance
B is measured using the unit of the variable
C. is measured using the squared unit of the variable
D. has values generally comparable with the average value
32. Relative risk is: [select all that apply]
A. Shows the relationship between a factor assumed to influence the occurrence of disease, and the disease
B is the ratio of the risk of disease for those exposed and those not exposed to that risk factor
C. Cannot be greater than 1
D. is expressed as a percentage
33. A regression line is a straight line which: [select all that apply]
A. is located as close as possible to all the points of a scatter chart
B. is defined by an equation having 2 parameters: the slope and the intercept
C. provides an approximate relationship between the values of two parameters
34. A Gauss curve, the curve of a normal distribution, has the following features (where m = mean, s = standard deviation):
A. in the interval [m - 1s; m + 1s] about 2/3 (~ 68%) of the series' values are located
B. in the interval [m - 2s; m + 2s] about 95% of the series' values are located
C. in the interval [m - 3s; m + 3s] about 99% of the series' values are located
D. in the interval [m - 1s; m + 1 s] about 50% of the series' values are located
35. Y represents the predicted value of y calculated using the equation Y = a + bX.
In the formula, SBP = 93 + 4 X; where X = value of postnatal age (hours) for the neonates ≤ 1,000 grams?
a. Determine the value and interpret the value of the intercept (a).
b. Determine the value of the slope (b) and interpret the value of the slope. (ONE POINT)
36. 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? (Choose one best answer and provide rationale).
A. odds of disease among exposed relative to the prevalence of exposure in the source population
B. cumulative incidence among the exposed
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
37. What is the best measure to estimate the percent of children with otitis media that have abnormal otoscope examination? Please explain.
a. Case fatality
b. Specificity
c. Sensitivity
d. Incidence rate
e. Risk
38. Which of the following statements about R2 is not true?
a. It is sometimes called the coefficient of determination.
b. Its value indicates percentage of variation of Y explained by all predictors as a set.
c. It is a measure of magnitude but not direction of relationships.
d. Its values can range from -1.00 to +1.00.
39. If the mean µ = 64.5 and the standard deviation s = 2.5. What is the probability, if we pick one man at random, that his height will be between 65 and 74 inches P(65 < X < 74)? Show the calculation and interpret the results.
40. 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.
41. 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.
42. Based on the data on table below:
FACTORS
|
Eigen Value
|
Percent of Variance
|
1
|
2.21
|
37.8
|
2
|
2.12
|
34.3
|
3
|
.74
|
12.3
|
4
|
.43
|
7.2
|
5
|
.38
|
6.4
|
6
|
.12
|
2.0
|
A. How many factors will be extracted? Provide justifications.
B. What percent of the variance the extracted factor(s) will explain? Provide justifications.
43. Use the table below (Table below. Component Matrix) and indicate the loading of the variables for each factor
Table below Component Matrix
FACTOR1 FACTOR2
Q1 0.026 0.865
Q2 0.387 0.619
Q3 0.760 0.091
Q4 .651 0.396
Q5 0.030 0.634
Q6 0.805 -.064
Q7 0.499 0.651
Q8 -0.794 0.667
Q9 0.728 -0.097
Q10 -0.183 0.770
Extraction Method: Principal Component Analysis.
A. What are the specific questions that were represented in Factor 1 and Factor 2? Provide justifications.
44. An instrument with 12 questions [i.e., a scale of 12 variables] was evaluated for internal consistency (reliability). The following is the result:
Is the scale internally consistent? How can you improve the internal consistency?
Cronbach's Alpha N of Items
0.523 12
Is the scale internally consistent? How can you improve the internal consistency?
SECTION 2: Please use the SPSS data set
Analyze the data using SPSS software to answer the following questions: (You need to 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
Methods: analysis of a secondary data from the Office of Statewide Health Planning and Development (OSHPD) [hospital discharge data].
1. 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 Category [agecat], Physically Active [active], History of Diabetes [diabetes], obesity [obesity], Smoking Status [smoker], Cat Scan Result [catscan].
a. Select the appropriate type of regression analysis and determine if there are statistically significant associations or not. 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).
Variables name
|
Adjusted Regression coefficient (95% Confidence Interval)
|
P-value
|
Gender
Male
Female
|
|
|
.....
|
|
|
2. Which of the following variables is a predictor of the log length of stay for rehabilitation [LOG_los]: gender, Age Category [agecat], Physically Active [active], History of Diabetes [diabetes], obesity [obesity], 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).
Variables name
|
Adjusted Regression Coefficient (95% Confidence Interval)
|
P-value
|
Gender
Male
Female
|
|
|
.....
|
|
|