Past Papers Basic Epidemiology Biostatistics

By: Prof. Fazal Rehman Shamil

Guess Paper 1: Basic  Epidemiology Biostatistics Fall – 2020 Past Papers

University Name – Confidential

NOTE: Q.1 is compulsory, attempt any four questions from the remaining. All questions carry equal marks. Phones and other Electronic Gadgets are not allowed.

Time Allowed: 3 hours

Total Marks:    70, Passing Marks (35)

Q.1      Differentiate:-

  1. Monitoring and surveillance (3)                        Quarantine and isolation  (4)
  2. Incubation period and latent period (3)                        Cross infection and iatrogenic infection  (4)

 

Q.2       Write note on:-

  1. Advantages of mean. (4)                    Gaussian.    (6)       3.   Skewed curves.  (4)

 

Q.3      80 persons attended a buffet dinner at a 5 star hotel. 25 persons developed vomiting and diarrhoea

within 6 hours. Following data was gathered.

 

 

Food Served

            Consumed food Did not consume food
Food poisoning + No food poisoning Food poisoning + No food poisoning
Mutton Karahi 20 28 5 7
Chicken Boti 12 17 13 18
Finger Fish 15 24 10 11
Kofta Kabab 18 26 7 9
Fresh Salad 23 24 2 11
Kheer 22 34 3 1

 

What is incriminated food item that most likely caused the food poisoning? Also comment on reason. (14)

Q.4      a.         Wilson described criterion for screening of diseases. Describe his criterion. (4)

  1. A new screening test was assessed against gold standards i,e biopsy for breast cancer detection.

Out of 1600 females of 40 years & above, 240 ladies were declared to be with the disease in

comparison to 140 conformed with the disease on biopsy. Sixty were found to be positive both

on screening as well as biopsy.

  1. Calculate sensitivity, specificity and predictive values of screening test. (8)

and interpret your results.

  1. Give your opinion regarding usefulness of new test in the light of sensitivity and specificity. (2)
  2. For a clinician, out of sensitivity, specificity and positive predictive value of screening test

which measure is of more use & why. (4)

Q.5      Describe in detail, cross over and concurrent parallel type of study designs. (14)

Q.6      Define sampling? Describe various types of sampling. (14)

Q.7      How will you investigate an epidemic of Hepatitis E.?  Give all salient points.  (14)

Q.8      Write note on:-

  1. Ogive (5)              Census  (6)              3. Matching   (3)

Guess Paper 2: Basic  Epidemiology Biostatistics Spring – 2020 Past Papers

University Name – Confidential

NOTE: Q.1 is compulsory, attempt any four questions from the remaining. All questions carry equal marks. Phones and other Electronic Gadgets are not allowed.

Time Allowed: 3 hours

Total Marks:    70, Passing Marks (35)

Q.1 What is your understanding about followings:-
1. Masking (2)
2. Confounding (2)
3. Epidemiology (2)
4. Host of disease (2)
5. Census (2)
6. Randomization (2)
7. Epidemic curve (2)

Q.2 Differentiate:-
1. Simple table and cumulative frequency table. (3)
2. Case control and cohort studies. (7)
3. Screening test and diagnostic test. (4)

Q.3 A researcher wanted to see the relationship of crime and genetic makeup. He inducted 480 persons in
the study. Of 240 criminals, 40 had parental history of crime. From the other group 10 had positive
history.
a. Name the study. (1)
b. Construct 2×2 table. (3)
c. Calculate relevant measure of association and interpret result. (10)

Q.4 a. Wilson described criterion for screening of diseases. Describe his criterion. (6)
b. A researcher conducted a study to evaluate a new screening test for carcinoma breast in 300
females. Out of 70 diagnosed cases, 54 were picked up by screening test. Screening test also
picked 26 from biopsy negative women.

Calculate sensitivity, specificity and predictive values and interpret results. (8)

Q.5 a, Describe in detail, incidence and prevalence. (7)
b. Give cross over type of study design. What are its advantages & disadvantages? (7)

Q.6 Define sampling. Describe various types of sampling. (14)

Q.7 How will you investigate an epidemic of cholera?
Give all salient points. (14)

Q.8 Write note on:-
1. Ogive (5)
2. Normal curve (6)
3. Matching (3)

Guess Paper 3: Basic  Epidemiology Biostatistics Spring – 2019 Past Papers

University Name – Confidential

NOTE: Q.1 is compulsory, attempt any four questions from the remaining. All questions carry equal marks. Phones and other Electronic Gadgets are not allowed.

Time Allowed: 3 hours

Total Marks:    70, Passing Marks (35)

PART I
Q. 1: Choose the Best Answer (20)
1. While measuring the temporal association between cause and effect, the best study design can be;
a.Comparative Cross Sectional Study b.Case Control Study
c.Cohort Study d.All type of analytical studies
2. For an intervention to be defined in health research oriented terms, all of the following are true except;
a. Any type of maneuver which is applied to measure a change
b. A small word of mouth can be an intervention if it brings any change
c. Distributing hygiene kits in a community to reduce the incidence of diarrhea diseases can also be an intervention.
d. Taking biopsy of liver for the diagnosis of liver cancer is an intervention.
e. Measuring the changes in blood pressure after liver biopsy can be an intervention.
3. If you have the whole population frame available but wide spread over large geographical area, which best type of sampling technique can be adopted to get a sample;
a.Simple random b.Systematic c.Multistage d.Stratified e.Non probability
4. Using Cross sectional studies, we can determine the:
a.Temporal Association between exposure and outcome
b.Protective nature of the exposure c.Burden of diseases in a population
d.Incidence of the diseases
5. While selecting controls, care must be taken that the controls should have the following except:
a. Absolutely free of the diseases of interest
b. Must be representative of the general population c.Must be having the exposure of interest
d.Must be matched with the cases e.None of the above
6. Characteristics of a sample must include all of the following except:
a. Large enough
b. Representative of the population form which it is drawn
c. Must be free from most of the inherent qualities of the population
d. Should be properly approached, selected and interviewed.
7. While selecting a probability type of sampling technique, all of the following are false except:
a. All subjects of the population must be included in the sample
b. All subjects must be having equal chance of being included in the sample
c. All subjects must be having no equal chance of being included in the sample
d. Chance of being included in the sample will be decided by the investigator
e. Chance of being included in the sample must be decided by the population itself
8. The process of sharing of common characteristics while defining a cohort is actually decided by;
a.The population under study b.The investigator c.The project sponsor
d.The objective e.The control group
9. The best method of controlling the phenomenon of confounding at the design stage is by;
a.Logistic regression analysis b.Using multiple exposures in both groups
c.Restriction of sample d.Stratification e.None of the above
10. The most commonly utilized study design in health research to draw conclusion about burden of any variable in a given population is;
a.Case reports b.Cross sectional surveys c.Observational studies
d.Analytical e.Case control
11. The box in a box plot shows the:
a.Mean b.Variance c.Standard deviation d.Inter-quartile range e.Outliers
12. The most useful graph for showing the age distributions of the Pakistani population in 2011, using the intervals 0 – 18, 19 – 28, 29 – 38 would be a
a.Bar chart b.Histogram c.Pie chart d.Scatter diagram e.Time-series graph
13. Calculate the standard deviation of these data; 5. 5. 5
a.0 b.2 c.3 d.5 e.15
14. A large sample standard deviation implies that the sample values are
a.Large b.Small c.Dispersed d.Biased e.Skewed
15. Calculate the mode of these data; 10, 4, 6, 4, 10.5
a.7.0 b.10.0 c.4.0 d.5.0 e.6.0
16. Calculate the mean of these data; 1, 3, 5, 7, 9, 11.
a.5.0 b.5.5 c.6.0 d.6.5 e.7.0
17. Calculate the variance of these data. 3, 5, 7,
a.4/3 b.8/3 c.2 d.4 e.5
18. Calculate the median of these data. 10, 5, 3, 20, 7, 3
a.10.0 b.3.0 c.8.0 d.6.0 e.8.5
19. The inter-quartile range is the;
a. Difference between the mean and median
b. Difference between the variance and standard deviation
c. Difference between the outliers
d.Degree of skew-ness e.Middle half of the data
20. Calculate the variance of these data; 5, 10, 15
a.5 b.10 c.16.66 d.25 e.50

PART II
Q. 2: Exposure to ultraviolet radiations through sun exposure is a cause of skin cancer. How will you answer or find the association through a cohort study.
Q. 3: In a hospital based study, a researcher tries to determine the association between stomach cancer and heavy coffee intake. He took a group of 120 cases of stomach cancer and checked their history for heavy coffee intake and found that 39 of them did have history of heavy coffee intake. At the same time he took 120 non stomach cancer patients and checked their history of heavy coffee intake and found that heavy coffee intake was present in 7 subjects.
TASK:
1. Identify the study design.
2. In your opinion, how the researcher would have selected the controls to avoid bias.
3. Construct a 2 x 2 table and make an analysis plan for this particular study.
Q. 5: A researcher wishes to learn if a certain drug slows the growth of tumors. She obtained 20 mice with tumors and randomly divided them into two groups of 10 mice in each group. She then injected one group of mice with the drug and used the second group as a control.
After 2 weeks, she sacrificed the mice and weighed the tumors. The average weight of tumors for drug induced group of mice was 0.67 mg with a standard deviation of 0.2mg while average weight of tumors for control group of mice was 0.76 mg with a standard deviation of 0.2mg.he researcher is interested in learning if the drug reduces the growth of tumors.
Q. 6: Briefly explain the three principle characteristics of a randomized controlled trials.
Q. 7: A corporation maintains a large fleet of cars for its sales persons. To check the average number of miles driven per month per car, a random sample of n=40 cars is examined. The mean is calculated to be 2752 miles. Records from previous years indicate the average miles driven per car per month was 2600, with a standard deviation of 350 miles. Use the sample data to test the hypothesis that the use of cars, this year is different from the previous years.
Formulas:-

+ 1.96* S.D. / n for 95% confidence interval

Test statistics t = X – µ / S.E. of mean

Prof. Fazal Rehman Shamil