Mohammed Hommady

Research Theoretical Part

1. What is the type of bias in meta analysis? Community of medicine that collects all studies and combines their results

A. Tendency to answer questions untruthfully or misleadingly on a survey

B. Recall retrospective studies
C. Loss of follow up
D. Publication
Answer: Publication bias
Reference: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3868184/

2. What is the most common type of study that risks a recall bias?
Answer: Case control
Reference: http://jech.bmj.com/content/58/8/635
3. What is the most common type of study that risks non response bias?
Answer: Cross sectional
Reference: http://www.bmj.com/content/348/bmj.g2573.full
4. Definition of case report research case report is a detailed report of the symptoms, signs,
diagnosis, treatment, and follow-up of an individual patient.
Retrospective analysis of one, two, or three clinical cases Case reports may contain a demographic profile of the
http://viceprovost.tufts.edu/HSCIRB/case-reports/ patient, but usually describe an unusual or novel occurrence

5. Cross sectional:
Observational study that assesses risk factor and outcome at snapshot in time also called prevalence study
A case-control study is a type of observational study in which two existing groups differing
6. Case-control study:
in outcome are identified and compared on the basis of some supposed causal attribute
A study that compares patients who have a disease or outcome of interest with patients who don't have the disease
or outcome, and looks back retrospectively to compare how frequently the exposure to a risk factor is present in
each group to determine the relationship between the risk factor and the disease. One of the most significant
triumphs of the case-control study was the demonstration of the link between tobacco smoking and lung cancer
observational study that assesses risk factor and outcome at snapshot in time also called prevalence study

7. You conducted a study in which a group of epileptic patients using carbamazepine for 10 years. Now
you compare them with their age equivalent healthy individuals. What is this type of study called?
A- Case control study
B- Retrospective cohort study
C- Cross sectional
D- Prospective cohort study
The answer is : Case control. (Case: epileptic / Control: healthy)
8. study with least bias?
A- cohort B- cross sectional
C- case control D- case study
The answer is cohort study Another question: Cohort can be used to calculate incidence

9. Study compared effect of medication on baby whose mother were not taking the medication while
pregnant and followed them till birth and after developing , type of the study:
A. Cohort
B. Cross sectional
C. Case cont
Answer is Cohort

10. What type of study is used to compare 2 groups of pregnant ladies on specific diet outcome of pregnancy:
A. Cohort study
B. Cross sectional
C. Prospective cohort
Answer is Prospective Cohort
 Another question: What is the Benefit of doing randomize selection?
11. Why do we randomize the sample in research? Answer is : to Reduce Bias
A. To make sure outcome is actually a result of our intervention
B. To have minimal difference in variables between the groups (to equalize the variables)
Answer is: To make sure outcome is actually a result of our intervention

The use of randomized experimental design should allow a degree of certainty that the research
findings cited in studies that employ this methodology reflect the effects of the interventions being
measured & not some other underlying variable or variables

12. Randomized control studies between 2 populations with coronary artery disease. What's the first question
you should ask?
A. Was the age standardized
B. Are the medical facilities in both cities equal
C. If the price of cigarettes cheaper in any of the cities
The answer is missing: Are the variables used in both communities the same and comparable?

13. You were conducting a randomized control trial, some of the participants left your study. How
will you deal with this situation? A. Remove patient from control group
A. Ask people from the other randomized group to leave B. Add patient to intervention group
B. Abandon the study if more than 5% of the participants leave C. Cancel the trial if 5% drop the research
D. Include those patients who left in result
C. Include the values of the participants that left in your final statistical analysis Answer D
The answer is : C. Include the values of the participants that left in your final statistical analysis

14. In a study they are selecting every 10th family in the city, what is the type of study
A- Systematic randomized study Simple Random sampling: Computer generated
B- Stratified study - Systematic sampling: Every Nth value is taken
C- Non randomized study - Cluster sampling: entire clusters are selected randomly.
- Stratified sampling: divided into strata and A random sample is taken from each of these strata
Answer: Systematic randomized study Non random: - Convenience: readily available sample

15. A clinical trial study designed to have two groups of breast cancer assigned to a group with treatment
consist from modified mastectomy with radiation and other group modified mastectomy with chemotherapy,
all will be followed and look for recurrence. what is the study type?
Answer is: Randomized controlled trial
16. Best test for screening?
Answer: sensitivity

17. If a researcher wants to start a study and wants only the subjects that do not have diabetes to participate.
What will be high in the test? Specificity is the probability that an individual without the disease will test negative. It is the number of
patients who have a negative test and do not have the disease (true negatives) divided by the number of
Answer: Specificity patients who do not have the disease. A test with high specificity will infrequently identify patients as
having a disease when they do not (ie, low false positive results). Uptodate
Reference: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2636062/

18. What is the specificity of a screening test?

A. Without the disease test positive
B. With the disease test negative
C. Without the disease test negative
D. With the disease test positive
The answer is : Without the disease test negative

19. Researcher wants to enroll participants who are diabetes free.What’s the diagnostic test value?
A. Specificity B. Sensitivity
C. Negative predictive value
D. Positive predictive value
The answer is : Specificity
20. Definition of Positive predictive value & Negative predictive value
PPV: is the probability that subjects with a + screening test truly have the disease.
NPV: is the probability that subjects with a - screening test truly don't have the disease.
http://sphweb.bumc.bu.edu/otlt/MPH-Modules/EP/EP713_Screening/EP713_Screening5.html
 Another definition: The study of the distribution and determinants
21. What is the definition of epidemiology? of health related events (including diseases and application of
this study to control of diseases and the others health problems)
Answer: Epidemiology is the study and analysis of the distribution and determinants of health
and disease conditions in defined populations.
Choose the answer which
22. What does a confidence interval of 95% mean? contain “mean population”
Explanation: A 95% confidence interval reflects a significance level of 0.05.
If it is hypothesized that a true parameter value is 0 but the 95% confidence
interval does not contain 0, then the estimate is significantly different from
zero at the 5% significance level.
Reference: https://en.wikipedia.org/wiki/Confidence_interval
23. What determines how precise the study is?
A. P-value B. Confidence interval
C. Relative risk D. Odds ratio
Answer: Confidence Interval
Reference: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2920077/

24. What does “p-value” mean?

P-value or probability value is the probability for a given statistical model that, when the null hypothesis is
true, the statistical summary would be the same as or of greater magnitude than the actual observed results

25. What is the definition of a null hypothesis?

A null hypothesis" is a general statement or default position that there is no relationship between two
measured phenomena, or no association among groups.
** Measure of Variability
26. What is a Standard deviation? - Range; the difference between highest and lowest score (for small data)
- Variance: the degree of spread within distribution (stable measure)
- Standard deviation: measure how the average score deviated away from the mean (most stable measure)
It is a measure used to quantify the amount of variation or dispersion of a set of data values. A low standard
deviation indicates that the data points tend to be close to the mean (also called the expected value) of the set,
while a high standard deviation indicates that the data points are spread out over a wider range of values.

27. Definition of evidence based medicine (biosocial ….) the integration of best research evidence
with clinical expertise and patient values.
Evidence based medicine (EBM) is the conscientious, explicit, and judicious use of current best
evidence in making decisions about the care of individual patients.

28. In a systematic review, which one of the following can be done to decrease selection bias?
A. English literature
B. Setting inclusion/exclusion criteria
C. Including papers with positive outcomes only
Answer: Setting inclusion/exclusion criteria
Reference: https://www.ncbi.nlm.nih.gov/books/NBK126701/
29. Post test probability of a diagnostic test:
A. Likelihood ratio
B. Predictive value
Answer: Likelihood ratio.
The likelihood ratio is a probability of an individual without the condition having the test result
Reference: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4025141/
30. The way to determine the accuracy of occult blood test for 11,000 elderly patients is by measuring:
(A) Sensitivity.
(B) Specificity.
(C) Positive predictive value. Answer: A. Sensitivity
(D) Negative predictive value.
 Prevalance the number of existing cases at a specific moment of time.
31. Definition of endemic or epidemic disease: (total number of cases/total population = Incidence x duration)
1. Endemic: Refers to the constant presence and/or usual prevalence of a disease or infectious agent in a
population within a geographic area.

2. Hyperendemic: Refers to persistent, high levels of disease occurrence. Occasionally, the amount of
disease in a community rises above the expected level.

3. Epidemic: Refers to an increase, often sudden, in the number of cases of a disease above what is
normally expected in that population in that area.

4. Pandemic: Refers to an epidemic that spreads over continents

https://www.vocabulary.com/articles/chooseyourwords/endemic-epidemic/
http://www.cdc.gov/ophss/csels/dsepd/ss1978/lesson1/section11.html

32. Definition of epidemic curve?

An epidemic curve gives a graphical display of the numbers of incident cases in an outbreak or epidemic,
plotted over time.
http://www.med.uottawa.ca/sim/data/Public_Health_Epidemic_Curves_e.htm

33. Most common nomograph used for positive predictive value:

Answer: Roc curve. Explanation: In a ROC curve the true positive rate (Sensitivity) is plotted in
function of the false positive rate (100-Specificity) for different cut-off points of a parameter.
Reference: https://www.omicsonline.org/evaluating-measures-of-indicators-of-diagnostic-test-
performance-fundamental-meanings-and-formulars-2155-6180.1000132.php?aid=4054

34. What is a funnel plot?

Answer: A funnel plot is a scatter plot of the effect estimates from individual studies against
some measure of each study’s size or precision.

Explanation: The standard error of the effect estimate is often chosen as the measure of study size
and plotted on the vertical axis8 with a reversed scale that places the larger, most powerful studies
towards the top. The effect estimates from smaller studies should scatter more widely at the bottom,
with the spread narrowing among larger studies.
Reference: http://www.bmj.com/content/343/bmj.d4002
35. What is the graph that is usually used to illustrate a relation between two variables?
Answer: Scatter plot
Reference: http://www.stat.ucla.edu/~rgould/m12s01/relations.pdf
36. A study of something shows reduced risk of DM from 10% to 5% what is called?
A. Efficacy B. Effectiveness
Answer: Effectiveness
Reference: https://www.ncbi.nlm.nih.gov/books/NBK44024/

37. What is the definition of Attributable risk? A number of cases of a disease attributable to one risk factor. CER - EER
Difference in rate of a condition between an exposed population and an unexposed population.

38. Post-test probability is plotted in?

A. Forest plot
B. Nomogram
C. ROC plot
Answer: Nomogram
Research Calculation Part
1. Cohort study, calculate the Relative Risk. Always remember:
A = Diseased + exposed
Answer: Relative Risk = (A / (A+B)) / (C / (C+D)). B = Healthy + exposed
C = Diseased + not exposed
D = Healthy + exposed

2. Case-control study, calculate the odds ratio.

Answer: Odds ratio = (A/B)/ (C/D) or A*D/ B*C
3. What is the incidence rate for 10000 population, 2000 old cases, and 1000 new cases?
A. 10% B. 12.5 C. 20% D. 25%
10000-(2000old) = 8000
Answer: 12.5% 1000/8000 = 12.5%
Substract any preexisting cases from the total population at risk, as these individuals are no longer at risk.
First Aid Step 2

4. Epidemiological study want to see the effect of smoking in lung cancer: 90% of lung cancer patients
are smokers while 30% of those who don’t have the disease are smokers. The specificity of smoking as
a risk factor is:
A. 30%
B. 40%
C. 70%
D. 90%
Answer: 70%
Explanation: Specificity = b/(d+b) = 70/ (30+70) = 70%

5. At a daycare center, 10 out of 50 had a red eye in the first week; another 30 developed the same
condition in the next 2 weeks. What is the attack rate (cumulative incidence)?
A. 20%
B. 40% Attack rate (cumulative incidence, risk, incidence proportion, probability of
C. 60% developing the disease) = new cases/size of population at START of period
D. 80% Anther question: New cases 200 Old cases 80 Total 280 So, (280/8000000)* 100000= 3.5
Answer: 80% (10+30 / 50)
Attack Rate = cases due to a specific cause in a short period of time divided by the population at
risk, often associated with an epidemic situation such as food borne disease (cumulative incidence)

6. 80 persons found to have Typhoid Fever in a population of 20,000 during the last 4 years.
If we measure it on a population of 100,000, what will be the incidence in one year?
A- 20
B- 100 80 persons from 20,000 in 4 years (Divide by 4 because question is asking about 1 year)
20 persons from 20,000 in 1 year (Multiply by 5 because question is asking about 100,000 population)
C- 150 100 persons from 100,000 in 1 year
D- 200
Answer: 100
7. In a cohort study on lubricant oil use and urinary bladder CA done over 20 years 10,000 exposed
10,000 non exposed 750 exposed got CA 150 non exposed got CA Then they asked about the
incidence in 1000 in one year?
A- 2.25
B- 45 900 persons from 20,000 in 20 years (Divide by 20 because question is asking about 1 year)
C- 0.45 45 persons from 20,000 in 1 year (Divide by 20 because question is asking about 1000 population)
2.25 persons from 1000 in 1 year
D- 0.225
Answer 2.25
8. Study about GDM association with malformation. 2 groups. 5000 control group, 50 developed.
1000 diseased group 20 developed.(not sure about the numbers) The best for risk factor
association? (and calculate)
A- Relative risk = 2
B- Odds ratio = 2
OR used for case control study
C- RR = 0.2 OR = ( 20*4950 ) / ( 50*980 ) = 2
D- OR = 0.2
Answer: Odd ratio = 2 (By community specialist)
 9. Cohort study – 2 groups: one of them exposed to patient with positive MERSA and the other group
is not exposed to these patients. According to picture, what is the ratio of exposed to nonexposed?
A. 66:1
B. 55:1 (A / (A+B)) (80 / (80+20)) Always remember:
RR = (C / (C+D)) = = 66.667
(6 / (6+494)) A = Diseased + exposed
C. 44:1 B = Healthy + exposed
C = Diseased + not exposed
Answer is : 66:1
D = Healthy + exposed

10. Cohort study – 2 groups: one of them exposed to patient with positive MERSA and the other group
is not exposed to these patients. According to picture, what is the ratio of exposed to nonexposed?
A. 66:1
B. 55:1 (A / (A+B)) (80 / (80+20)) Always remember:
RR = (C / (C+D)) = = 53.33 A = Diseased + exposed
(6 / (6+394))
C. 44:1 B = Healthy + exposed
C = Diseased + not exposed
Answer is : 55:1 D = Healthy + exposed

11. Lung cancer affected 80 of 100 smokers, 6 of 500 non smokers, What is Relative risk reduction?
A. 33:1 Question asked about Relative Risk Reduction RRR which equals (1 - RR)
B. 55:1 RRR = 1 - RR = 1 - 0.66 = 0.34
C. 66:1
Answer is : 33:1

12. A cohort study of smoking and lung cancer was conducted in a small island population. There were
a total of 1,000 people in the study, and the study was conducted over a ten year period. Four hundred
were smokers and 600 were not. Of the smokers, fifty developed lung cancer. Of the non-smokers, 10
developed lung cancer. What is the Relative Risk?
A. 7.5
Relative risk = probability of getting the disease if exposed/ Probability of getting the disease if not exposed.
B. 0.7 The probabilty of getting the disease if exposed = the number of diseased smokers/ number of total smokers
C. 8.5 =50/400=0.125. The probabilty of getting the disease if not exposed = the number of diseased non-smokers/
D. 75 number of total non-smokers = 10/600=0.016667. RR= 0.125/0.016667=7.49
Answer is: 7.5
13. The number of upper respiratory tract infection cases per 1000 population this year is 117 case. The
average number of disability from work is 2.5 days. What is the prevalence of disability per 1000?

Answer is : 292.5 Prevalence = Incidence X Duration of disease = 117x2.5 = 292.5

14. A study aims at exploring the association of cigarette smoking and the risk of IHD. Results were
as follows (Numbers are not exact, but are used for clarification purposes)
* Non smokers.OR:. 0.1
* Mild smokers..OR:. 1
* Heavy smokers.OR: 2
* Extensive heavy chain smokers OR:. 5
Which of these is true about this study findings?
A. Dose-Dependent Relationship
B. Risk Association Relationship

Answer is : Dose-Dependent Relationship The odd ratio is increasing as the patient is smoking heavier.

15. Study done between OCP usage and DVT, 1500 had DVT, 8500 as control group no DVT. 20 had DVT from
those used OCP and 50 had DVT from control group. Calculate morbidity rate in 1000 population:
A- incidence rate is 15 Prevalence is a statistical concept referring to the number of cases of a disease that are
B- prevalence is 150 present in a particular population at a given time.
C- Incidence rate is 150 Whereas incidence refers to the number of new cases that develop in a given period of time.
D- prevalence rate is 15
Answer is : Prevalence is 150
16. Research using Stool occult test to detect the presence of intestinal polyps. (Numbers were
provided in the questions) Depends on the numbers, so here are the equations:
A - Sensitivity 50% Sensitivity = A/(A+C) × 100
B - Specificity 96 % Specificity = D/(D+B) × 100
C - Positive predictive value 50% Positive Predictive Value = A/(A+B) × 100
D - Negative predictive value 94% Negative Predictive Value = D/(D+C) × 100
Answer is : Positive predictive value 50% in one question
Answer is : Specificity 96% in another question
17. A study aims at exploring the association of high fat intake and prostatic cancer., Group 1 has
prostatic cancer (1000) patients with 50 high fat intake, group 2 doesn’t have cancer (1000) pt with 10
high fat intake:-
A. OR 0.52
B. OR 5.2
C. RR 0.52
D. RR 5.2
50*990 / 10*950
49,500 / 9500
OR =
5.2

Answer is : OR 5.2. (Odd Ratio is typically used in case control studies)

Quick review
SMLE Research:
1. Relative risk formula: Incidence in exposed/incidence in non exposed = a/(a+b) / c/(c+d)
2. Odds ratio: (A/B)/ (C/D) or A*D/ B*C
3. Unknown scenario incidence (1000/8000): 12.5%
4. Lung cancer and smoking specificity: 70%
5. Daycare red eye cumulative attack rate 80%
6. Typhoid fever incidence: 100
7. Urinary bladder and lubricant oil incidence: 2.25
8. GDM and congenital malformations OR: 2.0
9. MRSA relative risk: 66:1 (if 100 contact, 500 no contact)
10. MRSA relative risk: 55:1 (if 100 contact, 400 no contact)
11. Lung cancer and smoking relative risk: 66:1. Relative risk reduction 33:1
12. Lung cancer and smoking relative risk: (7.5 if different answers)
13. Disability days of URTI: 292.5
14. Cigarettes smoking: Dose-Dependent Relationship
15. OCP and DVT prevalence: 150
16. Intestinal polyps: positive predictive value: 50%
17. Prostatic cancer and high fat intake OR: 5.2
18. Extra question: Colon cancer and smoking relative risk: 6.6
 New Questions
1. A study was done on 2 groups control (non-smokers) and smokers followed up for 20 years
to see the prevalence of colorectal cancer. What is this type of study?
A. Case control B. Cohort C. Cross-sectional D. Systemic review
Answer: Cohort
2. Best research study for effectiveness of preventative measure for periodic health check
A) Case control B) Cohort C. RCT
Answer: RCT
3. Study of case control about lung or colon (I forgot, and not sure about numbers) associated with
smoking, 2000 of them are cases and 2000 are control, 800 of cases were examined and 190 of control
were examined also, what is the odd ratio?
OR = (a*d) / (b*c)
A. 0.13 B. 11.2 C. 2.2 D. 6.3 OR = (800*1810) / (190*1200)
Answer: 6.3 OR = 6.3

Make sure to memorize the equation, because the numbers in the question may not be correct

4. Cohort Research about Colonon cancer and smoking. 600 Smokers, 200 of them have Colon Cancer,
600 non smokers 30 of them have Colon Cancer. Calculate RR?
(A / (A+B)) (200 / (200+400))
Answer: RR = 6.6 RR = = = RR = 6.6
(C / (C+D)) (30 / (30+570))

5. Study about stroke, the medication decreases the mortality from 8% to 4%, in 10 years. What is the
number needed to treat to prevent a death?
A. 4 B. 10 C. 20 D. 25 NNT = 1/ARR (ARR = CER - EER = 8 - 4= 4)
Answer: 25 NNT = 1/4 = 0.25 = 25%

6. Study to assess new test for H.pylori done in clinic. 70 have positive test by new test of 100 have
positive culture. 300 have negative test by new test of 400 have negative culture. What is the specificity?
Specificity = D/(D+B) × 100 + -

Answer: 75% Specificity = 300/(300+100) x 100 +

70 IAO
Specificity =75% -
30 300
Make sure to memorize the equation, because the numbers in the question may not be correct

7. You have devised a new test to diagnose a disease and you want to check it against a gold standard
test. There were figures showing the number of those who actually have the disease according to the
gold standard test and the number of those who were tested positive with your test. Also figures
showing the number of true negatives with your test. What is the specificity of your new test?
A- 40% B- 50% C- 60% D- 80%

Answer: Follow the equation. Specificity = D/(D+B) × 100

8. What is the meaning of standard deviation?

A. Measure central of tendency
B. Measure normality of data
C. Equal to range
D. Measure of variability
A measure that is used to quantify the amount of
variation or dispersion of a set of data values.
It is a measure of variability that measures how
the average score deviated away from the mean.

Answer is : D. Measure of variability or dispersion.

9.There is a study to the effect on intensive insulin regimen in the reduction of
neuropathy in the patient, the results are as following:
Event in the regular insulin regimen:0.092
Event in the intensive insulin regimen:0.022
Which of the following is correct? Answer: D. NNT = 14.2
A- Patient expected event rate: 0.07
NNT = 1/(exposed - nonexposed)
B- Odd ratio is 4.2 NNT = 1/(0.092 -0.022)
C- Number needed to harm: 7 NNT = 14.2
D- Number needed to treat: 14
10. Two communities had heart disease they compared and found community number one having higher
rate what would you like to ask the researchers?
A. Are the two communities having the same hospital facility?
B. Are the variables used in both communities the same and comparable?
C. Are the ages of the patients put in category?
Answer: is B. Are the variables used in both communities the same and comparable?
11. New research calculate sensitivity Total population 800, diseased 200 , 50 had positive result, and
another 200 had positive of the normal people Sensitivity?
A. 20 + -

B. 25 Sensitivity = C/(C+A) × 100 150 400

C. 30 Sensitivity = 50/(50+150) x 100 I 50
200
Sensitivity = 25%
Answer: B. 25

12. What is the definition of Relative Risk (RR)?

Answer: The ratio of the probability of an outcome in an exposed group to the probability
of an outcome in an unexposed group.

13. What is the definition of Odd Ratio (OR)?

Answer: Statistic defined as the ratio of the odds of A in the presence of B and the odds of A without
the presence of B

14. What is the definition of incidence?

Answer: measure of the probability of occurrence of a given medical condition in a population within
a specified period of time

15. What is the definition of sensitivity?

Answer: If a person has a disease, how often will the test be positive (true positive rate)
16. What is the definition of Specificity?
Answer: If a person does not have the disease how often will the test be negative (true negative rate)
17. What is explanation of CI 95%?
Answer: amount of uncertainty associated with a sample population estimate (the
mean or proportion) of a true population.
 Incomplete questions

1. Supposed that control event rate and Odds ratio were given, what can you calculate from them?
A - Numbers to harm
B - Numbers to treat
C - Risk difference Answer is : Maybe C
D - Experiment event

2. Case control study showing this information: Odd ratio .75, Control rate .05 what’s correct:
A - Number needed to tx is 69
B - Number needed to harm 69
C - Relative risk is 0.12 Answer maybe C
3. Risk of Exposed: 3. Risk of Unexposed: 2 (These were the only numbers in the question and it was a
case-control study about insecticide use and skin cancer). What can we calculate?
A. Number of patient to treat is 20
B. Number of patient to harm is 20
C. Relative risk is .7
D. Expected Patient event = 2
Answer is : Maybe D Other q bank. Answer : ARR = Risk1 - Risk 2 = 3-2 = 1 , NNT = 1/ARR = 1
 New Incomplete Questions

1. A team is doing research comparing between two chemotherapy treatments. The end point of the study
is survival rate. What parameter they would benefit mostly from?
A. Odds ratio B. Hazard ratio C. Relative risk D. Relative risk reduction Answer: Maybe D
2. Positive predictive value score?
A- People who have the disease
B- People who are predicted to have the disease
C- High risk people who are predicted to have the disease
D- Low risk people who are predicted to have the disease
3. Two studies, one assessing risk of alcohol in breast cancer, the other is smoking in breast cancer:
Alcohol RR is 1.8 and confidence interval is 1.2-4.3
Other reporter of the question:
Smoking RR is 1.6 and confidence interval is 0.6-3.7 Alcohol group OR 1.4 (CI 95%: 1.0 – 2.0)
Smoking group OR 1.6 (CI 95%: 0.7 – 10.8)
A. Risk of bias is high
B. Results are by chance
C. Smoking sample size is small
D. Alcohol and smoking have no effect on breast cancer

4. A company is studying one treatment. Which has most effective results?

A. RR is 2.8 // CI is 1.9-3.4
B. RR is 3.8 // CI is 1.7-6.7
Other reporter of the question:
What the best study to determine drug x effect on IHD
A.RR:0.3 CI 0.21 to 0.43 ✅
B. RR: 0.8 CI 0.41 to 0.62
C. RR: 1.21 CI 2.01 to 3.81
D. RR: 3.1 CI 4.21 to 6.54

For this one Chose the interval include RR value Above the null value
that is above 1 Or below if not there And the narrowest range

5. Which one of the following increases the quality of the randomized controlled study & make it stronger?
A. Systemic Assignment predictability by participants
B. Open Allocation
C. Including only the participants who received the full intervention
D. Following at least 50 % of the participants
E. Giving similar intervention to similar group

6. You made a research comparing two drugs, P value was 0.13. What does it mean?
A. No real evidence that there is difference between the 2 drugs Other reporter of the question: sorry I forgot the choices
but I'm sure I didn't see choice A in the exam
B. Sample sizes are small
- EXPLANATION: If you get a p-value of 0.13, it means that when the null hypothesis is true, a value of the
test statistic as or more extreme than what was observed occurs in about 13% of all samples. This is a re-
expression of the definition of p-values. That is, saying there is a 13% chance of observing results as or
more extreme than what was observed is equivalent to saying that you'd observe results as or more
extreme than what was observed in 13% of (random samples.
"P-value Interpretation:
P< 0.01 very strong evidence against Null hypothesis
0.01< = P < 0.05 moderate evidence against Null hypothesis
0.05< = P < 0.10 suggestive evidence against Null hypothesis
0.10< = P little or no real evidence against Null hypothesis

P tells about statistical significance. You can't blindly reject and accept by seeing 0.05. Thorough knowledge is needed to accept
and reject the values of P. The null hypothesis which states the opposite of your hypothesis (if your hypothesis says that drug A is
more effective than drug B, the null hypothesis says that drug A is not more effective than drug B)