Biostatistics Practice Questions

Q: In a case-control study on smoking and lung cancer, 33 out of 35 lung cancer patients were smokers. Of 82 controls, 27 were non-smokers. Calculate the odds ratio.

8.1. ### **Explanation** The **Odds Ratio (OR)** is the standard measure of association used in **Case-Control studies**. It represents the ratio of the odds of exposure among cases to the odds of exposure among controls. #### **Step 1: Construct the 2x2 Contingency Table** To calculate OR, we must first organize the data into a standard table: | | Lung Cancer (Cases) | No Lung Cancer (Controls) | | :--- | :---: | :---: | | **Smokers (Exposed)** | **a** = 33 | **b** = 55 (82 total - 27 non-smokers) | | **Non-Smokers (Non-exposed)** | **c** = 2 (35 total - 33 smokers) | **d** = 27 | #### **Step 2: Apply the Formula** The formula for Odds Ratio is: **(a × d) / (b × c)** * **OR** = (33 × 27) / (55 × 2) * **OR** = 891 / 110 = **8.1** An OR of 8.1 indicates that the odds of lung cancer are 8.1 times higher among smokers compared to non-smokers. --- #### **Analysis of Incorrect Options** * **Option A (0.21):** This value is less than 1, which would imply smoking is a "protective factor" against lung cancer. * **Option C (4.1) & D (2.1):** These are mathematical errors resulting from misplacing values in the 2x2 table (e.g., using the total number of subjects instead of the non-exposed cells). --- #### **High-Yield Clinical Pearls for NEET-PG** 1. **Study Design:** Odds Ratio is used for Case-Control studies (retrospective), while **Relative Risk (RR)** is used for Cohort studies (prospective). 2. **Interpretation:** * OR > 1: Positive association (Risk factor). * OR = 1: No association. * OR < 1: Negative association (Protective factor). 3. **Rare Disease Assumption:** If the disease is rare, the Odds Ratio provides a good approximation of the Relative Risk. 4. **Cross-Product Ratio:** OR is also known as the "Cross-product ratio" because it is the product of the diagonals (ad/bc).

Q: Based on the provided graph, what is the order of least margin of error?

3>2>1. ***3>2>1*** - **Margin of error** is inversely related to **sample size** - larger samples have smaller margins of error and narrower distributions. - From the graph, curve **3** has the widest distribution (largest margin of error), curve **2** is medium width, and curve **1** is narrowest (smallest margin of error). *3>1>2* - This incorrectly places curve **1** as having a larger margin of error than curve **2**. - The graph clearly shows curve **1** has the **narrowest distribution**, indicating the smallest margin of error, not medium. *1>3>2* - This reverses the correct order by suggesting curve **1** has the largest margin of error. - Curve **1** actually shows the **narrowest distribution** with the smallest margin of error, contradicting this ordering. *1=2=3* - This suggests all three curves have **equal margins of error**, which contradicts the visual evidence. - The graph clearly shows **different distribution widths**, with curve 1 being narrowest, curve 2 medium, and curve 3 widest.

Q: Which of the following is not an accepted method of randomization?

Odd/even day hospital admission. **Explanation:** Randomization is the "heart" of a Randomized Controlled Trial (RCT). Its primary purpose is to eliminate **selection bias** and ensure that both known and unknown confounding factors are distributed equally between the study and control groups. **Why Option B is correct:** Odd/even day hospital admission is a method of **Quasi-randomization** (systematic allocation). It is not considered true randomization because the allocation sequence is **predictable**. If a researcher or clinician knows that a patient arriving on a Monday (odd day) will receive the intervention, they might subconsciously delay or expedite a patient’s admission to influence which group they join. This violates the principle of concealment and introduces selection bias. **Why other options are incorrect:** * **A, C, and D:** Computer-generated sequences, the Lottery method, and Random Number Tables (like Tippett’s table) are all validated methods of **True Randomization**. They ensure that every participant has an equal, non-zero chance of being assigned to any group, and the sequence remains unpredictable. **High-Yield Clinical Pearls for NEET-PG:** * **Gold Standard:** The RCT is the gold standard study design to establish **causality**. * **Allocation Concealment:** This is the procedure used to prevent selection bias by keeping investigators unaware of the upcoming assignment. It is done *before* the intervention starts. * **Blinding:** This is done *after* allocation to reduce observer and participant bias. * **Types of Randomization:** 1. **Simple:** Like a coin toss or random table. 2. **Stratified:** Used when a specific confounding variable (e.g., age, gender) needs to be balanced. 3. **Block:** Ensures equal sample sizes in both groups throughout the study.

Q: Which of the following statements about a cohort study is false?

It is always prospective.. In epidemiology, a **Cohort Study** is an observational analytical study that starts with a group of people (a cohort) free of the disease, classified by their exposure status, and followed over time to observe the development of the outcome. ### Why Option D is the Correct Answer (The False Statement) While most cohort studies are prospective, they are **not always prospective**. There are three types of cohort studies: 1. **Prospective Cohort:** Starts in the present and follows subjects into the future. 2. **Retrospective (Historical) Cohort:** The investigator goes back in time using records (e.g., occupational or medical records) to identify exposure and follows the cohort up to the present or a point in the past to determine the outcome. 3. **Ambispective Cohort:** Combines both retrospective and prospective elements. ### Why the Other Options are Incorrect (True Statements) * **A. Incidence can be measured:** Since cohort studies follow a disease-free population over time to see who develops the condition, they are the "gold standard" for calculating **Incidence** and **Relative Risk (RR)**. * **B. Used to study chronic diseases:** Cohort studies are excellent for studying chronic conditions (e.g., Framingham Heart Study) because they allow for the assessment of multiple outcomes from a single exposure. * **C. It is expensive:** Because they require large sample sizes and long follow-up periods, cohort studies are significantly more expensive and time-consuming than case-control studies. ### NEET-PG High-Yield Pearls * **Directionality:** Cohort studies always move from **Cause to Effect**. * **Key Metric:** **Relative Risk (RR)** and **Attributable Risk (AR)** are derived from cohort studies. * **Best for:** Rare exposures (e.g., a specific chemical leak). * **Main Bias:** **Attrition Bias** (loss to follow-up) is the most common challenge in cohort studies.

Q: In a population of 5000, with a birth rate of 30 per 1000 population, 15 children died during their first year of life in one year. Of these, 9 died during the first month of life. What is the infant mortality rate in this population?

100. ### Explanation **1. Why Option D is Correct (The Underlying Concept)** To calculate the **Infant Mortality Rate (IMR)**, we must first determine the number of live births, as the denominator for IMR is always "per 1000 live births," not the total population. * **Step 1: Calculate Live Births** Birth Rate = (Number of live births / Total population) × 1000 30 = (Live Births / 5000) × 1000 Live Births = (30 × 5000) / 1000 = **150 live births.** * **Step 2: Calculate IMR** IMR = (Number of deaths under 1 year of age / Total live births) × 1000 IMR = (15 / 150) × 1000 IMR = 0.1 × 1000 = **100.** The 9 deaths during the first month (Neonatal Mortality) are already included in the 15 total infant deaths and are used only if calculating the Neonatal Mortality Rate. **2. Why Other Options are Incorrect** * **Option A (60):** This is the Neonatal Mortality Rate (9/150 × 1000). * **Option B (150):** This represents the total number of live births, not the rate. * **Option C (45):** This is a distractor resulting from incorrect multiplication or using the wrong denominator (e.g., 9/200). **3. Clinical Pearls & High-Yield Facts** * **IMR Definition:** Deaths of infants under 1 year of age per 1000 live births. It is considered the most sensitive indicator of the health status of a community. * **Neonatal Mortality Rate (NMR):** Deaths within the first 28 days of life. In India, NMR contributes to roughly 2/3rd of the IMR. * **Post-Neonatal Mortality Rate:** Deaths between 28 days and 1 year. It is primarily influenced by environmental factors (diarrhea, malnutrition). * **Formula Tip:** Always check if the denominator provided is "Total Population" or "Live Births." If the birth rate is given, you must calculate live births first.

Q: In a study, there were 35 cases of lung carcinoma and 82 controls. Of the cases, 33 had a positive history of smoking, and 55 of the controls had a positive history of smoking. What is the odds ratio?

8. ### Explanation **1. Understanding the Concept: Odds Ratio (OR)** The Odds Ratio is the measure of association used in **Case-Control studies**. It quantifies the relationship between an exposure (smoking) and an outcome (lung carcinoma). It is defined as the ratio of the odds of exposure among cases to the odds of exposure among controls. **2. Calculation Steps** To calculate the OR, we first arrange the data into a **2x2 Contingency Table**: | | Cases (Lung CA) | Controls (No CA) | | :--- | :---: | :---: | | **Exposed (Smokers)** | 33 (a) | 55 (b) | | **Non-Exposed (Non-smokers)** | 2 (c) | 27 (d) | * **Cases:** Total = 35. Smokers (a) = 33. Non-smokers (c) = 35 - 33 = 2. * **Controls:** Total = 82. Smokers (b) = 55. Non-smokers (d) = 82 - 55 = 27. **Formula:** $OR = \frac{a \times d}{b \times c}$ (Cross-product ratio) $OR = \frac{33 \times 27}{55 \times 2} = \frac{891}{110} = 8.1$ Rounding to the nearest whole number, the **Odds Ratio is 8**. This means smokers are 8 times more likely to develop lung carcinoma compared to non-smokers. **3. Analysis of Incorrect Options** * **B, C, and D:** These values are mathematically incorrect based on the provided data. They would only be reached if the number of non-exposed cases (c) was significantly lower or the exposed cases (a) were significantly higher. **4. NEET-PG High-Yield Pearls** * **Study Design:** Odds Ratio is the only measure of association for Case-Control studies because the incidence cannot be calculated (the researcher determines the number of cases/controls). * **Interpretation:** * OR > 1: Positive association (Risk factor). * OR = 1: No association. * OR < 1: Negative association (Protective factor). * **Rare Disease Assumption:** If a disease is rare, the Odds Ratio provides a good approximation of the **Relative Risk (RR)**.

Q: The dependent population in old age is generally defined as the population above what age?

65 years. ### Explanation In biostatistics and demography, the **Dependency Ratio** is a crucial indicator used to measure the economic burden on the working-age population. The population is typically divided into three age-based cohorts: 1. **Children (Young Dependents):** 0–14 years. 2. **Working Age (Productive Population):** 15–64 years. 3. **Elderly (Old Age Dependents):** 65 years and above. **Why 65 years is correct:** According to the World Health Organization (WHO) and standard demographic conventions, the **Old Age Dependency Ratio** specifically calculates the number of individuals aged **65 years and older** per 100 persons of working age (15–64 years). This threshold is internationally recognized for statistical reporting to ensure comparability across different nations. **Analysis of Incorrect Options:** * **53 & 55 years (Options A & B):** These ages do not correspond to any standard demographic classification. While some specific labor sectors might have early retirement, they are not used for calculating national dependency ratios. * **68 years (Option D):** While life expectancy is increasing, 68 is not the standard cutoff. Using a higher age would artificially lower the dependency ratio, underestimating the social security and healthcare needs of the elderly. **High-Yield Pearls for NEET-PG:** * **Total Dependency Ratio Formula:** $\frac{(\text{Pop. } 0-14) + (\text{Pop. } 65+)}{\text{Pop. } 15-64} \times 100$. * **India Context:** In many Indian government surveys (like NFHS), "Elderly" is often defined as **60+ years** due to lower retirement ages and life expectancy compared to the West. However, for standard biostatistical questions unless specified otherwise, the international standard of **65+ years** is the preferred answer. * **Demographic Dividend:** This occurs when the proportion of the working-age population (15–64) is high relative to the dependent population.

Q: An investigator is studying the impact seatbelts have on the severity of injuries incurred during a motor vehicle accident. Which of the following study designs would be most appropriate for answering this question?

Case-control study. **Explanation:** The primary objective of this study is to investigate the association between an exposure (seatbelt use) and an outcome (severity of injury). **Why Case-Control is the Correct Answer:** In injury epidemiology, particularly for motor vehicle accidents (MVAs), the outcome (injury) has already occurred by the time the investigator begins the study. A **Case-Control study** is the most appropriate and practical design here. * **Cases:** Individuals who sustained severe injuries. * **Controls:** Individuals involved in similar accidents who sustained minor or no injuries. The investigator then looks **backwards in time** (retrospective) to determine the frequency of seatbelt use in both groups. This design is efficient for studying outcomes that are sudden or "acute" events like accidents. **Analysis of Incorrect Options:** * **A. Case Series:** This only describes a group of injured patients without a comparison group. It cannot establish an association or calculate risk. * **C. Cohort Study:** While theoretically possible, it is impractical and unethical to follow a group of people and wait for them to have accidents to see if seatbelts worked. It would require a massive sample size and a very long duration. * **D. Clinical Trial:** It is unethical to randomly assign one group to "no seatbelt" (the intervention) and expose them to the risk of injury in a trial setting. **NEET-PG High-Yield Pearls:** * **Directionality:** Case-control is "Retrospective" (Effect to Cause), whereas Cohort is "Prospective" (Cause to Effect). * **Measure of Association:** Case-control studies use **Odds Ratio (OR)**; Cohort studies use **Relative Risk (RR)**. * **Best for Rare Diseases:** Case-control is the design of choice for rare diseases or outcomes with long latency periods. * **Injury Epidemiology:** For sudden-onset events like MVAs or outbreaks, case-control is often the most feasible initial study design.

Q: Which statistic is used to measure the linear association between two characteristics in the same individuals?

Coefficient of correlation. ### Explanation **Correct Answer: B. Coefficient of correlation** The **Coefficient of Correlation (r)**, specifically Pearson’s correlation coefficient, is the statistical tool used to measure the strength and direction of a **linear relationship** between two continuous quantitative variables (e.g., height and weight) measured in the same individuals. The value of ‘r’ ranges from -1 to +1. A value of +1 indicates a perfect positive linear relationship, -1 indicates a perfect negative relationship, and 0 indicates no linear association. **Why other options are incorrect:** * **A. Coefficient of Variation (CV):** This measures the relative dispersion of a single data set (Standard Deviation divided by Mean). It is used to compare the variability between two different series (e.g., comparing the variability of height in cm vs. weight in kg). * **C. Chi-square Test:** This is a test of significance used for **categorical (qualitative) data**. It measures the association between two nominal variables (e.g., smoking status and lung cancer) rather than a linear relationship between continuous variables. * **D. Standard Error (SE):** This is a measure of sampling error. It indicates how much the sample mean is likely to deviate from the actual population mean. **High-Yield Clinical Pearls for NEET-PG:** * **Coefficient of Determination ($r^2$):** This represents the proportion of variance in one variable that is predictable from the other. (e.g., if $r = 0.6$, then $r^2 = 0.36$ or 36%). * **Scatter Diagram:** This is the visual/graphic method used to represent the correlation between two quantitative variables. * **Regression:** While correlation measures the *strength* of association, regression is used to *predict* the value of one variable based on the other.

Question 1

In a case-control study on smoking and lung cancer, 33 out of 35 lung cancer patients were smokers. Of 82 controls, 27 were non-smokers. Calculate the odds ratio.

Accepted Answer

8.1

Answer

0.21

Answer

4.1

Answer

2.1

Question 2

Based on the provided graph, what is the order of least margin of error?

Accepted Answer

3>2>1

Answer

3>1>2

Answer

1>3>2

Answer

1=2=3

Question 3

Which of the following is not an accepted method of randomization?

Accepted Answer

Odd/even day hospital admission

Answer

Computer drawn randomization

Answer

Lottery

Answer

Random number table

Question 4

A diagnostic test for a particular disease has a sensitivity of 0.90 and a specificity of 0.90. The prevalence of the disease in the population is 10%. What is the probability that a person who tests positive actually has the disease?

Accepted Answer

81%

Answer

90%

Answer

50%

Answer

91%

Question 5

Which of the following statements about a cohort study is false?

Accepted Answer

It is always prospective.

Answer

Incidence can be measured.

Answer

It is used to study chronic diseases.

Answer

It is expensive.

Question 6

In a population of 5000, with a birth rate of 30 per 1000 population, 15 children died during their first year of life in one year. Of these, 9 died during the first month of life. What is the infant mortality rate in this population?

Accepted Answer

100

Answer

60

Answer

150

Answer

45

Question 7

In a study, there were 35 cases of lung carcinoma and 82 controls. Of the cases, 33 had a positive history of smoking, and 55 of the controls had a positive history of smoking. What is the odds ratio?

Accepted Answer

8

Answer

20

Answer

50

Answer

100

Question 8

The dependent population in old age is generally defined as the population above what age?

Accepted Answer

65 years

Answer

53 years

Answer

55 years

Answer

68 years

Question 9

An investigator is studying the impact seatbelts have on the severity of injuries incurred during a motor vehicle accident. Which of the following study designs would be most appropriate for answering this question?

Accepted Answer

Case-control study

Answer

Case series

Answer

Cohort study

Answer

Clinical trial

Question 10

Which statistic is used to measure the linear association between two characteristics in the same individuals?

Accepted Answer

Coefficient of correlation

Answer

Coefficient of variation

Answer

Chi square

Answer

Standard error

Biostatistics — MCQs

Biostatistics — MCQs

On this page

Practice by Chapter

Want unlimited practice?