Biostatistics — MCQs

Biostatistics Indian Medical PG Practice Questions and MCQs

Question 181: What is the study design used to calculate incidence?

A. Cross-sectional study
B. Cohort study (Correct Answer)
C. Case-control study
D. None of the above

Explanation: **Explanation:** The correct answer is **B. Cohort study**. **Why Cohort Study is correct:** Incidence refers to the number of **new cases** occurring in a defined population over a specific period. To calculate incidence, you must start with a group of individuals who are initially free of the disease (at risk) and follow them forward in time to see who develops the condition. A **Cohort study** (Prospective) is longitudinal by design, allowing for the direct measurement of the rate of development of new cases, thereby providing the **Incidence Rate** and **Relative Risk**. **Why other options are incorrect:** * **A. Cross-sectional study:** This is a "snapshot" study that measures the prevalence (existing cases) of a disease at a single point in time. It cannot distinguish between new and old cases, making it impossible to calculate incidence. * **C. Case-control study:** This study starts with the outcome (cases) and looks backward (retrospective) to determine exposure. Since the participants already have the disease at the start of the study, you cannot observe the development of new cases. It provides the **Odds Ratio**, not incidence. **High-Yield Clinical Pearls for NEET-PG:** * **Incidence =** (Number of new cases / Population at risk) × 1000. * **Prevalence =** Incidence × Mean Duration of disease ($P = I \times D$). * **Cohort Study** is the best design for studying rare exposures, while **Case-Control** is best for rare diseases. * **Incidence** is the best indicator for the etiology of a disease and the effectiveness of prevention programs.

Question 182: The values obtained are arranged in ascending or descending order to calculate which of the following?

A. Median (Correct Answer)
B. Mode
C. Mean
D. Ratio

Explanation: ### Explanation **1. Why Median is the Correct Answer:** The **Median** is defined as the middle-most value in a distribution when the data points are arranged in a specific order (either ascending or descending). It is a measure of central tendency that divides the dataset into two equal halves. Because it depends on the *position* of the values rather than their magnitude, it is the preferred measure of central tendency for **skewed distributions** as it is not influenced by extreme outliers. **2. Why the Other Options are Incorrect:** * **Mode (B):** This is the value that occurs most frequently in a dataset. It does not require the data to be ordered; it simply requires a frequency count. * **Mean (C):** The Arithmetic Mean is the average calculated by summing all values and dividing by the total number of observations ($Σx/n$). It does not require ordering. * **Ratio (D):** A ratio is a relationship between two independent quantities (e.g., Male:Female ratio). It is a descriptive statistic, not a measure of central tendency, and does not involve ordering a series of values. **3. High-Yield Clinical Pearls for NEET-PG:** * **Relationship in Normal Distribution:** Mean = Median = Mode. * **Skewness:** * **Positively Skewed:** Mean > Median > Mode (Tail to the right). * **Negatively Skewed:** Mode > Median > Mean (Tail to the left). * **Best Measure:** * For **Nominal** data: Mode. * For **Ordinal** data: Median. * For **Symmetrical (Interval/Ratio)** data: Mean. * For **Skewed** data: Median. * **Property of Median:** It is the only measure used for calculating **Centiles, Quartiles, and Deciles.**

Question 183: Which type of scale is the Likert scale?

A. Ordinal scale (Correct Answer)
B. Nominal scale
C. Variance scale
D. Categorical scale

Explanation: **Explanation:** The **Likert scale** is a psychometric scale commonly used in research to measure attitudes, opinions, or perceptions (e.g., "Strongly Disagree" to "Strongly Agree"). It is classified as an **Ordinal scale** because the data categories follow a logical, hierarchical order or rank, but the mathematical distance between the categories is not uniform or quantifiable. **Why the correct answer is right:** In an **Ordinal scale**, variables are ranked. In a Likert scale, "Strongly Agree" represents a higher level of agreement than "Agree," but we cannot mathematically state that the difference between "Agree" and "Neutral" is exactly the same as the difference between "Neutral" and "Disagree." Since there is a clear rank but no fixed interval, it is ordinal. **Why the other options are wrong:** * **Nominal scale:** These are used for naming variables without any quantitative value or order (e.g., Gender, Blood Group, Religion). Likert scales have an inherent order, so they are not nominal. * **Variance scale:** This is not a standard type of measurement scale in biostatistics. Variance is a measure of dispersion, not a classification of data. * **Categorical scale:** While a Likert scale is a *type* of categorical data, "Categorical" is a broad umbrella term that includes both Nominal and Ordinal scales. In competitive exams like NEET-PG, you must choose the **most specific** answer, which is Ordinal. **High-Yield Clinical Pearls for NEET-PG:** * **NOIR Mnemonic:** Scales of measurement in increasing order of complexity: **N**ominal < **O**rdinal < **I**nterval < **R**atio. * **Central Tendency:** For Ordinal data (like Likert scales), the **Median** is the most appropriate measure of central tendency. * **Visual Analogue Scale (VAS):** Often used for pain; if it is a simple 1-10 ranking, it is Ordinal. * **Ratio Scale:** The most "powerful" scale because it has a **true zero point** (e.g., Height, Weight, BP, Pulse rate).

Question 184: What sampling method is recommended by WHO for immunization coverage evaluation?

A. Simple random sampling
B. Cluster random sampling (Correct Answer)
C. Stratified random sampling
D. Convenience sampling

Explanation: **Explanation:** The **WHO Expanded Programme on Immunization (EPI)** utilizes **Cluster Random Sampling** (specifically the **30 x 7 cluster survey design**) to evaluate immunization coverage. This method is preferred because it is logistically feasible, cost-effective, and time-efficient in large populations where a complete sampling frame (a list of every individual) is unavailable. * **Why it is correct:** In this design, 30 clusters (e.g., villages or wards) are selected randomly. Within each cluster, 7 children of the target age group are surveyed. This provides a statistically valid estimate of coverage within a ±10% margin of error, which is sufficient for public health monitoring. **Analysis of Incorrect Options:** * **Simple Random Sampling:** Requires a complete list of all individuals in the population. In developing regions, such lists are rarely available or updated, making this method impractical for field surveys. * **Stratified Random Sampling:** Involves dividing the population into subgroups (strata) and sampling from each. While highly accurate, it is complex and requires detailed prior knowledge of population characteristics. * **Convenience Sampling:** A non-probability sampling method that is prone to significant bias. It is never recommended for formal WHO coverage evaluations. **High-Yield Clinical Pearls for NEET-PG:** * **30 x 7 Design:** Total sample size = 210 children. * **Sampling Frame:** Only a list of clusters (villages/blocks) is needed, not a list of individuals. * **Probability Proportional to Size (PPS):** Clusters are selected using PPS to ensure larger villages have a higher chance of being included, reducing selection bias. * **Primary Sampling Unit (PSU):** In this method, the **cluster** is the PSU, not the individual child.

Question 185: Herd immunity is not observed in which of the following diseases?

A. Poliomyelitis
B. Measles
C. Diphtheria
D. Tetanus (Correct Answer)

Explanation: ### Explanation **Concept of Herd Immunity** Herd immunity (community immunity) refers to the indirect protection from an infectious disease that happens when a large percentage of a population becomes immune, thereby reducing the overall amount of virus or bacteria able to spread. For herd immunity to occur, the disease **must be transmitted from person to person.** **Why Tetanus is the Correct Answer** Tetanus is caused by *Clostridium tetani* spores found in the soil and environment. The infection is acquired through direct contact with contaminated wounds, not through human-to-human transmission. Since an immune individual cannot "break the chain of transmission" to protect an unvaccinated neighbor, **herd immunity does not exist for Tetanus.** Protection is purely individual and depends entirely on one's own vaccination status. **Analysis of Incorrect Options** * **Poliomyelitis:** Transmitted via the feco-oral route. Mass vaccination (especially with OPV) induces intestinal immunity, reducing the shedding of the virus in the community and protecting the unvaccinated. * **Measles:** Highly contagious via respiratory droplets. It requires a very high herd immunity threshold (approx. 94-95%) to stop outbreaks. * **Diphtheria:** Transmitted via respiratory droplets. Vaccination with the Diphtheria toxoid reduces the carrier state and limits the spread of *Corynebacterium diphtheriae* within a population. **High-Yield Clinical Pearls for NEET-PG** * **Herd Immunity Threshold:** The proportion of immune individuals in a population above which a disease no longer persists. It is calculated as $1 - (1/R_0)$. * **Prerequisite:** Herd immunity only applies to diseases where the **only reservoir is humans.** * **Tetanus Fact:** It is the only vaccine-preventable disease that is **infectious but not contagious.** * **Eradication:** Herd immunity is a key factor in the successful eradication of Smallpox and the near-eradication of Polio.

Question 186: In calculating the Dependency Ratio, what is the numerator expressed as?

A. Population under 10 years and 60 years and above.
B. Population under 15 years and 60 years and above.
C. Population under 10 years and 65 years and above.
D. Population under 15 years and 65 years and above. (Correct Answer)

Explanation: **Explanation:** The **Dependency Ratio** is a demographic indicator used to measure the economic burden on the productive portion of a population. It is defined as the ratio of "dependents" (those typically not in the labor force) to the "working-age" population. **1. Why Option D is Correct:** According to international standards (UN and WHO), the dependency ratio is calculated using the following formula: $$\text{Dependency Ratio} = \frac{\text{Population (0–14 years) + Population (65 years and above)}}{\text{Population (15–64 years)}} \times 100$$ * **Numerator:** Includes children (under 15) and the elderly (65+), who are considered economically inactive. * **Denominator:** Includes the working-age group (15–64 years). **2. Why Other Options are Incorrect:** * **Options A & C:** The cutoff for the pediatric age group in global statistics is consistently **15 years**, not 10. * **Option B:** While some developing countries (including India in certain national surveys) have historically used **60 years** as the threshold for the elderly, the **standard international definition** for the Dependency Ratio specifically uses **65 years**. For competitive exams like NEET-PG, the UN standard (65+) is the preferred answer unless "Old Age Dependency Ratio in India" is specifically specified. **3. High-Yield Clinical Pearls for NEET-PG:** * **Total Dependency Ratio:** Sum of Young Dependency (0-14) and Old-Age Dependency (65+). * **Demographic Dividend:** Occurs when the proportion of the working-age population (15-64) is high relative to dependents, potentially accelerating economic growth. * **India Context:** In the Indian Census, the elderly are often categorized as **60+**, but for the standardized Dependency Ratio formula, **65+** remains the academic gold standard. * **Child Dependency Ratio:** (0-14 years / 15-64 years) × 100.

Question 187: A person's opinion for a test was expressed as very satisfied, satisfied, dissatisfied, or very dissatisfied. What type of measurement scale does this represent?

A. Nominal
B. Ordinal (Correct Answer)
C. Interval
D. Ratio

Explanation: ### Explanation **Why Ordinal is Correct:** The measurement scale described is **Ordinal** because the data is categorized into groups that follow a **natural order or rank**. In this case, "very satisfied" represents a higher level of satisfaction than "satisfied," which is higher than "dissatisfied." While we can rank these opinions, the mathematical distance (interval) between "satisfied" and "very satisfied" is not quantifiable or necessarily equal to the distance between "dissatisfied" and "very dissatisfied." **Analysis of Incorrect Options:** * **Nominal:** This scale is for qualitative data with no inherent order or ranking (e.g., Gender, Blood Group, Religion). Since the options in the question have a clear hierarchy, they are not merely nominal. * **Interval:** This scale has a defined order and equal intervals between values, but **no absolute zero** (e.g., Temperature in Celsius). Opinion scales do not have fixed mathematical intervals. * **Ratio:** This is the highest level of measurement. It has all the properties of an interval scale plus a **true/absolute zero** (e.g., Height, Weight, Blood Pressure). Opinion scores cannot have a "zero" value representing a total absence of the quality. **High-Yield Clinical Pearls for NEET-PG:** * **Mnemonic (NOIR):** **N**ominal (Name only), **O**rdinal (Order/Rank), **I**nterval (In-between distance is equal), **R**atio (Ratio/Absolute zero exists). * **Likert Scales:** Most satisfaction surveys and pain scales (Mild, Moderate, Severe) are classic examples of **Ordinal** data. * **Statistical Test Selection:** For Nominal/Ordinal data, use **Non-parametric tests** (e.g., Chi-square). For Interval/Ratio data, use **Parametric tests** (e.g., T-test, ANOVA). * **Qualitative vs. Quantitative:** Nominal and Ordinal are **Qualitative** (Categorical); Interval and Ratio are **Quantitative** (Numerical).

Question 188: In random sampling, what is the probability of selecting an item from the population?

A. Not known
B. Known (Correct Answer)
C. Undecided
D. Zero

Explanation: ### Explanation **Why the correct answer is right:** In biostatistics, **Random Sampling** (also known as Probability Sampling) is defined by the principle that every unit in the population has a **known, non-zero chance** of being selected into the sample. This probability is typically equal for all members (as in Simple Random Sampling) or proportional to specific criteria (as in Stratified Sampling). Because the probability is "known," researchers can use statistical theory to calculate the sampling error and generalize the findings from the sample back to the entire population with a specific degree of confidence. **Why the incorrect options are wrong:** * **A. Not known:** This is a characteristic of **Non-probability sampling** (e.g., Convenience or Quota sampling). In these methods, the likelihood of selecting any specific individual is unknown, making it impossible to calculate the representativeness of the sample. * **C. Undecided:** This is not a statistical term. In any structured study design, the selection criteria must be predefined. * **D. Zero:** If the probability of selection is zero, the item has no chance of being included. For a sample to be representative of a population, every member must have a probability **greater than zero**. **High-Yield Facts for NEET-PG:** * **Gold Standard:** Simple Random Sampling is the most basic form of probability sampling, often using a "Random Number Table" or computer-generated sequences. * **Sampling Frame:** To perform random sampling, you must have a complete list of all units in the population, called the Sampling Frame. * **Systematic Sampling:** Also a probability sampling method where every $k^{th}$ item is picked (Sampling Interval $k = N/n$). * **Key Distinction:** Only probability (random) sampling allows for the calculation of **Standard Error**, which is essential for determining Confidence Intervals and P-values.

Question 189: What method is used to estimate the percentage of children immunized in a community as per WHO guidelines?

A. Multistage random sampling
B. Cluster random sampling (Correct Answer)
C. Systematic random sampling
D. All of the above

Explanation: **Explanation:** The correct answer is **Cluster Random Sampling**. This method is the gold standard recommended by the WHO for the **Expanded Programme on Immunization (EPI)** to estimate vaccination coverage in a community. **Why Cluster Random Sampling?** In large populations, creating a complete list of every individual (sampling frame) is often impossible. Cluster sampling overcomes this by dividing the population into natural groups or "clusters" (e.g., villages or wards). The WHO specifically uses the **"30 x 7" cluster survey design**, where 30 clusters are randomly selected, and 7 children of the target age group are surveyed within each cluster, totaling a sample size of 210. This method is logistically easier, cost-effective, and highly efficient for field-based community medicine. **Analysis of Incorrect Options:** * **A. Multistage Random Sampling:** While cluster sampling is a type of multistage sampling, the WHO guidelines specifically mandate the cluster technique for EPI surveys. Multistage is a broader term used for national-level surveys like NFHS. * **C. Systematic Random Sampling:** This requires a complete list of the population and selecting every $n^{th}$ individual. It is impractical for immunization surveys in areas where house numbering or population registries are incomplete. **High-Yield Facts for NEET-PG:** * **WHO 30 x 7 Design:** Used to estimate immunization coverage within a ±10% margin of error. * **Primary Sampling Unit (PSU):** In this design, the **village or ward** is the PSU, not the individual child. * **Design Effect:** Cluster sampling usually has a higher sampling error than simple random sampling; this is compensated for by the "Design Effect" (usually taken as 2 for EPI surveys). * **Application:** Besides immunization, cluster sampling is also used for rapid assessment of health needs during disasters.

Question 190: What non-parametric test is used to compare three or more independent groups of sampled data?

A. Chi-square test
B. Fisher's exact test
C. Kruskal-Wallis test (Correct Answer)
D. McNemar test

Explanation: ### Explanation **Correct Answer: C. Kruskal-Wallis test** The **Kruskal-Wallis test** is the non-parametric equivalent of the One-way ANOVA. It is used to compare the medians of **three or more independent groups** when the data is ordinal or not normally distributed. In medical research, this is often applied when comparing clinical scores (like pain scales) across multiple treatment groups where the sample size is small or the variance is unequal. **Analysis of Incorrect Options:** * **A. Chi-square test:** Used to compare **categorical (qualitative) data** between two or more independent groups. It assesses the association between variables rather than comparing means or medians of continuous data. * **B. Fisher's exact test:** A variation of the Chi-square test used for categorical data when the sample size is very small (specifically when any cell value in a 2x2 table is less than 5). * **D. McNemar test:** Used to compare **paired (dependent) categorical data**. It is typically used in "before-and-after" studies involving nominal data (e.g., presence or absence of a symptom after treatment). **High-Yield Clinical Pearls for NEET-PG:** * **Parametric vs. Non-parametric:** If the data is normally distributed, use **ANOVA** for >2 groups; if not, use **Kruskal-Wallis**. * **Paired Data:** For comparing >2 **dependent/related** groups (non-parametric), the **Friedman test** is used. * **The "Rule of Two":** To compare 2 independent groups, use the **Mann-Whitney U test** (non-parametric) or **Unpaired t-test** (parametric).

Practice by Chapter

Collection and Presentation of Data

Practice Questions

Measures of Central Tendency

Practice Questions

Measures of Dispersion

Practice Questions

Normal Distribution

Practice Questions

Sampling Methods

Practice Questions

Sample Size Calculation

Practice Questions

Hypothesis Testing

Practice Questions

Tests of Significance

Practice Questions

Correlation and Regression

Practice Questions

Survival Analysis

Practice Questions

Multivariate Analysis

Practice Questions

Statistical Software in Research

Practice Questions

Want unlimited practice?

Get full access to all questions, explanations, and performance tracking.

Start For Free