Biostatistics — MCQs

Biostatistics Indian Medical PG Practice Questions and MCQs

Question 471: What is the predictive value of a positive test?

A. True positive / (True positive + False positive) * 100
B. True positive / (True positive + False positive) * 100 (Correct Answer)
C. False positive / (True positive + False positive) * 100
D. False positive / (True positive + False positive) * 100

Explanation: **Explanation:** The **Positive Predictive Value (PPV)** is a measure of a diagnostic test's precision. It answers the critical clinical question: *"If the test result is positive, what is the probability that the patient actually has the disease?"* **1. Why Option B is Correct:** The formula for PPV is the number of **True Positives (TP)** divided by the **Total number of people who tested positive** (which includes both True Positives and False Positives). * **Formula:** $PPV = [TP / (TP + FP)] \times 100$ This represents the proportion of "test positives" who are truly diseased. **2. Analysis of Incorrect Options:** * **Options C & D:** These formulas use "False Positives" in the numerator. This would calculate the **False Discovery Rate**, which is the inverse of PPV (1 - PPV). It represents the proportion of positive results that are actually healthy individuals. * **Note on Option A:** While mathematically identical to B in your list, the core concept remains that the numerator must be True Positives. **3. NEET-PG High-Yield Pearls:** * **Prevalence Dependency:** Unlike Sensitivity and Specificity (which are inherent to the test), **Predictive Values depend on the prevalence** of the disease in the population. * **Direct Relationship:** If Prevalence increases, PPV increases. * **Inverse Relationship:** If Prevalence increases, Negative Predictive Value (NPV) decreases. * **Screening Utility:** PPV is the most useful measure for a clinician when interpreting a lab report for an individual patient. * **NPV Formula:** $TN / (TN + FN) \times 100$. It indicates the probability that a patient is healthy given a negative test result.

Question 472: Which of the following equations correctly relates incidence, prevalence, and duration of a disease in a stable situation?

A. Incidence = Prevalence x Duration
B. Prevalence = Incidence x Duration (Correct Answer)
C. Incidence = Prevalence + Duration
D. Prevalence = Incidence + Duration

Explanation: ### Explanation **1. Understanding the Relationship (The "Bathtub" Analogy)** In biostatistics, the relationship between incidence and prevalence is best understood through the **Steady State Model**. * **Incidence (I):** Represents the rate of *new* cases entering the population. * **Duration (D):** Represents how long a person stays in the "diseased state" before recovery or death. * **Prevalence (P):** Represents the total *existing* cases at a given time. In a stable population (where the number of people entering the diseased state equals the number leaving it), **Prevalence = Incidence × Mean Duration (P = I × D)**. This is because the total pool of disease depends on how fast new cases occur and how long they persist. **2. Analysis of Options** * **Option B (Correct):** Correctly reflects that prevalence is a product of the frequency of new cases and their longevity. * **Option A (Incorrect):** This suggests that incidence increases with duration, which is logically flawed. Incidence is determined by risk factors, not how long a disease lasts. * **Options C & D (Incorrect):** These suggest an additive relationship. In epidemiology, these variables are multiplicative; if the duration of a disease doubles (e.g., due to better life-prolonging treatment), the prevalence will also double, even if the incidence remains the same. **3. NEET-PG Clinical Pearls & High-Yield Facts** * **The Rule of Thumb:** * If a treatment **cures** a disease quickly, **Duration ↓** and **Prevalence ↓**. * If a treatment **prevents death** but doesn't cure (e.g., Insulin for Diabetes), **Duration ↑** and **Prevalence ↑**. * **Prevalence** is a measure of **burden** of disease (useful for healthcare planning). * **Incidence** is a measure of **risk** (useful for determining etiology). * **Note:** This formula (P = I × D) is only valid when prevalence is low (less than 10%).

Question 473: What is the denominator used for calculating literacy rate?

A. Population above 7 years (Correct Answer)
B. Population above 14 years
C. Entire population
D. Per 1000 population

Explanation: **Explanation:** In the context of Indian demographics and the Census, the **Literacy Rate** is defined as the percentage of the population who can both read and write with understanding in any language. **1. Why Option A is Correct:** According to the Census of India, a person is considered literate only if they are aged **7 years or above**. Children below the age of 7 are excluded from the denominator because they are developmentally in the early stages of learning, and their inability to read or write is not considered "illiteracy" in a socio-economic sense. Therefore, the formula is: *Literacy Rate = (Number of literate persons aged 7+ / Total population aged 7+) × 100.* **2. Why the Other Options are Incorrect:** * **Option B (Above 14 years):** This is often confused with the "Adult Literacy Rate," which typically measures literacy in the 15+ age group (often used by UNESCO). * **Option C (Entire population):** This would calculate the "Crude Literacy Rate." While used in some historical contexts, it is not the standard "Literacy Rate" used in modern Indian health and census statistics because it includes infants. * **Option D (Per 1000 population):** Literacy is traditionally expressed as a **percentage (%)**, unlike mortality or morbidity rates (like IMR or CBR) which are expressed per 1000. **High-Yield Facts for NEET-PG:** * **Effective Literacy Rate:** This is the same as the Literacy Rate (calculated for 7+ years). * **Kerala** consistently holds the highest literacy rate in India, while **Bihar** has historically recorded the lowest. * **Gender Gap:** The difference between male and female literacy is a key social indicator in Community Medicine; a narrowing gap indicates improving social development. * **Definition of Literate:** A person does not need to have formal education or a minimum pass certificate to be "literate"; they only need the ability to read and write with understanding.

Question 474: The Child Pugh score is a type of what kind of scale?

A. Nominal
B. Ordinal (Correct Answer)
C. Quantitative
D. Qualitative

Explanation: **Explanation:** The **Child-Pugh Score** is used to assess the prognosis of chronic liver disease (cirrhosis). It is an **Ordinal Scale** because it categorizes patients into groups (Class A, B, or C) based on a numerical score derived from five parameters (Bilirubin, Albumin, INR, Ascites, and Encephalopathy). 1. **Why Ordinal?** An ordinal scale represents data that has a **natural order or rank**, but the mathematical distance between the ranks is not necessarily equal. In the Child-Pugh system, Class A (5–6 points) is "better" than Class B (7–9 points), which is "better" than Class C (10–15 points). Since there is a clear progression of severity, it is ordinal. 2. **Why other options are incorrect:** * **Nominal:** This scale is for naming or labeling categories without any quantitative value or order (e.g., Blood groups A, B, O; Gender). Since Child-Pugh implies a "rank" of severity, it is not nominal. * **Quantitative (Interval/Ratio):** These scales involve precise measurements where the difference between numbers is consistent (e.g., Height in cm, Weight in kg). While the score uses numbers, the "gap" between Class A and B isn't a physical measurement. * **Qualitative:** While ordinal data is a type of categorical (qualitative) data, "Ordinal" is the more specific and correct biostatistical term for ranked data. **High-Yield Clinical Pearls for NEET-PG:** * **Parameters of Child-Pugh (Mnemonic: ABCDE):** **A**lbumin, **B**ilirubin, **C**oagulation (INR), **D**istension (Ascites), **E**ncephalopathy. * **APGAR Score** and **Glasgow Coma Scale (GCS)** are also classic examples of **Ordinal Scales** frequently asked in exams. * **Visual Analogue Scale (VAS)** for pain is another high-yield Ordinal scale.

Question 475: While testing a hypolipidemic drug, serum lipid levels were tested both before and after its use. Which statistical test is best suited for the analysis of the results?

A. Paired T test (Correct Answer)
B. Student's T test
C. Chi-square test
D. None of the above

Explanation: ### Explanation **Why Paired T-test is the Correct Answer:** The Paired T-test is used to compare the **means of two related groups** (dependent samples). In this scenario, the serum lipid levels are measured in the **same set of individuals** at two different time points: "before" and "after" the intervention. Since each subject acts as their own control, the data points are paired. This test determines if the mean difference between these two observations is statistically significant. **Analysis of Incorrect Options:** * **Student’s T-test (Unpaired/Independent T-test):** This is used to compare the means of two **independent** groups (e.g., comparing lipid levels between Group A taking the drug and Group B taking a placebo). It is incorrect here because the measurements are taken from the same group. * **Chi-square Test:** This is a non-parametric test used for **categorical (qualitative) data** to compare proportions (e.g., "improved" vs. "not improved"). Since serum lipid levels are **quantitative (numerical)** data, the Chi-square test is inappropriate. **Clinical Pearls & High-Yield Facts for NEET-PG:** 1. **Quantitative Data (Means):** * 2 groups (Related/Before-After) → **Paired T-test** * 2 groups (Independent/Different people) → **Unpaired T-test** * >2 groups (Independent) → **ANOVA** (Analysis of Variance) 2. **Qualitative Data (Proportions):** * Comparing two or more proportions → **Chi-square Test** * Small samples (any cell value <5) → **Fisher’s Exact Test** 3. **Key Concept:** Always identify the **type of data** (Numerical vs. Categorical) and the **relationship** (Dependent vs. Independent) before choosing a statistical test.

Question 476: Which is the best method of central tendency used to represent a quantitative variable?

A. Mean (Correct Answer)
B. Median
C. Mode
D. Box and whisker plot

Explanation: ### Explanation **Why Mean is the Correct Answer:** The **Arithmetic Mean** is considered the "gold standard" and the most commonly used measure of central tendency for quantitative (numerical) data. Its primary advantage is that it **includes every single observation** in the dataset during calculation. In biostatistics, the mean is mathematically stable and serves as the basis for further advanced statistical tests, such as the t-test and ANOVA. For a normally distributed (symmetrical) dataset, the mean provides the most precise estimate of the center. **Why Other Options are Incorrect:** * **B. Median:** This is the middle-most value. While it is the best measure for **skewed data** or data with extreme outliers (e.g., incubation periods, survival rates), it is not the default "best" for all quantitative variables because it ignores the actual numerical magnitude of most observations. * **C. Mode:** This is the most frequently occurring value. It is primarily used for **nominal (qualitative) data** (e.g., most common blood group). it is the least stable measure of central tendency. * **D. Box and Whisker Plot:** This is a **graphical method** to represent the distribution, range, and median of data. It is not a "measure" or "method" of central tendency itself. **High-Yield Clinical Pearls for NEET-PG:** * **Normal Distribution:** Mean = Median = Mode. * **Best measure for Skewed Data:** Median. * **Best measure for Qualitative Data:** Mode. * **Most sensitive to Outliers:** Mean (it shifts towards the tail). * **Relationship in Positive Skew:** Mean > Median > Mode. * **Relationship in Negative Skew:** Mode > Median > Mean.

Question 477: Which type of diagram is best suited for representing trends over time?

A. Scatter diagram
B. Line diagram (Correct Answer)
C. Bar diagram
D. Pie chart

Explanation: **Explanation:** The correct answer is **Line diagram** because it is specifically designed to show the relationship between two continuous variables, most commonly where the x-axis represents **time** (e.g., years, months, or days). By connecting data points with lines, it allows for the immediate visualization of **trends, fluctuations, or patterns** (increasing, decreasing, or stable) over a specific period. In epidemiology, line diagrams are essential for plotting secular trends of diseases or epidemic curves. **Analysis of Incorrect Options:** * **Scatter diagram:** Used to show the **correlation** or association between two quantitative variables (e.g., height and weight). It displays individual data points to identify patterns like positive or negative correlation but does not depict a chronological trend. * **Bar diagram:** Used for **categorical or discrete data** (e.g., number of cases in different hospitals). While a "Chronological Bar Chart" exists, a line diagram is superior for showing the *continuity* of a trend. * **Pie chart:** Used to show the **proportional distribution** of a whole (e.g., the percentage of different causes of maternal mortality). It represents a snapshot in time, not a progression over time. **High-Yield Clinical Pearls for NEET-PG:** * **Histogram:** Best for representing **continuous frequency distributions**. * **Frequency Polygon:** Derived from a histogram by joining the midpoints of the bars; useful for comparing two or more frequency distributions. * **Ogive:** A graph representing **cumulative frequency**. * **Box-and-Whisker Plot:** Best for showing the **median and dispersion** (interquartile range) of data.

Question 478: A diagnostic test was performed. Out of 80 individuals who tested positive, 40 did not have the disease. Out of 9920 individuals who tested negative, 9840 did not have the disease. What is the sensitivity of the test?

A. 13%
B. 33% (Correct Answer)
C. 50%
D. 99%

Explanation: ### Explanation To solve this problem, we must first organize the data into a standard **2x2 contingency table**. | | Disease Present (+) | Disease Absent (-) | Total | | :--- | :---: | :---: | :---: | | **Test Positive (+)** | **40 (TP)** | 40 (FP) | 80 | | **Test Negative (-)** | 80 (FN) | **9840 (TN)** | 9920 | | **Total** | 120 | 9880 | 10000 | **Step-by-Step Calculation:** 1. **True Positives (TP):** Total test positives (80) minus False Positives (40) = **40**. 2. **False Negatives (FN):** Total test negatives (9920) minus True Negatives (9840) = **80**. 3. **Sensitivity Formula:** $\frac{TP}{TP + FN} \times 100$ 4. **Calculation:** $\frac{40}{40 + 80} = \frac{40}{120} = \frac{1}{3} \approx \mathbf{33.3\%}$. #### Why the Correct Answer is Right: Sensitivity (True Positive Rate) measures the ability of a test to correctly identify those with the disease. In this cohort, there are 120 diseased individuals, but the test only caught 40 of them, resulting in 33%. #### Why Other Options are Wrong: * **Option A (13%):** Incorrect calculation; likely a result of misplacing values in the 2x2 table. * **Option C (50%):** This is the **Positive Predictive Value (PPV)**: $\frac{TP}{TP+FP} = \frac{40}{80} = 50\%$. * **Option D (99%):** This is the **Specificity**: $\frac{TN}{TN+FP} = \frac{9840}{9840+40} \approx 99.6\%$. #### High-Yield Clinical Pearls for NEET-PG: * **SNOUT:** **S**ensitivity rules **OUT** disease (when a highly sensitive test is negative). * **SPIN:** **S**pecificity rules **IN** disease (when a highly specific test is positive). * **Prevalence Impact:** Sensitivity and Specificity are **independent** of disease prevalence, whereas PPV and NPV are directly affected by it. * **Screening vs. Diagnosis:** Screening tests require high sensitivity; confirmatory tests require high specificity.

Question 479: The 50th percentile is equivalent to which statistical measure?

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

Explanation: **Explanation:** The **Median** is the correct answer because, by definition, it is the middle-most value of a data set when arranged in ascending or descending order. In a frequency distribution, the median divides the population into two equal halves: 50% of the observations lie below it and 50% lie above it. Therefore, the **50th percentile** is mathematically identical to the median. **Analysis of Options:** * **A. Mean:** This is the arithmetic average of all observations. In a perfectly symmetrical (Normal) distribution, the mean equals the median, but in skewed distributions, they differ. It is not defined by percentiles. * **C. Mode:** This is the most frequently occurring value in a data set. It represents the "peak" of the distribution curve rather than a positional cutoff like a percentile. * **D. Range:** This is a measure of dispersion (Maximum value minus Minimum value), not a measure of central tendency or position. **NEET-PG High-Yield Pearls:** * **Quartiles:** The 25th percentile is the **1st Quartile (Q1)**, the 50th percentile is the **2nd Quartile (Q2/Median)**, and the 75th percentile is the **3rd Quartile (Q3)**. * **Skewness:** In a **Positively Skewed** distribution (tail to the right), the order is: Mean > Median > Mode. In a **Negatively Skewed** distribution (tail to the left), the order is: Mode > Median > Mean. * **Best Measure:** The Median is the preferred measure of central tendency for **skewed data** or data with extreme outliers (e.g., incubation periods, survival time, or household income).

Question 480: What is the first quartile of the following data set: 1, 3, 4, 2?

A. 1
B. 3
C. 1.5 (Correct Answer)
D. 4

Explanation: ### Explanation **1. Understanding the Concept (Why 1.5 is correct)** In biostatistics, quartiles divide a sorted data set into four equal parts. To find the First Quartile ($Q_1$), follow these steps: * **Step 1: Arrange data in ascending order:** 1, 2, 3, 4. * **Step 2: Determine the position of $Q_1$:** For a small data set ($n=4$), the formula for the position is $\frac{n+1}{4}$. * Position = $\frac{4+1}{4} = 1.25$. * **Step 3: Calculate the value:** Since the position is 1.25, $Q_1$ lies between the 1st and 2nd values. * $Q_1 = \text{1st value} + 0.25 \times (\text{2nd value} - \text{1st value})$ * $Q_1 = 1 + 0.25 \times (2 - 1) = \mathbf{1.25}$ (In many simplified NEET-PG contexts, the average of the lower half is used). * **Alternative Method (Tukey’s):** Find the median of the lower half. The median of {1, 2, 3, 4} is 2.5. The lower half is {1, 2}. The mean of 1 and 2 is **1.5**. **2. Analysis of Incorrect Options** * **Option A (1):** This is the minimum value (0th percentile), not the first quartile. * **Option B (3):** This represents the Third Quartile ($Q_3$) or the 75th percentile for this data set. * **Option D (4):** This is the maximum value (100th percentile). **3. Clinical Pearls & High-Yield Facts** * **Interquartile Range (IQR):** $Q_3 - Q_1$. It represents the middle 50% of the data and is the preferred measure of dispersion for skewed data. * **Box-and-Whisker Plot:** The "box" represents the IQR, with the central line marking the Median ($Q_2$). * **Relationship:** $Q_1$ = 25th percentile; $Q_2$ = 50th percentile (Median); $Q_3$ = 75th percentile. * **NEET-PG Tip:** If the data set is small and even, always remember to sort the numbers first; skipping this step is the most common cause of error.

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