Biostatistics Practice Questions

Q: Systolic blood pressure of a group of 200 people follows a normal distribution with a mean BP of 120 mm Hg and a standard deviation of 10 mm Hg. Which of the following is true?

68% of people have BP between 110-130 mm Hg. ### Explanation This question tests your understanding of the **Normal Distribution (Gaussian Curve)** and the **Empirical Rule**, which is a high-yield topic in Biostatistics. #### Why Option A is Correct In a normal distribution, data is symmetrically distributed around the mean. The Empirical Rule states: * **Mean ± 1 Standard Deviation (SD)** covers approximately **68.2%** of the values. * **Mean ± 2 SD** covers approximately **95.4%** of the values. * **Mean ± 3 SD** covers approximately **99.7%** of the values. Given: Mean = 120 mm Hg and SD = 10 mm Hg. * Calculation for 1 SD: $120 \pm 10 = 110$ to $130$ mm Hg. * Therefore, 68% of the population falls within the 110–130 mm Hg range. #### Why Other Options are Incorrect * **Option B:** 95% of the people would fall within Mean ± 2 SD ($120 \pm 20$), which is **100–140 mm Hg**, not 110–130. * **Option C:** As calculated above, the range of 100–140 mm Hg corresponds to 95% of the population, not 68%. * **Option D:** 99% (specifically 99.7%) of the people would fall within Mean ± 3 SD ($120 \pm 30$), which is **90–150 mm Hg**. #### High-Yield Clinical Pearls for NEET-PG 1. **Symmetry:** In a perfectly normal distribution, **Mean = Median = Mode**. 2. **Z-Score:** This represents the number of standard deviations a value is from the mean. A BP of 130 in this example has a Z-score of +1. 3. **Standard Error (SE):** Do not confuse SD with SE. $SE = SD / \sqrt{n}$. SE is used to calculate Confidence Intervals, while SD describes the dispersion of individual data points. 4. **Skewness:** If the mean is greater than the median, it is a **Positively Skewed** distribution (tail to the right). If the mean is less than the median, it is **Negatively Skewed** (tail to the left).

Q: Which of the following is the best method of randomization?

Random number table. ### 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, making them comparable at baseline. **Why Option D is Correct:** The **Random Number Table** (e.g., Tippett’s table or Fisher and Yates table) is traditionally considered the "gold standard" and the most reliable manual method for randomization in clinical research. It ensures that every participant has an equal, non-zero, and independent chance of being assigned to any group. In the context of standard medical examinations like NEET-PG, it is prioritized as the most robust method for ensuring true randomness. **Analysis of Incorrect Options:** * **Option A (Computer-generated):** While widely used in modern large-scale trials for convenience, traditional biostatistics textbooks still emphasize the Random Number Table as the fundamental "best" method for academic testing purposes. * **Option B (Odd/even day admission):** This is **Quasi-randomization** (Systematic sampling). It is predictable; researchers know which patient will go into which group tomorrow, leading to potential selection bias. * **Option C (Lottery method):** While a form of random allocation, it is primitive, difficult to document/audit, and prone to manipulation or physical bias (e.g., improper mixing of chits). **High-Yield Clinical Pearls for NEET-PG:** * **Purpose of Randomization:** To eliminate selection bias and ensure **comparability** of groups. * **Blinding:** Eliminates **ascertainment (observer) bias**. * **Concealment of Allocation:** Prevents the researcher from knowing the sequence before assignment; it is the step that *protects* the randomization process. * **Sequence:** Randomization $\rightarrow$ Allocation Concealment $\rightarrow$ Blinding.

Q: If 10 women use an IUCD for 10 years, and assuming the failure rate of IUCD is 2 per 100 women-years (HWY), what is the number of expected accidental pregnancies?

2. ### Explanation **1. Understanding the Concept (Pearl Index)** The failure rate of contraceptives is measured using the **Pearl Index**, expressed as the number of accidental pregnancies per 100 women-years (HWY) of exposure. To calculate the expected pregnancies, we use the formula: $$\text{Total Pregnancies} = \frac{\text{Failure Rate} \times \text{Total Women-Years}}{100}$$ **Step-by-step Calculation:** * **Total Women-Years:** 10 women $\times$ 10 years = **100 women-years**. * **Failure Rate:** Given as 2 per 100 women-years. * **Calculation:** $\frac{2 \times 100}{100} = \mathbf{2}$ **pregnancies.** **2. Analysis of Incorrect Options** * **Option A (1):** This would be the result if the total exposure was only 50 women-years (e.g., 5 women for 10 years). * **Option C (5):** This would imply a failure rate of 5 per 100 HWY, which is higher than the standard failure rate for modern IUCDs like Cu-T 380A. * **Option D (20):** This error usually occurs if one forgets to divide by the "100" in the HWY denominator, simply multiplying 10 women $\times$ 2 (rate). **3. Clinical Pearls for NEET-PG** * **Pearl Index Definition:** It is the most common method to compare the efficacy of contraceptive methods. * **Denominator:** Always remember the denominator is **100 women-years** (1,200 months of exposure). * **Typical vs. Perfect Use:** The Pearl Index for **Cu-T 380A** is approximately 0.8 per 100 HWY (very effective), while for Oral Contraceptive Pills, "typical use" failure is around 9 per 100 HWY. * **Lowest Failure Rate:** Currently, the **Subdermal Implant (Nexplanon)** has the lowest Pearl Index (~0.05).

Q: Pearson's Skewness Coefficient is given by?

SD/(Mean-Median). **Explanation** Skewness refers to the degree of asymmetry in a probability distribution. In a perfectly symmetrical (Normal) distribution, the Mean, Median, and Mode are identical, and skewness is zero. **Why the Correct Answer is Right:** The **Pearson’s Skewness Coefficient** (specifically the Second Coefficient) is mathematically defined as: $$Skewness = \frac{3 \times (Mean - Median)}{Standard Deviation (SD)}$$ While the standard formula includes a multiplier of 3, in competitive exams like NEET-PG, the relationship is often simplified to the ratio of the difference between Mean and Median to the Standard Deviation. Therefore, **Option C [SD / (Mean - Median)]** represents the inverse relationship used to calculate the magnitude of skewness relative to the spread of data. **Analysis of Incorrect Options:** * **Option A (Mean-Mode/SD):** This is the formula for Pearson’s First Coefficient of Skewness. While valid, it is less frequently used in clinical research because the Mode is often an unstable measure in small samples. * **Option B (Mode-Mean/SD):** This is mathematically incorrect as it would reverse the sign of the skewness (e.g., making a positively skewed distribution appear negative). * **Option D (SD/Median-Mean):** This is the inverse of the correct relationship and lacks the standard mathematical convention for calculating asymmetry. **High-Yield Clinical Pearls for NEET-PG:** 1. **Positive Skew (Right-sided):** Tail points to the right. **Mean > Median > Mode.** (Common in income data or incubation periods). 2. **Negative Skew (Left-sided):** Tail points to the left. **Mean < Median < Mode.** 3. **Normal Distribution:** Mean = Median = Mode. Skewness = 0. 4. **Median** is the preferred measure of central tendency for skewed data as it is least affected by extreme outliers.

Q: What is the scale of measurement used for classifying a person as 'hypertensive', 'normotensive', or 'hypotensive'?

Ordinal scale. ### Explanation **1. Why Ordinal Scale is Correct:** The classification of blood pressure into categories like **hypotensive, normotensive, and hypertensive** involves data that is qualitative but possesses a **natural rank or order**. In this case, there is a clear progression of severity or magnitude (Hypo < Normo < Hyper). While the exact numerical difference between these categories is not uniform, the relative position is fixed. Therefore, it falls under the **Ordinal Scale** (Order = Ordinal). **2. Why Other Options are Incorrect:** * **Nominal Scale:** This is used for simple labeling without any inherent order (e.g., Gender, Blood Group, or Eye Color). Since "Hypertensive" is objectively "higher" than "Normotensive," it is more than just a label. * **Interval Scale:** This scale has a definite order and equal intervals between units, but **no absolute zero** (e.g., Temperature in Celsius). Clinical categories do not have equal mathematical intervals. * **Ratio Scale:** This is the highest level of measurement and possesses an **absolute zero** (e.g., Height, Weight, or the actual BP reading in mmHg). If the question asked about the *actual systolic value* (e.g., 120 mmHg), the answer would be Ratio. **3. Clinical Pearls & High-Yield Facts for NEET-PG:** * **Mnemonic (NOIR):** **N**ominal (Name), **O**rdinal (Order), **I**nterval (In-between), **R**atio (Real zero). * **Key Distinction:** If a variable is descriptive (Mild, Moderate, Severe), it is **Ordinal**. If it is a raw numerical value (Pulse rate, Glucose level), it is **Ratio**. * **Likert Scales:** (e.g., "Strongly Agree" to "Strongly Disagree") are always **Ordinal**. * **Statistical Test Tip:** For Nominal/Ordinal data, use **Non-parametric tests** (e.g., Chi-square). For Interval/Ratio data, use **Parametric tests** (e.g., T-test, ANOVA).

Q: Calculate the positive predictive value of an ELISA test for HIV, given a sensitivity of 99%, specificity of 99%, and a prevalence of HIV in the population of 5 per 1000?

33. ### Explanation **1. Understanding the Calculation (Why C is Correct)** Positive Predictive Value (PPV) is the probability that a person who tests positive actually has the disease. It is heavily influenced by the **prevalence** of the disease in the population. To calculate PPV, we can use a hypothetical population of 10,000: * **Prevalence:** 5 per 1,000 = 50 cases in 10,000. * **True Positives (TP):** Sensitivity (99%) of 50 = **49.5** * **False Positives (FP):** 10,000 - 50 = 9,950 healthy people. Specificity is 99%, so the False Positive Rate is 1%. 1% of 9,950 = **99.5** * **PPV Formula:** $TP / (TP + FP) \times 100$ * $49.5 / (49.5 + 99.5) \times 100 = 49.5 / 149 \times 100 \approx \mathbf{33.2\%}$ **2. Analysis of Incorrect Options** * **Option A (10):** This value is too low. While low prevalence reduces PPV, a test with 99% sensitivity/specificity still maintains a moderate PPV at 0.5% prevalence. * **Option B (70):** This would be the PPV if the prevalence were significantly higher (approx. 2-3%). * **Option D (All):** PPV is a specific mathematical derivative based on fixed parameters; it cannot be multiple values simultaneously. **3. High-Yield Clinical Pearls for NEET-PG** * **Prevalence Dependency:** PPV is **directly proportional** to prevalence. As prevalence increases, PPV increases. Conversely, Negative Predictive Value (NPV) is **inversely proportional** to prevalence. * **Screening vs. Diagnostic:** In low-prevalence populations (like general screening), even a highly specific test will yield many false positives. * **Sensitivity/Specificity:** These are inherent properties of the test and do **not** change with disease prevalence, unlike PPV and NPV. * **Formula Shortcut (Bayes' Theorem):** $PPV = \frac{\text{Sensitivity} \times \text{Prevalence}}{(\text{Sensitivity} \times \text{Prevalence}) + (1 - \text{Specificity}) \times (1 - \text{Prevalence})}$

Question 1

A study was conducted to assess the role of radiation in leukemia. Among 100 patients with leukemia, 70 reported a history of radiation exposure. Among 100 controls, 30 reported a history of radiation exposure. What type of bias is most likely present in this study?

Accepted Answer

Recall bias

Answer

Reporting bias

Answer

Interviewer bias

Answer

Hawthorne bias

Question 2

Systolic blood pressure of a group of 200 people follows a normal distribution with a mean BP of 120 mm Hg and a standard deviation of 10 mm Hg. Which of the following is true?

Accepted Answer

68% of people have BP between 110-130 mm Hg

Answer

95% of people have BP between 110-130 mm Hg

Answer

68% of people have BP between 100-140 mm Hg

Answer

99% of people have BP between 100-140 mm Hg

Question 3

Which of the following is the best method of randomization?

Accepted Answer

Random number table

Answer

Computer-generated randomization

Answer

Odd/even day hospital admission

Answer

Lottery method

Question 4

If 10 women use an IUCD for 10 years, and assuming the failure rate of IUCD is 2 per 100 women-years (HWY), what is the number of expected accidental pregnancies?

Accepted Answer

2

Answer

1

Answer

5

Answer

20

Question 5

In a community of 3000 people, 80% are Hindus, 10% Muslims, 5% Sikh, 4% Christians, and 1% Jains. To select a sample of 300 people to analyze food habits, what would be the ideal sampling method?

Accepted Answer

Stratified random sampling

Answer

Simple random sampling

Answer

Systematic random sampling

Answer

Inverse sampling

Question 6

All of the following are continuous variables except?

Accepted Answer

Religion

Answer

Age

Answer

BMI

Answer

Blood pressure

Question 7

Pearson's Skewness Coefficient is given by?

Accepted Answer

SD/(Mean-Median)

Answer

Mean-Mode/SD

Answer

Mode-Mean/SD

Answer

SD/(Median-Mean)

Question 8

What is the scale of measurement used for classifying a person as 'hypertensive', 'normotensive', or 'hypotensive'?

Accepted Answer

Ordinal scale

Answer

Interval scale

Answer

Nominal scale

Answer

Ratio scale

Question 9

Calculate the positive predictive value of an ELISA test for HIV, given a sensitivity of 99%, specificity of 99%, and a prevalence of HIV in the population of 5 per 1000?

Accepted Answer

33

Answer

10

Answer

70

Answer

All

Question 10

Which of the following is true regarding statistical significance testing?

Accepted Answer

The probability associated with a Type 1 error is denoted by alpha (α).

Answer

Type 1 error is rejecting the null hypothesis when it is true.

Answer

Type 2 error is accepting the null hypothesis when it is false.

Answer

The significance level (alpha) is typically set to 5%, but can be varied.

Biostatistics — MCQs

Biostatistics — MCQs

On this page

Practice by Chapter

Want unlimited practice?