Biostatistics Practice Questions

Q: When the mean, median, and mode of a distribution are all zero, what type of distribution is it?

Standard normal distribution. ### Explanation **1. Why the Correct Answer is Right:** In a **Normal Distribution** (Gaussian distribution), the curve is perfectly symmetrical and bell-shaped. In such a distribution, the **Mean, Median, and Mode are all equal** (Mean = Median = Mode). A **Standard Normal Distribution** is a specific type of normal distribution where the data is standardized using Z-scores. It is defined by two specific parameters: * **Mean ($\mu$) = 0** * **Standard Deviation ($\sigma$) = 1** Since it is a symmetrical distribution, the Median and Mode also coincide with the Mean at the center. Therefore, when all three measures of central tendency are zero, it must be a Standard Normal Distribution. **2. Why the Incorrect Options are Wrong:** * **B & C (Skewed Distributions):** In skewed distributions, the mean, median, and mode are pulled apart. In **Positively skewed** data, Mean > Median > Mode. In **Negatively skewed** data, Mode > Median > Mean. They cannot all be equal to zero. * **D (J-shaped Distribution):** This is an asymmetrical distribution where the frequency is at its maximum at one end of the scale. It does not follow the central symmetry required for the mean, median, and mode to coincide at zero. **3. Clinical Pearls & High-Yield Facts for NEET-PG:** * **Z-score:** Indicates how many standard deviations a value is from the mean. In a standard normal distribution, the Z-score of the mean is 0. * **Area under the curve:** In a normal distribution, **68%** of values fall within ±1 SD, **95%** within ±2 SD (specifically 1.96 SD), and **99.7%** within ±3 SD. * **Symmetry Rule:** If you know a distribution is perfectly symmetrical and unimodal, the Mean, Median, and Mode will always be identical.

Q: Which of the following variables is measured on an ordinal scale?

Severity of anemia. ### Explanation In biostatistics, data is classified into four levels of measurement: Nominal, Ordinal, Interval, and Ratio. **Why "Severity of Anemia" is correct:** The **Ordinal scale** is used for data that can be categorized and placed in a **logical rank or order**, but the mathematical distance between the ranks is not defined. Severity of anemia is typically classified as *Mild, Moderate, or Severe*. While we know "Severe" is worse than "Mild," we cannot mathematically quantify exactly how much worse it is using just these labels. Other common ordinal examples include cancer staging (Stage I-IV) or Likert scales (Satisfied to Dissatisfied). **Analysis of Incorrect Options:** * **A. Type of Anemia:** This is a **Nominal scale**. It categorizes data into groups based on names or labels (e.g., Microcytic, Macrocytic, Normocytic) without any inherent quantitative ranking or order. * **C. Hemoglobin level & D. Serum ferritin level:** These are **Ratio scales** (a type of continuous/numerical data). They have a true zero point and consistent intervals between values. For example, a hemoglobin of 14 g/dL is exactly double 7 g/dL. **High-Yield Clinical Pearls for NEET-PG:** * **NOIR Mnemonic:** **N**ominal (Name only), **O**rdinal (Order/Rank), **I**nterval (Fixed distance, no true zero), **R**atio (True zero). * **Qualitative Data:** Includes Nominal and Ordinal scales. * **Quantitative Data:** Includes Discrete (whole numbers, e.g., number of beds) and Continuous (e.g., height, weight, biochemical values). * **Key Distinction:** If you can rank the categories but cannot subtract them, it is **Ordinal**. If you can measure the exact difference between values, it is **Numerical/Ratio**.

Q: Which type of diagram best demonstrates a secular trend?

Line diagram. ### Explanation **1. Why Line Diagram is Correct:** A **secular trend** refers to the long-term changes (increases or decreases) in the occurrence of a disease or health event over a prolonged period (usually years or decades). A **Line Diagram** is the most suitable tool for this because it plots data points chronologically and connects them, effectively showing the **direction and rate of change** over time. It allows for the visualization of trends, fluctuations, and projections, making it the gold standard for time-series data in epidemiology. **2. Why Other Options are Incorrect:** * **Bar Diagram:** These are used for **discrete (qualitative)** data to compare different categories (e.g., number of cases in different cities). They do not show continuous trends over time as effectively as lines. * **Histogram:** This is used for **continuous quantitative** data to show frequency distributions (e.g., age distribution of a population). It represents a snapshot in time rather than a long-term trend. * **Pie Chart:** This is used to show the **proportional distribution** of a whole (e.g., the percentage of different causes of maternal mortality). It cannot depict changes over time. **3. High-Yield Clinical Pearls for NEET-PG:** * **Time Trends:** * *Secular:* Long-term (e.g., the decline of Polio over decades). * *Periodic:* Seasonal (e.g., Dengue in monsoons) or Cyclic (e.g., Measles epidemics every 2-3 years). * **Frequency Polygon:** Created by joining the midpoints of a histogram; also used for frequency distributions. * **Scatter Diagram:** Used to show the **correlation** between two continuous variables. * **Ogive:** A graph representing cumulative frequency.

Q: All of the following are tests for the degree of closeness of a measured or calculated quantity to its actual or true value, except:

Range chart. In biostatistics and quality control, it is crucial to distinguish between **Accuracy** and **Precision**. **1. Why "Range Chart" is the correct answer:** The question asks for tests that measure the closeness to the "true value," which is the definition of **Accuracy**. A **Range Chart (R-chart)** measures the difference between the highest and lowest values in a sample. It is a measure of **dispersion or variability**, which relates to **Precision** (the consistency of results), not accuracy. It does not indicate how close the results are to the actual target value. **2. Explanation of incorrect options:** * **Mean Chart ($\bar{X}$ chart):** This tracks the average of samples over time. Since the mean is compared against the target/true value, it is a primary tool for monitoring **Accuracy**. * **Levey-Jennings (LJ) Chart:** Widely used in clinical laboratories, this chart plots control data against established mean and standard deviation limits. It is used to detect both systematic errors (loss of accuracy) and random errors. * **Shewhart Control Chart:** This is the umbrella term for quality control charts (including Mean and Range charts). In medical statistics, they are used to ensure a process remains within "statistical control" relative to its true intended value. **Clinical Pearls for NEET-PG:** * **Accuracy:** Closeness to the "True Value." (Measured by Mean, LJ charts). * **Precision:** Closeness of repeated measurements to "Each Other." (Measured by Range, Standard Deviation, Coefficient of Variation). * **Systematic Error:** Affects Accuracy (Shift in Mean). * **Random Error:** Affects Precision (Increased Range/SD). * **Westgard Rules:** These are the specific criteria used to interpret LJ charts to decide if an analytical run is in control.

Q: Which of the following is true regarding cohort studies?

Associated with antecedent causation. **Explanation:** In epidemiology, a **Cohort Study** is a longitudinal, observational study where a group of individuals (the cohort) is defined based on the presence or absence of exposure to a risk factor and followed forward in time to observe the development of an outcome. **Why the correct answer is right:** * **Associated with antecedent causation:** This is the hallmark of cohort studies. Because the study begins with exposed and non-exposed individuals who are initially free of the disease, the **exposure (cause) clearly precedes the outcome (effect)**. This temporal sequence is essential for establishing a causal relationship, fulfilling one of Bradford Hill’s primary criteria for causation. **Analysis of incorrect options:** * **A & B (Disease to risk factor / Effect to cause):** These describe **Case-Control studies**, which are retrospective. In case-control studies, you start with the diseased individuals (cases) and look backward to identify risk factors. Cohort studies move in the opposite direction: **Risk factor to disease** (Cause to effect). * **C (Not associated with attributable risk):** This is incorrect because cohort studies are the primary method used to calculate **Attributable Risk (AR)** and **Relative Risk (RR)**. Since incidence can be directly measured in a cohort study, we can determine how much of the disease is specifically due to the exposure. **High-Yield Pearls for NEET-PG:** * **Incidence:** Cohort studies are the only observational study design that can directly calculate the **Incidence** of a disease. * **Prospective vs. Retrospective:** While most cohorts are prospective, "Historical Cohorts" exist where data is gathered from past records, but the direction of inquiry remains Exposure → Outcome. * **Best for:** Rare exposures (not rare diseases). * **Key Disadvantage:** High cost, long duration, and risk of "Loss to follow-up" (Attrition bias).

Q: For the given distribution of weights of a group of students, which measure of central tendency is most appropriate?

Mean. ***Mean*** - For a **normal/symmetric distribution** like student weights, the mean provides the most **accurate representation** of central tendency as it uses all data points. - In a **bell-shaped distribution**, mean, median, and mode are approximately equal, making mean the **preferred choice** due to its mathematical properties. *Median* - While median is **robust to outliers**, it's not the most appropriate for **symmetric distributions** where extreme values are naturally distributed. - Median is preferred for **skewed distributions** or when data contains significant outliers that could distort the mean. *Mode* - Mode identifies the **most frequently occurring value** but may not represent the central tendency well in continuous data like weights. - Most useful for **categorical data** or discrete variables, less meaningful for **continuous measurements** like body weight. *All of the above* - Though all measures can be calculated, the **mean is specifically most appropriate** for normally distributed continuous data. - Different measures serve different purposes: mean for **normal distributions**, median for **skewed data**, and mode for **categorical variables**.

Q: A study provides the following test results for a disease: Present (40 +ve, 10 -ve), Absent (225 +ve, 225 -ve). What is the sensitivity of this study?

80. ### Explanation **1. Why the correct answer is right:** Sensitivity is the ability of a test to correctly identify those with the disease (True Positives). To calculate sensitivity, we use the formula: **Sensitivity = [True Positives (TP) / (True Positives + False Negatives (FN))] × 100** From the data provided: * **Disease Present:** 40 tested positive (TP), 10 tested negative (FN). Total diseased = 50. * **Disease Absent:** 225 tested positive (FP), 225 tested negative (TN). Total healthy = 450. Applying the formula: Sensitivity = [40 / (40 + 10)] × 100 Sensitivity = [40 / 50] × 100 = **80%**. **2. Why the incorrect options are wrong:** * **Option A (40):** This represents the absolute number of True Positives, not the percentage (sensitivity). * **Option B (20):** This is the False Negative Rate (10/50 × 100 = 20%). Sensitivity and False Negative Rate are complementary (Sensitivity + FNR = 100%). * **Option D (50):** This represents the Specificity of the test [TN / (TN + FP)], calculated as [225 / (225 + 225)] × 100 = 50%. **3. Clinical Pearls & High-Yield Facts for NEET-PG:** * **Sensitivity (True Positive Rate):** Crucial for **screening tests** (e.g., ELISA for HIV) because it minimizes False Negatives. A highly sensitive test, when negative, helps **Rule Out** the disease (**SNOUT**). * **Specificity (True Negative Rate):** Crucial for **confirmatory tests** (e.g., Western Blot) because it minimizes False Positives. A highly specific test, when positive, helps **Rule In** the disease (**SPIN**). * **Predictive Values:** Unlike sensitivity/specificity, Positive and Negative Predictive Values are heavily dependent on the **prevalence** of the disease in the population.

Question 1

When the mean, median, and mode of a distribution are all zero, what type of distribution is it?

Accepted Answer

Standard normal distribution

Answer

Negatively skewed distribution

Answer

Positively skewed distribution

Answer

J-shaped distribution

Question 2

Which of the following variables is measured on an ordinal scale?

Accepted Answer

Severity of anemia

Answer

Type of anemia

Answer

Hemoglobin level

Answer

Serum ferritin level

Question 3

Regarding crude birth rate, all are true except?

Accepted Answer

Better measure of fertility than general fertility rate

Answer

Unaffected by age distribution

Answer

Indicator of fertility

Answer

Excludes stillbirths

Question 4

Which type of diagram best demonstrates a secular trend?

Accepted Answer

Line diagram

Answer

Bar diagram

Answer

Histogram

Answer

Pie chart

Question 5

Total cholesterol level is represented by the equation: Total cholesterol level = a + b (calorie intake) + c (physical activity) + d (body mass index). This equation is an example of which type of regression?

Accepted Answer

Multiple linear regression

Answer

Simple linear regression

Answer

Simple curvilinear regression

Answer

Multiple logistic regression

Question 6

All of the following are tests for the degree of closeness of a measured or calculated quantity to its actual or true value, except:

Accepted Answer

Range chart

Answer

Mean chart

Answer

Levey Jennings (LJ) chart

Answer

Shewhart control chart

Question 7

Which of the following is true regarding cohort studies?

Accepted Answer

Associated with antecedent causation

Answer

Disease to risk factor study

Answer

Effect to cause study

Answer

Not associated with attributable risk

Question 8

In what interval is the sample registration system conducted?

Accepted Answer

6 months

Answer

1 year

Answer

2 years

Answer

5 years

Question 9

For the given distribution of weights of a group of students, which measure of central tendency is most appropriate?

Accepted Answer

Mean

Answer

Median

Answer

Mode

Answer

All of the above

Question 10

A study provides the following test results for a disease: Present (40 +ve, 10 -ve), Absent (225 +ve, 225 -ve). What is the sensitivity of this study?

Accepted Answer

80

Answer

40

Answer

20

Answer

50

Biostatistics — MCQs

Biostatistics — MCQs

On this page

Practice by Chapter

Want unlimited practice?