Biostatistics Practice Questions

Q: Which of the following is not a measure of dispersion?

Mean. ***Mean*** - The **mean** is a measure of **central tendency**, representing the average value of a dataset. - It describes where the center of the data lies, not how spread out the data points are. *Range* - The **range** is a measure of **dispersion** that indicates the difference between the **maximum** and **minimum** values in a dataset. - It quantifies the overall spread of the data from its lowest to highest points. *Variance* - **Variance** is a measure of **dispersion** that quantifies the **average squared deviation** of each data point from the mean. - It provides insight into how much the individual data points in a distribution deviate from the central tendency. *Standard error* - The **standard error** measures the **precision and sampling variability** of a sample statistic (e.g., sample mean) as an estimate of the population parameter. - While it relates to variability, it specifically quantifies how much a sample statistic varies across different samples, rather than measuring the dispersion of individual observations within a dataset. - In the context of this question, it is considered a measure related to dispersion, though technically it measures sampling variability.

Q: Test quoted as highly sensitive means?

High false positive and low false negative. ***High false positive and low false negative*** - A **highly sensitive test** means it is good at correctly identifying individuals who *have* the disease, leading to a **low rate of false negatives**. - To achieve this high sensitivity, the test might have a lower specificity, meaning it incorrectly identifies more healthy individuals as having the disease, resulting in a **high rate of false positives**. *High false positive and high false negative* - This indicates a test with **poor diagnostic utility**, as it frequently misidentifies both sick and healthy individuals. - It would not efficiently screen or rule out a disease due to its high error rates in both directions. *Low false positive and high false negative* - This describes a test with **high specificity but low sensitivity**. It is good at correctly identifying individuals *without* the disease (low false positives). - However, it misses many true cases, indicating a high number of **false negatives**. *Low false positive and low false negative* - This represents an **ideal test** that is both highly sensitive and highly specific, meaning it is excellent at correctly identifying both sick and healthy individuals. - Such a test would have minimal errors in both false positives and false negatives, but this is rarely found in clinical practice.

Q: An old man with hypertension and BP 210/110 mm Hg is classified as having severe hypertension. Which scale is used for this classification?

Ordinal. ***Ordinal*** - The classification of **hypertension severity** (e.g., mild, moderate, severe) represents an **ordered ranking** where the difference between categories isn't necessarily equal or quantifiable [1], [2]. - This scale allows for **comparison of severity**, indicating that severe is worse than moderate, but without precise numerical differences between stages [2]. *Nominal* - This scale is used for **categorization without any order** or numerical value, such as gender or blood type. - It would classify hypertension as simply "hypertensive" or "non-hypertensive" without indicating severity. *Interval* - An interval scale has **ordered categories** with **equal differences** between points. - While it has order, it lacks a true zero point, common examples include Celsius or Fahrenheit temperature scales. *Ratio* - A ratio scale has **ordered categories**, **equal intervals**, and a **true zero point**, allowing for meaningful ratios. - Examples include height, weight, or blood pressure measurements themselves, but not their classification into severity stages [3].

Q: A study that examines individuals who have already contracted a disease to identify risk factors is called:

Case control. ***Case control*** - A **case-control study** specifically examines individuals who have already contracted the disease (**cases**) and compares them to those without the disease (**controls**). - The **cases** component directly addresses studying people who have already developed the disease to identify **risk factors** and **exposures** that led to the condition. - This is a **retrospective study design** that works backward from disease to exposure. *Control cohort* - A control cohort refers to a group of individuals who **do not have the disease or exposure** of interest and serve as a comparison group. - This is a component of studies, not a study type itself. - This option focuses on **healthy or unexposed individuals**, not those who have already contracted the disease. *Cohort* - A **cohort study** follows a group of individuals over time to observe who develops disease (**prospective**) or examines past exposures and outcomes (**retrospective**). - While it may include diseased individuals, its primary focus is on **disease incidence** and **temporal relationships**, starting from exposure and moving forward to disease outcome. *Cross-sectional* - A **cross-sectional study** examines disease and exposure status **simultaneously** at a single point in time. - It provides a **snapshot** of prevalence but does not specifically focus on examining those who have already contracted disease to identify risk factors. - It cannot establish **temporal relationships** between exposure and disease.

Q: A cohort study follows 500 healthcare workers for 4 years to assess the incidence of occupational tuberculosis. During the study period, 20 workers developed tuberculosis. What is the incidence rate of tuberculosis per 1000 person-years in this cohort?

10 per 1000 person-years. ***10 per 1000 person-years*** - The **incidence rate** is calculated by dividing the number of new cases by the total person-time at risk in the population. - Total person-years = 500 workers × 4 years = **2000 person-years** - Incidence rate = 20 cases / 2000 person-years = **0.01 per person-year** - To express this per 1000 person-years: 0.01 × 1000 = **10 per 1000 person-years** - This is the correct calculation following the standard epidemiological formula for incidence rate. *5 per 1000 person-years* - This value would be obtained if the total person-years at risk were 4000 (e.g., 500 workers followed for 8 years instead of 4 years). - It underestimates the true incidence rate by using an incorrect denominator. *7.5 per 1000 person-years* - This result would occur if the person-years at risk were approximately 2667 person-years (20/2667 × 1000 = 7.5). - This reflects an incorrect calculation of the **denominator** (person-years at risk). *12.5 per 1000 person-years* - This value incorrectly assumes a denominator of 1600 person-years (20/1600 × 1000 = 12.5). - This could result from miscalculating the total follow-up time or the number of participants, leading to an overestimation of the incidence rate.

Q: In a UK study, it was found that there were more deaths from Asthma than the sales of Anti-asthma drugs would suggest. This is an example of

Ecological study. ***Ecological study*** - An **ecological study** analyzes data at the population or group level rather than at the individual level. - In this scenario, the comparison of asthma deaths (population-level data) with anti-asthma drug sales (another population-level aggregate) for an entire country (UK) is characteristic of an ecological study. - This represents an **ecological correlation** where aggregate data is used to identify patterns at the population level. *Experimental study* - An **experimental study** involves direct intervention by the researcher to control variables and assign subjects to different groups (e.g., treatment vs. control) to assess cause-and-effect. - This study design does not involve any intervention or randomization; it's an observational analysis of existing population data. *Case-control study* - A **case-control study** compares individuals with a disease (cases) to individuals without the disease (controls) to identify risk factors at the individual level. - The given scenario is not comparing individuals but rather aggregate data from a population. *Cohort study* - A **cohort study** follows a group of individuals (a cohort) over time to observe the incidence of disease or outcomes in relation to specific exposures. - The scenario describes a cross-sectional comparison of population-level data at a specific point or period, not a longitudinal follow-up of individuals.

Q: Mean bone density amongst 2 groups of 50 people each is compared, which would be the best test:

Student t-test. ***Student t-test*** - The **Student's t-test** is the appropriate statistical test for comparing the **means of two independent groups** when the data is continuous and normally distributed. - Bone density is a **continuous variable**, and the scenario involves comparing the mean bone density between two distinct groups. *Fisher exact test* - The **Fisher exact test** is used for analyzing **categorical data** in a 2×2 contingency table, especially when sample sizes are small. - It is not suitable for comparing continuous variables like bone density. *McNemar test* - **McNemar's test** is used to analyze paired nominal data, typically when comparing two related proportions from the same subjects before and after an intervention. - This scenario involves **independent groups**, not paired data. *Chi-square test* - The **chi-square test** is primarily used to compare **categorical variables** to see if there is a significant association between them. - It's not appropriate for comparing the means of continuous data like bone density.

Q: A study was conducted to investigate the relationship between COPD and smoking. Data was collected from government hospital records on COPD cases and cigarette sales records from finance and taxation departments. What is the study design?

Ecological study. ***Ecological study*** - This study uses **aggregate data** (COPD cases from hospital records, cigarette sales from taxation departments) at the population level, not individual data. - It investigates the relationship between exposure (smoking) and outcome (COPD) across different populations or groups. *Cross-sectional study* - A **cross-sectional study** collects data on exposure and outcome at a **single point in time** from individuals, which is not the case here as aggregate data is used. - It describes the prevalence of a disease and exposure in a population, but does not examine the relationship using population-level aggregates. *Operational study* - An **operational study** focuses on evaluating the effectiveness and efficiency of health services or programs in real-world settings. - It typically involves assessing how well interventions are implemented and their impact, rather than investigating the relationship between disease and exposure using aggregate data. *Case-control study* - A **case-control study** compares individuals with a disease (cases) to individuals without the disease (controls) and looks back retrospectively to identify exposures. - This design relies on individual-level data and is not suitable when only population-level aggregate data is available.

Q: For a positively skewed curve, which measure of central tendency is largest?

Mean. ***Mean*** - In a **positively skewed distribution**, the tail of the distribution extends towards higher values, pulling the **mean** in that direction, making it the largest among the three measures of central tendency. - The presence of **outliers** with large values in the tail disproportionately increases the mean. *Mode* - The **mode** represents the most frequently occurring value in the data set. - In a positively skewed distribution, the mode will be located at the **peak of the distribution**, which is typically the smallest value among the three measures of central tendency. *All are equal* - This statement is characteristic of a **perfectly symmetrical distribution** (e.g., a normal distribution), where the **mean, median, and mode** are all equal. - A positively skewed curve is asymmetrical, meaning these measures will not be equal. *Median* - The **median** is the middle value in an ordered data set, dividing the data into two equal halves. - In a positively skewed distribution, the median will be shifted towards the right of the mode but will still be to the left of the mean, meaning it is **smaller than the mean**.

Question 1

Which of the following is not a measure of dispersion?

Accepted Answer

Mean

Answer

Range

Answer

Variance

Answer

Standard error

Question 2

Test quoted as highly sensitive means?

Accepted Answer

High false positive and low false negative

Answer

Low false positive and high false negative

Answer

High false positive and high false negative

Answer

Low false positive and low false negative

Question 3

An old man with hypertension and BP 210/110 mm Hg is classified as having severe hypertension. Which scale is used for this classification?

Accepted Answer

Ordinal

Answer

Nominal

Answer

Interval

Answer

Ratio

Question 4

A study that examines individuals who have already contracted a disease to identify risk factors is called:

Accepted Answer

Case control

Answer

Control cohort

Answer

Cohort

Answer

Cross-sectional

Question 5

A cohort study follows 500 healthcare workers for 4 years to assess the incidence of occupational tuberculosis. During the study period, 20 workers developed tuberculosis. What is the incidence rate of tuberculosis per 1000 person-years in this cohort?

Accepted Answer

10 per 1000 person-years

Answer

5 per 1000 person-years

Answer

12.5 per 1000 person-years

Answer

7.5 per 1000 person-years

Question 6

In a UK study, it was found that there were more deaths from Asthma than the sales of Anti-asthma drugs would suggest. This is an example of

Accepted Answer

Ecological study

Answer

Experimental study

Answer

Case-control study

Answer

Cohort study

Question 7

Mean bone density amongst 2 groups of 50 people each is compared, which would be the best test:

Accepted Answer

Student t-test

Answer

McNemar test

Answer

Chi-square test

Answer

Fisher exact test

Question 8

You have diagnosed a patient clinically as having SLE and ordered 6 tests out of which 4 tests have come positive and 2 are negative. Which of the following values are required to determine the probability of SLE at this point?

Accepted Answer

Prior probability of SLE, sensitivity and specificity of each test

Answer

Relative risk of SLE in the patient

Answer

Incidence and prevalence of SLE

Answer

Incidence of SLE and the predictive value of each test

Question 9

A study was conducted to investigate the relationship between COPD and smoking. Data was collected from government hospital records on COPD cases and cigarette sales records from finance and taxation departments. What is the study design?

Accepted Answer

Ecological study

Answer

Cross-sectional study

Answer

Operational study

Answer

Case-control study

Question 10

For a positively skewed curve, which measure of central tendency is largest?

Accepted Answer

Mean

Answer

Mode

Answer

All are equal

Answer

Median

Biostatistics — MCQs

Biostatistics — MCQs

On this page

Practice by Chapter

Want unlimited practice?