Biostatistics Practice Questions

Q: Which of the following statements is true about direct age standardization?

A standard population is used. ***A standard population is used*** - In **direct age standardization**, age-specific death rates from the study population are applied to a **standard population's** age distribution to calculate an expected number of events. - This method helps to compare mortality or morbidity across different populations by removing the confounding effect of differing age structures. *Number of people in each age group is not known* - This statement is incorrect; to apply the study population's age-specific rates to the standard population, the **number of people in each age group of the standard population must be known**. - Without this demographic information, direct age standardization cannot be performed effectively. *Age specific death rates are not known* - This statement is incorrect because **age-specific death rates** for the *study population* are a prerequisite for direct age standardization. - These rates are multiplied by the corresponding age groups of a **standard population** to calculate standardized rates. *Standardized mortality ratio is used* - The **Standardized Mortality Ratio (SMR)** is a measure used in *indirect* age standardization, not direct age standardization. - SMR compares the number of observed deaths in a study population to the number expected if the study population had the same age-specific death rates as a **standard population**.

Q: In the estimation of statistical probability, Z score is applicable to:

Normal distribution. ***Normal distribution*** - The **Z-score** (or standard score) is a measure of how many **standard deviations** an element is from the mean. It is specifically used when working with **normally distributed data**. - It allows for the comparison of scores from different normal distributions by standardizing them to a common scale. *Poisson distribution* - This distribution deals with the **number of events** occurring in a fixed interval of time or space, given a known average rate, and is not typically used with Z-scores directly. - It is a **discrete probability distribution**, unlike the continuous nature required for direct Z-score application. *Skewed distribution* - A skewed distribution has an **asymmetrical shape**, where points cluster more on one side of the mean. - Z-scores can be calculated for skewed distributions, but their interpretation as probabilities (e.g., using a standard normal table) is **not valid** because the data do not follow a bell-shaped curve. *Binomial distribution* - This distribution describes the **number of successes** in a fixed number of independent Bernoulli trials. - It is a **discrete probability distribution** and generally, Z-scores are not directly applied to it, although for a large number of trials, it can be approximated by a normal distribution.

Q: The two important values necessary for describing the variation in a series of observations are:

Mean and standard deviation. ***Mean and standard deviation*** - The **mean** provides a measure of the **central tendency**, representing the average value in the dataset. - The **standard deviation** quantifies the **dispersion** or spread of the data points around the mean, indicating the variability. *Median and standard deviation* - The **median** is a measure of **central tendency**, specifically the middle value, but it doesn't directly pair with standard deviation for describing overall variation in the most common statistical contexts. - While standard deviation describes spread, using the median for central tendency often leads to other measures of spread like **interquartile range (IQR)** for a more consistent representation of non-normally distributed data. *Mean and range* - The **mean** indicates the central point of the data, but the **range** (difference between maximum and minimum values) is a less robust measure of variation. - **Range** is highly susceptible to outliers and does not provide information about the distribution of data points within the entire set. *Median and range* - The **median** describes the **center** of the data, particularly useful for skewed distributions or data with outliers. - The **range** is a simple measure of spread, but it's very sensitive to extreme values and does not give a comprehensive picture of data variability.

Q: Which one of the following tests should be applied to compare mean haemoglobin level of two groups of antenatal mothers?

Unpaired t-test. ***Unpaired t-Test*** - The **unpaired t-test** is used to compare the means of **two independent groups** on a continuous variable, such as hemoglobin levels. - Antenatal mothers in two distinct groups are independent, and **hemoglobin level is a continuous variable**, making this the appropriate choice. *Analysis of variance* - **ANOVA** (Analysis of Variance) is used to compare the means of **three or more independent groups**. - Since there are only **two groups** being compared, ANOVA is not the most efficient or appropriate test. *Chi-square test* - The **Chi-square test** is used to analyze the association between **two categorical variables**. - Hemoglobin level is a **continuous variable**, not categorical, so this test is not suitable for comparing means. *Paired t-test* - The **paired t-test** is used to compare the means of **two related groups** or the same group measured at two different times (e.g., before and after an intervention). - The two groups of antenatal mothers are **independent**, not paired or related.

Q: Which one of the following epidemiologic methods can be used to identify risk factors and estimate the degree of risk?

Case control and Cohort studies. **Case control and Cohort studies** - **Case-control studies** effectively identify **risk factors** by comparing exposure histories between individuals with a disease (cases) and those without (controls). - **Cohort studies** directly estimate the **degree of risk** (e.g., relative risk, incidence rates) by following exposed and unexposed groups over time to observe disease development. *Cohort study and Randomized control trial* - While **cohort studies** identify risk factors, **randomized controlled trials (RCTs)** primarily evaluate the **efficacy of interventions** by randomly assigning exposure. - RCTs are ethically difficult to use for identifying harmful risk factors directly, as intentionally exposing participants to potential harm is generally not permissible. *Cohort study and Ecological studies* - **Ecological studies** examine disease rates and exposures at a **population level**, making them useful for generating hypotheses but not for establishing individual-level risk factors or degrees of risk due to the **ecological fallacy**. - They cannot directly link individual exposure to individual outcome. *Case control and Cross-sectional studies* - **Cross-sectional studies** assess prevalence and provide a snapshot of health status and exposure at a single point in time, but they cannot establish **temporality** or the degree of association between exposure and outcome. - They are useful for describing prevalence but not for inferring causality or precise risk.

Q: What is the relative risk of developing pulmonary embolism in users of oral contraceptives as per the information given below?

4.80. ***4.80*** - **Relative Risk (RR)** = Risk in exposed / Risk in unexposed - From the table provided: - **OC users (exposed):** 120 developed PE out of 200 women → Risk = 120/200 = 0.60 - **Non-OC users (unexposed):** 10 developed PE out of 80 women → Risk = 10/80 = 0.125 - **RR = 0.60 / 0.125 = 4.8** - This indicates OC users have **4.8 times higher risk** of developing pulmonary embolism compared to non-users - This significant association aligns with known **thrombogenic effects** of estrogen-containing oral contraceptives - **Clinical relevance:** Highlights importance of screening for VTE risk factors before prescribing OCs *0.24* - This value would result from incorrect calculation or misinterpretation of table values - Does not represent any valid epidemiological measure from the given data *0.48* - This is simply the decimal misplacement of 4.8 divided by 10 - Results from calculation error, not proper relative risk computation *2.40* - This is exactly half of the correct answer (4.8/2) - May result from using wrong numerator or denominator values - Does not represent the correct relative risk calculation

Q: In a case-control study, 300 women aged 20-45 years suffering from breast cancer were compared with age-matched 300 women without breast cancer. It was observed that 120 women among cases and 60 women among controls were obese. The odds ratio of developing breast cancer among obese women is:

8/3. **8/3** - The **odds ratio** is calculated using the formula (a×d) / (b×c) from a 2×2 contingency table. - Setting up the table: Cases (breast cancer) vs Controls (no breast cancer) by exposure (obesity status) - a = obese cases = 120 - b = obese controls = 60 - c = non-obese cases = 300 - 120 = 180 - d = non-obese controls = 300 - 60 = 240 - **Odds ratio = (120 × 240) / (60 × 180) = 28,800 / 10,800 = 8/3** - This indicates that **obese women have 2.67 times the odds** of developing breast cancer compared to non-obese women. *11/5* - This answer suggests an **incorrect calculation** of the odds ratio, likely due to misassignment of values in the 2×2 table or an arithmetic error. - The result (2.2) does not match the correct cross-product ratio from the given data. *11/3* - This value is not derived from the correct **odds ratio** calculation using the given data. - Errors in setting up the 2×2 table or confusing which cells represent **exposed cases**, **exposed controls**, **unexposed cases**, and **unexposed controls** lead to such incorrect results. *9/5* - This option would result from an **incorrect placement** of values when calculating the cross-product ratio. - Possibly from reversing the numerator and denominator components or miscalculating the unexposed groups.

Q: Predictive accuracy of a screening test depends on the following EXCEPT:

Disease incidence. ***Disease incidence*** - **Disease incidence** refers to the rate at which new cases of a disease occur in a population over a specified period. While related to disease prevalence, it is not a direct factor in calculating the predictive accuracy of a screening test. - Predictive accuracy, specifically **positive predictive value (PPV)** and **negative predictive value (NPV)**, relies on the test's inherent properties (sensitivity and specificity) and the **prevalence** of the disease, not its incidence. *Specificity of screening test* - **Specificity** is crucial for predictive accuracy as it determines the probability that a test correctly identifies those *without* the disease. - A test with high specificity will have fewer **false positives**, which directly impacts the positive predictive value. *Disease prevalence* - **Disease prevalence** profoundly influences the predictive accuracy of a screening test. The **positive predictive value** increases with higher disease prevalence. - In populations with low disease prevalence, even highly sensitive and specific tests can yield a large number of **false positives**. *Sensitivity of screening test* - **Sensitivity** is a key determinant of predictive accuracy, as it measures the proportion of *true positives* correctly identified by the test. - A test with high sensitivity helps ensure that most individuals *with* the disease are detected, which affects both **positive and negative predictive values**.

Q: What is the specificity of sputum microscopy in detection of Pulmonary Tuberculosis (PTB) as per the information given below?

90 %. ***90 %*** - Specificity is calculated as the number of **true negatives** divided by the sum of true negatives and **false positives**. - From the table: True Negatives = 180 (PTB Absent, Sputum Negative) and False Positives = 20 (PTB Absent, Sputum Positive). - Specificity = (180 / (180 + 20)) × 100 = (180 / 200) × 100 = **90%**. - This represents the ability of the test to correctly identify those **without the disease**. *36 %* - This value does not correspond to any standard diagnostic test metric such as sensitivity, specificity, positive predictive value, or negative predictive value based on the provided data. - It might be a miscalculation or a different ratio not typically used in this context. *94 %* - This value does not match any standard calculation from the given 2×2 table. - It may represent a misinterpretation of the data or an incorrect calculation. *10 %* - This value represents the **false positive rate** (1 - specificity). - Calculated as: False Positives / Total without disease = 20 / 200 = 10%. - It is the complement of specificity, not specificity itself.

Q: A research study comparing two groups shows a statistically significant difference (p=0.04) but the confidence interval is very wide (0.5 to 4.2). How should this result be interpreted?

The result is statistically significant but imprecise. ***The result is statistically significant but imprecise*** - A **p-value of 0.04** indicates **statistical significance** at the conventional ɑ=0.05 level, meaning the observed difference is unlikely due to chance. - A **wide confidence interval (0.5 to 4.2)** suggests that while the true effect is likely positive, its magnitude is **highly uncertain** or **imprecise**, possibly due to a small sample size. *Additional statistical tests are needed* - While more analysis is often valuable, the current statistical outputs (p-value and CI) are sufficient to interpret the **significance** and **precision** of the original finding. - Simply adding more tests without addressing the underlying **imprecision** (e.g., through larger studies) would not fundamentally change the interpretation of the current result. *The result shows no meaningful difference between groups* - The **p-value of 0.04** suggests there *is* a statistically significant difference, so stating there's "no meaningful difference" is incorrect based on the statistical evidence. - However, the **precision of the effect** with the large confidence interval means the *clinical meaningfulness* is still very uncertain, as the effect could be anywhere from small to quite large. *The result is both statistically and clinically significant* - The result is **statistically significant** (p=0.04). - However, the **wide confidence interval (0.5 to 4.2)** means the **clinical significance** is unknown, as the true effect size could be small (0.5) or large (4.2); it is not definitively "clinically significant."

Question 1

Which of the following statements is true about direct age standardization?

Accepted Answer

A standard population is used

Answer

Number of people in each age group is not known

Answer

Age specific death rates are not known

Answer

Standardized mortality ratio is used

Question 2

In the estimation of statistical probability, Z score is applicable to:

Accepted Answer

Normal distribution

Answer

Poisson distribution

Answer

Skewed distribution

Answer

Binomial distribution

Question 3

The two important values necessary for describing the variation in a series of observations are:

Accepted Answer

Mean and standard deviation

Answer

Median and standard deviation

Answer

Mean and range

Answer

Median and range

Question 4

Which one of the following tests should be applied to compare mean haemoglobin level of two groups of antenatal mothers?

Accepted Answer

Unpaired t-test

Answer

Analysis of variance

Answer

Chi-square test

Answer

Paired t-test

Question 5

Which one of the following epidemiologic methods can be used to identify risk factors and estimate the degree of risk?

Accepted Answer

Case control and Cohort studies

Answer

Cohort study and Ecological studies

Answer

Case control and Cross-sectional studies

Answer

Cohort study and Randomized controlled trial

Question 6

What is the relative risk of developing pulmonary embolism in users of oral contraceptives as per the information given below?

Accepted Answer

4.80

Answer

0.24

Answer

0.48

Answer

2.40

Question 7

In a case-control study, 300 women aged 20-45 years suffering from breast cancer were compared with age-matched 300 women without breast cancer. It was observed that 120 women among cases and 60 women among controls were obese. The odds ratio of developing breast cancer among obese women is:

Accepted Answer

8/3

Answer

11/5

Answer

11/3

Answer

9/5

Question 8

Predictive accuracy of a screening test depends on the following EXCEPT:

Accepted Answer

Disease incidence

Answer

Specificity of screening test

Answer

Disease prevalence

Answer

Sensitivity of screening test

Question 9

What is the specificity of sputum microscopy in detection of Pulmonary Tuberculosis (PTB) as per the information given below?

Accepted Answer

90 %

Answer

94 %

Answer

10 %

Answer

36 %

Question 10

A research study comparing two groups shows a statistically significant difference (p=0.04) but the confidence interval is very wide (0.5 to 4.2). How should this result be interpreted?

Accepted Answer

The result is statistically significant but imprecise

Answer

Additional statistical tests are needed

Answer

The result shows no meaningful difference between groups

Answer

The result is both statistically and clinically significant

Biostatistics — MCQs

Biostatistics — MCQs

On this page

Practice by Chapter

Want unlimited practice?