Biostatistics Practice Questions

Q: Quintiles divide a set of variables into how many divisions?

5. **Explanation:** In biostatistics, **Quantiles** are cut-points used to divide a distribution of data into equal-sized subgroups. The term **Quintile** is derived from the Latin word *quintus* (meaning five). **1. Why Option B is Correct:** A quintile divides a population or dataset into **5 equal parts**, each representing 20% of the total (1/5th). To create these 5 divisions, 4 cut-points are required. In public health, quintiles are most commonly used to categorize the **Wealth Index** (from poorest to richest) to study socio-economic disparities in health outcomes. **2. Analysis of Incorrect Options:** * **Option A (3):** This refers to **Terciles**, which divide data into 3 equal parts (33.3% each). * **Option C (10):** This refers to **Deciles**, which divide data into 10 equal parts (10% each). * **Option D (15):** This is not a standard statistical quantile used in medical research. **High-Yield Clinical Pearls for NEET-PG:** * **Median:** Divides data into **2** equal parts (50th percentile). * **Quartiles:** Divide data into **4** equal parts (25% each). Note: The Interquartile Range (IQR) is $Q3 - Q1$. * **Percentiles:** Divide data into **100** equal parts (1% each). * **Application:** In Community Medicine, the **NFHS (National Family Health Survey)** uses wealth quintiles to report data on maternal and child health indicators. * **Relationship:** The 2nd Quartile, 5th Decile, and 50th Percentile are all mathematically equal to the **Median**.

Q: What is the Gross reproduction rate for a region with a total fertility rate of 6 and a male:female ratio of 1?

3. ### Explanation **Gross Reproduction Rate (GRR)** is a key demographic indicator that measures the average number of daughters a woman would bear during her reproductive life (15–49 years) if she were to pass through those years conforming to age-specific fertility rates. **Calculation:** The Total Fertility Rate (TFR) represents the total number of children (both male and female) born to a woman. To find the GRR, we must isolate the number of female births. * **Formula:** $GRR = TFR \times \frac{\text{Female Births}}{\text{Total Births}}$ * In this question, the male-to-female ratio is 1:1. This means 50% (or 0.5) of all births are female. * **Calculation:** $6 \times 0.5 = 3$. --- ### Why the other options are incorrect: * **Option A (2):** This would be the GRR if the female proportion was only 1/3rd of total births (Ratio 2:1). * **Option C (5):** This value does not correlate with a 1:1 sex ratio and a TFR of 6. * **Option D (6):** This is the **Total Fertility Rate (TFR)**. GRR only counts female offspring; therefore, it is always lower than the TFR (unless only females are born). --- ### High-Yield Pearls for NEET-PG: * **Net Reproduction Rate (NRR):** Unlike GRR, NRR accounts for **maternal mortality**. It is the number of daughters a newborn girl will bear, considering the risk she might die before completing her reproductive span. * **NRR = 1:** This is the demographic goal for **Replacement Level Fertility**. When NRR = 1, the TFR is approximately **2.1**. * **Relationship:** $TFR > GRR > NRR$. * If NRR is 1, the population stabilizes in the long run (Zero Population Growth).

Q: Which of the following statistical tests can be used to study ordinal data from two independent samples from a population that is not normally distributed?

The Wilcoxon rank-sum test. **Explanation:** The core of this question lies in identifying the correct **non-parametric test** for comparing two independent groups. **Why Option B is Correct:** The **Wilcoxon rank-sum test** (also known as the **Mann-Whitney U test**) is the non-parametric equivalent of the independent Student’s t-test. It is specifically used when: 1. The data is **ordinal** (ranked) or continuous but **not normally distributed**. 2. There are **two independent samples** (e.g., comparing pain scores between Group A and Group B). Since the question specifies non-normal distribution and ordinal data, this is the most appropriate choice. **Why Other Options are Incorrect:** * **A. Student’s t-test:** This is a **parametric test**. It requires the data to be continuous (interval/ratio scale) and follow a **normal distribution**. * **C. Chi-square test:** This test is used for **categorical (nominal) data** to compare proportions or test the association between two variables (e.g., Smoker vs. Non-smoker). * **D. One-way ANOVA:** This is a parametric test used to compare the means of **three or more** independent groups. Its non-parametric counterpart is the Kruskal-Wallis test. **High-Yield Clinical Pearls for NEET-PG:** * **Parametric vs. Non-Parametric:** If the data is "Normal," use Parametric. If "Skewed" or "Ordinal," use Non-Parametric. * **Wilcoxon Signed-Rank Test:** Do not confuse this with the Rank-Sum test. The *Signed-Rank* test is for **paired** data (e.g., before and after treatment in the same patient). * **Memory Aid:** **M**ann-Whitney **U** test = **U**npaired data; **W**ilcoxon **S**igned-rank = **S**ame person (Paired).

Q: Which of the following is NOT included in the Physical Quality of Life Index (PQLI)?

Maternal Mortality Rate (MMR). ### Explanation The **Physical Quality of Life Index (PQLI)** is a composite index developed by Morris David Morris to measure the quality of life or social welfare in a country. It focuses on the results of development rather than economic growth (GNP). **Why Maternal Mortality Rate (MMR) is the Correct Answer:** PQLI is calculated based on exactly three indicators. **Maternal Mortality Rate (MMR) is NOT one of them.** MMR is a vital health statistic, but it is not a component of this specific index. **Analysis of Other Options:** The PQLI consists of three specific indicators, each scaled from 0 to 100: * **Literacy (Option A):** Specifically, the adult literacy rate (percentage of the population aged 15+ who can read and write). * **Infant Mortality Rate (Option C):** Used as a sensitive indicator of the overall health environment and social well-being. * **Life Expectancy at Age 1 (Option D):** Note that it is life expectancy at **age 1**, not at birth. This is because infant mortality is already accounted for as a separate component. **High-Yield Clinical Pearls for NEET-PG:** * **PQLI Range:** The index ranges from 0 (worst) to 100 (best). * **PQLI vs. HDI:** Do not confuse PQLI with the **Human Development Index (HDI)**. HDI includes Life Expectancy at **Birth**, Literacy/Education, and **Income (GNI per capita)**. * **The "Income" Factor:** The most common "distractor" in PQLI questions is "Income" or "GNP." Remember: **PQLI does NOT include any economic/income measure.** * **Calculation:** PQLI is the arithmetic mean of the three components: $(IMR + Life\ Expectancy\ at\ age\ 1 + Literacy) / 3$.

Q: Which measure of central tendency is determined by arranging variables in ascending or descending order?

Median. ### Explanation **Correct Answer: C. Median** The **Median** is defined as the middle-most value of a data set when the observations are arranged in a specific order (either ascending or descending). It divides the distribution into two equal halves, such that 50% of the values lie above it and 50% lie below it. * **Calculation:** If the number of observations ($n$) is odd, the median is the $(\frac{n+1}{2})^{th}$ value. If $n$ is even, it is the average of the two middle values. * **Medical Significance:** The median is the preferred measure of central tendency for **skewed distributions** (e.g., incubation periods, survival time in cancer) because it is not influenced by extreme outliers. **Why other options are incorrect:** * **Mean (Arithmetic Average):** Calculated by summing all observations and dividing by the total count. It does not require ordering but is highly sensitive to extreme values (outliers). * **Mode:** The value that occurs most frequently in a data set. It is determined by frequency, not by the positional order of all variables. * **Range:** This is a measure of **dispersion**, not central tendency. It represents the difference between the maximum and minimum values in a data set. **High-Yield Clinical Pearls for NEET-PG:** * **Relationship in Normal Distribution:** Mean = Median = Mode. * **Positional Average:** The Median is strictly a positional average. * **Qualitative Data:** Mode is the best measure for nominal/qualitative data (e.g., most common blood group). * **Skewness:** * In **Positively Skewed** data (tail to the right): Mean > Median > Mode. * In **Negatively Skewed** data (tail to the left): Mode > Median > Mean.

Q: Which of the following is true regarding random error?

Error in sampling. ### Explanation **Correct Answer: C. Error in sampling** **Understanding Random Error** In biostatistics, **Random Error** (also known as sampling error) occurs due to chance variations that happen when a sample is taken from a population. Even with a perfectly designed study, a sample may not perfectly represent the population simply due to "the luck of the draw." * **Key Characteristic:** It is unpredictable and non-systematic. * **Mitigation:** Random error can be reduced by **increasing the sample size** (which narrows the confidence interval and increases precision). **Analysis of Incorrect Options:** * **Option A (Systematic differences):** This describes **Selection Bias**. Bias is a systematic error that results in an incorrect estimate of the association between exposure and outcome. * **Option B (Questions about past history):** This refers to **Recall Bias**, a type of information/measurement bias common in case-control studies where cases tend to remember past events more clearly than controls. * **Option D (Different rates of admission):** This is a specific type of selection bias known as **Berkson’s Bias** (Admission Rate Bias), occurring when hospital-based samples do not represent the general population. **High-Yield Pearls for NEET-PG:** 1. **Random Error vs. Bias:** Random error affects **Precision** (reliability); Systematic error (Bias) affects **Validity** (accuracy). 2. **P-value:** The p-value is the probability that the observed result occurred due to random error (chance) alone. 3. **Sample Size:** Increasing sample size reduces random error but has **no effect** on systematic bias. 4. **Types of Bias:** Always remember that Bias is an error in design/conduction, whereas Random Error is an error in sampling.

Q: What does prevalence represent?

Proportion. ### Explanation **Prevalence** is defined as the total number of all individuals who have a particular disease or attribute at a specific point in time (or during a specific period) divided by the total population at risk. **Why Proportion is the Correct Answer:** In epidemiology, a **proportion** is a type of ratio where the numerator is always included in the denominator (A / A+B). Prevalence follows this rule: the numerator (existing cases) is a subset of the denominator (the total population). It is expressed as a percentage or a decimal (e.g., 0.05 or 5%) and does not have a unit of "time" inherent in its denominator. **Analysis of Incorrect Options:** * **Rate:** A rate measures the speed at which an event occurs (e.g., Incidence). It must have a time component in the denominator (e.g., cases per 1,000 person-years). Prevalence is a "snapshot," not a measure of speed. * **Ratio:** While all proportions are ratios, a "Ratio" in biostatistics typically refers to the relationship between two independent quantities where the numerator is *not* part of the denominator (e.g., Maternal Mortality Ratio, Sex Ratio). * **Mean:** This is a measure of central tendency (average) and does not describe the frequency of a disease in a population. **High-Yield Clinical Pearls for NEET-PG:** * **The Bathtub Analogy:** Prevalence is the water in the tub; **Incidence** is the faucet (new cases), and **Recovery/Death** is the drain. * **Formula:** $Prevalence = Incidence \times Mean\ Duration\ of\ Disease\ (P = I \times D)$. * **Usage:** Prevalence is best for estimating the **burden of chronic diseases** and planning health services. Incidence is better for studying **etiology/causation** of acute diseases. * **Point vs. Period:** Point prevalence is a snapshot at one moment; Period prevalence includes existing cases plus new cases over a duration (e.g., one year).

Q: All are true about the Chi-Square test except?

The lowest expected frequency should be less than 5.. ### Explanation The **Chi-Square ($\chi^2$) test** is a fundamental statistical tool used in medical research to analyze categorical data. **1. Why Option D is the correct answer (The Exception):** For a Chi-Square test to be valid, a key assumption is that the **expected frequency in any cell should not be less than 5**. If the expected frequency is less than 5, the test becomes inaccurate because the distribution no longer approximates the Chi-Square distribution. In such cases, **Fisher’s Exact Test** is preferred (for $2 \times 2$ tables) or **Yates’ Correction** is applied. **2. Analysis of Incorrect Options:** * **Option A:** Chi-Square is indeed a **non-parametric test** because it does not assume a normal distribution of the underlying population and deals with frequencies rather than mean/standard deviation. * **Option B:** It is the primary test used to assess the **association between qualitative (categorical) variables** (e.g., comparing the incidence of a disease between smokers and non-smokers). * **Option C:** Like most statistical tests, the validity of the Chi-Square test relies on the assumption that the **sample is randomly selected** and observations are independent. **3. NEET-PG High-Yield Pearls:** * **Degrees of Freedom (df):** Calculated as $(r-1) \times (c-1)$, where $r$ = rows and $c$ = columns. * **Null Hypothesis ($H_0$):** Assumes there is no association between the variables. * **Fisher’s Exact Test:** Use this instead of Chi-Square when the sample size is very small or expected cell frequency is $<5$. * **McNemar’s Test:** A variation of Chi-Square used for **paired data** (e.g., before-and-after studies).

Question 1

Quintiles divide a set of variables into how many divisions?

Accepted Answer

5

Answer

3

Answer

10

Answer

15

Question 2

What is the Gross reproduction rate for a region with a total fertility rate of 6 and a male:female ratio of 1?

Accepted Answer

3

Answer

2

Answer

5

Answer

6

Question 3

Which of the following statistical tests can be used to study ordinal data from two independent samples from a population that is not normally distributed?

Accepted Answer

The Wilcoxon rank-sum test

Answer

The Student's t-test

Answer

The Chi-square test

Answer

The one-way analysis of variance

Question 4

Which of the following is NOT included in the Physical Quality of Life Index (PQLI)?

Accepted Answer

Maternal Mortality Rate (MMR)

Answer

Literacy

Answer

Infant Mortality Rate (IMR)

Answer

Life expectancy at 1 year

Question 5

What is the meaning of 'odds'?

Accepted Answer

The ratio of the frequency of occurrence of a characteristic to its non-occurrence

Answer

The chance that some event will occur

Answer

The ratio of the frequency of non-occurrence of a characteristic to its occurrence

Answer

The inverse of probability

Question 6

Which measure of central tendency is determined by arranging variables in ascending or descending order?

Accepted Answer

Median

Answer

Mean

Answer

Mode

Answer

Range

Question 7

Which of the following is true regarding random error?

Accepted Answer

Error in sampling

Answer

Systematic differences in characteristic between cases and control

Answer

Cases and controls are asked questions about their past history

Answer

Different rates of admission in hospital

Question 8

What does prevalence represent?

Accepted Answer

Proportion

Answer

Rate

Answer

Ratio

Answer

Mean

Question 9

All are true about the Chi-Square test except?

Accepted Answer

The lowest expected frequency should be less than 5.

Answer

It is a non-parametric test of significance.

Answer

It is used to test the significance of association between two or more qualitative characteristics.

Answer

The sample must be randomly selected.

Question 10

On a given day, a hospital had 50 admissions with about 20 girls and 30 boys. Out of these, 10 girls and 20 boys needed surgery. What is the probability of picking a person requiring surgery?

Accepted Answer

2/5

Answer

1/3

Answer

1/2

Answer

3/5

Biostatistics — MCQs

Biostatistics — MCQs

On this page

Practice by Chapter

Want unlimited practice?