Biostatistics Practice Questions

Q: A professor at AIIMS was asked to conduct a study on hazardous effects of cellphone use on health of urban Indians. He selected the study group in the fashion shown below. It indicates:

Cluster random sampling. **Cluster random sampling** - The image shows distinct **groups (clusters)** like "Reliance," "Airtel," and "Vodafone," from which entire clusters or randomly selected individuals from within certain clusters are chosen for the sample. - In this method, the **population is divided into clusters**, and then a random sample of these clusters is drawn. All units within the selected clusters (or a random selection of units within selected clusters) are included in the sample. - This is the sampling method depicted in the image. *Simple random sampling* - This method involves selecting subjects from the entire population **randomly and independently**, where each member has an equal chance of being selected. - The image illustrates pre-defined groups and selection from within and between them, which isn't characteristic of a single, undifferentiated pool for simple random selection. *Systematic random sampling* - This technique involves selecting every **k-th individual** from a list, after a random start. - The visual representation does not suggest a continuous list or a patterned, interval-based selection process. *Stratified random sampling* - In this method, the population is divided into **homogeneous subgroups (strata)** based on shared characteristics, and then a simple random sample is drawn from each stratum. - While there are groups (Reliance, Airtel, Vodafone), the selection process shown (selecting some individuals from one group, some from another, and possibly an entire smaller group from a larger one) does not strictly adhere to sampling proportionally from each stratum to ensure representation.

Q: The given image shows which kind of sampling?

Systematic random sampling. ***Systematic random sampling*** - The image illustrates **systematic random sampling** where participants are selected at regular intervals from a list, using a starting point chosen randomly. - For example, if we have 100 people and want to sample 10, we could pick every 10th person after a random start between 1 and 10. *Simple random sampling* - In **simple random sampling**, every individual in the population has an **equal chance** of being selected, like drawing names from a hat. - The image does not show a random selection of individuals from the entire pool without any specific pattern or interval. *Stratified random sampling* - **Stratified random sampling** involves dividing the population into **subgroups (strata)** based on shared characteristics, then taking a random sample from each stratum. - The image does not show any deliberate division of the population into distinct strata before sampling. *Cluster random sampling* - **Cluster random sampling** involves dividing the population into **clusters**, randomly selecting entire clusters, and then sampling all individuals within the chosen clusters. - The image does not depict the selection of entire pre-defined groups or clusters of individuals.

Q: In the following diagram which is correct?

Mean > median > mode. ***Mean > median > mode*** - The diagram illustrates a **positively skewed distribution** (right-skewed), where the tail extends to the right. - In a positively skewed distribution, the correct order is always: **Mode mode > mean* - This order describes a **negatively skewed (left-skewed) distribution**, where the tail extends to the left. - In a negatively skewed distribution: Mean mode > median* - While the mean is indeed greater than the mode in a positively skewed distribution, the **median always lies between the mode and mean**. - The correct relationship for positive skew is: Mode < **Median** < Mean (not Mode < Mean < Median). - This violates the fundamental property that median is the middle value in skewed distributions. *Mean = mode = median* - This equality holds only for a **symmetrical distribution**, such as a **normal distribution** (bell curve). - In symmetrical distributions, data is evenly distributed around the center point. - The diagram clearly shows an **asymmetrical, right-skewed distribution**, making this incorrect.

Q: What is correct about the distribution curve shown below?

Positively skewed distribution. ***Positively skewed distribution*** - The curve shown is **skewed to the right** (positively skewed), meaning the tail of the distribution extends further to the right. - In a positively skewed distribution, the **mean is typically greater than the median**, which is greater than the mode. - There are more values clustered on the left side of the graph, with outliers extending to the right. - The relationship is: **Mode < Median < Mean** *Normal distribution* - A **normal distribution** (or Gaussian distribution) is symmetrical, forming a bell-shaped curve. - In such a distribution, the **mean, median, and mode are all equal** and located at the center of the curve. - There is no skewness in a normal distribution. *Negatively skewed distribution* - A **negatively skewed distribution** is skewed to the left, meaning the tail of the distribution extends further to the left. - In a negatively skewed distribution, the **mean is typically less than the median**, which is less than the mode. - There are more values clustered on the right side of the graph, with outliers extending to the left. - The relationship is: **Mean < Median < Mode** *Square wave distribution* - A **square wave distribution** is a periodic, non-sinusoidal waveform where the amplitude alternates regularly and instantaneously between two fixed values. - This type of distribution is **not represented by a continuous, curved shape** like the one shown and is not a standard probability distribution in biostatistics.

Q: The following statistical diagram is called

Forest plot. ***Forest plot*** - A **forest plot** is a graphical display used primarily in **meta-analysis** to show the results of multiple studies comparing treatment effects. - It displays individual study effect sizes (as squares or points) with their **confidence intervals** (as horizontal lines), along with an overall pooled effect estimate (typically shown as a diamond). - The vertical line represents **no effect** (null hypothesis), and studies whose confidence intervals cross this line show non-significant results. - Forest plots allow quick visual assessment of consistency across studies and the overall effect magnitude. *Funnel plot* - A funnel plot is used to **detect publication bias** in meta-analyses by plotting study effect sizes against their precision (or sample size). - It typically shows a scatter plot with a triangular "funnel" shape, where smaller studies show more scatter and larger studies cluster at the top. - This is distinctly different from a forest plot, which displays confidence intervals horizontally. *Box and whisker plot* - A box and whisker plot represents the **distribution of numerical data** through quartiles, median, and outliers. - It shows the minimum, first quartile (Q1), median (Q2), third quartile (Q3), and maximum values in a box-and-whisker format. - It does not display multiple study results or confidence intervals. *Stem and leaf plot* - A stem and leaf plot is a **simple way to display quantitative data** by separating each data point into a "stem" (leading digit) and a "leaf" (trailing digit). - This method organizes small to moderately sized datasets and shows the actual data values while preserving their distribution shape. - It does not show comparative study results or confidence intervals.

Q: The following statistical diagram is called

Funnel plot. ***Funnel plot*** - The diagram shows a **scatter plot** of studies arranged by **trial size (number of subjects)** on the y-axis and a measure of effect (implied effect size, typically odds ratio, risk ratio, or difference in means) on the x-axis, resembling an inverted funnel. - This characteristic funnel shape is used to visually assess **publication bias** or heterogeneity among studies in a meta-analysis. *Forest plot* - A **forest plot** displays the results of individual studies and their combined effect estimate, often represented by squares and a diamond. - It does not have the "funnel" shape seen in the provided image. *Box and whisker plot* - A **box and whisker plot** graphically displays the distribution of numerical data through their quartiles, showing the median, interquartile range, and potential outliers. - It is used to summarize dataset distributions and does not resemble the shown plot. *Stem and leaf plot* - A **stem and leaf plot** is a method for displaying quantitative data in a way that preserves original data values and provides a visual representation of their distribution. - This plot organizes data by separating observed values into a stem (leading digit) and a leaf (trailing digit), which is distinctly different from the given image.

Q: The following statistical diagram is called

Box and whisker plot. ***Box and whisker plot*** - This diagram displays the **distribution** of a dataset through **quartiles**, with the "box" representing the interquartile range (25th to 75th percentile) and the "whiskers" extending to the minimum and maximum values (or a specified percentile range). - The horizontal line inside each box indicates the **median** of the data, providing a visual summary of central tendency and spread for different categories. *Forest plot* - A forest plot is typically used in **meta-analyses** to display the results of multiple studies measuring the same outcome. - It shows **individual study estimates** and their confidence intervals, along with an overall pooled estimate. *Funnel plot* - A funnel plot is used to assess **publication bias** in meta-analyses. - It plots the effect size against a measure of study precision, and in the absence of bias, the plot should resemble a symmetrical inverted funnel. *Stem and leaf plot* - A stem and leaf plot is a way of organizing numerical data to show its **distribution** while retaining the individual data points. - It separates each data point into a "stem" (the leading digit(s)) and a "leaf" (the trailing digit).

Q: The following statistical diagram is called

Stem and leaf plot. ***Stem and leaf plot*** - This diagram displays quantitative data by separating each value into a "stem" (first digit(s)) and a "leaf" (last digit), arranged in order. - The provided image clearly shows digits on the left serving as stems (e.g., 1, 2, 3) and corresponding digits on the right as leaves (e.g., 80, 40, 60, 70), indicating a stem and leaf plot. *Forest plot* - A forest plot graphically presents the results of a **meta-analysis**, showing the estimated treatment effects and confidence intervals from multiple studies. - It does not organize individual data points by their numerical values in a stem-and-leaf structure. *Funnel plot* - A funnel plot is used to assess **publication bias** in a meta-analysis, plotting the effect size against a measure of study precision (e.g., standard error). - It appears as a scatter plot and does not resemble the structure of the given diagram. *Box and whisker plot* - A box and whisker plot displays the **five-number summary** of a set of data: minimum, first quartile, median, third quartile, and maximum. - It uses a rectangular "box" and "whiskers" extending from it, which is distinctly different from the digit-based organization seen in the image.

Q: The following statistical diagram is known as

Forest plot. ***Forest plot*** - This diagram, featuring a series of horizontal lines (representing **confidence intervals**) for different studies or outcomes, centered around a point estimate (often a **hazard ratio** or odds ratio), is characteristic of a forest plot. - Forest plots are commonly used in **meta-analyses** to graphically present the results of individual studies and their combined effect. *Kaplan Meier plot* - A Kaplan-Meier plot is a **survival curve** that shows the probability of a subject surviving beyond a certain time point. - It consists of a **stepwise function** decreasing over time, rather than individual point estimates with confidence intervals. *Spaghetti plot* - A spaghetti plot is used to display **multiple time series** on a single graph, where each line represents an individual's data over time. - This type of plot helps visualize **individual variability** and trends, but it does not represent hazard ratios or confidence intervals in the way shown. *Funnel plot* - A funnel plot is a scatter plot used to detect **publication bias** in meta-analyses, where the effect size is plotted against a measure of study precision. - It typically appears as a symmetrical, **funnel-shaped distribution** of points, which is visually distinct from the given diagram.

Q: A scatter diagram is shown below between two quantitative variables. Which of the following is the correct interpretation?

There is non-linear correlation between the two variables. ***There is non-linear correlation between the two variables*** - The data points in the scatter diagram clearly show a **pattern**, indicating a relationship between the variables. - However, this relationship is not a straight line; it curves upwards and then downwards, which defines a **non-linear correlation**. *There is correlation between the two variables and Pearson coefficient is 1* - While there is a **correlation**, the Pearson correlation coefficient of **1** implies a perfect positive linear relationship, meaning all points lie exactly on an upward-sloping straight line, which is not what is shown here. - The data points clearly deviate from a single straight line, showing both positive and negative trends at different stages. *There is correlation between the two variables and Pearson coefficient is -1* - The Pearson correlation coefficient of **-1** implies a perfect negative linear relationship, meaning all points lie exactly on a downward-sloping straight line. - The scatter plot shows a curved pattern, not a perfect negative linear trend. *There is no association between the two variables* - This statement is incorrect because the data points clearly show a **discernible pattern**, indicating that the variables are related. - If there were no association, the points would be scattered randomly with no clear trend or shape.

Question 1

A professor at AIIMS was asked to conduct a study on hazardous effects of cellphone use on health of urban Indians. He selected the study group in the fashion shown below. It indicates:

Accepted Answer

Cluster random sampling

Answer

Simple random sampling

Answer

Systematic random sampling

Answer

Stratified random sampling

Question 2

The given image shows which kind of sampling?

Accepted Answer

Systematic random sampling

Answer

Simple random sampling

Answer

Stratified random sampling

Answer

Cluster random sampling

Question 3

In the following diagram which is correct?

Accepted Answer

Mean > median > mode

Answer

Median > mode > mean

Answer

Mean > mode > median

Answer

Mean = mode = median

Question 4

What is correct about the distribution curve shown below?

Accepted Answer

Positively skewed distribution

Answer

Normal distribution

Answer

Negatively skewed distribution

Answer

Square wave distribution

Question 5

The following statistical diagram is called

Accepted Answer

Forest plot

Answer

Funnel plot

Answer

Box and whisker plot

Answer

Stem and leaf plot

Question 6

The following statistical diagram is called

Accepted Answer

Funnel plot

Answer

Forest plot

Answer

Box and whisker plot

Answer

Stem and leaf plot

Question 7

The following statistical diagram is called

Accepted Answer

Box and whisker plot

Answer

Forest plot

Answer

Funnel plot

Answer

Stem and leaf plot

Question 8

The following statistical diagram is called

Accepted Answer

Stem and leaf plot

Answer

Forest plot

Answer

Funnel plot

Answer

Box and whisker plot

Question 9

The following statistical diagram is known as

Accepted Answer

Forest plot

Answer

Kaplan Meier plot

Answer

Spaghetti plot

Answer

Funnel plot

Question 10

A scatter diagram is shown below between two quantitative variables. Which of the following is the correct interpretation?

Accepted Answer

There is non-linear correlation between the two variables

Answer

There is correlation between the two variables and Pearson coefficient is 1

Answer

There is correlation between the two variables and Pearson coefficient is -1

Answer

There is no association between the two variables

Biostatistics — MCQs

Biostatistics — MCQs

On this page

Practice by Chapter

Want unlimited practice?