CENTRAL TENDENCY, DISPERSION & SAMPLING

CSIR-NET • GATE • DBT • ICMR

L11: Central Tendency, Dispersion & Sampling

Biostatistics & Methods in Biology

Detailed Bullet Notes + Formulas + Examples + 10 Interactive MCQs

📚 Index / Table of Contents

1. Types of Data
2. Variables and Measurement Scales
3. Population and Sample
4. Sampling and Sampling Distribution
5. Measures of Central Tendency
6. Arithmetic Mean
7. Median
8. Mode
9. Geometric and Harmonic Mean
10. Measures of Dispersion
11. Range and Interquartile Range
12. Variance and Standard Deviation
13. Coefficient of Variation
14. Biological Applications
15. CSIR-NET/GATE Important Points
16. Quick Revision
17. 10 MCQs with Interactive Submission

1. Types of Data

Data are the basic observations or measurements collected during a biological, medical, biochemical, ecological or experimental investigation. Proper classification of data is essential because the type of data determines the appropriate method of statistical analysis.

1.1 Qualitative Data

• Qualitative data describe characteristics or categories rather than numerical quantities.
• They are generally expressed in words, labels or categories.
• Examples include:
  • Sex: male/female.
  • Blood group: A, B, AB, O.
  • Genotype: AA, Aa, aa.
  • Phenotype: tall, dwarf.
  • Cell morphology: spherical, elongated, irregular.
• Qualitative data can be nominal or ordinal.

1.2 Quantitative Data

• Quantitative data are numerical measurements.
• They describe the amount or magnitude of a characteristic.
• Examples include:
  • Body weight in kg.
  • Height in cm.
  • Protein concentration in mg/mL.
  • DNA concentration in ng/µL.
  • Enzyme activity in U/mL.
  • Cell number per mL.

1.3 Discrete Data

• Discrete data consist of countable values.
• They usually arise from counting rather than continuous measurement.
• Examples:
  • Number of bacterial colonies.
  • Number of cells in a microscopic field.
  • Number of mutations.
  • Number of offspring.
  • Number of positive samples.
• Discrete variables generally take separate numerical values such as 0, 1, 2, 3...
• A value such as 2.56 offspring is not meaningful for a simple count variable.

1.4 Continuous Data

• Continuous data can theoretically take any value within a range.
• They arise from measurement.
• Examples include:
  • Temperature.
  • pH.
  • Blood pressure.
  • Protein concentration.
  • DNA concentration.
  • Cell diameter.
  • Reaction time.
• Continuous variables may contain decimal values.

Exam Tip: Number of bacterial colonies is generally a discrete variable, whereas bacterial growth rate, temperature, OD, concentration and cell size are generally continuous variables.

2. Variables and Measurement Scales

2.1 Nominal Scale

• Nominal data are categorical data with no inherent ranking.
• The categories are simply different labels.
• Examples:
  • Blood group.
  • Species name.
  • Genotype categories.
  • Gender categories.
• Arithmetic operations such as addition and subtraction are not meaningful.
• Frequency and percentage are commonly used for nominal data.

2.2 Ordinal Scale

• Ordinal data have a meaningful order or ranking.
• The difference between consecutive categories may not be equal.
• Examples:
  • Mild, moderate and severe disease.
  • Low, medium and high expression.
  • Small, medium and large colony size.
• Median and percentile-based methods can be useful for ordinal information.

2.3 Interval Scale

• Interval scales have ordered values with equal intervals.
• However, they do not possess a meaningful absolute zero.
• Temperature measured in Celsius is a common example.
• The difference between 10°C and 20°C is the same as between 20°C and 30°C.
• But 40°C is not meaningfully "twice as hot" as 20°C.

2.4 Ratio Scale

• Ratio scales have equal intervals and a true zero.
• Most biological measurements are ratio-scale measurements.
• Examples:
  • Mass.
  • Length.
  • Concentration.
  • Cell number.
  • Time.
  • Volume.
• Ratios are meaningful for ratio-scale data.

Scale	Main Feature	Example
Nominal	Categories without order	Blood group
Ordinal	Ordered categories	Disease severity
Interval	Equal intervals, no true zero	Temperature °C
Ratio	Equal intervals + true zero	Weight, concentration

3. Population and Sample

3.1 Population

• A population is the complete set of individuals, observations or objects of interest.
• For example, if a researcher wants to study the average height of all students in a university, all students constitute the population.
• A population may be finite or theoretically infinite.
• The numerical characteristics of a population are called parameters.
• Common population parameters include:
  • Population mean = μ
  • Population variance = σ²
  • Population standard deviation = σ
  • Population proportion = p

3.2 Sample

• A sample is a subset selected from the population.
• Researchers often study samples because examining the complete population may be impossible, expensive or time-consuming.
• Numerical characteristics calculated from a sample are called statistics.
• Examples:
  • Sample mean = x̄
  • Sample variance = s²
  • Sample standard deviation = s

Remember:
Population → Parameter
Sample → Statistic

3.3 Census

• A census attempts to collect information from every member of the population.
• It can provide highly comprehensive information.
• However, census studies may require substantial time, money and resources.

4. Sampling and Sampling Distribution

4.1 Sampling

• Sampling is the process of selecting a subset from a larger population.
• A good sample should represent the target population as closely as possible.
• Sampling reduces the practical burden of studying every individual.

4.2 Simple Random Sampling

• Every member of the population has an equal or known chance of being selected.
• Random number generators or lottery methods can be used.
• It reduces systematic selection bias.

4.3 Systematic Sampling

• Individuals are selected at regular intervals from an ordered list.
• For example, every 10th sample may be selected after a random starting point.

4.4 Stratified Sampling

• The population is divided into meaningful subgroups called strata.
• Samples are then collected from each stratum.
• Useful when different subgroups need adequate representation.

4.5 Cluster Sampling

• The population is divided into clusters.
• Some clusters are selected randomly.
• All or some members within selected clusters are studied.

4.6 Sampling Distribution

• A sampling distribution is the probability distribution of a statistic obtained from repeated samples of the same size from a population.
• For example, imagine repeatedly selecting samples of 30 organisms and calculating the mean body weight of every sample.
• The collection of these sample means forms a sampling distribution of the sample mean.
• Sampling distributions are fundamental for statistical inference.

4.7 Standard Error

• The standard error describes the variability of a sample statistic across repeated samples.
• For the sample mean:

SE(x̄) = σ / √n

• When population standard deviation is unknown, the sample standard deviation is commonly used:

SE(x̄) ≈ s / √n

• As sample size increases, the standard error of the mean decreases.
• Therefore, larger samples generally produce more precise estimates of the population mean.

Important: Standard deviation describes variability among individual observations, whereas standard error describes variability of a statistic across repeated samples.

5. Measures of Central Tendency

A measure of central tendency describes the central or typical location of a dataset. The three most important measures are:

• Mean
• Median
• Mode

These measures are useful for summarizing large biological datasets into a single representative value.

6. Arithmetic Mean

• The arithmetic mean is calculated by dividing the sum of all observations by the number of observations.
• It is commonly represented by x̄ for a sample.

x̄ = Σx / n

Example

Suppose the OD values of five cultures are:

0.4, 0.6, 0.8, 1.0, 1.2

Mean = (0.4 + 0.6 + 0.8 + 1.0 + 1.2) / 5 = 0.8

• The mean uses every observation in the dataset.
• It is highly useful for normally distributed numerical data.
• However, the mean can be strongly affected by extreme observations.

Weighted Mean

• When observations have different importance or weights, a weighted mean can be used.

Weighted Mean = Σ(wx) / Σw

Properties of Arithmetic Mean

• The sum of deviations from the arithmetic mean is zero.
• It is affected by extreme values.
• It is widely used in statistical calculations.
• It is suitable for quantitative measurements under appropriate assumptions.
• It is mathematically convenient for further analysis.

Exam Point: If a dataset contains a very large outlier, the arithmetic mean can shift considerably toward that outlier.

7. Median

• The median is the middle value of an ordered dataset.
• It divides the observations into two equal halves.
• Approximately 50% of observations lie below the median and 50% lie above it.
• The dataset must first be arranged in ascending or descending order.

Odd Number of Observations

For n observations where n is odd:

Median position = (n + 1) / 2

Even Number of Observations

For an even number of observations, the median is the average of the two central observations.

Median = (middle value 1 + middle value 2) / 2

Example

Dataset: 2, 4, 5, 7, 8

The middle value is 5, so median = 5.

Advantages of Median

• Less affected by extreme values than the mean.
• Useful for skewed distributions.
• Useful for ordinal data where ranking is meaningful.
• Frequently used for income, survival time and other skewed biological or clinical measurements.

8. Mode

• The mode is the most frequently occurring observation.
• A dataset may have one mode, more than one mode or no unique mode.
• A distribution with one mode is called unimodal.
• A distribution with two modes is called bimodal.
• Multiple modes may indicate different subpopulations.

Example

Dataset: 2, 3, 3, 4, 5, 3, 6

The mode is 3 because it occurs most frequently.

Applications

• Useful for categorical data.
• Useful when the most common category is of interest.
• For example, the most common blood group in a study population can be identified using the mode.

9. Geometric Mean and Harmonic Mean

9.1 Geometric Mean

• The geometric mean is appropriate for multiplicative data and ratios.
• For n positive observations:

GM = ⁿ√(x₁ × x₂ × x₃ × ... × xₙ)

• It is useful for growth rates and fold changes.
• It is less influenced by extremely large values compared with the arithmetic mean in some multiplicative contexts.
• All observations should generally be positive for the standard geometric mean.

9.2 Harmonic Mean

• The harmonic mean is the reciprocal of the arithmetic mean of reciprocals.

HM = n / Σ(1/x)

• It is useful for averaging rates under appropriate conditions.
• It is especially relevant when quantities are expressed as rates or ratios with a common numerator.

Quick comparison:
Arithmetic Mean → ordinary numerical measurements
Geometric Mean → multiplicative changes / fold changes
Harmonic Mean → rates and ratios

10. Measures of Central Dispersion

Measures of central tendency tell us where the center of a dataset lies, but they do not tell us how widely the observations are distributed around that center. Measures of dispersion describe the spread or variability of data.

The major measures include:

• Range
• Interquartile range
• Variance
• Standard deviation
• Coefficient of variation

11. Range and Interquartile Range

11.1 Range

• Range is the simplest measure of dispersion.
• It is calculated as the difference between the maximum and minimum values.

Range = Maximum − Minimum

Example

For data: 5, 8, 10, 12, 18

Range = 18 − 5 = 13

• Range is easy to calculate.
• However, it depends only on two observations: the minimum and maximum.
• It can therefore be strongly influenced by extreme values.

11.2 Quartiles

• Quartiles divide ordered data into four parts.
• Q1 represents the first quartile.
• Q2 corresponds to the median.
• Q3 represents the third quartile.

11.3 Interquartile Range

IQR = Q3 − Q1

• IQR describes the spread of the middle 50% of observations.
• It is less affected by extreme values than the range.
• It is particularly useful for skewed data.

12. Variance and Standard Deviation

12.1 Variance

Variance measures the average squared deviation of observations from their mean.

Population Variance

σ² = Σ(x − μ)² / N

Sample Variance

s² = Σ(x − x̄)² / (n − 1)

• The use of n − 1 in the sample variance is associated with the unbiased estimation of population variance under standard assumptions.
• Variance is expressed in squared units.
• For example, if the original measurement is mg/mL, variance has units of (mg/mL)².

12.2 Standard Deviation

Standard deviation is the square root of variance.

SD = √Variance

• Standard deviation is expressed in the same units as the original measurements.
• A small SD indicates that observations are clustered relatively close to the mean.
• A large SD indicates greater variability.
• SD is one of the most commonly reported measures of variability for quantitative biological data.

Interpretation

• Mean tells us the central location.
• SD tells us the typical spread around the mean.
• Mean ± SD is frequently used to summarize approximately symmetric quantitative datasets.

Important: Standard deviation is not the same as standard error. SD describes variability among observations; SE describes uncertainty or sampling variability of a statistic.

13. Coefficient of Variation

The coefficient of variation is a relative measure of dispersion. It is especially useful when comparing variability between datasets with different means or different measurement scales.

CV = (SD / Mean) × 100

• CV is usually expressed as a percentage.
• A lower CV indicates lower relative variability.
• A higher CV indicates greater relative variability.
• CV is useful for comparing precision between experimental measurements.

Example

Experiment A: Mean = 100, SD = 5

CV = (5 / 100) × 100 = 5%

Experiment B: Mean = 20, SD = 2

CV = (2 / 20) × 100 = 10%

Therefore, Experiment A has lower relative variability.

14. Applications in Biology and Biotechnology

14.1 Microbiology

• Mean bacterial growth rate can summarize replicate cultures.
• SD can describe variation among biological replicates.
• CFU counts are commonly treated as count data.
• OD measurements such as OD600 are quantitative measurements.
• Growth curves can be compared using summary statistics and appropriate statistical tests.

14.2 Molecular Biology

• DNA concentration can be summarized using mean and SD.
• Protein concentration can be represented as mean ± SD for replicate measurements.
• qPCR experiments often involve multiple biological and technical replicates.
• Fold changes may sometimes be summarized using geometric means or log-transformed values depending on experimental design.

14.3 Biotechnology

• Enzyme activity can be summarized using central tendency and dispersion.
• Fermentation yield can be compared among experimental conditions.
• Biomass concentration can be described using mean, median and SD.
• Coefficient of variation can help evaluate process consistency.

14.4 Ecology

• Species counts are often discrete variables.
• Population density is quantitative.
• Median may be preferred when ecological measurements are highly skewed.

14.5 Clinical and Medical Biology

• Clinical measurements often vary among individuals.
• Median and interquartile range can be useful for skewed clinical data.
• Mean and SD are commonly used for approximately normally distributed measurements.

15. Comparison of Central Tendency and Dispersion

Measure	What it Describes	Main Advantage	Main Limitation
Mean	Arithmetic center	Uses every observation	Sensitive to outliers
Median	Middle position	Robust to extreme values	Does not use magnitude of every observation
Mode	Most frequent value	Can be used for categorical data	May not be unique
Range	Total spread	Very simple	Uses only minimum and maximum
IQR	Middle 50% spread	Less affected by outliers	Ignores tails of distribution
Variance	Squared variability	Useful mathematically	Squared units
SD	Spread around mean	Same units as data	Can be affected by outliers
CV	Relative variability	Useful for comparing variability	Not appropriate when mean is zero or near zero

16. CSIR-NET / GATE Important Points

🧠 High-Yield Memory Points

• Mean: Sum of observations divided by number of observations.
• Median: Middle value after arranging data.
• Mode: Most frequently occurring value.
• Range: Maximum − Minimum.
• IQR: Q3 − Q1.
• Variance: Average squared deviation from mean.
• SD: Square root of variance.
• CV: SD/Mean × 100.
• Population: Complete group of interest.
• Sample: Subset of the population.
• Parameter: Numerical characteristic of a population.
• Statistic: Numerical characteristic calculated from a sample.
• Sampling distribution: Distribution of a statistic across repeated samples.
• SE of mean: σ/√n.
• Increasing sample size decreases the standard error of the sample mean.
• Mean is strongly influenced by extreme values.
• Median is more resistant to extreme values.
• Mode can be applied to categorical data.
• CV is a relative measure of variability.
• Continuous variables can theoretically take infinitely many values within a range.
• Discrete variables arise from counting.

Frequently Tested Concept 1: Mean vs Median

• For a perfectly symmetric unimodal distribution, mean, median and mode can coincide.
• For a positively skewed distribution, the mean is commonly pulled toward the higher values.
• For a negatively skewed distribution, the mean is commonly pulled toward the lower values.
• Median is generally more resistant to outliers.

Frequently Tested Concept 2: Sample Size

• Larger sample size generally reduces the standard error of the sample mean.
• According to the standard error relationship, increasing n by a factor of four reduces the SE of the mean by approximately half, assuming other quantities remain constant.

Frequently Tested Concept 3: Standard Deviation vs Variance

• Variance is measured in squared units.
• SD is measured in the original units.
• SD is therefore usually easier to interpret biologically.

17. Quick Revision Sheet

Concept	Formula / Key Idea
Mean	x̄ = Σx/n
Population Variance	σ² = Σ(x−μ)²/N
Sample Variance	s² = Σ(x−x̄)²/(n−1)
Standard Deviation	SD = √Variance
Range	Maximum − Minimum
IQR	Q3 − Q1
Coefficient of Variation	CV = SD/Mean × 100
SE of Mean	SE = σ/√n
Median	Middle observation after ordering
Mode	Most frequently occurring observation

One-line revision:

Mean = Center | Median = Middle | Mode = Most frequent | Range = Total spread | IQR = Middle 50% spread | Variance = Squared spread | SD = Typical spread | CV = Relative spread | SE = Sampling uncertainty.

18. Practice MCQs – 10 Questions

Instructions: Select one answer for each question and click Submit Answers. The correct answers and explanations will appear only after submission.

Q1. Which measure of central tendency is generally most affected by an extreme outlier?

A. Median B. Mode C. Arithmetic mean D. Quartile

Q2. The range of the dataset 4, 7, 9, 12 and 20 is:

A. 12 B. 16 C. 20 D. 24

Q3. Which of the following represents the coefficient of variation?

A. Mean/SD × 100 B. SD/Mean × 100 C. Variance/Mean × 100 D. Mean × SD

Q4. Which measure is most appropriate for describing the spread of the middle 50% of observations?

A. Range B. Variance C. Interquartile range D. Mean

Q5. Which statement about standard deviation is correct?

A. It is the square of variance B. It is the square root of variance C. It is always equal to the mean D. It is independent of data variability

Q6. If the sample size is increased while population variability remains constant, the standard error of the sample mean generally:

A. Increases B. Decreases C. Becomes zero immediately D. Remains exactly unchanged

Q7. Which type of variable is the number of bacterial colonies counted on an agar plate?

A. Continuous B. Discrete C. Interval only D. Nominal only

Q8. Which statement correctly distinguishes a parameter from a statistic?

A. Parameter describes a sample and statistic describes a population B. Both terms always mean exactly the same thing C. Parameter describes a population and statistic describes a sample C. Neither is numerical

Q9. Which measure is particularly useful when the data contain strong outliers?

A. Median B. Arithmetic mean only C. Maximum value D. Minimum value

Q10. A dataset has mean = 50 and SD = 5. What is its coefficient of variation?

A. 5% B. 10% C. 25% D. 50%

📌 L11 Quick Revision

Mean → Central average
Median → Middle value
Mode → Most frequent value
Range → Maximum − Minimum
IQR → Q3 − Q1
Variance → Squared dispersion
SD → √Variance
CV → SD/Mean × 100
Population → Complete group
Sample → Subset
Parameter → Population characteristic
Statistic → Sample characteristic
SE → Sampling variability

Prepare these concepts carefully for CSIR-NET, GATE Biotechnology, DBT-BET, ICMR-JRF and other life-science entrance examinations.