STAT-101: Introductory Statistics for
Physicists — Fully Detailed Solved
Paper
Q.1 Short Answers (10×2=20)
(i) Differentiate between Parameter and Statistic
A parameter is a fixed numerical value that describes some characteristic of an entire population. It is
usually unknown because it is often impossible or impractical to measure every single member of a
population. Examples include the population mean (μ), population variance (σ²), and population
proportion (P).
A statistic is a numerical value calculated from a sample (a smaller subset taken from the population).
Because it is computed from actual collected data, its value is known once the sample is measured.
Examples include the sample mean (x̄ ), sample variance (s²), and sample proportion (p̂ ).
The key relationship is that statistics are used to estimate unknown parameters. For example, if we want
to know the average height of all students in a university (a parameter, since measuring everyone is
impractical), we might measure 100 randomly chosen students and compute their average height (a
statistic), then use that as an estimate of the population parameter.
Feature Parameter Statistic
Belongs to Population Sample
Value Fixed but usually unknown Known, but varies from sample to sample
Notation Greek letters (μ, σ, P) Roman letters (x̄ , s, p̂ )
Purpose What we want to know What we use to estimate it
(ii) Write down the types of average
“Average” is a general term for a measure of central tendency — a single value that represents the center
of a data set. There are five main types:
1. Arithmetic Mean (A.M.) — Sum of all values divided by the number of values. Most commonly
used average. Formula: x̄ = (Σx)/n
2. Median — The middle value of the data when arranged in ascending or descending order. If there
are an even number of values, it is the average of the two middle values. It is useful when data has
extreme outliers.
3. Mode — The value that occurs most frequently in the data set. A data set can have one mode
(unimodal), two modes (bimodal), or more.
4. Geometric Mean (G.M.) — The n-th root of the product of n values: G.M. = (x₁ × x₂ × … ×
xₙ)^(1/n). Useful for data involving rates of growth or ratios.
5. Harmonic Mean (H.M.) — The reciprocal of the average of reciprocals: H.M. = n / Σ(1/x).
Useful when dealing with rates such as speed.
Each type of average is useful in different situations depending on the nature of the data and whether the
data contains extreme values.
(iii) What is a Random Experiment?
A random experiment is any process or action that: 1. Can be repeated (in theory) any number of times
under the same conditions. 2. Has a well-defined set of all possible outcomes (called the sample space,
denoted S). 3. The exact outcome of any single trial cannot be predicted with certainty in advance,
although the set of possible outcomes is known.
Examples: - Tossing a coin → possible outcomes: {Head, Tail} - Rolling a six-sided die → possible
outcomes: {1, 2, 3, 4, 5, 6} - Measuring the lifetime of a light bulb → possible outcomes: any positive
real number
The concept of a random experiment is foundational to probability theory because every probability
calculation begins by defining the random experiment and its sample space.
(iv) Define Discrete Random Variable
A random variable is a variable whose value is a numerical outcome of a random experiment. A
discrete random variable is one that can take only a finite or countably infinite number of distinct
(separate) values — typically whole numbers (integers) — and cannot take values between those points.
Key characteristics: - The possible values can be listed (counted), even if the list is infinite. - There are
“gaps” between possible values — no value can fall between two consecutive possible values. - Each
possible value has an associated probability, and these probabilities sum to 1.
Examples: - Number of heads obtained in 3 tosses of a coin → possible values: {0, 1, 2, 3} - Number of
students absent from a class on a given day → possible values: {0, 1, 2, 3, …} - Number of cars passing
through a toll booth in an hour
This contrasts with a continuous random variable, which can take any value within an interval (e.g.,
height, weight, time).
(v) What is a Bernoulli Trial? Give an Example
A Bernoulli trial is a random experiment that satisfies the following conditions: 1. There are exactly two
possible outcomes, usually labeled “success” and “failure.” 2. The probability of success, denoted p,
remains constant every time the trial is performed. 3. The probability of failure is therefore q = 1 − p. 4.
Each trial is independent of the others (the outcome of one trial does not affect another).
Examples: - Tossing a coin: “Success” = getting a Head (p = 0.5), “Failure” = getting a Tail (q = 0.5). -
Checking a manufactured item: “Success” = item is defective (p = 0.02), “Failure” = item is non-defective
(q = 0.98). - Answering a True/False question: “Success” = answering correctly by guessing (p = 0.5).
A sequence of independent Bernoulli trials, each with the same probability of success, forms the basis of
the Binomial Distribution (see part vi).
(vi) What is Binomial Distribution?
The Binomial Distribution is a discrete probability distribution that gives the probability of obtaining
exactly x successes in n independent Bernoulli trials, where each trial has the same probability of
success p.
Conditions required for a Binomial situation: 1. There is a fixed number of trials, n. 2. Each trial
results in only two outcomes: success or failure. 3. The probability of success, p, is the same for every
trial. 4. The trials are independent of each other.
Probability Formula:
P(X = x) = C(n, x) · pˣ · (1−p)ⁿ⁻ˣ, for x = 0, 1, 2, …, n
where: - C(n, x) = n! / [x!(n−x)!] is the number of ways to choose which x of the n trials are successes
(the “combinations” formula) - pˣ is the probability of getting x successes - (1−p)ⁿ⁻ˣ is the probability of
getting the remaining (n−x) failures
Example: If a coin is tossed 5 times (n=5, p=0.5), the probability of getting exactly 3 heads (x=3) is:
P(X=3) = C(5,3) × (0.5)³ × (0.5)² = 10 × 0.125 × 0.25 = 0.3125
The mean of a binomial distribution is np and the variance is np(1−p).
(vii) Write down the importance of Normal Distribution
The Normal Distribution (also called the Gaussian distribution or “bell curve”) is one of the most
important distributions in statistics for the following reasons:
1. Natural occurrence: Many real-world variables — such as heights, weights, measurement errors,
blood pressure, and exam scores — follow approximately a normal distribution.
2. Central Limit Theorem (CLT): Regardless of the shape of the original population distribution,
the distribution of sample means approaches a normal distribution as the sample size increases.
This is enormously important because it allows statisticians to use normal-distribution-based
methods even when the underlying population is not normal.
3. Basis for statistical inference: Most hypothesis tests (Z-tests, t-tests), confidence intervals, and
quality control methods are built on the assumption of normality, either directly or via the CLT.
4. Mathematical simplicity: The normal distribution is completely described by just two
parameters — the mean (μ) and the standard deviation (σ) — making calculations relatively
simple.
5. Symmetry and predictability: Because it is symmetric and bell-shaped, well-known rules apply,
such as the 68-95-99.7 rule (about 68% of data lies within 1 standard deviation of the mean, 95%
within 2, and 99.7% within 3).
6. Approximation tool: Other distributions (such as the Binomial and Poisson, under certain
conditions) can be approximated by the Normal distribution, simplifying complex calculations.
(viii) Differentiate between Point Estimator and Point Estimate
A point estimator is the general formula, rule, or method (a function of sample data) used to produce
an estimate of a population parameter. It is itself a random variable because its value depends on which
sample is drawn — different samples give different results.
A point estimate is the specific numerical value obtained by plugging actual sample data into the point
estimator. It is a fixed number, not a random variable, because it has already been calculated from real
data.
Example: - The point estimator for the population mean μ is the formula: x̄ = (Σxᵢ)/n - If we take a
sample of 6 students’ marks and calculate x̄ = 13.5, then 13.5 is the point estimate of μ for that particular
sample.
Feature Point Estimator Point Estimate
A formula/rule (random
Nature A single calculated number
variable)
Changes with sample? The formula stays the same The numerical value changes
Example x̄ = (Σxᵢ)/n x̄ = 13.5
(ix) Define Type-I and Type-II Errors
In hypothesis testing, we test a null hypothesis (H₀) against an alternative hypothesis (H₁). Since
decisions are based on sample data (not the entire population), two types of errors can occur:
Type-I Error (denoted α, “alpha”): This occurs when we reject the null hypothesis (H₀) when it is
actually TRUE. In other words, we conclude there is an effect or difference when, in reality, there is
none. This is also called a “false positive.” The probability of making this error is called the level of
significance, usually set at 0.05 (5%) or 0.01 (1%).
Example: Concluding that a new drug is effective when, in reality, it has no effect.
Type-II Error (denoted β, “beta”): This occurs when we fail to reject the null hypothesis (H₀) when
it is actually FALSE. In other words, we fail to detect a real effect or difference that does exist. This is
also called a “false negative.”
Example: Concluding that a new drug has no effect when, in reality, it does work.
H₀ is actually True H₀ is actually False
Reject H₀ Type-I Error (α) Correct decision
Fail to Reject H₀ Correct decision Type-II Error (β)
There is generally a trade-off between the two: decreasing α (making it harder to reject H₀) tends to
increase β, and vice versa.
(x) What are Critical Values and where do they come from?
A critical value is a specific numerical boundary (or “cut-off point”) on the scale of a test statistic (such
as Z, t, χ², or F) that separates the “rejection region” (where we reject H₀) from the “acceptance region”
/ “non-rejection region” (where we do not reject H₀).
How critical values are determined:
1. First, a level of significance (α) is chosen — commonly α = 0.05 or α = 0.01. This represents the
probability of making a Type-I error that we are willing to accept.
2. Based on α and the type of test (one-tailed or two-tailed), the critical value is looked up from
standard statistical tables for the relevant distribution:
• Z-table (Standard Normal Distribution) — used when population variance is known or
sample size is large.
• t-table (Student’s t-distribution) — used when population variance is unknown and sample
size is small.
• χ² (Chi-square) table — used for tests of variance, goodness of fit, and independence.
• F-table — used in ANOVA and comparing two variances.
3. The critical value depends on α and (for t, χ², and F distributions) the degrees of freedom.
Example: For a two-tailed Z-test at α = 0.05, the critical values are ±1.96. If the calculated test statistic
falls beyond ±1.96, we reject H₀; if it falls within ±1.96, we do not reject H₀.
In short, critical values come from the theoretical sampling distribution of the test statistic, tabulated
for various significance levels and degrees of freedom.
Q.2 Calculate Mean and Variance from the Following Data (10
marks)
Given Data:
Sales 0-4 5-9 10-14 15-19 20-24 25-29
f 1 14 23 21 15 6
Step 1: Find the mid-point (x) of each class
The mid-point represents each class interval with a single value, calculated as: Mid-point = (Lower limit
+ Upper limit) / 2
• For 0-4: (0+4)/2 = 2
• For 5-9: (5+9)/2 = 7
• For 10-14: (10+14)/2 = 12
• For 15-19: (15+19)/2 = 17
• For 20-24: (20+24)/2 = 22
• For 25-29: (25+29)/2 = 27
Step 2: Build the calculation table
We need to calculate f×x (frequency times mid-point) and f×x² for every row.
Class f x (mid-point) f·x x² f·x²
0-4 1 2 1×2 = 2 4 1×4 = 4
5-9 14 7 14×7 = 98 49 14×49 = 686
10-14 23 12 23×12 = 276 144 23×144 = 3312
15-19 21 17 21×17 = 357 289 21×289 = 6069
20-24 15 22 15×22 = 330 484 15×484 = 7260
25-29 6 27 6×27 = 162 729 6×729 = 4374
Total N = 80 Σf·x = 1225 Σf·x² = 21705
Check N: 1+14+23+21+15+6 = 80 ✓
Step 3: Calculate the Mean
The formula for the mean of grouped (frequency distribution) data is:
x̄ = Σ(f·x) / N
x̄ = 1225 / 80 = 15.3125
Step 4: Calculate the Variance
The formula for population variance of grouped data is:
σ² = [Σ(f·x²) / N] − (x̄ )²
This formula comes from the definition Var(X) = E(X²) − [E(X)]², where E(X²) = Σ(f·x²)/N is the “mean
of the squares” and [E(X)]² = (x̄ )² is the “square of the mean.”
Step-by-step calculation:
First term: Σ(f·x²)/N = 21705 / 80 = 271.3125
Second term: (x̄ )² = (15.3125)² = 234.4727 (rounded to 4 decimals)
σ² = 271.3125 − 234.4727 = 36.84 (approximately)
Step 5: (Optional) Sample Variance using (n−1)
If a “sample” variance (unbiased estimator) is required instead, use N−1 in the denominator for the
variance correction:
s² = [Σf·x² − N·(x̄ )²] / (N−1) = [21705 − 80×234.4727] / 79 = [21705 − 18757.81] / 79 = 2947.19/79 ≈
37.31
Final Answers:
• Mean (x̄ ) = 15.3125
• Variance (σ²) ≈ 36.84 (population) or ≈ 37.31 (sample, with n−1)
• Standard Deviation (σ) = √36.84 ≈ 6.07
Q.3
Part (a): Probability — Class of 20 Men and 20 Women (5 marks)
Given information: - Total people in class = 20 men + 20 women = 40 - Half of the men have brown
eyes → 20/2 = 10 men with brown eyes - Half of the women have brown eyes → 20/2 = 10 women with
brown eyes
Question: Find P(person chosen at random is a man OR has brown eyes)
Step 1: Define the events - Let A = the event that the chosen person is a man - Let B = the event that the
chosen person has brown eyes
We need to find P(A ∪ B) = P(A OR B), which means the person is a man, OR has brown eyes, OR both.
Step 2: Calculate P(A) — probability the person is a man
P(A) = (number of men) / (total people) = 20/40 = 1/2
Step 3: Calculate P(B) — probability the person has brown eyes
Total people with brown eyes = (brown-eyed men) + (brown-eyed women) = 10 + 10 = 20
P(B) = 20/40 = 1/2
Step 4: Calculate P(A ∩ B) — probability the person is a man AND has brown eyes
This is simply the number of men with brown eyes divided by the total:
P(A ∩ B) = 10/40 = 1/4
Step 5: Apply the Addition Rule of Probability
To avoid double-counting people who are both “men” AND “have brown eyes,” we subtract the overlap:
P(A ∪ B) = P(A) + P(B) − P(A ∩ B)
P(A ∪ B) = 1/2 + 1/2 − 1/4 = 2/4 + 2/4 − 1/4 = 3/4
Final Answer: P(man OR brown eyes) = 3/4 = 0.75 = 75%
Part (b): Probability of Rain (5 marks)
Given information: On average, rain falls on 15 days out of every 30 days.
Step 1: Find the probability of rain on any given day
P(rain) = 15/30 = 1/2, therefore P(no rain) = 1 − 1/2 = 1/2
We treat each day as a Bernoulli trial with “success” = rain, p = 1/2.
(i) Find P(first 3 days of a week are FINE (no rain) AND the remaining days are WET (rain))
A week has 7 days. “First three days fine” means days 1, 2, 3 have NO rain. “Remaining wet” means days
4, 5, 6, 7 all have rain.
Step 1: Since each day is independent, we multiply the probabilities of each individual day’s outcome.
Step 2: P(no rain on a single day) = 1/2, and we need this for 3 days: P(first 3 days fine) = (1/2) × (1/2) ×
(1/2) = (1/2)³
Step 3: P(rain on a single day) = 1/2, and we need this for the remaining 4 days: P(remaining 4 days wet)
= (1/2) × (1/2) × (1/2) × (1/2) = (1/2)⁴
Step 4: Combine (multiply, since both conditions must happen together):
P(first 3 fine AND remaining 4 wet) = (1/2)³ × (1/2)⁴ = (1/2)⁷ = 1/128 ≈ 0.0078
(ii) Find P(rain falls on EXACTLY 3 days out of a 7-day week)
This is now a Binomial Distribution problem because: - There are n = 7 independent trials (days) - Each
day has only two outcomes (rain or no rain) - p = 1/2 (probability of rain) is constant - We want exactly x
= 3 “successes” (rainy days)
Step 1: Write the binomial formula
P(X = x) = C(n, x) · pˣ · (1−p)ⁿ⁻ˣ
Here: n = 7, x = 3, p = 1/2, (1−p) = 1/2
Step 2: Calculate C(7,3) — the number of ways to choose which 3 of the 7 days are rainy:
C(7,3) = 7! / (3! × 4!) = (7×6×5) / (3×2×1) = 210/6 = 35
Step 3: Calculate the probability part
pˣ × (1−p)ⁿ⁻ˣ = (1/2)³ × (1/2)⁴ = (1/2)⁷ = 1/128
Step 4: Multiply everything together
P(X=3) = 35 × (1/128) = 35/128
Final Answer: P(rain on exactly 3 days) = 35/128 ≈ 0.2734 (27.34%)
Q.4
Part (a): Point Estimates from Sample n=6: {6, 10, 13, 14, 18, 20} (4 marks)
(i) Point estimate of the population mean
The sample mean is calculated by adding all values and dividing by the count:
x̄ = (Σxᵢ) / n = (6 + 10 + 13 + 14 + 18 + 20) / 6
Sum = 6+10+13+14+18+20 = 81
x̄ = 81/6 = 13.5
Point estimate of population mean = 13.5
(ii) Point estimate of the population standard deviation
The (sample) standard deviation measures how spread out the data values are from the mean. The formula
used is:
s = √[ Σ(xᵢ − x̄ )² / (n−1) ]
Step 1: Find the deviation of each value from the mean (x̄ = 13.5):
xᵢ xᵢ − x̄ (xᵢ − x̄ )²
6 6 − 13.5 = −7.5 56.25
10 10 − 13.5 = −3.5 12.25
13 13 − 13.5 = −0.5 0.25
14 14 − 13.5 = 0.5 0.25
18 18 − 13.5 = 4.5 20.25
20 20 − 13.5 = 6.5 42.25
Sum 131.5
Step 2: Divide by (n−1) = (6−1) = 5 — this is called the sample variance:
s² = 131.5 / 5 = 26.3
Step 3: Take the square root to get the standard deviation:
s = √26.3 ≈ 5.128
Point estimate of population standard deviation ≈ 5.128
(iii) Standard Error of the Mean
The Standard Error (SE) of the mean tells us how much the sample mean is expected to vary from
sample to sample. It is calculated as:
SE = s / √n
Step 1: We already found s ≈ 5.128 and n = 6.
Step 2: Calculate √n = √6 ≈ 2.449
Step 3: Divide:
SE = 5.128 / 2.449 ≈ 2.094
Standard Error of the Mean ≈ 2.094
Part (b): Estimation in Statistics — Point vs Interval Estimation (6 marks)
What is Estimation in Statistics?
Estimation is a branch of statistical inference concerned with using information from a sample to make
an informed judgment (or “estimate”) about the value of an unknown population parameter (such as the
population mean μ, population variance σ², or population proportion P). Since it is usually impossible or
too costly to measure an entire population, estimation provides a practical way to learn about the
population using only a portion of it.
There are two main types of estimation: Point Estimation and Interval Estimation.
1. Point Estimation
Point estimation involves using sample data to calculate a single value (a “point”) that serves as the
“best guess” for the unknown population parameter.
• The formula used to calculate this value is called the point estimator.
• The actual number obtained is called the point estimate.
Example: Suppose we want to estimate the average weight of all apples in an orchard (population mean
μ). We weigh a sample of 6 apples and find their average weight is 150 grams. This single value, 150
grams, is the point estimate of μ.
Advantage: Simple and easy to communicate.
Disadvantage: Gives no information about how accurate or reliable the estimate is. A point estimate
by itself doesn’t tell us how close it is likely to be to the true population value.
2. Interval Estimation
Interval estimation involves constructing a range of values — called a confidence interval (CI) —
within which the population parameter is expected to lie, along with a stated level of confidence
(commonly 95% or 99%).
A confidence interval is generally expressed in the form:
Point Estimate ± Margin of Error
The “margin of error” depends on the standard error of the estimate and a critical value from the Z or t
distribution corresponding to the chosen confidence level.
Example: Continuing the apple example, instead of just saying “the average weight is 150 grams,” we
might say: “We are 95% confident that the true average weight of all apples in the orchard lies
between 145 grams and 155 grams.” This range (145 to 155) is the interval estimate.
Advantage: Provides a sense of the precision and reliability of the estimate — a narrow interval
suggests a more precise estimate, while a wide interval suggests more uncertainty.
Disadvantage: Slightly more complex to calculate and interpret than a single point value.
Comparison Table
Aspect Point Estimation Interval Estimation
Result A single numerical value A range (lower limit to upper limit)
Information on
None given Margin of error / confidence level given
accuracy
Formula form x̄ (just the statistic) x̄ ± (critical value × standard error)
Numerical Example x̄ = 13.5 13.5 ± 2(2.094) ≈ (9.31, 17.69)
Reliability info Not communicated Communicated via confidence level (e.g., 95%)
Quick summaries, simple Scientific reporting, decision-making under
Common use
reporting uncertainty
Conclusion: While point estimation gives us a quick, single-number answer, interval estimation is
generally preferred in scientific and research contexts because it conveys both the estimate and the degree
of confidence/uncertainty associated with it — which is crucial in physics and experimental sciences
where measurement uncertainty must always be reported.
Q.5 Correlation Coefficient Between X and Y (10 marks)
Given Data:
X 2 4 5 6 8 11
Y 18 12 0 8 7 5
The correlation coefficient (r) measures the strength and direction of the linear relationship between two
variables. It always lies between −1 and +1: - r close to +1 → strong positive relationship (both increase
together) - r close to −1 → strong negative relationship (one increases as the other decreases) - r close to 0
→ little or no linear relationship
Step 1: Set up the calculation table
We need to compute, for each pair: X², Y², and X×Y
X Y X² Y² X·Y
2 18 2² = 4 18² = 324 2×18 = 36
4 12 4² = 16 12² = 144 4×12 = 48
5 0 5² = 25 0² = 0 5×0 = 0
6 8 6² = 36 8² = 64 6×8 = 48
8 7 8² = 64 7² = 49 8×7 = 56
11 5 11² = 121 5² = 25 11×5 = 55
Step 2: Find the column totals (sums)
• ΣX = 2+4+5+6+8+11 = 36
• ΣY = 18+12+0+8+7+5 = 50
• ΣX² = 4+16+25+36+64+121 = 266
• ΣY² = 324+144+0+64+49+25 = 606
• ΣXY = 36+48+0+48+56+55 = 243
• n (number of pairs) = 6
Step 3: Write the formula for Pearson’s Correlation Coefficient
r = [n·ΣXY − ΣX·ΣY] / √{ [n·ΣX² − (ΣX)²] × [n·ΣY² − (ΣY)²] }
This formula essentially compares how X and Y vary together (the numerator, related to “covariance”)
with how much each variable varies individually (the denominator, related to the “standard deviations” of
X and Y).
Step 4: Calculate the Numerator
Numerator = n·ΣXY − ΣX·ΣY = 6 × 243 − 36 × 50 = 1458 − 1800 = −342
(The negative sign already tells us the correlation will be negative.)
Step 5: Calculate the Denominator — Part 1 (for X)
n·ΣX² − (ΣX)² = 6 × 266 − (36)² = 1596 − 1296 = 300
Step 6: Calculate the Denominator — Part 2 (for Y)
n·ΣY² − (ΣY)² = 6 × 606 − (50)² = 3636 − 2500 = 1136
Step 7: Multiply the two parts and take the square root
Denominator = √(300 × 1136) = √340800
Calculating: √340800 ≈ 583.78
Step 8: Divide Numerator by Denominator
r = −342 / 583.78 ≈ −0.586
Final Answer: r ≈ −0.586
Step 9: Interpretation
Since r ≈ −0.586 is negative and of moderate magnitude (between 0.5 and 0.7 in absolute value), this
tells us:
• There is a moderate negative (inverse) relationship between X and Y.
• As the value of X increases, the value of Y tends to decrease, and vice versa.
• The relationship is not perfectly linear (since |r| ≠ 1), and there is considerable scatter in the data,
but a clear downward trend exists.
END OF SOLUTIONS