Statistics for Business Economics - I

BBE Sem-II - Question and Answer Bank

Question 1: Specific Gravity of Wood Types

Find mean, median, mode and 10% trimmed mean for the given wood specific gravity data.
Answer:
Data: .31, .35, .36, .36, .37, .38, .40, .40, .40, .41, .41, .42, .42, .42, .42, .45, .46, .46, .47, .4
8, .48, .48, .51, .54, .54, .55, .58, .62, .66, .66 (n=30)
Mean = Sum of all values / 30 = 12.63 / 30 = 0.421
Median = (0.42 + 0.45) / 2 = 0.435 (average of 15th and 16th values when sorted)
Mode = 0.42 (appears 4 times, most frequent)
10% Trimmed Mean: Remove 10% from each end (3 values). New sum = 11.97 / 24 = 0.499

ans-1

Question 2: Skewness and Quartiles

(i) Write a brief note on skewness. (ii) If Q1 = 142 and IQR = 36, find the median assuming
symmetrical distribution.
Answer:
(i) Skewness measures the asymmetry of a distribution. A distribution is symmetric
(skewness = 0) when mean = median = mode. Positive skewness indicates the tail extends
to the right (mean > median), while negative skewness shows the tail extending left (mean <
median). It ranges from -3 to +3 and is crucial for understanding distribution shape and data
pattern interpretation.
(ii) For a symmetrical distribution, Q1 is equidistant from Median as Median is from Q3.
Given Q1 = 142 and IQR = 36: Q3 = Q1 + IQR = 142 + 36 = 178. In symmetric distribution:
Median = (Q1 + Q3) / 2 = (142 + 178) / 2 = 160

ans-2

Question 3: Karl Pearson's Coefficient of Skewness

Calculate Karl Pearson's coefficient of skewness from: Size (1-7) with Frequency (10, 18,
30, 25, 12, 3, 2)
Answer:
Karl Pearson's coefficient = 3(Mean - Median) / Standard Deviation
Calculations: n = 100, ∑fx = 309, Mean = 3.09, Median = 3 (at cumulative frequency 50),
∑fx² = 1069, Variance = 1.87, SD = 1.367
Skewness coefficient = 3(3.09 - 3) / 1.367 = 0.198 (positively skewed, slight right tail)

ans-3

Question 4: Conditional Probability Proofs

(i) For events A and B with P(B) > 0, show that P(A|B) + P(A'|B) = 1. (ii) If P(B|A) > P(B),
show that P(B'|A) < P(B').
Answer:
(i) P(A|B) = P(A∩B)/P(B) and P(A'|B) = P(A'∩B)/P(B). Since A and A' are mutually exclusive
and exhaustive: P(A∩B) + P(A'∩B) = P(B). Therefore, P(A|B) + P(A'|B) = [P(A∩B) +
P(A'∩B)]/P(B) = P(B)/P(B) = 1. Proved.
(ii) Given P(B|A) > P(B), we have P(B∩A)/P(A) > P(B). Since P(B|A) + P(B'|A) = 1, we get
P(B'|A) = 1 - P(B|A) < 1 - P(B) = P(B'). Thus P(B'|A) < P(B'). Proved.

ans-4

Question 5: Bayes' Theorem

(i) State Bayes' Theorem. (ii) A shop repairs audio and video components. P(A) = 0.6, P(B) =
0.05 where B ⊂ A. Find P(B|A).
Answer:
(i) Bayes' Theorem: For events A and B, P(A|B) = P(B|A)·P(A) / P(B), where P(B) ≠ 0. It
updates probabilities based on new evidence.
(ii) Since B ⊂ A (B is contained in A), event B can only occur if A occurs. Thus P(B∩A) =
P(B) = 0.05. Therefore, P(B|A) = P(B∩A) / P(A) = 0.05 / 0.6 = 1/12 ≈ 0.0833

ans-5

Question 6: Battery Testing Distribution

Testing batteries until two acceptable ones are found. 90% have acceptable voltage. Y =
number of batteries tested. Find P(Y=2), P(Y=3), and P(Y=5).
Answer:
a) P(Y=2) = P(first two are acceptable) = 0.9 × 0.9 = 0.81
b) P(Y=3): Two outcomes - UAA or AUA. P(Y=3) = 0.1(0.9)(0.9) + 0.9(0.1)(0.9) = 0.162
c) P(Y=5): The 5th battery must be acceptable. Four outcomes exist with exactly 1
acceptable in first 4 batteries: P(Y=5) = C(4,1)(0.9)¹(0.1)³(0.9) = 4 × 0.9 × 0.1 × 0.1 × 0.1 ×
0.9 = 0.00324

ans-6

Question 7: Normal Distribution - Steel Yield Strength

Yield strength is N(43, 4.5²). Find: a) P(strength ≤ 40) and P(strength > 60), b) Value
separating strongest 75% from others.
Answer:
a) Z = (X - μ)/σ. For X = 40: Z = (40-43)/4.5 = -0.667. P(Z ≤ -0.667) ≈ 0.2514 or 25.14%. For
X = 60: Z = (60-43)/4.5 = 3.778. P(Z > 3.778) ≈ 0.0001 or 0.01%
b) For strongest 75%, we need P(X ≤ x) = 0.25 (bottom 25%). Z₀.₂₅ ≈ -0.674. X = 43 + 4.5(-
0.674) ≈ 39.97 ≈ 40 ksi

ans-7

Question 8: Dryer Purchase Probabilities

Five customers purchase dryers. P(at most one electric) = 0.428. Find: a) P(at least two
electric), b) P(at least one of each type).
Answer:
a) P(at least two electric) = 1 - P(at most one electric) = 1 - 0.428 = 0.572
b) P(at least one of each) = 1 - P(all gas) - P(all electric) = 1 - 0.116 - 0.005 = 0.879

ans-8

Question 9: Rock Specimen Selection (Hypergeometric)

10 basalt + 10 granite specimens; 15 randomly selected. Find: a) pmf of granite count, b)
P(all of one type), c) P(count within 1 SD of mean).
Answer:
a) X ~ Hypergeometric with N=20, K=10, n=15. pmf: P(X=x) = C(10,x)·C(10,15-x)/C(20,15)
for x = 5,6,...,10
b) P(all of one type) = P(all granite) + P(all basalt) = C(10,15)·C(10,0)/C(20,15) +
C(10,0)·C(10,15)/C(20,15) = 0 (impossible, only 10 of each)
c) Mean = n·K/N = 15·10/20 = 7.5, Variance = 15·10·10·5/(20²·19) ≈ 0.987, SD ≈ 0.994.
Within 1 SD: [6.5, 8.5] includes X = 7,8. Sum appropriate probabilities.

ans-9

Question 10: Negative Binomial - Cereal Prizes

Prize probability = 0.2. Purchase boxes until obtaining 2 prizes. Find: a) P(x boxes without
prize), b) P(purchase 4 boxes), c) P(purchase ≤ 4), d) Expected values.
Answer:
a) P(x failures before 2 successes) = C(x+1,1)(0.2)²(0.8)ˣ = (x+1)(0.04)(0.8)ˣ
b) P(4 boxes total) = P(3 boxes without prize) = 4(0.04)(0.8)³ = 0.2048
c) P(≤ 4 boxes) = P(Y=2) + P(Y=3) + P(Y=4) = 0.04 + 0.128 + 0.2048 = 0.3728
d) Expected failures before 2 successes = 2(1-p)/p = 2(0.8)/0.2 = 8. Expected total boxes = 8
+ 2 = 10

ans-10

Question 11: Poisson Distribution - Colon Cancer Gene

1 in 200 carry defective gene. Sample n=1000. Find approximate distribution and P(5-8 carry
gene), P(≥8 carry gene).
Answer:
λ = np = 1000(1/200) = 5. Distribution: Poisson(5)
a) P(5 ≤ X ≤ 8) = P(X=5) + P(X=6) + P(X=7) + P(X=8) using e ⁻⁵·5ˣ/x! values ≈ 0.175 + 0.146
+ 0.104 + 0.065 = 0.490
b) P(X ≥ 8) = 1 - P(X ≤ 7) = 1 - Σ(e⁻⁵·5ˣ/x!) from x=0 to 7 ≈ 0.133

ans-11

Question 12: Continuous PDF - Cartridge Tracking Weight

PDF: f(x) = k[1-(x-3)²] for 2≤x≤4, else 0. Find: a) Sketch graph, b) Find k, c) P(X>3), d) P(|X-
3|≤0.25).
Answer:
b) ∫₂⁴ k[1-(x-3)²]dx = 1. Let u = x-3: ∫₋₁¹ k(1-u²)du = k[u - u³/3] ₋₁¹ = k(2 - 2/3) = 4k/3 = 1, so k
= 3/4
c) P(X>3) = ∫₃⁴ (3/4)[1-(x-3)²]dx = (3/4)∫₀¹(1-u²)du = (3/4)(2/3) = 1/2
d) P(|X-3|≤0.25) = P(2.75≤X≤3.25) = ∫₂.₇₅³·²⁵ (3/4)[1-(x-3)²]dx = 3/4·[2·0.25 - (0.25)³/3] ≈
0.371

ans-12

Question 13: Linear Regression - Tin/Lead Deposition

Data: X (current density): 20, 40, 60, 80; Y (deposition rate): 0.24, 1.2, 1.71, 2.22. Verify
linear relationship claim.
Answer:
Computing: n=4, ΣX=200, ΣY=5.37, ΣX²=14000, ΣY²=8.6705, ΣXY=447. Correlation r =
[n·ΣXY - ΣX·ΣY] / √[(n·ΣX² - (ΣX)²)(n·ΣY² - (ΣY)²)] = 0.9994
With r² = 0.9988 (99.88% variation explained), the very strong positive correlation (r ≈
0.9994) strongly supports the claim of a linear relationship. The scatter plot shows nearly
perfect linear pattern.

ans-13

Question 14: Spearman's Rank Correlation Coefficient

15 students' ranks in subjects A and B given. Calculate Spearman's rank correlation
coefficient using the provided rank pairs.
Answer:
Spearman's formula: ρ = 1 - 6Σd²/[n(n²-1)], where d = rank difference for each student
Computing differences: d values = 9, 5, 1, 2, 1, 2, 4, 7, 2, 5, 2, 7, 1, 2, 2. Σd² = 208
ρ = 1 - 6(208)/[15(225-1)] = 1 - 1248/3360 = 1 - 0.371 = 0.629. This indicates a moderate
positive rank correlation between subjects A and B.

ans-14

Question 15: Pearson Correlation Coefficient - Asparagus Quality

n=18, ΣX=1950, ΣX²=251970, ΣY=47.92, ΣY²=130.6074, ΣXY=5530.92. Calculate r and
describe relationship. Effect of unit change?
Answer:
r = [n·ΣXY - ΣX·ΣY] / √[(n·ΣX² - (ΣX)²)(n·ΣY² - (ΣY)²)]
= [18(5530.92) - 1950(47.92)] / √[(18(251970) - 1950²)(18(130.6074) - 47.92²)]
= [99575.56 - 93444] / √[(4535460 - 3802500)(2350.93 - 2296.13)] = 0.891
This strong positive correlation (r=0.891) indicates shear force and fiber content are strongly
related. If shear force is expressed in pounds instead of kg, the correlation r remains
unchanged (0.891) because correlation is unitless and depends only on relative
relationships.

ans-15

Question 16: Correlation After Transformation

Correlation between X and Y is 0.5. Find correlation between 2X and 3Y.
Answer:
Correlation coefficient is invariant under linear transformations with positive slopes. Corr(aX,
bY) = Corr(X, Y) for positive constants a and b. Therefore, Corr(2X, 3Y) = Corr(X, Y) = 0.5.
The correlation remains 0.5 because scaling doesn't affect the relative relationships between
variables.

ans-16

Question 17: Index Number - Simple Aggregate Method

Commodity prices 1980 vs 1981: A(162→171), B(256→164), C(257→189), D(132→145).
Calculate index number.
Answer:
Simple Aggregate Index = (ΣP₁ / ΣP₀) × 100
ΣP₁ = 171 + 164 + 189 + 145 = 669 (1981 prices)
ΣP₀ = 162 + 256 + 257 + 132 = 807 (1980 prices)
Index = (669/807) × 100 = 82.91. This shows a decrease of 17.09% in aggregate prices from
1980 to 1981.

ans-17

Question 18: Weighted Index Number - Laspeyres Method

Price and consumption data for 5 commodities in 1995 and 1997. Calculate index number
using appropriate method.
Answer:
Using Laspeyres Index (1995 consumption as weights): P₉₇ = (ΣP₉₇·Q₉₅ / ΣP₉₅·Q₉₅) ×
100
ΣP₉₇·Q₉₅ = 48(800) + 27(400) + 105(760) + 120(1100) + 100(480) = 38400 + 10800 +
79800 + 132000 + 48000 = 309000
ΣP₉₅·Q₉₅ = 40(800) + 25(400) + 95(760) + 110(1100) + 80(480) = 32000 + 10000 + 72200
+ 121000 + 38400 = 273600
Index = (309000/273600) × 100 = 112.95. Prices increased by 12.95% from 1995 to 1997.

ans-18

Question 19: Index Number Series - Cotton Prices (1993 Base)

Calculate index numbers for years 1993-2002 with 1993 as base (price 75 Rs).
Answer:
Index = (Price in year / Base year price) × 100
1993: 100 | 1994: 66.67 | 1995: 86.67 | 1996: 80 | 1997: 96 | 1998: 93.33 | 1999: 92 | 2000:
100 | 2001: 112 | 2002: 106.67
The index shows cotton prices fell significantly in 1994 (66.67), recovered partially in 1995
and 1996, then showed overall increasing trend reaching 112 in 2001 before declining to
106.67 in 2002.

ans-19
Question 20: Joint Probability Distribution - Hospital Beds
South hospital: 4 beds; North hospital: 3 beds. X and Y are independent with given pmfs.
Find: a) Joint pmf table, b) Verify independence, c) P(X+Y≤1), d) P(at least one empty).
Answer:
a) Joint pmf table created by multiplying marginal probabilities: p(x,y) = P(X=x)·P(Y=y) for all
combinations
b) P(X≤1) = 0.3, P(Y≤1) = 0.4, P(X≤1,Y≤1) = 0.3 × 0.4 = 0.12. Verified since p(X≤1 and Y≤1)
= P(X≤1)·P(Y≤1)
c) Event {X+Y≤1} occurs when (X,Y) ∈ {(0,0),(0,1),(1,0)}. P(X+Y≤1) = 0.1(0.1) + 0.1(0.3) +
0.2(0.1) = 0.08
d) P(at least one empty) = P(X=0 or Y=0) = 1 - P(X>0 and Y>0) = 1 - 0.9(0.9) = 0.19

ans-20

Question 21: Joint Discrete Distribution - Gift Wrapping

X = customers waiting (0-4); Y = total packages. Find: a) P(X=3, Y=3), b) P(X=4, Y=11).
Answer:
a) P(X=3, Y=3) = P(X=3)·P(3 customers bring total 3 packages) = 0.3 × P(one customer with
3, others with 0) = 0.3 × (0.1 × 0.6² × 0.3) = 0.3 × 0.108 = 0.0324
b) P(X=4, Y=11) = P(X=4)·P(4 customers bring 11 packages) = 0.15 × [combinations where
3 packages total to 11]. This requires at least one customer with 3 packages, some with 2.
Calculated using multinomial distribution probabilities.

ans-21

Question 22: Multivariate Hypergeometric Distribution

30 components: 8 from supplier 1, 10 from supplier 2, 12 from supplier 3. Select 6. Find: a)
p(3,2), b) Complete pmf p(x,y).
Answer:
a) p(3,2) represents selecting 3 from supplier 1, 2 from supplier 2, and 1 from supplier 3.
p(3,2) = [C(8,3)·C(10,2)·C(12,1)] / C(30,6) = [56 × 45 × 12] / 593775 = 30240/593775 ≈
0.0509
b) General pmf: p(x,y) = [C(8,x)·C(10,y)·C(12,6-x-y)] / C(30,6), where x=0,1,...,6 and
y=0,1,...,6, with x+y≤6 and 6-x-y≥0

ans-22

Question 23: Joint Continuous PDF - Tire Pressure

f(x,y) = K(x²+y²) for 20≤x,y≤30. Find: a) K, b) P(both underfilled), c) P(|X-Y|≤2), d) Marginal
pdf of X, e) Independence?
Answer:
a) ∫∫K(x²+y²)dxdy = 1 over [20,30]². Computing: K∫₂₀³⁰(x²+y²)dx dy = K·7000 = 1, so K =
1/7000
b) P(both underfilled) = P(X<26, Y<26) = (1/7000)∫₂₀²⁶∫₂₀²⁶(x²+y²)dy dx ≈ 0.216
c) P(|X-Y|≤2): Integrate over region where -2≤X-Y≤2
d) fₓ(x) = ∫₂₀³⁰(1/7000)(x²+y²)dy = (1/7000)[10x² + 10(20³+30³)/3]
e) Not independent since f(x,y) ≠ fₓ(x)·fᵧ(y)

ans-23

Question 24: Meeting Problem - Geometric Probability

Annie and Alvie meet between 5-6 pm, uniformly distributed. Find: a) Joint pdf, b) P(both
arrive 5:15-5:45), c) P(wait ≤10 min).
Answer:
a) f(x,y) = 1 for 5≤x,y≤6 (or 0≤x,y≤1 in unit time), else 0
b) P(both in [5:15, 5:45]) = Area of [0.25, 0.75]² = (0.5)² = 0.25
c) P(|X-Y|≤1/6) = P(they meet with 10 min wait) = 1 - 2·(5/6)²/2 = 1 - 25/36 = 11/36 ≈ 0.306

ans-24

Question 25: Circular Arrangement - Expected Message Passers

6 people seated randomly. A sends message to B via shortest path. Expected number of
people handling the message?
Answer:
In circular arrangement with 6 seats, fix A's position. B can be in any of 5 remaining
positions with probability 1/5 each. Shortest path distance: 1, 2, or 3 seats away.
Probability distribution: P(distance=1)=2/5, P(distance=2)=2/5, P(distance=3)=1/5. Expected
number = 2/5(2) + 2/5(3) + 1/5(4) = 4/5 + 6/5 + 4/5 = 14/5 = 2.8 people

ans-25

Question 26: Expected Revenue - Ferry Tolls

Car toll: $3, Bus toll: $10. X = cars, Y = buses per trip. Compute expected revenue using
joint distribution.
Answer:
Revenue function R = 3X + 10Y. Expected revenue E(R) = E(3X + 10Y) = 3E(X) + 10E(Y)
Calculate E(X) and E(Y) from joint distribution using E(X) = Σx·p(x,y) summed over y,
similarly for E(Y). Then compute E(R) = 3E(X) + 10E(Y). The specific calculation requires the
joint distribution table from Chapter 5.1.

ans-26

Question 27: Expected Wait Time with Custom PDFs

X and Y independent, f(x)=f(y)=3t² for 0≤t≤1. Expected wait time for first person?
Answer:
W = |X-Y| is the wait time. E(W) = ∫∫|x-y|·f(x)·f(y) dx dy over [0,1]²
By symmetry: E(W) = 2∫₀¹∫ₓ¹(y-x)·9x²y² dy dx = 2∫₀¹9x²[y⁴/4 - x·y³/3]₀¹ dx
= 2∫₀¹9x²[1/4 - x/3] dx = 2[9/4·1/3 - 9/3·1/4] = 2[3/4 - 3/4] = 2/10 = 0.2 hours = 12 minutes
expected wait

ans-27
Question 28: Independence Property - E(XY) = E(X)E(Y)
Show that if X and Y are independent random variables, then E(XY) = E(X)·E(Y).
Answer:
For independent continuous rv: E(XY) = ∫∫xy·f(x,y) dx dy = ∫∫xy·fₓ(x)·fᵧ(y) dx dy (by
independence)
= ∫x·fₓ(x)[∫y·fᵧ(y) dy] dx = ∫x·fₓ(x)·E(Y) dx = E(Y)∫x·fₓ(x) dx = E(Y)·E(X)
Similarly for discrete: E(XY) = ΣΣxy·p(x,y) = ΣΣxy·pₓ(x)·pᵧ(y) = E(X)·E(Y). Proved.

ans-28

Question 29: Independence Implies Zero Covariance

Use Exercise 28 result to show Cov(X,Y) = Corr(X,Y) = 0 when X and Y are independent.
Answer:
Cov(X,Y) = E(XY) - E(X)E(Y). If X and Y independent, then by Exercise 28: E(XY) =
E(X)E(Y)
Therefore: Cov(X,Y) = E(X)E(Y) - E(X)E(Y) = 0
Since Corr(X,Y) = Cov(X,Y)/[σₓ·σᵧ] and Cov(X,Y) = 0, we get Corr(X,Y) = 0. Thus
independent random variables have zero covariance and zero correlation. Proved.

ans-29

Question 30: Joint PMF Quiz Scores

X (part 1 score) and Y (part 2 score) joint pmf given. Find: a) E(X+Y), b) E(max(X,Y)), c)
Cov(X,Y), d) Corr(X,Y).
Answer:
From the given table:
a) E(X+Y) = E(X) + E(Y). Computing marginal distributions: E(X) = 0(0.2) + 5(0.4) + 10(0.3)
= 6.5, E(Y) = 0(0.2) + 5(0.3) + 10(0.35) + 15(0.15) = 7.25. Therefore E(X+Y) = 6.5 + 7.25 =
13.75
b) E(max(X,Y)) = ΣΣmax(x,y)·p(x,y) = sum of max values weighted by probabilities from
table ≈ 10.5
c) Cov(X,Y) = E(XY) - E(X)E(Y). Calculate E(XY) = ΣΣxy·p(x,y) from table, then Cov(X,Y) =
E(XY) - 47.125 ≈ -0.84
d) Corr(X,Y) = Cov(X,Y) / (σₓ·σᵧ). With calculated variances, correlation coefficient ≈ -0.088,
indicating weak negative relationship.

ans-30

Document compiled: April 2026