ISS 2017 Statistics Paper-1 Solution: Question 9 (First Moment of a Density)
Continuing our question-by-question walk through the ISS Statistics Paper-1 previous year papers, we now move to the 2017 paper. Today's question looks short, but it hides a lovely shortcut that most students miss the first time they see it, so we will work through it both the "long" way and the "smart" way.
Quick Summary
Topic: Continuous probability distributions — finding the normalizing constant and the first moment about the origin (the mean)
Question Reference: ISS 2017, Statistics Paper-1, Question 9
Correct Answer: Option (a) — E(X) = 1
The Question
In a continuous distribution, the probability density function is given by
f(x) = y0 x(2 − x), for 0 ≤ x ≤ 2, and f(x) = 0 otherwise, where y0 is a constant.
Its first moment about the origin is given by
(a) 1
(b) 2
(c) 3
(d) 4
Step 1: Understand What "First Moment About the Origin" Means
Before touching any algebra, it helps to be absolutely clear on the terminology, because this is exactly where many students lose marks. The "r-th moment about the origin" of a continuous random variable X, usually written μr', is defined as:
μr' = E(Xr) = ∫ xr f(x) dx
So the first moment about the origin is simply r = 1, which gives μ1' = E(X) = ∫ x f(x) dx. In plain language, this question is just asking us to find the mean of the distribution. Do not confuse this with the first moment about the mean, which is always 0 by definition — that trap is a favourite among MCQ setters.
Step 2: Check That f(x) Is a Valid Density First
Here is a step almost everyone is tempted to skip. We are told f(x) = y0 x(2 − x) is a probability density function, which means it must satisfy the basic rule that the total area under the curve equals 1:
∫02 f(x) dx = 1
So before we can compute any moment, we first need to pin down the value of the unknown constant y0. Let's expand the integral:
∫02 y0 x(2 − x) dx = y0 ∫02 (2x − x2) dx
Step 3: Evaluate the Normalizing Integral
Integrate term by term, using the standard rule ∫xⁿ dx = xⁿ⁺¹/(n+1):
∫02 (2x − x2) dx = [ x2 − x3/3 ]02
Now substitute the limits. At x = 2: 22 − 23/3 = 4 − 8/3 = 12/3 − 8/3 = 4/3. At x = 0, every term is 0.
So ∫02 (2x − x2) dx = 4/3.
Step 4: Solve for the Constant y0
Going back to our normalization condition:
y0 × (4/3) = 1
Multiplying both sides by 3/4:
y0 = 3/4
So the complete, valid density function is f(x) = (3/4) x(2 − x) for 0 ≤ x ≤ 2.
Step 5: Compute the First Moment, E(X)
Now we apply the formula from Step 1 using our now-known f(x):
E(X) = ∫02 x · f(x) dx = ∫02 x · (3/4) x(2 − x) dx = (3/4) ∫02 x2(2 − x) dx
Expand the integrand first:
x2(2 − x) = 2x2 − x3
So we need:
(3/4) ∫02 (2x2 − x3) dx = (3/4) [ 2x3/3 − x4/4 ]02
Substituting x = 2: 2(23)/3 − 24/4 = 16/3 − 16/4 = 16/3 − 4 = 16/3 − 12/3 = 4/3.
So E(X) = (3/4) × (4/3) = 1.
Step 6: Final Answer and Verification
We get E(X) = 1, which is exactly option (a). This matches the official ISS 2017 Statistics Paper-1 answer key, which also lists the answer to Question 9 as (a).
Pro Tip: Before you ever set up an integral for a mean, glance at the density for symmetry — it can save you the entire calculation. Here, write x = 1 + t. Then x(2 − x) = (1 + t)(1 − t) = 1 − t². Now write x = 1 − t instead: x(2 − x) = (1 − t)(1 + t) = 1 − t² again — the exact same value. This means the density is perfectly symmetric about x = 1 (it looks like a little hill peaking at x = 1 and falling away equally on both sides). Whenever a density is symmetric about some point "a" over its entire support, the mean is automatically equal to "a" — no integration needed at all. So the moment you spot this symmetry, you already know E(X) = 1, and the long calculation above becomes a nice way to double-check rather than the only way to solve it. This habit of scanning for symmetry before reaching for the integral sign is something students are usually drilled on repeatedly until it becomes automatic, because in a two-hour, 80-question paper, every integral you skip is time you get back.
Why This Question Matters
This question is really testing two separate ISS Paper-1 fundamentals bundled into one: (1) the idea that any valid pdf must integrate to 1 over its support, which is how you solve for unknown constants, and (2) the definition of moments, which quietly underlie almost every later topic — variance, skewness, kurtosis, moment generating functions, and even estimation theory in Paper-2.Getting comfortable with moments about the origin versus moments about the mean early on removes a huge amount of confusion later. Coaching for the ISS exam, such as at Sunrise Classes, tends to emphasize this exact combination — normalize first, then compute — because it is one of the most frequently recycled question patterns across multiple years of the paper.
Frequently Asked Questions
What exactly does "first moment about the origin" mean in statistics?
It refers to E(X), the expected value or mean of the random variable, computed as ∫ x f(x) dx over the support of the distribution. The word "origin" simply tells you to measure x from 0, as opposed to measuring deviations from the mean.
Why do we need to find y0 before computing the moment?
Because f(x) only becomes a genuine probability density function once the total area under it equals 1. Until y0 is fixed by that condition, f(x) = y0 x(2 − x) is just a shape, not a probability distribution, so any moment computed from it would be meaningless.
How is the first moment about the origin different from the first central moment?
The first moment about the origin is E(X), the mean itself. The first central moment is E(X − μ), the average deviation from the mean, and this always equals 0 for any distribution by the very definition of the mean. Exam setters often ask about "the first central moment" purely to see if you will mistakenly answer with the mean instead of 0.
Can we find the mean of this distribution without doing any integration?
Yes, in this particular case. Since f(x) = y0 x(2 − x) is symmetric about x = 1 over its entire support [0, 2], the mean must equal 1 purely by the symmetry argument, with no integration required. This shortcut works for any density that is symmetric about a point within its support.
What if the question had asked for the second moment about the origin instead?
You would compute E(X²) = ∫02 x² f(x) dx using the same y0 = 3/4 found in Step 4. From E(X²) and E(X), you could then also get the variance using Var(X) = E(X²) − [E(X)]².
Is this density a known, named distribution?
Yes — f(x) = y0 x(2 − x) on [0, 2] is a special case of a symmetric triangular-type parabolic density, and more specifically it is a rescaled Beta-type density on the interval [0, 2]. Recognizing such standard shapes can make future questions in this series faster to solve.
If anything in this derivation felt shaky, drop a comment below and we'll work through it together — and if you found this useful, go ahead and share it with a fellow ISS aspirant who might be stuck on the same question.

Comments