ISS 2017 Statistics Paper-1 Solution: Question 4 (Uniform Distribution Probability Assertions)
Continuing our question-by-question walkthrough of the ISS Statistics Paper-1 previous year papers, today we move to Question 4 of the 2017 paper. This one tests whether you really understand what the Uniform distribution can and cannot produce — a conceptual trap that catches a lot of aspirants who rush through probability questions without checking the support of the distribution first.
Quick Summary
Topic:Continuous Uniform distribution U(0,1) and probability assertions
Question Reference:ISS 2017, Statistics Paper-1, Question 4
Correct Answer:(c) Both 1 and 2
The Question
Let X, a continuous random variable, follow U(0, 1) distribution. Then, we assert that
P(X ≥ 0.27) = 0.73
P(0.27 < X < 1.27) = 0.73
Which of the above assertions is/are correct?
(a) 1 only
(b) 2 only
(c) Both 1 and 2
(d) Neither 1 nor 2
Step 1: Write Down What U(0, 1) Actually Means
Before touching either assertion, it helps to write the probability density function (pdf) of X explicitly. Since X ~ U(0, 1), its pdf is
f(x) = 1, for 0 ≤ x ≤ 1, and f(x) = 0 everywhere else.
This second part — f(x) = 0 outside [0, 1] — is the entire question. A Uniform(0, 1) random variable is physically incapable of taking any value less than 0 or greater than 1. Whatever happens in the interval (1, 1.27) simply cannot contribute any probability, because the density there is zero.
From this pdf, the cumulative distribution function (CDF) is obtained by integrating f(x) from the lower limit up to x:
F(x) = 0, for x < 0F(x) = x, for 0 ≤ x ≤ 1F(x) = 1, for x > 1
Step 2: Check Assertion 1 — P(X ≥ 0.27) = 0.73
For any continuous random variable, P(X ≥ a) = 1 − P(X < a) = 1 − F(a), because a single point carries zero probability for a continuous distribution.
Here a = 0.27, which lies inside [0, 1], so we use F(x) = x directly:
P(X ≥ 0.27) = 1 − F(0.27) = 1 − 0.27 = 0.73
This matches the assertion exactly. So Assertion 1 is correct.
Step 3: Check Assertion 2 — P(0.27 < X < 1.27) = 0.73
This is where most students either second-guess themselves or make an error, because the interval (0.27, 1.27) seems to stretch beyond the support of X. Let's handle it carefully using the CDF formula for an interval probability:
P(0.27 < X < 1.27) = F(1.27) − F(0.27)
Now, 1.27 is greater than 1, which is the upper limit of the support. From the CDF we wrote above, F(x) = 1 for any x > 1. So:
F(1.27) = 1
And since 0.27 lies inside [0, 1]:
F(0.27) = 0.27
Putting these together:
P(0.27 < X < 1.27) = F(1.27) − F(0.27) = 1 − 0.27 = 0.73
So even though the interval extends past the value 1, the probability mass beyond 1 is exactly zero, and the computed probability still comes out to 0.73.Assertion 2 is also correct.
Pro Tip: The trick in this question is not computational — it's about recognizing that extending an interval into a region with zero density changes nothing numerically. Whenever an interval in a Uniform (or any bounded-support) distribution question stretches past the support's boundary, just replace that boundary value with F = 1 (or F = 0 on the lower side) and continue the same subtraction you'd do normally. The way this kind of question is usually taught is to first write out F(x) piece by piece for all three regions — below, inside, and above the support — before touching the actual numbers in the question. Do that consistently and these assertion-reasoning uniform distribution questions stop being tricky at all.
Step 4: Compare the Two Assertions and Pick the Final Answer
We found:
Assertion 1: P(X ≥ 0.27) = 0.73 — Correct
Assertion 2: P(0.27 < X < 1.27) = 0.73 — Correct
Since both assertions evaluate to true, the correct option is (c) Both 1 and 2.
Cross-checking against the official ISS 2017 Statistics Paper-1 answer key, the listed answer for Question 4 is also C, so our independently derived solution matches the official key exactly.
Why This Question Matters
This question is a classic example of an assertion-type MCQ designed to test conceptual clarity rather than calculation speed. It specifically checks whether a student blindly trusts the numbers written in the interval (1.27 here) or actually goes back to the definition of the distribution's support. Questions like this appear repeatedly across ISS, IIT JAM(MS), and GATE(ST) papers in slightly different disguises — sometimes with Exponential, Normal, or Binomial distributions instead of Uniform — so mastering the underlying logic (not just this one numeric answer) pays off well beyond this single question.
Frequently Asked Questions
Why is P(X = a) always zero for a continuous random variable like the Uniform distribution?
For a continuous random variable, probability corresponds to the area under the pdf curve over an interval, not to a single point. A single point has zero width, so the area (and hence the probability) at exactly that point is always zero. This is why P(X ≥ a) and P(X > a) are equal for continuous distributions, even though they'd differ for a discrete random variable.
Does it matter whether the inequality signs in a Uniform distribution probability are strict or non-strict?
No, not for continuous distributions. Since individual points carry zero probability, P(X < a), P(X ≤ a), P(X > a), and P(X ≥ a) all behave consistently via the CDF, and whether you use strict or non-strict inequalities in an interval makes no numerical difference to the final probability.
What is the general formula for probability under a Uniform(a, b) distribution?
For X ~ U(a, b), the probability that X lies between two points c and d (with a ≤ c ≤ d ≤ b) is simply (d − c)/(b − a). This is because the pdf is constant at 1/(b − a) over the support, so probability is just proportional to interval length.
What happens if an interval in a probability question extends beyond the distribution's support on both sides?
You simply cap the CDF at its boundary values: F(x) = 0 for any x below the lower limit of support, and F(x) = 1 for any x above the upper limit. The actual probability is then determined only by the portion of the interval that overlaps the true support.
Is the mean of a U(0, 1) distribution relevant to solving this kind of assertion question?
Not directly for this particular question, since it only asks about probabilities over intervals, not about expectation. However, knowing that E(X) = (a + b)/2 = 0.5 and Var(X) = (b − a)2/12 = 1/12 for U(0, 1) is useful general knowledge, as ISS papers frequently follow up a probability-interval question with a moments-based one on the same distribution.
How many such assertion/reasoning-style questions typically appear in an ISS Statistics Paper-1?
Assertion-based questions (where you evaluate two or more statements and choose a combination) appear fairly frequently across ISS Paper-1 papers, often clustered in the probability and distribution theory sections. Practicing a good number of them — ideally by writing out the full CDF or pdf each time rather than relying on memorized shortcuts, a habit built through steady drilling at a place like Sunrise Classes — builds the kind of reliability needed to avoid silly errors under exam time pressure.
If anything in this derivation feels unclear, or if you solved it differently, drop a comment below — working through the disagreement is often the fastest way to fix a shaky concept. And if you found this useful, do share it with a fellow ISS aspirant who's revising probability distributions right now.

Comments