inverse normal problems and finding unknown values — HSC mathematics advanced, live

Inverse Normal Problems and Finding Unknown Values

A forward normal question gives you a value and asks for a probability. An inverse question runs the other way: you are given the probability first, use Φ⁻¹ to find the z-score that cuts off that area, and then rebuild the real quantity with x = μ + zσ. The curve never changes shape; μ and σ only decide what the ruler under it says, so the same equation can be rearranged to find a missing mean or standard deviation instead of a missing value. This is the real knowscape from knowhere, not a picture of one. Drag it. Watch what actually changes.

mathematics advanced · statistical analysis · inverse normal problems and finding unknown valuesdrag it · it is yours

why this one carries the topic.

Statistics is the art of turning a scatter of individual points into one shape you can reason about. Once you know a distribution's centre and spread, the z-score turns any value into a distance — how far from normal, in standard deviations — and correlation measures how tightly two shapes move together, never whether one causes the other.

A normal curve with a shaded tail whose area you set, a live z ruler showing Φ⁻¹ of that area, and an x ruler beneath it labelled μ − 3σ to μ + 3σ, so the value x = μ + zσ is read straight off the picture and swaps tails with the toggle.

what examiners catch — Students look up Φ⁻¹(0.20) when the question gives the top 20%, producing z = −0.84 instead of +0.84, and then forget to convert z back to the original units. Write the upper-tail statement as a left area first, find z, then write x = μ + zσ and rearrange for whichever letter the question has left unknown.

five things, not forty.

Inverse normal, Φ⁻¹, takes a probability (area to the left) as input and returns the z-score that cuts off that area.

The nth percentile is the value below which n% of the data falls, so it is Φ⁻¹(n/100) in z, then x = μ + zσ in the original units.

An upper-tail probability must be turned into a left area first: P(X > x) = 0.2 means Φ⁻¹(0.8) ≈ 0.84, and by symmetry Φ(−z) = 1 − Φ(z).

If x is known but μ or σ is not, rearrange the same equation: μ = x − zσ or σ = (x − μ)/z; two probability facts give two simultaneous equations.

Changing μ or σ never moves the shaded area: the probability lives on the z ruler, and μ and σ only relabel the x ruler beneath it.

nothing here is a standalone fact.

knowhere maps every concept to what it rests on and what rests on it — 4 underneath this one, 0 built on top. Each one says why, in a sentence, not as an arrow on a diagram.

this conceptinverse normal problems and finding unknown valuesA normal curve with a shaded tail whose area you set, a live z ruler showing Φ⁻¹ of that area, and an x ruler beneath it labelled μ − 3σ to μ + 3σ, so the value x = μ + zσ is read straight off the picture and swaps tails with the toggle.

sits under itcalculating probabilities using the normal distributionbecause backwards needs forwards

sits under itthe standard normal distribution and z-scoresbecause unknown μ and σ problems only unlock through z

sits under itinverse functionsbecause Φ⁻¹ undoes Φ exactly as any inverse function does

sits under itcontinuous random variables and pdfsbecause probability as area under a density curve

6 more, same treatment.

Each one is its own knowscape in the app — built for how a particular student takes things in, not one explanation handed to everybody.

expected value and mean of discrete random variablesin the appdefinition and properties of discrete random variablesin the appcalculating probabilities using the normal distributionin the appcontinuous random variables and pdfsin the appthe standard normal distribution and z-scoresin the appvariance and standard deviation of discrete random variablesin the app

they don't read it. they run it.

Every HSC and VCE concept in knowhere is built like this one — mapped to your curriculum, never capped by it. Free for a week. No lock-in, cancel inside the week and pay nothing.

the 2026 exam pass

Free for a week, then one payment. It ends itself after the last exam — no subscription.

$49 once. 0 days left

Free for a week, then a plan you can stop any time.

not your card? send it to whoever's is.