MATH2209 Chap.4 Normal Distributions and Z Scores
Normal Distributions and Z Scores
The normal model describes a symmetric continuous distribution through its mean and standard deviation. Standardisation maps a raw value to its signed distance from the mean, allowing one standard normal scale to answer probability questions across different measurements.
This chapter separates location from area, sketches the requested tail before using a table, and reverses the transformation for percentile questions while preserving signs and units.
What this chapter covers
- 01
Normal curve properties
- 02
Standard normal scale
- 03
Raw values and z scores
- 04
Left and right tail areas
- 05
Between-value probabilities
- 06
Inverse normal calculations
Worked example · free
Find an upper-tail heart-rate probability
- 1z = (85 - 70) / 10 = 1.50.
- 1The value is 1.5 standard deviations above the mean.
- 1The required region is the upper tail, not the supplied left area.
- 1P(X > 85) = 1 - 0.9332 = 0.0668.
Key terms
- Normal Distribution
- A symmetric continuous probability distribution defined by its mean and standard deviation.
- Z Score
- Signed distance from a mean measured in standard-deviation units.
- Upper Tail
- The area under a distribution to the right of a stated boundary.
Normal Distributions and Z Scores FAQ
Why can a positive z score have a large probability?
The z score only locates a boundary. The area to its left may be large, while the area to its right is small. Probability size depends on which region the question requests, not on the sign alone.
How do inverse normal questions work?
Begin with the percentile area, find its standard normal z value, then return to the raw scale with x = mean + z times standard deviation. A lower percentile should produce a negative z and a raw value below the mean.
Does inclusive wording matter for a normal variable?
For a continuous model, the probability at one exact point is zero. Therefore P(X below a) and P(X at or below a) are equal under the model, although the distinction can matter for discrete distributions.
How do I separate location from tail area?
Calculate and interpret z first: its sign says which side of the mean contains the boundary, and its magnitude gives distance in standard-deviation units. Next draw the normal curve and shade the event requested by the words above, below or between. Only then use a cumulative area or complement. A high positive z can have a large area to its left and a small area to its right, so sign alone never determines probability size.
For inverse work, predict which side of the mean the percentile must occupy, find z and return with x equal to mu plus z times sigma. Restore the raw measurement unit and check that the final direction matches the original sketch.
Assessment move
Draw a small bell curve for every question, mark the mean and boundary, and shade the requested region. Treat location and area as two separate decisions. First calculate z=(x-mu)/sigma and interpret its sign and magnitude in standard-deviation units. Only then decide whether the requested probability is left, right or between two values.
Write the available table or software area beside the sketch and use a complement only when the shaded region requires it. This sequence prevents a positive z score from being mistaken automatically for a small probability. Create paired drills with boundaries equally far below and above the mean. Use symmetry to predict which tail areas match, then verify numerically.
Include between-area questions in which two cumulative probabilities must be subtracted. Label each endpoint before subtracting so that the smaller left area is removed from the larger one. Retain several decimal places until the final percentage. For inverse questions, start from the target cumulative area, find z and then use x=mu+z sigma. Before calculating, predict whether the answer must lie below or above the mean.
The sign of z and the final raw value should agree with that prediction. Restore the measurement unit in the last line because z itself is dimensionless. Mix direct and inverse questions so that the requested output, not a memorised formula order, controls the method. Add a model-check sentence to longer answers: the calculation assumes a normal population or an appropriate normal approximation.
A probability from a theoretical curve does not prove that an observed biological dataset is normal. Finish revision sessions with a tail-language audit. Translate above, below, at most, at least and between into inequalities and shaded regions without numbers. Then solve one full problem from raw value through z, area, complement if needed and contextual interpretation.
Your written conclusion should name the population, measurement and requested region rather than merely repeat the calculator output.
Working through Normal Distributions and Z Scores in MATH2209? Sia is AskSia’s AI Statistics tutor — ask any MATH2209 Normal Distributions and Z Scores question and get a clear, step-by-step explanation grounded in how MATH2209 is taught and assessed. Read this chapter free, then take your hardest questions to Sia.