BUSS1020 Chap.5 Continuous Probability Distributions
Continuous Probability Distributions
Continuous probabilities are areas beneath density curves rather than probabilities at exact points. This chapter compares the constant-density uniform model, the symmetric normal model and the right-skewed exponential waiting-time model. It develops normal standardisation, direction checks and normality assessment, then keeps rate and time units aligned for exponential probabilities.
The practice questions show why clock readings must become interval lengths and why a density height is not itself a probability. Sketches do real analytical work: they determine the requested tail, reveal whether the result should exceed one half and distinguish interval area from curve height. The service-level example adds a model audit rather than assuming every dataset is normal.
Uniform and exponential drills use monotonicity checks so probabilities move sensibly as intervals widen or waiting thresholds increase. The final review compares model predictions with fresh observed performance and treats systematic tail misses as evidence about skew, changing variance or a process shift. This makes model checking part of the method rather than an optional sentence.
Label every shaded interval and axis unit before using software so the returned decimal still answers the original continuous event.
What this chapter covers
- 01
Density and interval probability
- 02
Continuous uniform distribution
- 03
Normal distribution and standardisation
- 04
Assessing approximate normality
- 05
Exponential waiting-time model
- 06
Units, tails and direction checks
Worked example · free
Evaluate a delivery service threshold
- 1Sketch the area to the left of 60 on a bell curve centred at 52.
- 1Standardise with z equal to 60 minus 52 divided by 6, giving 1.3333.
- 1Use the cumulative standard-normal area at 1.3333, approximately 0.9088.
- 1Interpret that the model predicts about 90.88 per cent meet the threshold.
- 1State that the conclusion depends on the normal model and representative data.
Key terms
- Density curve
- A nonnegative curve whose interval areas represent continuous probabilities and whose total area is one.
- Uniform distribution
- A continuous model with constant density between two bounds.
- Normal distribution
- A symmetric bell-shaped family controlled by a mean and standard deviation.
- Standard normal
- The normal distribution with mean zero and standard deviation one.
- Exponential distribution
- A right-skewed waiting-time model associated with a constant-rate Poisson process.
Continuous Probability Distributions FAQ
Why is an exact continuous value assigned zero probability?
A single point has no width and therefore no area beneath a continuous density curve. Intervals carry probability. This does not mean the value is impossible; it means probability is represented through ranges rather than isolated points.
How do I avoid choosing the wrong normal tail?
Sketch the bell curve, mark the mean and threshold, and shade the requested region. Standardise as observed threshold minus mean over standard deviation. Then check whether a threshold above the mean should produce a left area above one half.
When is an exponential model unsuitable?
The model can fail when event rates change predictably, arrivals cluster or scheduled behaviour creates dependence. A single constant rate then averages away operational structure. Match time and rate units and assess whether the process assumptions are credible.
Exam move
Practise continuous questions as geometry first. Mark the support, bounds and requested area before writing a formula. For normal probabilities, predict whether the answer is above or below one half and whether it is a left, right or middle area. Rehearse standardisation with observed value minus mean. For uniform problems, use interval lengths rather than raw clock labels.
For exponential problems, convert rate and time into matching units and state the stable-rate assumption. Compare histogram, outlier and symmetry evidence before relying on a normal model. Draw the three densities on a common axis and explain what feature of the process creates each shape. Shade several normal regions before touching a table, including between, below and above questions.
Use a symmetric pair of z-scores to check that left and right tail areas match. For a uniform model, clip the favourable interval to the stated support and divide lengths in the same unit. For an exponential model, calculate survival at two thresholds and confirm that the longer wait has the smaller probability. Write the rate as events per hour or per minute beside every exponent so dimensional mistakes are visible.
Treat normality as a collection of evidence rather than a yes-or-no label: inspect shape, outliers and the decision's sensitivity to tails. When the model is questionable, state which assumption is weak and what alternative display or analysis would help. End each probability with a sentence about a randomly selected observation under the stated model, not a certainty about an individual future case.
Working through Continuous Probability Distributions in BUSS1020? Sia is AskSia’s AI Statistics tutor — ask any BUSS1020 Continuous Probability Distributions question and get a clear, step-by-step explanation grounded in how BUSS1020 is taught and assessed. Read this chapter free, then take your hardest questions to Sia.