Biostatistics · Intermediate

Continuous Distribution

Written by SignalsLab

Early edition: these lessons are being reviewed.

Content

Summary

Continuous random variables assume an infinite number of values within a range, requiring probabilities to be calculated as the area under the probability density function (PDF) curve. The normal distribution is a primary continuous example defined by its mean and standard deviation, while the Poisson distribution models discrete counts of events in fixed intervals.

Intuition

To understand continuous distributions, imagine measuring blood pressure. Unlike counting people (discrete), blood pressure can be any value within a range, meaning the chance of it being exactly 120.000... is zero. Instead, we look at the probability of it falling within an interval, like 110 to 130, which corresponds to the area under the bell-shaped normal curve. For counts, like disease deaths, we use the Poisson distribution, which handles rare events over time. Here, the probability depends on the rate of events and the time interval, with the mean and variance being equal.

Key equations

f(x)=1σ2πe−(x−μ)22σ2
(1)

The probability density function for the normal distribution, where μ is the mean and σ is the standard deviation.

P(X=k)=μke−μk!
(2)

The probability mass function for the Poisson distribution, where μ=λt is the expected number of events in time t.

Derivation

  1. Continuous variables have infinite possible values, so probability is defined by the area under the PDF curve, not point values.
  2. The normal distribution is symmetric and bell-shaped, defined by mean (center) and standard deviation (spread).
  3. Changing the mean shifts the curve horizontally; changing the standard deviation alters the width and height.
  4. The Poisson distribution models discrete counts based on assumptions: probability of one event scales with interval size, probability of zero events is approx 1−λΔt, and probability of >1 event is negligible.
  5. The Poisson PMF is derived from these assumptions, with mean and variance both equal to μ.

Worked example

Problem

Given a normal distribution of systolic blood pressures with mean 120 and standard deviation 20, determine the range capturing 99.7% of values. Also, if disease deaths follow a Poisson distribution with μ=4.6 per year, what is μ for a six-month period?

  1. For the normal distribution, the empirical rule states 99.7% of values lie within three standard deviations of the mean.
  2. Calculate lower bound: 120 - 3(20) = 60.
  3. Calculate upper bound: 120 + 3(20) = 180.
  4. For the Poisson distribution, μ scales linearly with time. For six months (t=0.5 years), multiply the annual μ by 0.5.
  5. Calculate new μ:4.6∗0.5=2.3.

Answer Normal range: 60 to 180. Poisson μ for six months: 2.3.

Common mistakes

  • Confusing the normal distribution (continuous) with the binomial or Poisson distributions (discrete).
  • Calculating the probability of a continuous variable taking an exact single value, which is always zero.
  • Forgetting that for Poisson distributions, the mean and variance are equal.
  • Incorrectly scaling the Poisson parameter μ for different time intervals.

Animation

Animation coming soon

The animated version of this lesson is being prepared for the web. In the Signals AI app, lessons are drawn step by step.

Code

This is a text lesson: it has no animation code yet.

ccBYNC© 2026 SignalsLab. Lesson text shared as is under CC BY-NC 4.0.