6.4
Histogrammes de probabilité
Un histogramme de probabilité est une représentation visuelle d'une distribution de probabilité. Semblable à un histogramme classique, l'histogramme d…
Les histogrammes de probabilité fournissent des informations visuelles sur le centrage et la propagation des distributions de probabilité qui sont difficiles à comprendre sous forme de tableaux.
Prenons le cas du nombre de sièges occupés dans un covoiturage.
Sur la base de l’observation quotidienne, la probabilité qu’un nombre quelconque de sièges soit occupé entre un et cinq est calculé. Ici, le nombre de sièges occupés est la variable aléatoire.
Le tracé d’un histogramme avec le nombre de sièges occupés sur l’axe des X et les probabilités correspondantes sur l’axe des Y crée un histogramme de probabilité.
Chacune de ces barres rectangulaires a une unité de large. Cela signifie que l’aire de chaque rectangle représente également la probabilité de chaque résultat.
Pour obtenir plus d’informations sur les données, la moyenne et la variance peuvent être calculées à l’aide de la table de distribution.
Pour trouver la moyenne, multipliez x par la probabilité correspondante et additionnez-les.
De même, multipliez le carré de la moyenne x moins la population par la probabilité, et additionnez-les pour obtenir la variance.
La racine carrée de la variance donne l’écart-type.
View the full transcript and gain access to JoVE Core videos
Q1: What is a probability histogram and how is it constructed?
A probability histogram is a visual representation of a probability distribution using contiguous rectangular bars. The horizontal axis displays the random variable (such as the number of seats occupied), while the vertical axis shows probability. Each bar is exactly one unit wide, making the area of each rectangle equal to the probability of that outcome.
Q2: Why is the area under each bar in a probability histogram important?
In a probability histogram, the area of each rectangular bar represents the probability of that specific outcome. Since each bar is one unit wide, the height directly equals the probability. This area-probability relationship is fundamental in statistics for understanding how probability distributions are visualized and interpreted.
Q3: How do you calculate the mean from a probability histogram?
To find the mean from a probability histogram, multiply each value of the random variable by its corresponding probability, then sum all these products. This calculation uses the distribution data displayed in the histogram to determine the center or average value of the probability distribution.
Q4: What is the relationship between variance and standard deviation in a probability histogram?
Variance measures the spread of data in a probability histogram by multiplying the square of each value minus the mean by its probability, then summing these products. Standard deviation is simply the square root of the variance, providing a more interpretable measure of spread in the same units as the original data.
Q5: What information can you extract from the shape of a probability histogram?
A probability histogram reveals the shape, center, and spread of a probability distribution at a glance. The visual pattern shows how probabilities are distributed across outcomes, making it easier to identify whether data is concentrated, dispersed, or skewed compared to reading raw probability tables.
Q6: How does a probability histogram differ from a typical frequency histogram?
A probability histogram displays probabilities on the vertical axis rather than frequencies or counts. While both use contiguous bars to show distributions, a probability histogram normalizes the data so that the total area under all bars equals one, representing the complete probability space.
Q7: Why is a probability histogram useful for understanding random variables?
A probability histogram transforms abstract probability distributions into visual form, making it easier to comprehend how likely different outcomes are for a random variable. This visual representation helps students and researchers quickly grasp the centering and spread characteristics that are difficult to interpret from tables alone.