Recherche de valeurs aberrantes à l’aide de l’IQR

Les valeurs aberrantes peuvent avoir des effets importants sur les statistiques telles que la moyenne, ainsi que sur les statistiques qui reposent sur la moyenne, telles que la variance et l’écart-type. L’écart interquartile, ou IQR, est une autre façon de mesurer la dispersion qui est moins influencée par les valeurs aberrantes. L’IQR est également souvent utilisé pour repérer les valeurs aberrantes. Si une valeur est inférieure à \(\text{Q1} - 1.5 \times \text{IQR}\) ou supérieure à \(text{Q3} + 1.5 \times \text{IQR}\), elle est considérée comme une valeur aberrante. En fait, c’est ainsi que sont calculées les longueurs des moustaches dans un diagramme en boîte matplotlib.

Diagramme en boîte montrant la médiane, les quartiles et les valeurs aberrantes

Dans cet exercice, vous calculerez l’IQR et l’utiliserez pour trouver des valeurs aberrantes. pandas est chargé en tant que pd et numpy en tant que np, et food_consumption est disponible.

Cet exercice fait partie du cours

Introduction aux statistiques en Python

Afficher le cours

Exercice interactif pratique

Essayez cet exercice en complétant cet exemple de code.

# Calculate total co2_emission per country: emissions_by_country
emissions_by_country = ____

print(emissions_by_country)

Modifier et exécuter le code

Cet exercice fait partie du cours

Introduction aux statistiques en Python

IntermédiaireNiveau de compétence

4.8+

Commencer le cours gratuitement

Summary statistics gives you the tools you need to boil down massive datasets to reveal the highlights. In this chapter, you'll explore summary statistics including mean, median, and standard deviation, and learn how to accurately interpret them. You'll also develop your critical thinking skills, allowing you to choose the best summary statistics for your data.

Exercise 1: Les statistiques, qu’est-ce que c’est ?Exercise 2: Statistiques descriptives et inférentielles Exercise 3: Classification des types de données Exercise 4: Mesures du centre Exercise 5: Calcul de la moyenne et de la médiane Exercise 6: Moyenne, médiane et forme de la distribution Exercise 7: Mesures de dispersion Exercise 8: Variance et écart-type Exercise 9: Quartiles, quantiles et quintiles Exercise 10: Recherche de valeurs aberrantes à l’aide de l’IQR

Exercice en cours

In this chapter, you'll learn how to generate random samples and measure chance using probability. You'll work with real-world sales data to calculate the probability of a salesperson being successful. Finally, you’ll use the binomial distribution to model events with binary outcomes.

Exercise 1: What are the chances?Exercise 2: With or without replacement?Exercise 3: Calculating probabilities Exercise 4: Sampling deals Exercise 5: Discrete distributions Exercise 6: Creating a probability distribution Exercise 7: Identifying distributions Exercise 8: Expected value vs. sample mean Exercise 9: Continuous distributions Exercise 10: Which distribution?Exercise 11: Data back-ups Exercise 12: Simulating wait times Exercise 13: The binomial distribution Exercise 14: Simulating sales deals Exercise 15: Calculating binomial probabilities Exercise 16: How many sales will be won?

It’s time to explore one of the most important probability distributions in statistics, normal distribution. You’ll create histograms to plot normal distributions and gain an understanding of the central limit theorem, before expanding your knowledge of statistical functions by adding the Poisson, exponential, and t-distributions to your repertoire.

Exercise 1: The normal distribution Exercise 2: Distribution of Amir's sales Exercise 3: Probabilities from the normal distribution Exercise 4: Simulating sales under new market conditions Exercise 5: Which market is better?Exercise 6: The central limit theorem Exercise 7: Visualizing sampling distributions Exercise 8: The CLT in action Exercise 9: The mean of means Exercise 10: The Poisson distribution Exercise 11: Identifying lambda Exercise 12: Tracking lead responses Exercise 13: More probability distributions Exercise 14: Distribution dragging and dropping Exercise 15: Modeling time between leads Exercise 16: The t-distribution

In this chapter, you'll learn how to quantify the strength of a linear relationship between two variables, and explore how confounding variables can affect the relationship between two other variables. You'll also see how a study’s design can influence its results, change how the data should be analyzed, and potentially affect the reliability of your conclusions.

Exercise 1: Correlation Exercise 2: Guess the correlation Exercise 3: Relationships between variables Exercise 4: Correlation caveats Exercise 5: What can't correlation measure?Exercise 6: Transforming variables Exercise 7: Does sugar improve happiness?Exercise 8: Confounders Exercise 9: Design of experiments Exercise 10: Study types Exercise 11: Longitudinal vs. cross-sectional studies Exercise 12: Congratulations!