Interview Prep
Career
GenAI
Prompt Engg
ChatGPT
LLM
Langchain
RAG
AI Agents
Machine Learning
Deep Learning
GenAI Tools
LLMOps
Python
NLP
SQL
AIML Projects

Reading list

Machine Learning Basics for a Newbie
6 Steps of Machine learning Lifecycle Introduction to Predictive Modeling
Introduction to Exploratory Data Analysis & Data Insights Descriptive Statistics Inferential Statistics How to Understand Population Distributions?
Reading Data Files into Python Different Variable Datatypes
Probability for Data Science Basic Concepts of Probability Axioms of Probability Conditional Probability
Central Tendencies for Categorical Variables Understanding Discrete Distributions Performing EDA on Categorical Variables
Dealing with Missing Values Understanding Outliers Identifying Outliers in Data Outlier Detection in Python Outliers Detection Using IQR, Z-score, LOF and DBSCAN
Sample and Population Central Limit Theorem Confidence Interval and Margin of Error
Bivariate Analysis Introduction
Covariance Pearson Correlation Spearman's Correlation & Kendall's Tau Correlation versus Causation Tabular and Graphical methods for Bivariate Analysis Performing Bivariate Analysis on Continuous-Continuous Variables
Tabular and Graphical methods for Continuous-Categorical Variables Introduction to Hypothesis Testing P-value Two sample Z-test T-test T-test vs Z-test Performing Bivariate Analysis on Continuous-Catagorical variables
Chi-Squares Test Bivariate Analysis on Categorical Categorical Variables
Multivariate Analysis A Comprehensive Guide to Data Exploration The Data Science behind IPL
Supervised Learning vs Unsupervised Learning Reinforcement Learning Generative and Descriminative Models Parametric and Non Parametric model
Machine Learning Pipeline Preparing Dataset Build a Benchmark Model: Regression Build a Benchmark Model: Classification
Evaluation Metrics for Machine Learning Everyone should know Confusion Matrix Accuracy Precision and Recall AUC-ROC Log Loss R2 and Adjusted R2
Dealing with Missing Values Replacing Missing Values Imputing Missing Values in Data Working with Categorical Variables Working with Outliers Preprocessing Data for Model Building
Understanding Cost Function Understanding Gradient Descent Math Behind Gradient Descent Assumptions of Linear Regression Implement Linear Regression from Scratch Train Linear Regression in Python Implementing Linear Regression in R Diagnosing Residual Plots in Linear Regression Models Generalized Linear Models Introduction to Logistic Regression Odds Ratio Implementing Logistic Regression from Scratch Introduction to Scikit-learn in Python Train Logistic Regression in python Multiclass using Logistic Regression How to use Multinomial and Ordinal Logistic Regression in R ? Challenges with Linear Regression Introduction to Regularisation Implementing Regularisation Ridge Regression Lasso Regression
Introduction to K Nearest Neighbours Determining the Right Value of K in KNN Implement KNN from Scratch Implement KNN in Python
Bias Variance Tradeoff Introduction to Overfitting and Underfitting Visualizing Overfitting and Underfitting Selecting the Right Model What is Validation? Hold-Out Validation Understanding K Fold Cross Validation
Introduction to Feature Selection Feature Selection Algorithms Missing Value Ratio Low Variance Filter High Correlation Filter Backward Feature Elimination Forward Feature Selection Implement Feature Selection in Python Implement Feature Selection in R
Introduction to Decision Tree Purity in Decision Tree Terminologies Related to Decision Tree How to Select Best Split Point in Decision Tree? Chi-Squares Information Gain Reduction in Variance Optimizing Performance of Decision Tree Train Decision Tree using Scikit Learn Pruning of Decision Trees
Introduction to Feature Engineering Feature Transformation Feature Scaling Feature Engineering Frequency Encoding Automated Feature Engineering: Feature Tools
Introduction to Naive Bayes Conditional Probability and Bayes Theorem Introduction to Bayesian Adjustment Rating: The Incredible Concept Behind Online Ratings! Working of Naive Bayes Math behind Naive Bayes Types of Naive Bayes Implementation of Naive Bayes
Understanding how to solve Multiclass and Multilabled Classification Problem Evaluation Metrics: Multi Class Classification
Introduction to Ensemble Techniques Basic Ensemble Techniques Implementing Basic Ensemble Techniques Finding Optimal Weights of Ensemble Learner using Neural Network Why Ensemble Models Work well?
Introduction to Stacking Implementing Stacking Variants of Stacking Implementing Variants of Stacking Introduction to Blending Bootstrap Sampling Introduction to Random Sampling Hyper-parameters of Random Forest Implementing Random Forest Out-of-Bag (OOB) Score in the Random Forest IPL Team Win Prediction Project Using Machine Learning Introduction to Boosting Gradient Boosting Algorithm Math behind GBM Implementing GBM in python Regularized Greedy Forests Extreme Gradient Boosting Implementing XGBM in python Tuning Hyperparameters of XGBoost in Python Implement XGBM in R/H2O Adaptive Boosting Implementing Adaptive Boosing LightGBM Implementing LightGBM in Python Catboost Implementing Catboost in Python
Different Hyperparameter Tuning methods Implementing Different Hyperparameter Tuning methods GridsearchCV RandomizedsearchCV Bayesian Optimization for Hyperparameter Tuning Hyperopt
Understanding SVM Algorithm SVM Kernels In-depth Intuition and Practical Implementation SVM Kernel Tricks Kernels and Hyperparameters in SVM Implementing SVM from Scratch in Python and R
Introduction to Principal Component Analysis Steps to Perform Principal Compound Analysis Computation of Covariance Matrix Finding Eigenvectors and Eigenvalues Implementing PCA in python Visualizing PCA A Brief Introduction to Linear Discriminant Analysis Introduction to Factor Analysis
Introduction to Clustering Applications of Clustering Evaluation Metrics for Clustering Understanding K-Means Implementation of K-Means in Python Implementation of K-Means in R Choosing Right Value for K Profiling Market Segments using K-Means Clustering Hierarchical Clustering Implementation of Hierarchial Clustering DBSCAN Defining Similarity between clusters Build Better and Accurate Clusters with Gaussian Mixture Models
Understand Basics of Recommendation Engine with Case Study
8 Ways to Improve Accuracy of Machine Learning Models
Introduction to Dask Working with CuML
Introduction to Machine Learning Interpretability Framework and Interpretable Models model Agnostic Methods for Interpretability Implementing Interpretable Model Understanding SHAP Out-of-Core ML Introduction to Interpretable Machine Learning Models Model Agnostic Methods for Interpretability Game Theory & Shapley Values
Introduction to Machine Learning Interpretability Framework and Interpretable Models model Agnostic Methods for Interpretability Implementing Interpretable Model Understanding SHAP Out-of-Core ML Introduction to Interpretable Machine Learning Models Model Agnostic Methods for Interpretability Game Theory & Shapley Values
Introduction to AutoML Implementation of MLBox Introduction to PyCaret TPOT Auto-Sklearn EvalML
Pickle and Joblib Introduction to Model Deployment
Deploying Machine Learning Model using Streamlit Deploying ML Models in Docker Deploy Using Streamlit Deploy on Heroku Deploy Using Netlify Introduction to Amazon Sagemaker Setting up Amazon SageMaker Using SageMaker Endpoint to Generate Inference Deploy on Microsoft Azure Cloud Introduction to Flask for Model Deploying ML model using Flask
Model Deployment in Android Model Deployment in Iphone

Understanding Skewness in Data and Its Impact on Data Analysis (Updated 2024)

Abhishek
Abhishek Last Updated : 27 Sep, 2024
9 min read

Introduction

The concept of skewness is baked into our way of thinking. When we look at a visualization, our minds intuitively discern the pattern in that chart, whether we are data scientists or beginners working on a python dataset.

As you might already know, India has more than 50% of its population below the age of 25 and more than 65% below the age of 35. If you plot the distribution of the age of the population of India, you will find that there is a hump on the left side of the distribution, and the right side is comparatively planar. In other words, we can say that there’s a skew toward the end, right?

So even if you haven’t read up on skewness as a data science or analytics professional, you have interacted with the concept on an informal note. And it’s a pretty easy topic in statistics – and yet a lot of folks skim through it in their haste to learn other seemingly complex data science concepts. To me, that’s a mistake. Skewness is a fundamental descriptive statistics concept that everyone in data science and analytics needs to know. In this tutorial, we’ll discuss the concept of skewness in the easiest way possible, one of the important concepts in statistics for data science. So buckle up because you’ll learn a concept that you’ll value during your entire data science career. In essence, understanding what is skewness is essential for meaningful data analysis and interpretation.

In this article you also get to learn about positive skewness and negative skewness and their fundamentals.

Skewness

Learning Objectives

  • You’ll learn about skewness, its types, and its importance in the field of data science.
  • You will learn what the coefficient of skewness is and how to calculate it.
  • Lastly, you will learn how we can transform skewed data.

Table of contents

What Is Skewness?

Skewness is the measure of the asymmetry of an ideally symmetric probability distribution and is given by the third standardized moment. If that sounds way too complex, don’t worry! Let me break it down for you.

In simple words, skewness in statistics is the measure of how much the probability distribution of a random variable deviates from the normal distribution. Now, you might be thinking – why am I talking about normal distribution here?

Well, the normal distribution is the probability distribution without any skewness. You can look at the image below, which shows symmetrical distribution that’s a normal distribution, and you can see that it is symmetrical on both sides of the dashed line. Apart from this, there are two types of skewness:

  • Positive Skewness
  • Negative Skewness
Positive Skewness | Negative Skewness

The probability distribution with its tail on the right side is a positively skewed distribution, and the one with its tail on the left side is a negatively skewed distribution. If you’re finding the above figures confusing, that’s alright. We’ll understand this in more detail later.

Skewness in statistics is demonstrated on a bell curve when data points are not distributed symmetrically to the left and right sides of the median on a bell curve. If the bell curve is shifted to the left or the right, it is said to be skewed. Before that, let’s understand why this is such an important concept for you as a data science professional.

Types of Skewness

There are three main types of skewness in statistics:
Right Skew: Tail extends to the right, most data clustered on the left. (mean > median)
Left Skew: Tail extends to the left, most data clustered on the right. (mean < median)
Zero Skew: Perfectly symmetrical distribution, with mean, median, and mode all equal.

Why Is Skewness Important?

Now, we know that skewness of data is the measure of the lack of symmetry, and its types are distinguished by the side on which the tail of probability distribution lies. But why is knowing the skewness of the data important?

First, linear models work on the assumption that the distribution of the independent variable and the target variable are similar. Therefore, knowing about the skewness in statistics of data helps us create better linear models.

Secondly, let’s take a look at the below distribution. It is the distribution of horsepower of cars:

positively skewed distribution of auto horsepower

You can clearly see that the above distribution is positively skewed. Now, let’s say you want to use this as a feature for the model that will predict the mpg (miles per gallon) of a car.

Since our data is positively skewed here, it means that it has a higher number of data points having low values, i.e., cars with less horsepower. So when we train our model on this data, it will perform better at predicting the mpg of cars with lower horsepower as compared to those with higher horsepower.

Also, skewness tells us about the direction of outliers. You can see that our distribution is positively skewed, and most of the outliers are present on the right side of the distribution.

Note: The skewness does not tell us about the number of outliers. It only tells us the direction.

Now we know why skewness of data is important, before understanding distributions, let us quickly understand what the central limit theorem is.

Central Limit Theorem

The central limit theorem says that the sampling distribution of the mean will always be normally distributed as long as extreme values or the sample size is large enough. Regardless of whether the population has a normal, Poisson, binomial, or any other distribution, the sampling distribution of the mean will be normal.

Hypothesis Testing uses the Central Limit Theorem. Using the Central Limit Theorem, we can extend the approach employed in Single Sample Hypothesis Testing for normally distributed populations to those that are not normally distributed.

What Is Symmetric/Normal Distribution?

Symmetric/Normal distribution,Positive skewness

Yes, we’re back again with the normal distribution. It is used as a reference for determining the skewness of a distribution. As I mentioned earlier, the ideal normal distribution is the probability distribution with almost no skewness. It is nearly perfectly symmetrical. Due to this, the value of skewness for a normal distribution is zero or zero skewness.

But why is it nearly perfectly symmetrical and not absolutely symmetrical?

That’s because, in reality, no real word data has a perfectly normal distribution. Therefore, even the value of skewness is not exactly zero; it is nearly zero. Although the value of zero is used as a reference for determining the skewness of a distribution.

You can see in the above image that the same line represents the mean, median, and mode. It is because the mean, median, and mode of a perfectly normal distribution are equal.

So far, we’ve understood the skewness of normal distribution using a probability or frequency distribution. Now, let’s understand it in terms of a boxplot because that’s the most common way of looking at a distribution in the data science space.

normal distribution zero skewness boxplot

The above image is a boxplot of symmetric distribution. You’ll notice here that the distance between Q1 and Q2 and Q2 and Q3 is equal, i.e.:

boxplot quartile normal distribution

But that’s not enough to conclude if a distribution is skewed or not. We also take a look at the length of the whisker; if they are equal, then we can say that the distribution is symmetric, i.e., it is not skewed.

It’s now time to learn about the two types of skewness which we discussed earlier. Let’s start with positive skewness.

Understanding Positively Skewed Distribution | Positive Skewness

Symmetric/Normal distribution,Positive skewness

A positive skewness is the right-skewed distribution with the long tail on its right side. The value of skewness of data for a positively skewed distribution is greater than zero. As you might have already understood by looking at the figure, the value of the mean is the greatest one, followed by the median and then by mode.

So why is this happening?

Well, the answer to that is that the skewness of the data distribution is on the right; it causes the mean to be greater than the median and eventually move to the right. Also, the mode occurs at the highest frequency of the distribution, which is on the left side of the median. Therefore, the measure of central tendencies is mode < median < mean.

boxplot quartile normal distribution

In the above boxplot, you can see that Q2 is present nearer to Q1. This represents a positively skewed distribution. In terms of quartiles, it can be given by:

boxplot quartile positive skewness

In this case, it was very easy to tell if the data was skewed or not. But what if we have something like this:

positive skewness whiskers boxplot

Here, Q2-Q1 and Q3-Q2 are equal, and yet the distribution is positively skewed. The keen-eyed among you will have noticed the length of the right whisker is greater than the left whisker. From this, we can conclude that the data is positively skewed.

So, the first step is always to check the equality of Q2-Q1 and Q3-Q2. If that is found equal, then we look for the length of the whiskers.

Note: A high level of skewness or highly skewed data can generate misleading results from statistical tests. Extreme positive skewness in statistics is not desirable for a distribution.

Understanding Negatively Skewed Distribution | Negative Skewness

Symmetric/Normal distribution,Positive skewness

Source: Wikipedia

As you might have already guessed, a negatively skewed distribution is the left-skewed distribution with the long tail on its left side. The value of skewness for a negatively skewed distribution is less than zero. You can also see in the above figure that the measure of central tendencies is mean < median < mode.

negative skewness boxplot

In the boxplot, the relationship between quartiles for a negative skewness is given by:

boxplot quartile negative skewness

Similar to what we did earlier, if Q3-Q2 and Q2-Q1 are equal, then we look for the length of whiskers. And if the length of the left whisker is greater than that of the right whisker, then we can say that the data is negatively skewed.

negative skewness whiskers boxplot

Coefficient of Skewness

Pearson developed two methods to find skewness in a sample.

  1. Pearson’s Coefficient of Skewness using mode.
    SK1= Mean- mode/ sd
    where sd is the standard deviation for the sample.
  2. Pearson’s Coefficient of Skewness using the median.
    SK2=3(mean-median)/sd
    where sd is the standard deviation for the sample. It is generally used when the mode is unknown.

Note: There isn’t an Excel function to find Pearson’s coefficient of skewness. In the descriptive statistics area of the data analysis tool, skewness of data is calculated by using the third power of deviations around the mean. This is different from Pearson’s coefficient of skewness, which uses either the mode or the mean.

How Do We Transform Skewed Data?

Since you know how much the skewed data can affect our machine learning model’s predicting capabilities, it is better to transform the skewed data into normally distributed data. Here are some of the ways you can transform your skewed data:

  • Power Transformation
  • Log Transformation
  • Exponential Transformation

Note: The selection of transformation depends on the statistical characteristics of the data.

Conclusion

Skewness is a measure of lack of symmetry. It is a shape parameter that characterizes the degree of asymmetry of a distribution. A distribution is said to be positively skewed with a degree of skewness greater than 0 when the tail of a distribution is toward the high values indicating an excess of low values. Conversely, it is negatively skewed with a degree of skewness less than 0 (Sk<0)when the tail of the distribution is toward the low values indicating an excess of high values.

Hope you understand and get understanding about the skewness and positive skewness we have given all the information so that you wil able to clear yor doubts.

Key Takeaways

  • Skewness is a measure of the lack of symmetry in a distribution. A distribution is asymmetrical when its left and right sides are not mirror images.
  • In this article, we covered the concept of skewness and learned the difference between positively skewed and negatively skewed distribution.
  • We can transform skewed data using Power, Log, and Exponential Transformations.

Frequently Asked Questions

Q1. What is positively skewed vs skewed right?

A. Both terms describe the same distribution type where the tail is longer on the right side, indicating more values are concentrated on the left.

Q2. What are positive and negative skewness values?

A. Positive skewness values indicate a distribution tailing off to the right, while negative skewness values indicate a distribution tailing off to the left.

Q3. What is positively skewed mean median mode?

A. In a positively skewed distribution, the mean is greater than the median, which is greater than the mode (mean > median > mode).

Q4. What does a positive coefficient of skewness mean?

A. A positive coefficient of skewness of data indicates that the distribution has a longer right tail, suggesting a higher frequency of lower values.

Negative SkewnessNormal DistributionoutliersPositive SkewnessSkewnessskewness in statisticsstatistics
Abhishek
Abhishek

Free Courses

Generative AI 4.7

Generative AI - A Way of Life

Explore Generative AI for beginners: create text and images, use top AI tools, learn practical skills, and ethics.
Large Language Models 4.5

Getting Started with Large Language Models

Master Large Language Models (LLMs) with this course, offering clear guidance in NLP and model training made simple.
Prompt Engineering 4.6

Building LLM Applications using Prompt Engineering

This free course guides you on building LLM apps, mastering prompt engineering, and developing chatbots with enterprise data.
LlamaIndex 4.8

Improving Real World RAG Systems: Key Challenges & Practical Solutions

Explore practical solutions, advanced retrieval strategies, and agentic RAG systems to improve context, relevance, and accuracy in AI-driven applications.
RAG systems using LlamaIndex 4.7

Microsoft Excel: Formulas & Functions

Master MS Excel for data analysis with key formulas, functions, and LookUp tools in this comprehensive course.

Recommended Articles

Responses From Readers

Clear

Jerad
Jerad

I'd be curious your thoughts on the impact of assymmetry on linear modeling without the random component being normal (e.g. logistic regression) or non linear modeling (e.g. NN). 95% of what I do isn't the simple linear model and I know that most modeling methods don't assume symmetry... But do they still benefit from transformations that make them more symmetrical?

123

Steve Bogatsu
Steve Bogatsu

Evening Abhishek. Thanks for an informative and simplified explanation of data analytics. As HR performance management specialist, I am often challenged why performance management distribution curves are tilted and skewed to the right and not asymmetric as many of my colleagues would expect. For instance, in a four bucket rating system (Below Expectation, Meet Expectation, Exceed Expectation and Exceptional Performance). A distribution curve of individual ratings always tend to tilt and skew to the right. When challenged about the curve's behaviour, my response has always been along the lines of saying: For a curve to be asymmetrical, your data needs to meet two conditions. Firstly your data must be sufficient and lastly it must be randomly selected. Now, in all instances data was sufficient (2500 - 3500 employees). So the first condition was met. The second is not met because companies do not employ people at random. Companies recruit, select and employ suitably qualified employees. Hence the shape and slope of the curve. Do you agree with this reasoning? Your comment will be appreciated.

123

Sergii
Sergii

Good job! It's very simple article for understanding and author has done this on highest mark!

123

Seyed
Seyed

That's important in distribution detection.

123

Ashok
Ashok

Very nice explanation... Thanks for the article

123

mugo
mugo

good work

123

Dr Datrika Venkata Madhusudan Rao
Dr Datrika Venkata Madhusudan Rao

Nice article, but you would have mentioned first, the values of determination for normalised data; second, in case of non normalised data, how to modify or convert non normalised data to normalised data.

123

S.Debroy
S.Debroy

Great article..... Fundamental is always important.....

123

Martins
Martins

Nice, well explained

123

Peter
Peter

Well explained. I would highly appreciate a follow-up article on transformation from skewed to normally distributed data

123

Aashish Rana
Aashish Rana

i loved this article.

123

suleiman
suleiman

Very helpful, my question is if you have both positive and negative skew in one skew in one data set, which is the prepared option to use? is it ,the mean, mode or median

123

Gwen
Gwen

Great, clear instruction on skew and visualization! Thank you!

123

Abdulrahman Muhammad Bello
Abdulrahman Muhammad Bello

nice, very easy to understand

123

Abha
Abha

Very well explained. Thanks for this.

123

Write for us

Write, captivate, and earn accolades and rewards for your work
  • Reach a Global Audience
  • Get Expert Feedback
  • Build Your Brand & Audience
  • Cash In on Your Knowledge
  • Join a Thriving Community
  • Level Up Your Data Science Game
imag

Flash Card

What is skewness in statistics, and why is it important?

Skewness is a measure of the asymmetry of a probability distribution. It indicates how much a distribution deviates from a normal distribution. Understanding skewness is crucial for data analysis as it helps in interpreting the distribution of data points. Skewness is visualized on a bell curve, where asymmetry indicates a shift to the left or right, affecting data interpretation.

What is skewness in statistics, and why is it important?

Quiz

What does skewness measure in a probability distribution?

Flash Card

What are the different types of skewness, and how do they affect data interpretation?

There are three types of skewness: positive, negative, and zero skewness. Positive skewness (right-skewed) has a long tail on the right, with most data clustered on the left. Here, the mean is greater than the median. Negative skewness (left-skewed) has a long tail on the left, with most data clustered on the right. In this case, the mean is less than the median. Zero skewness indicates a perfectly symmetrical distribution where the mean, median, and mode are equal.

Quiz

Which type of skewness is characterized by a long tail on the right and most data clustered on the left?

Flash Card

Why is understanding skewness important for creating linear models?

Linear models assume that the distribution of the independent and target variables are similar. Knowing the skewness helps in creating better linear models by ensuring that the assumptions of the model are met. Highly skewed data can lead to misleading results in statistical tests, making it crucial to understand and address skewness.

Quiz

Why is it important to understand skewness when creating linear models?

Flash Card

How can skewness impact statistical tests?

Skewness can lead to inaccurate results in statistical tests if not properly addressed. High skewness indicates a lack of symmetry, which can violate the assumptions of many statistical tests. Addressing skewness ensures that the results of statistical tests are reliable and valid.

Quiz

What is a potential consequence of not addressing skewness in statistical tests?

Flash Card

What are Pearson's methods for calculating the coefficient of skewness?

Pearson developed two methods to calculate skewness: using the mode and using the median. The first method, SK1, uses the formula: (Mean - Mode) / Standard Deviation. The second method, SK2, is used when the mode is unknown and uses the formula: 3(Mean - Median) / Standard Deviation.

Quiz

Which formula is used in Pearson's second method for calculating skewness when the mode is unknown?

Flash Card

What techniques can be used to transform skewed data into normally distributed data?

Transformations can help convert skewed data into a normal distribution, improving model performance. Common techniques include Power Transformation, Log Transformation, and Exponential Transformation. The choice of transformation depends on the statistical characteristics of the data and the degree of skewness.

Quiz

Which of the following is a technique used to transform skewed data into a normal distribution?

Flash Card

Why is it beneficial to transform skewed data for machine learning models?

Skewed data can negatively impact the predictive capabilities of machine learning models. Transforming skewed data into a normal distribution helps in meeting the assumptions of many algorithms. This transformation leads to more accurate and reliable predictions by the model.

Quiz

What is one benefit of transforming skewed data for machine learning models?

Congratulations, You Did It!
Well Done on Completing Your Learning Journey. Stay curious and keep exploring!
Difference Between Skewness and Kurtosis
Difference Between Skewness and Kurtosis
Importance of Skewness, Kurtosis, Co-efficient of Variation
Importance of Skewness, Kurtosis, Co-efficient of Variation

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details