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 Continuous Variables Spread of Data KDE plots for Continuous Variable Overview of Distribution for Continuous variables Normal Distribution Skewed Distribution Skeweness and Kurtosis Distribution for Continuous Variable
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

Common mistakes analysts make during analysis and how to avoid them?

Kunal Jain
Kunal Jain Last Updated : 27 Aug, 2021
5 min read

Quite often I come across situations where people end up making wrong inferences based on half baked analysis. Or when people force fit data to what they already believe. A popular quote on the subject says:

If you torture the data long enough, it will confess.

– Ronald Coase, Economist

I personally disagree with the quote and firmly believe the other way “If you slice and dice the data in unbiased manner, it will reveal the truth.”

Having said that, I am aware of situations and people who intentionally or non-intentionally end up making wrong inferences. Following is an example which brings out one such case:

[stextbox id=”section”]Example of a typical error[/stextbox]

A BFSI Organization had come up with potentially ground breaking idea. It looked brilliant on paper and people  internally were excited about implementing it. Since it was a strategic shift, the team decided to run a pilot in selected locations. First reads from the pilot came out after 5 months of implementation. The MIS team analyzed the data and quickly concluded success of pilot basis following graph:

comparison error

Almost any metric you look at told same story unanimously. The whole project team was gung-ho about the success of the project and were getting ready to implement the strategy Pan India.

This is when a wise analyst entered and asked to look at pre and post scenario together before concluding any thing. This graph had a different story to tell:

comparison error 2

The entire story changed after looking at this graph. A clear winner strategy suddenly turned into a loser! Imagine the loss company would have suffered, had it implemented new strategy Pan India. Actually, locations were nominated by Regional Directors and they chose locations where they had higher confidence of good implementation (hence they had better performance before hand).

The purpose of this post is to bring out some of the common mistakes analysts make and how to avoid them:

[stextbox id=”section”]1. Drawing Inferences only basis mean (without removing Outliers)[/stextbox]

If you believe that any event does not represent a normal outcome, you need to filter it out from your analysis. For example, if a friend of the CEO or a member of Board of Directors invests a big amount through one of your products, that should be removed from data. Typically used definition to identify outliers is multiple of standard definition (2x or 3x).

To put numbers on this example, let us say Sales size for your product varies between Rs. 100 – 10,000 and there are 500 such cases such that the average works out at Rs. 5,000. If there is one sale of Rs. 5,00,00,000, the average all of a sudden becomes ~ Rs. 1,05,000. If you don’t get this kind of Sale every month, you will end up concluding that average sales size has gone down.

Look at another example why looking at mean might be misleading:

m5pyL

Following practices would help you to make sure you are not drawing wrong inferences by looking at mean:

  • Look at the distribution and filter out any outliers from your analysis
  • Observe the skew of (mean/median) to figure out amount of skew coming from bigger or smaller values. Higher or lower the value (compared to 1), higher is the skew. In case of high skews, look at both mean and median before making and conclusions.

[stextbox id=”section”]2. Comparing different sets of population, segment or cluster[/stextbox]

The example at the start of the article is perfect example of this. This error can happen whenever you do not use non-random way to distribute the population. Whenever you do so, please make sure that populations are similar on all the key parameters.

How to avoid this bias / error?

It is best to stay away from comparing non-random distributed population. If you need to do so due to logistic & resource constraints, compare Pre vs. Post before you arrive at any conclusion.

[stextbox id=”section”]3. Drawing inferences on thin data (and extrapolating it)[/stextbox]

This happens when you want to bring out insights for every possible segment of data. In doing so, you end up with segments or clusters which have small population and the reads may not be statistically significant (or will contain a lot of noise). Following is another example of this kind of error:

u5HhK

How to avoid drawing inferences based on thin data?

Always plot confidence intervals to the values to calculate or extrapolate. This will give you a sense of whether the extrapolation is accurate or erroneous. Usual practice is to look at 90% confidence intervals before reaching any conclusion.

[stextbox id=”section”]4. Wrong applications of the inferences[/stextbox]

It is human tendency to generalize insights and findings. You extend or apply a learning based on different set of population or circumstances to a different set. Those insights may or may not be relevant. If your credit scoring model was based on a population coming from a particular channel (e.g. Branches), you can not apply it to a different set (e.g. Online). You will end up getting things wrong. Here is another example which brings out this error:

Vdqwt

How to avoid wrong application of inferences?

Always check if you are extending your models to a population which it has not seen it past. If you are aware of any changes, continue to monitor the population on key variables (e.g. for credit scoring model, you need to monitor age, income, unemployment rate, credit file match % etc.)

If any of these distributions are different compared to the population on which you are basing your learnings, think again!

[stextbox id=”section”]5. Correlation does not mean Causation[/stextbox]

Correlation is a tool every analyst uses on a frequent basis. The biggest caution while using it is that it should not be treated as causation. If two events are happening close to each other, it is not necessary that they are happening because of one another. For example, if my age is increasing with time and my brother’s age is also increasing with time, it does not mean my age is driving his. Picture below shows another such example:

correlation_cartoon

How to avoid this error?

Just treat correlation as correlation and not causation.

 

These were the 5 most common errors in my experience. The more you put your thought in spotting these errors, the better you become at it. Initially, I used to make these errors myself. Now, I can spot them effortlessly.

If you know of any other errors people make, please feel free to add your comments below.

Image credit: All cartoons taken from XKCD.com

If you like what you just read & want to continue your analytics learning, you can subscribe to our emails or like our facebook page

Kunal Jain
Kunal Jain

Kunal Jain is the Founder and CEO of Analytics Vidhya, one of the world's leading communities of Al professionals. With over 17 years of experience in the field, Kunal has been instrumental in shaping the global Al landscape. His expertise spans diverse markets, from developed economies like the UK to emerging ones like India, where he has successfully led and delivered complex data-driven solutions. As a recognized thought leader, Kunal has empowered countless individuals to realize their Al ambitions through his visionary approach to Al education and community building. Before founding Analytics Vidhya, Kunal earned both his undergraduate and postgraduate degrees from IIT Bombay and held key roles at Capital One and Aviva Life Insurance across multiple geographies. His passion lies at the intersection of analytics, Al, and fostering a thriving community of data science professionals.

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

amit singh
amit singh

Liked the illustrations in cartoons....the causation- correlation error along with non-biased sample selection are the 2 most common ones in my experience

123

Solomon
Solomon

Hi Kunal, The backward approach whether the campaign actually did benefit or not was quite a learning. Thanks

123

Glenn
Glenn

Great post - = I have witnessed the above mistakes and many more. Unfortunately, the creator of said mistake will often argue passionately in favor of the mistake to decision makers, whom often are less qualified to assess the veracity of the analysis, and they go .

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

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