Marginal Books

Monte Carlo Simulation with Python: Volume 2

Title               Monte Carlo Simulation with Python: Volume 2
Author          Akram Najjar 
Price              $5.99
Published     November 2026
Size                390 pages (97,000 words) 
Language     English  

Alert: when errors are found in the book, and related workouts are updated, an Errata document (with a new version  number) is uploaded to the Resources Folder indicated below.

Volume 2 provides complete, step-by-step documentation for 40 downloadable Python Models that simulate real-world issues and processes across these topics:

Reliability Block Diagrams
Simulation of Statistical Process Control (SPC)
Simulation of Process Capability Analysis (PCA)
The Lilliefors Test for Normality
The QQ-Plot Test for Normality
Simulating Conjoint Analysis
D_Optimal Conjoint Analysis Dataset Generator
Simulating Goodness of Fit and Independence Testing Using Chi-Square
Simulating an Analytic Hierarchical Process (AHP)
Generating Analyst AHP Datasets
Generating Saaty CI Columns for any M for use in AHP
Simulating the Optimization of Kitchen Cabinets (PuLP)
Simulating the Optimization of Portfolios (PuLP)
Simulating K-Means Clustering
Calculating the Elbow Test for Optimal K
Simulating Logistic Regression (Three Processes)
The Analysis of the Confusion Matrix Analysis
Plotting the ROC Chart from Logistic Regression
AUC for Logistic Regression (Initial and Resampled)
Simulating Mahalanobis Outlier Detection
Check if a Matrix or a Dataset or Several Covariance Matrices are Positive Definite

Included with the 30 Models are various Helper Scripts that generate datasets and apply tests. Three Appendices cover statistical topics of use in simulation: MLR, Markov Chains and Probability Distributions.

The benefits of the Book are:

1) To master Monte Carlo simulation techniques drawn from business processes.
2) To understand and apply 14 key probability distributions, including Binomial, Poisson, Gamma, Weibull, Dirichlet and others.
3) To strengthen the data analysis foundations to support simulation, including Random Number Generation, Multiple Linear Regression, Covariance/Correlation and Confusion Matrices.
4) To apply advanced simulation techniques, such as the use of 3D and 4D arrays, shuffling to avoid selection bias, sensitivity and influence analysis, validation of results against expected behavior using goodness-of-fit testing with Chi-Square.

Volume 1 is available on Amazon and covers 30 Models that simulate issues and processes in Machine Learning and Data Science methods. (Click Here to view the page of Volume 1 on this website).

History:
This book is the 4th generation of a Monte Carlo Simulation work. The first generation as a 2-part book written after 15 years of developing training workshops on Monte Carlo Simulation and related Data Analysis topics and available until end 2025 on Amazon. The second generation is 20-hour 48-
lecture course uploaded to UDEMY. The current book is the third generation consisting of a full upgrade of the first two.The 3rd Generation is still on Amazon and is called "​Master Monte Carlo Simulation in Business Processes" using Excel.

The Book is only available on AMAZON . . . . Click Here

Downloads

Click on the Icon to go to OneDrive.
You will be able to download the following two zipped file:

The Project Folder which contains all the Python Models and Helper Scripts. These are password protected for readers who have purchased Volume 2. The password is included in the purchased Book.

Various Resources are zipped in one file  for complimentary download (no need for a password). The file contains:
1) Errata History and corrected material.
2) A Sample Chapter + its Python Script
3) Tables of Contents that are more detailed than in the Book
4) Distributions vs Models: an Excel workbook that contains a list of all Models and Helper (rows) and the Distributions they use (cols). A Filter in Excel will allow you to list the Models that use each Distribution.
5) Three Appendices: on Distributions, Markov Chains and Multiple Linear Regression.