PES
MODERN COLLEGE OF PHARMACY (Ladies)
MOSHI, PUNE
Savitribai Phule Pune University
M.PHARM
Semester- II
By
Mrs. Sneha Patil
Assistant Professor
Dept. of Pharmaceutics
Sensitive analysis
Content
1. Introduction
2. Types
3. Other techniques
4. Reference
1. Introduction
 Sensitive analysis is a technique to determine the impact of
independent variable on a particular dependent variable under a
given set of assumptions
 Its usage will depend on one or more input variables within the
specific boundaries
 This is also known as what-if analysis
 There are two main approaches for analyzing sensitivity
1. Local Sensitive Analysis
2. GlobalSensitive Analysis
Local Sensitive Analysis Sensitive Analysis
2. Types of analyzing sensitivity
1. Local sensitive analysis
 This analysis is based on the numerical or analytical derivative based,
As the derivatives are taken at a single point, this is called local
 This method is suitable for simple cost functions but not for complex
models
 This is a one-at-a-time (OAT) technique, which analyzes the impact of
one parameter on the cost function, keeping other parameters fixed
2. Global sensitive analysis
 This is the second approach which is often implemented using Monte
Carlo technique and uses a global set of samples to explore the
design
3. Various other techniques
3. Differential Sensitivity Analysis
 It is a direct method which involves solving temporal sensitivity
analysis to simple partial derivatives
 While this technique is computationally efficient, the task of solving
equations is intense
4. One at a time sensitive measure
 This is often referred to as local analysis because it is an indicator
only for the point estimates discussed and not for the entire
distribution
5. Factorial Analysis
 This includes selecting the specified number of samples for a
particular parameter and then running the combination model
Various other techniques continue…..
6. Regression Analysis
 This is a comprehensive method of obtaining responses for complex
models.
7. Subjective sensitive analysis
 This is a subjective, qualitative, simple and easy method to exclude
input parameters
 Indicating the sensitivity of the simulation to the model values is the
key application of the sensitive analysis
 Sensitive analysis is a way to forecast a decision's outcome if a
scenario turns out to be different from the main predictions
 It helps in assessing the risk of strategy, identifying and analyzing the
dependency of the output on the input values
4. Reference
 Karri V V S Narayana Reddy, K Gowthamarajan, Arun Radhakrishnan,
Arun Radhakrishnan. A Textbook of Computer aided drug
development. S. vikas and company, PV Publication; 2021 edition; Pg.
no. 273, 274
Sensitive analysis - Unit I (Computer aided drug development.pptx

Sensitive analysis - Unit I (Computer aided drug development.pptx

  • 1.
    PES MODERN COLLEGE OFPHARMACY (Ladies) MOSHI, PUNE Savitribai Phule Pune University M.PHARM Semester- II By Mrs. Sneha Patil Assistant Professor Dept. of Pharmaceutics Sensitive analysis
  • 2.
    Content 1. Introduction 2. Types 3.Other techniques 4. Reference
  • 3.
    1. Introduction  Sensitiveanalysis is a technique to determine the impact of independent variable on a particular dependent variable under a given set of assumptions  Its usage will depend on one or more input variables within the specific boundaries  This is also known as what-if analysis  There are two main approaches for analyzing sensitivity 1. Local Sensitive Analysis 2. GlobalSensitive Analysis Local Sensitive Analysis Sensitive Analysis
  • 4.
    2. Types ofanalyzing sensitivity 1. Local sensitive analysis  This analysis is based on the numerical or analytical derivative based, As the derivatives are taken at a single point, this is called local  This method is suitable for simple cost functions but not for complex models  This is a one-at-a-time (OAT) technique, which analyzes the impact of one parameter on the cost function, keeping other parameters fixed 2. Global sensitive analysis  This is the second approach which is often implemented using Monte Carlo technique and uses a global set of samples to explore the design
  • 5.
    3. Various othertechniques 3. Differential Sensitivity Analysis  It is a direct method which involves solving temporal sensitivity analysis to simple partial derivatives  While this technique is computationally efficient, the task of solving equations is intense 4. One at a time sensitive measure  This is often referred to as local analysis because it is an indicator only for the point estimates discussed and not for the entire distribution 5. Factorial Analysis  This includes selecting the specified number of samples for a particular parameter and then running the combination model
  • 6.
    Various other techniquescontinue….. 6. Regression Analysis  This is a comprehensive method of obtaining responses for complex models. 7. Subjective sensitive analysis  This is a subjective, qualitative, simple and easy method to exclude input parameters  Indicating the sensitivity of the simulation to the model values is the key application of the sensitive analysis  Sensitive analysis is a way to forecast a decision's outcome if a scenario turns out to be different from the main predictions  It helps in assessing the risk of strategy, identifying and analyzing the dependency of the output on the input values
  • 7.
    4. Reference  KarriV V S Narayana Reddy, K Gowthamarajan, Arun Radhakrishnan, Arun Radhakrishnan. A Textbook of Computer aided drug development. S. vikas and company, PV Publication; 2021 edition; Pg. no. 273, 274