The *Sensitivity Testing and Analysis Course* is an explanation of the
test and analysis methods used in conducting sensitivity tests (such as the
Neyer D-Optimal test, Langlie test, and Bruceton test). The class covers:

- What can be learned from a sensitivity test.
- How to perform a test.
- How to analyze and interpret the results.

Sensitivity tests are often used to estimate the parameters associated with latent continuous variables which cannot be measured. For example, each explosive specimen has a threshold. The specimen will detonate if and only if an applied shock exceeds this value. Since there is no way to determine the threshold of an individual, specimens are tested at various levels to determine parameters of the population. A new test described here produces efficient estimates of the parameters of the distribution, even with limited prior knowledge. This test efficiently characterizes the entire distribution and desired percentiles of any population.

Sensitivity test methods are used to study a wide range of phenomena, including:

- Determining the initiation sensitivity of energetic devices for automotive, mining, demolition, and military devices
- Determining the lethal toxic dose to animals of various chemicals (LD50 testing)
- Determining the strength of materials
- Determining the required dosage of pharmaceuticals
- Determining the intensity level required to detect a stimulus

The course covers both the basic theory and practical aspects of testing and analysis. Upon completion of this course, the students will be able to use software to conduct and analyze a wide variety of sensitivity tests, and should be able to understand and explain the results of the analysis.

This is a comprehensive course; for all technicians, professionals, and managers in development, production, quality, or test organizations who design, build, or test components that are destructively tested.

**The class is given either on-site at your
company, or in conjunction with conferences.**

**What is a sensitivity test?****Review of Statistics for Normal Distribution**- Resistor example
- Normal (Gaussian) probability curve
- Mean. Standard deviation of population
- Other parameters of the population
- Likelihood functions
- Maximum Likelihood Estimates
- Variances and covariance of estimates
- Confidence Intervals
- Cramer-Rao Theorem, Asymptotic Confidence Intervals
**Sensitivity test statistics**- What is measured?
- Statistics the same, measurements and computations different
- Use of Likelihood function
- Confidence Levels
- Cramer-Rao Theorem, Asymptotic Confidence Intervals
- Efficient test design
**Efficient sensitivity testing**- Egg drop test motivation
- Explanation of new test
- Can you do any better?
- How to determine the sample size
- Hands-on running of the software
**How to use the software for testing**- Mechanics of
**SenTest**^{TM} - How to determine limits of Mu and Sigma
- How to determine appropriate test hardware
- Running
**SenTest**with simulated components^{TM} **How to use the software for analysis**- History Plot (Xs and 0s)
- Contour Plot
- Numerical Analysis
- Probability Plot
- Multi Contour Plot
- Different Populations
**Special Topics**- What to do if no overlap
- How reliable are no-fire and all-fire levels?
- Adaptability of the Optimal techniques
**Test (Optional)**- Comprehensive test of sensitivity test and analysis statistics

Contact us at Neyer Software LLC