Abstract
This chapter aims to build intuition about probability density functions (PDFs), Monte Carlo sampling, and yield estimation. It has an emphasis on graphical analysis as opposed to equations. Such intuition will help in many design scenarios, when one is observing actual PDF data in the form of scatterplots, histograms, and normal quantile (NQ) plots.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For further clarification: Two identically distributed distributions have exactly the same distribution shape (e.g., normal) and distribution parameters (e.g., same mean and standard deviation). Two “independently distributed” distributions have no correlation with each other; if we have a value for one distribution, that value does not change what the probable values for the other distribution might be.
- 2.
In the statistics literature, “Monte Carlo methods” are a broad set of algorithms, where the unifying element is that each algorithm has some randomization. While we use the label “sample” to mean a single point in process variable space drawn from a distribution or its corresponding output performance values, in the statistics literature such a point is an “observation” and a “sample” is a set of observations. The circuits community tends to use “sample” in the way we do.
- 3.
We agree, the terminology is somewhat confusing!
- 4.
CDF = Cumulative Distribution Function. CDF(x) is the area under the PDF from −∞ to x.
References
Agresti A, Coull BA (1998) Approximate is better than exact for interval estimation of binomial proportions. Am Stat 52:119–126
Drennan PG, McAndrew CC (2003) Understanding MOSFET mismatch for analog design. IEEE J Solid State Circuits (JSSC) 38(3):450–456
Efron B, Tibshirani R (1994) An introduction to the bootstrap. Chapman & Hall/CRC, London
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction, 2nd edn. Springer, NY
Li X, McAndrew CC, Wu W, Chaudry S, Victory J, Gildenblat G (2010) Statistical modeling with the PSP MOSFET model. IEEE Trans Comput Aided Des Integr Circuits Syst 29(4):599–606
McAndrew CC, Stevanovic I, Li X, Gildenblat G (2010) Extensions to backward propagation of variance for statistical modeling. IEEE Des Test Comput 27(2):36–43
McConaghy T (2010) Symbolic density models of one-in-a-billion statistical tails via importance sampling and genetic programming. In: Riolo R, McConaghy T, Vladislavleva E (eds) Genetic programming theory and practice VIII. Springer, NY (invited paper)
Parzen E (1962) On estimation of a probability density function and mode. Ann Math Stat 33:1065–1076
Rosenblatt M (1956) Remarks on some nonparametric estimates of a density function. Ann Math Stat 27:832–837
Ross TD (2003) Accurate confidence intervals for binomial proportion and Poisson rate estimation. Comput Biol Med 33:509–531
Wilson EB (1927) Probable inference, the law of succession, and statistical inference. J Am Statist Assoc 22:209–212
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2013 Springer Science+Business Media New York
About this chapter
Cite this chapter
McConaghy, T., Breen, K., Dyck, J., Gupta, A. (2013). A Pictorial Primer on Probabilities. In: Variation-Aware Design of Custom Integrated Circuits: A Hands-on Field Guide. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-2269-3_3
Download citation
DOI: https://doi.org/10.1007/978-1-4614-2269-3_3
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-2268-6
Online ISBN: 978-1-4614-2269-3
eBook Packages: EngineeringEngineering (R0)