Wednesday, March 21, 2012
Universal Limits in HighDimensional Statistics
The MIT Center on Operations Research is hosting a talk tomorrow on universal limits in highdimensional statistics. The basic idea is that, for all fields of empirical study from sociology to highenergy physics, some criterion for "statistical significance" is crucial for making decisions based on the data. (The current hunt for the Higgs Boson particle is in fact based on a modified criterion for statistical significance.) The problem, however, is that we are entering a world of big data, in which data structures have many dimensions, thus altering the potential usefulness of such criterion for statistical significance.
Blog Archive

▼
2012
(56)

▼
March
(29)
 Physics Envy
 Irving Louis Horowitz
 MyPersonality
 Why are Economists so (Consistently) Led Astray Ab...
 Popularity of Programming Languages
 Big Science and Sociology
 Statistical Lexicon
 McKinsey on Big Data
 Inequality: Everyone's Thinking About It
 Universal Limits in HighDimensional Statistics
 Rethinking Tragedy and Success
 Why Inequality Matters
 Inequality "Crisis" of Marriage
 Corporate Culture Revisited
 Misc. Links
 MIT Inequality Talk
 Scatter Plot Matrix in R
 Taxes and Inequality
 3D Scatter Plots Redux
 Checking Weather in Stata
 Is Everything Culture?
 Ternary (or Triaxial) Plots
 Causality and Ethnography
 The Mystery of PowerLaw Distributions
 Visualizing a Correlation Table
 Why Models are Not Data
 R versus Stata Redux
 Culture and Poverty
 Values and Politics

▼
March
(29)