Data Analysis What Can Be Learned From the Past 50 Years

Book Details






Data Analysis What Can Be Learned From the Past 50 Years

PDF Free Download | Data Analysis What Can Be Learned From the Past 50 Years by Peter J. Huber

Contents of Data Analysis eBook

  • What is Data Analysis?
  • Tukey’s paper
  • The Path of Statistics
  • Strategy Issues in Data Analysis
  • Strategy in Data Analysis
  • Philosophical issues
  • On the theory of data analysis and its teaching
  • Science and data analysis
  • Economy of forces
  • Issues of size
  • Strategic planning
  • Planning the data collection
  • Choice of data and methods
  • Systematic and random errors
  • Strategic reserves
  • Human factors
  • The stages of data analysis
  • Inspection
  • Error checking
  • Modification
  • Comparison
  • Modeling and Model fitting
  • Simulation
  • What-if analyses
  • Interpretation
  • Presentation of conclusions
  • Tools required for strategy reasons
  • Ad hoc programming
  • Graphics
  • Record keeping
  • Creating and keeping order
  • Massive Data Sets
  • Introduction
  • Disclosure: Personal experiences
  • What is i massive? A classification of size
  • Obstacles to scaling
  • Human limitations: visualization
  • Human – machine interactions
  • Storage requirements
  • Computational complexity
  • Conclusions
  • On the structure of large data sets
  • Types of data
  • How do data sets grow?
  • On data organization
  • Derived data sets
  • Data base management and related issues
  • Data archiving
  • The stages of a data analysis
  • Planning the data collection
  • Actual collection
  • Data access
  • Initial data checking
  • Data analysis proper
  • The final product: presentation of arguments and conclusions
  • Examples and some thoughts on strategy
  • Volume reduction
  • Supercomputers and software challenges
  • When do we need a Concorde?
  • General Purpose Data Analysis and Supercomputers
  • Languages, Programming Environments and Databased Prototyping
  • Summary of conclusions
  • Languages for Data Analysis
  • Goals and purposes
  • Natural languages and computing languages
  • Natural languages
  • Batch languages
  • Immediate languages
  • Language and literature
  • Object orientation and related structural issues
  • Extremism and compromises, slogans and reality
  • Some conclusions
  • Interface issues
  • The command line interface
  • The menu interface
  • The batch interface and programming environments
  • Some personal experiences
  • Miscellaneous issues
  • On building blocks
  • On the scope of names
  • On notation
  • Book-keeping problems
  • Requirements for a general purpose immediate language
  • Approximate Models
  • Models
  • Bayesian modeling
  • Mathematical statistics and approximate models
  • Statistical significance and physical relevance
  • Judicious use of a wrong model
  • Composite models
  • Modeling the length of day
  • The role of simulation
  • Summary of conclusions
  • Pitfalls
  • Simpson’s paradox
  • Missing data
  • The Case of the Babylonian Lunar Six
  • X-ray crystallography
  • Create order in data
  • General considerations
  • Principal component methods
  • Principal component methods: Jury data
  • Multidimensional scaling
  • Multidimensional scaling: the method
  • Multidimensional scaling: a synthetic example
  • Multidimensional scaling: map reconstruction
  • Correspondence analysis
  • Correspondence analysis: the method
  • Further examples: marketing and Shakespearean plays
  • Multidimensional scaling vs Correspondence analysis
  • Hodson’s grave data
  • Plato data
  • More case studies
  • A nutshell example
  • Shape invariant modeling
  • Comparison of point configurations
  • The cyclodecane conformation
  • The Thomson problem
  • Notes on numerical optimization

Related Books

Leave a Reply

Your email address will not be published.

What's the problem with this file?

There is a temporary issue with downloading files and we are working on.
In the meantime, we appreciate your patience.