I.  Early Development of Probability
 A. Pascal and Fermat
  1. Correspondence 
  2. Problem of Points (for unfinished dice game)
  3. Pascal's correction of de Mere's erroneous gambling rule of thumb
 B. Laplace and Bernoulli
  1. Formalization of Probability Rules
  2. Independence
  3. Conditional Probability
  4. Expected Values
  5. St. Petersburg Paradox
 C. Normal Distribution
  1. Approximation to the Binomial (de Moivre)
  2. Early versions of the Central Limit Theorem (de Moivre, Laplace)
  3. Application to Social Sciences, Model for real data (Quetelet)
  4. Model for astronomy data (Gauss)
  5. Least Squares (Gauss, Legendre)
II. The Early British Statisticians
 A. Correlation and Regression (Galton, Edgeworth)
  1. Francis Galton's study of heights of parents and children
  2. Concept of regression to the mean
 B. Karl Pearson and his advances and errors
  1. Chi-square tests
  2. Method of moments
  3. Basic reasons for disagreements with Fisher on the above two things
  4. Pearson's correlation coefficient
  5. Disagreements with Yule
 C. Gosset and the Groundbreaking Early Work of Fisher
  1. Gosset and the Guinness brewery
  2. Development of Student's t-test (contributions by Gosset and Fisher)
  3. Friendship and Collaboration between Gosset and Fisher
  4. Fisher's 1922 paper and the main creations (likelihood, sufficiency, consistency, efficiency, concept of parameters in models)
 D. The Incredible Legacy of Fisher
  1. Savage's legendary 1970 Fisher Lecture which brought renewed focus onto Fisher's accomplishments
  2. Fisher's Development of ANOVA and Design of Experiments
  3. "The Lady Tasting Tea" and Fisher's exact test
  4. Fisher's personality traits
 E. The Unpleasant Side of Fisher's Legacy
  1. Fisher's Personal Faults and his Battles with other Statisticians
  2. Fisher and the Smoking/Lung Cancer Controversy (and Causality issue)
  3. Fisher (and Galton and Pearson) and Eugenics, and changes to how they are honored/remembered
III. The Rise of the Formal Mathematical Side of Statistics
 A. Decision Theory, Testing, and Formal Inference
  1. Neyman-Pearson Lemma and Approach to Testing
  2. Friendship and Collaboration between Neyman and Egon Pearson
  3. Neyman as the father of the Berkeley Statistics Department
  4. Abraham Wald (Wald tests, Sequential Testing, WWII aircraft study)
  5. Charles Stein (shrinkage estimation, his personal beliefs)
  6. "Holy Trinity" of Hypothesis Testing Methods:  
    - Wald test
    - Likelihood Ratio Test (Neyman-Pearson and Wilks)
    - Score Test (Rao)
 B. Optimal Point Estimation (Rao, Blackwell, Lehmann, Scheffe)
  1. Rao-Blackwell Theorem (using sufficient statistic to improve an unbiased estimator)
  2. Lehmann-Scheffe Theorem (to get the best (minimum variance) unbiased estimator)
  3. Importance of Blackwell as a researcher, mentor, and pioneering black statistician
  4. Rao's incredible 1945 paper (Cramer-Rao and Rao-Blackwell results)
  5. Scheffe's career at Berkeley, fundamental work in testing and estimation
  6. Lehmann's great legacy at Berkeley and as a textbook writer
 C. Practical Applications of Mathematical Statistics (Box, Cox, Wilks)
  1. Box's origins as a chemist and his relationship with his mentor George Barnard
  2. Box's building the statistics department at Wisconsin
  3. Box's work in time series (famous book with Jenkins) and Bayesian statistics
  4. Story behind the Box-Cox transformation
  5. David Cox's contributions (stochastic processes, survival analysis)
  6. Incredibly long research career of Cox
  7. Wilks's career at Princeton, doing government consulting, editing the Annals
  8. Wilks' Theorem and Wilks Award!!!
 D. The Importance of Indian Statisticians
  1. Mahalanobis (and his distance measure) and the Indian Statistical Institute
  2. Influence of Fisher and the British statistical tradition on the early ISI
  3. Roy (caring teacher) and Bose and their move to North Carolina
  4. C.R. Rao takes the reins after Mahalanobis
  5. Influence of Soviet visitors to the ISI
  6. C.R. Rao's personality and his amazing legacy
 E. The Rise of Statistics Departments in American Universities (G. Cox, Snedecor, Cochran, Hotelling)
  1. Gertrude Cox: First Lady of American Statistics (trained at Iowa State, built program at N.C. State)
  2. Snedecor:  Mentor of G. Cox, built program at Iowa State
  3. Cochran: Born in Scotland, came to America and worked with Snedecor and Cox
  4. Cochran's Theorem (foundation for F-tests) and many interesting studies Cochran worked on
  5. Popular Textbooks (Snededor & Cochran on Statistical Methods; Cochran & Cox on Experimental Design)
  6. Hotelling:  Left Columbia and built program at North Carolina (UNC); Hotelling's T^2 and "Hotelling's tea"
  7. Hotelling: Brilliant innovator in statistics education
 F. Early Female Statisticians Blazing a Trail for others to Follow
  1. Florence Nightingale's work as a nurse and her innovative early graphs (coxcomb plot)
  2. F.N. David's work with Karl Pearson, Gosset, and other British statisticisns
  3. F.N. David's move to California (had close ties with Berkeley, built the UC-Riverside program)
  4. Elizabeth Scott (left astronomy for statistics) a major figure in the Berkeley department
  5. Scott worked closely with Neyman (Neyman-Scott Paradox showed MLEs not always consistent)
  6. Fought for equality for women in academia
IV. Increasing Specialization in Statistics and Dissension Among Factions
 A. Development of Bayesian Statistics
  1. Origins of "inverse probability" (Laplace, Bayes, uniform (objective) prior on p) in 1700s
  2. De Finetti (and Ramsay) and their foundational resurrection of Bayesian ideas
  3. Jeffreys and his method for obtaining an objective prior
  4. Savage and Lindley promote (subjective) Bayesian statistics to a wider audience
  5. Fisher's issues with Bayesianism and his fiducial inference alternative
  6. Jim Berger and a return to objective Bayes approach
 B. Renewed Focus on Exploratory Data Analysis and Graphics (Tukey, Mosteller, Cleveland, Wilkinson)
  1. Tukey's Exploratory Data Analysis; invented boxplots, stem-and-leaf plots
  2. Bill Cleveland (coined term "data science")
  3. John Chambers (co-inventor of S language, which led to R)
  4. Mosteller:  Great collaborator, most famously with Tukey (and he worked with Laird!)
  5. Leland Wilkinson ("Grammar of Graphics", inspired ggplot2 package in R)
 C. The Rise of Computationally Intensive Methods
  1. Monte Carlo Methods (Fermi, Ulam, von Neumann)
  2. Developed around World War II in Los Alamos (atomic/nuclear bomb project)
  3. Metropolis-Hastings algorithm (1953 algorithm for optimization; 1970 Hastings extension for sampling)
  4. Gibbs sampling (Alan Gelfand and Adrian Smith <-- Lindley's student)
  5. Enabled the use of Bayesian statistics in complex problems (Revolutionary!)
  6. The Bootstrap (Brad Efron) <-- enabled inferences when true sampling distribution unknown
  7. The EM algorithm (Nan "Girlboss" Laird, with Dempster and Rubin)
  8. The 4 winners of the International Prize so far:  D.R. Cox; Efron; Laird, Rao
 D. The Two Cultures of Statistics (Breiman)
  1. "Data Modeling" culture and "Algorithmic modeling" culture
  2. Black-box methods vs. trying to model & interpret the data-generating process
 E. Attempts to Increase Diversity in Statistics
  1. Programs to increase minority participation (Louise Ryan)
  2. Increasing success for Women in Statistics (Nancy Reid)