Statistics and Data Science 363

Introduction to Statistical Methods

Spring 2019

Exam Overview

Topics for Exam 1

• Displaying data visually bar charts, segmented bar charts, histograms, boxplots, empirical cumulative distribution function, empirical survival function, time plots, scatterplots, explanatory and response variables
• Displaying data in tables, marginal distributions

• Summarizing one dimensional data numerically  - mean, variance, standard deviation, five number summary, quantiles, standardized variables
• Summarizing two dimensional data numerically  - covariance, correlation, linear regression, fit, residuals, extrapolation, non-linear transformations

• Producing data - observational study, natural and randomize controlled experiments
• Principles of experimental design issues with control, factors, levels, simple and stratified random samples

• Axioms of probability axioms, simple consequences of the axioms, conditional probability, law of total probability, Bayes formula, independence

• Random variables distribution functions, mass function for discrete random variables, density function for continuous random variables, their properties and their relationships

• Simulating random variables discrete random variables using sampling from a distribution, continuous random variables using the probability transform

• Expected values laws of the unconscious statistician, computing means and variances from the mass or density function.

• Families of random variables. Review but do not focus on memorizing formulas

Topics for Exam 2

• Law of large numbers and Monte Carlo integration
• Central limit theorem for sums and sample means arising from a simple random sample, estimation of probabilities using the z-score
• Delta method normal approximation for single and multivariable functions of sample means

• Method of moments estimation
• Maximum likelihood estimation
• Interval estimation, confidence intervals

• Issue associated with hypothesis testing null and alternative hypotheses, type I and type II errors, significance level and power.
• Likelihood ratios Neyman-Pearson framework
• Composite hypotheses power function, p-value
• One and two sample proportion tests
• One and two sample z procedures

• t-procedures one sample, matched pairs, two sample t-tests

·      Chi-square procedures G-test, determining degrees of freedom

·      One way analysis of variance F statistics, numerator and denominator degrees of freedom, confidence intervals

Course Homepage