Summer graduate Courses

In the rapidly evolving field of computational biology, the integration of artificial intelligence (AI) and machine learning (ML) is opening new frontiers in research and applications. This advanced course, designed for graduate-level students, delves into the transformative impact of AI and ML on computational biology, exploring both theoretical foundations and practical applications.

The utility of designed experiments has been recognized in the world
of business and marketing as a tool to increase conversion, strengthen
customer retention, and improve the bottom line. Companies like
Google, Amazon, Meta, Netflix, Airbnb and Lyft have all adopted
experimentation and A/B testing for these purposes. As such, data
science practitioners and professionals find experimentation a
foundational tenet of the field. This course provides an in-depth look
into statistical and computational techniques for designing and
analyzing experiments that are regularly used in tech and data science
companies. Concepts that will be covered include:

• hypothesis testing under two and multiple conditions
• randomization and factorial experimental design
• multi-armed bandits
• A/B and A/B/C testing
• modern experimentation in industry
• the relationship between power, effective sample size, and level of confidence
• metrics for interpreting the effectiveness of an experiment

This course gives an overview of Bayesian Networks with application in R. The focus will be Bayesian network modeling, from structural learning to parameter learning and inference. Classic discrete, Gaussian, and conditional Gaussian networks will be described. Applications will showcase the wealth of R packages dedicated to learning and inference.

This course covers:

• A Definition of a Random Variable
• Properties of Discrete Random Variables: The Distribution (pmf and CDF), Mean, Variance
• Important Discrete Random Variables: Binomial, Poisson, Geometric, Negative Binomial
• Properties of Discrete Random Variables: The Distribution (pdf and CDF), Mean, Variance
• Important Continuous Random Variables: Uniform, Exponential, Normal
• Advanced Topics: Sums of Random Variables, Covariance, Independence, Transformations

This course covers:

• A The Distribution of Estimators (Moment Generating Functions)
• Properties of Estimators: Bias, Mean Square Error, Relative Efficiency and Consistency
• Advance Topics of Estimators: Cramer-Rao Lower Bound, Maximum Likelihood Estimators and Method of Moments Estimators
• Interval Estimators: Pivotal Quantities, Confidence Intervals
• Introduction to Hypothesis Testing: Stating the Null and Alternative Hypothesis, Types of Errors, Power of a Test, Neyman-Pearson Lemma

This course aims to provide students with a foundational understanding of image processing using Python. Topics covered include: Basics of working with images, Intensity transformation, Spatial filtering, Frequency domain filtering, Morphological image processing, Color image processing, Image segmentation, Feature extraction, Image pattern classification. By the end of this course, students will have a comprehensive grasp of image processing techniques in Python.

This course covers:

• A One-Sample Analysis: Confidence Intervals and Hypothesis Testing for a Population Mean, Population Variance and a Population Proportion
• Tests for Normality
• Two-Sample Analysis: Two-Sample Means, Paired t-test, Two-Sample Variances (F-test, Bonett, and Levine)
• Other Chi-Square Tests: Chi-Square Goodness of Fit, Chi-Square Test for Association

Analysis of Variance: 1-way ANOVA, Multiple Range Tests, Kruskal-Wallis Test, Welch’s ANOVA, 2-Way ANOVA, ANOVA with Interaction, Model Adequacy Checking

Regression Analysis: Correlation, Simple Linear Regression, Quadratic Regression, Transformations in Regression, Multiple Regression

Storytelling Through Data Visualization is designed to introduce students to the principles and best practices of data visualization. Students will learn how to effectively communicate data and information through visual storytelling. The course will cover topics such as data preparation, chart selection, design principles, and interactive visualization, through hands-on exposure to industry-standard data visualization software platforms.

Time series are ordered series of data points collected over time.  This course is an introduction to the analysis of time series using R software.  The main topics covered in this course include the following: basic characteristics and visualization of time series, autocorrelation, stationarity, ARIMA models, time series regression, seasonality, and forecasting.

This course will build on the topics explored in TSR1. It will start with additional time domain topics such as unit root testing, long-memory, and modeling volatility with autoregressive conditionally heteroskedastic (ARCH) specifications. These fundamentals will then be extended to state space models (also called dynamic linear models). This is a very general class of models that subsume many special cases of interest. Here we will explore prediction, filtering, smoothing and several special topics. Time permitting, we will discuss the frequency domain approach to time series analysis.

This course will cover data structures and algorithms that advanced Python programmers need to write code that runs faster and more efficiently. Topics will include Big O notation, linked-lists, searching, sorting, greedy algorithms, hashes, stacks, queues, and graphs. The course is designed to meet the demands of coding interviews.