Adaptive Designs for Clinical Trials

Mr. Peter Bruce is President of The Institute for Statistics Education at Statistics.com, if you flip a coin hundreds of times, there are sure to be points at which the proportion of heads or tails seems high. It is this phenomenon that makes it tricky to stop a clinical trial part way through, and claim success with statistical validity. The statistical design protocol must allow for flexible endpoints, and this flexibility must be paid for with more stringent alpha levels. Flexible (adaptive) designs are increasingly popular - learn more with Vidyadhar Phadke in his online course, "Adaptive Designs for Clinical Trials," at Statistics.com. For more details please visit at http://www.statistics.com/adaptive/.

Classic statistical study designs have static features (sample size, allocation scheme, etc.) that don't let you take advantage of new information that comes in during a clinical trial. Adaptive designs let you modify the characteristics of ongoing trials based on interim results in the study. Adaptive designs increase the probability of success, reduce costs and the time to market, and promote accurate drug delivery to patients. However, they must be done properly to preserve statistical validity.

"Adaptive Designs for Clinical Trials" will introduce the adaptive design theory and the hands-on techniques for planning, designing, monitoring, and analyzing adaptive trials. It covers sample-size re-estimation, drop-loser, biomarker-adaptive design, and response-adaptive randomization designs.

Who Should Take This Course:

Statisticians with responsibility for designing, analyzing and reporting clinical trials.

Course Program:

Course outline: The course is structured as follows

SESSION 1: 

• General Concept
• Fundamental Theory
• Group Sequential Design
• Adaptive Interim Analysis in Clinical Trials

SESSION 2: 

• Adaptive Dose Finding Design
• Enrichment Design for Target Clinical Trials

SESSION 3: 

• Two-Stage Adaptive Design
• Sample size estimation/allocation

SESSION 4: 

• Protocol Amendments
• Clinical Trial Simulation
• Efficiency of Adaptive Design
• Case Studies

Dr. Vidyadhar Phadke, instructor, is a Senior Statistician with Cytel, Inc. the leading provider of clinical trial design services and a pioneer in the area of adaptive design.

Participants can ask questions and exchange comments with Dr. Phadke via a private discussion board throughout the period. The course takes place online at statistics.com in a series of 4 weekly lessons and assignments, and requires about 15 hours/week. Participate at your own convenience; there are no set times when you are required to be online.

For Indian participants statistics.com accepts registration for its courses at special prices in Indian Rupees through its partner, the Center for eLearning and Training (C-eLT), Pune.

For India Registration and pricing, please visit us at www.india.statistics.com.

Email: info@c-elt.com

Call: 020 66009116

Websites:

www.india.statistics.com

www.c-elt.com

Modeling in R

In "Modeling in R" you learn how to use R to build statistical models and use them to analyze data. Multiple regression is covered first, then logistic regression and the generalized linear model (multiple regression and logistic regression illustrated as special cases). The Poisson model for count data, and the concept of overdispersion are also covered. You learn how to analyze longitudinal data using straightforward graphics and simple inferential approaches, then mixed-effects models and the generalized estimating approach for such data.

The course emphasizes how to fit the models listed and interpret results, rather than how to derive the theoretical background of the models. Join Dr. Sudha Purohit in her online course "Modeling in R". For more details please visit at http://www.statistics.com/modelingr/.

Who Should Take This Course:

Anyone who is familiar with R and wants to learn how to use it to build and use statistical models.

Course Program:

Course outline: The course is structured as follows

SESSION 1: Linear Regression, Logistic Regression

• Multiple linear regression with R
• Simple examples, dummy explanatory variables, interpreting regression coefficients; finding a parsimonious model

SESSION 2: The Generalized Model With R

• Logistic regression with R
• The need for a different model when the response variable is binary, the logistic transform and fitting the model to some simple examples, deviance residuals
• Multiple regression and logistic regression as special cases of the generalized linear model
• The Poisson model for count data.
• The problem of overdispersion

SESSION 3: Analysing Longitudinal Data Using R

• Examples of longitudinal data
• Simple graphics for longitudinal data and simple inference using the summary measure approach
• The 'long form' of longitudinal data
• Models for longitudinal data when independence of the repeated measurements is assumed
• Mixed-effects models for longitudinal data

SESSION 4:  Generalized Estimating Equations

• Modeling the correlational structure of the repeated measurements
• The generalized estimating equation approach for non-normal response variables in longitudinal data
• The dropout problem

Dr. Sudha Purohit, Instructor, is a Visiting Lecturer in Statistics at the University of Pune and, before her retirement in 2000, was Head of the Department of Statistics at A. G. College, Pune, India. She is a co-author of "Statistics Using R" (jointly with Prof. Shailaja Deshmukh and Dr. Sharad Gore), as well as "Life-Time Data: Statistical Models and Methods", "Introduction to Biometry", and (with Dr. Shailaja Deshmukh) "Microarray Data: Statistical Analysis Using R". 

Participants can ask questions and exchange comments with Dr. Purohit via a private discussion board throughout the period. The course takes place online at statistics.com in a series of 4 weekly lessons and assignments, and requires about 15 hours/week. Participate at your own convenience; there are no set times when you are required to be online.

For Indian participants statistics.com accepts registration for its courses at special prices in Indian Rupees through its partner, the Center for eLearning and Training (C-eLT), Pune.

For India Registration and pricing, please visit us at www.india.statistics.com.

Email: info@c-elt.com

Call: 020 66009116

Websites:

www.india.statistics.com

www.c-elt.com

Wrangling and Munging Data with SQL and R

"I didn't have time to write a short letter, so here's a long one" (Mark Twain). Such is the case with data in organizations - its natural state is sprawling, complex, often messy and overweight. Statistical analysis (including much data mining) needs trim, well-organized data.

Most big data are stored in relational database management systems in a set of related tables. Statistical analysis needs that data in a single table. Learn how to use SQL (structured query language) programming language to pull data from various tables in a database and assemble it in a format amenable to statistical analysis in R.

The purpose of this course is to teach you how to extract data from a relational database using SQL, and merge it into a single file in R, so that you can perform statistical operations. Join Kathryn Vasilaky in her online course "Wrangling and Munging with SQL and R". For more details please visit at http://www.statistics.com/data-munging/.

Who Should Take This Course:

This course is meant for beginners in data science who need to learn how to extract data from their relational databases.  It can also be a good kickstarter course for individuals who have fluency in SPSS, SAS, or STATA. Such data scientists might not have had to work with relational databases directly before, or they may not be familiar with the syntax and logic of a more object oriented language like R.

Course Program:

Course outline: The course is structured as follows

Session 1: Thinking Ahead, How to Organize your Data?

• Discussion and visuals of data models how data are stored in Postgres(SQL), i.e. entity relationship schemes, vs. R, flat files or data frames.
• Unique identifiers, and primary vs. foreign keys
• Defining your statistical objectives. Writing pseudo code to manipulate your data into its necessary form.
• Questions we’ll ask: Will I need all the data (panel), or should I collapse it on a particular variable (cross section)?
• Restoring a database in Postgres (this is repeated in Week Two?)

Session 2:  Basic SQL Procedures and Functions

• Using commands: Select, Where, Like, Order By
• Using functions, Count, Avg, Sum
• Using group-by and sortCopying tables to csv

Session 3:  Bringing SQL into R

• Joins (Inner, Outer, and multiple joins) in SQL
• Using the ODBC driver to run SQL queries in R.
• Reading in csv files
• Joins vs merges?
• Formatting dates
• Subsetting data and merging it back in

Session 4:  Working in R

The Reshape2 function in R to reshape data long or wide in R
Plyr function in R for grouping data

• Performing a few basic statistical calculations in R
• Data summaries
• Linear regression
• T-test
• Basic Graphs with Ggplot

Dr. Kathryn Vasilaky has worked at the World Bank, the Gates Foundation, the Federal Reserve, TroopSwap (a tech start-up in Washington DC), and as a soloist dancer with the San Francisco Ballet. She has a wealth of experience extracting and preparing data for analysis and business decision-making: macroeconomic data, commodity data, data resulting from experiments, social network data, e-commerce data, and other web data.

This course takes place over the internet at the Institute for 4 weeks. During each course week, you participate at times of your own choosing - there are no set times when you must be online. The course typically requires 15 hours per week. Course participants will be given access to a private discussion board so that they will be able to ask questions and exchange comments with instructor, Dr. Iain Pardoe. The class discussions led by the instructor, you can post questions, seek clarification, and interact with your fellow students and the instructor.

For Indian participants statistics.com accepts registration for its courses at special prices in Indian Rupees through its partner, the Center for eLearning and Training (C-eLT), Pune.

For India Registration and pricing, please visit us at www.india.statistics.com.

Email: info@c-elt.com

Call: 020 66009116

Websites:

www.india.statistics.com

www.c-elt.com