Wednesday, 28 May 2014

Introduction to Statistical Issues in Clinical Trials

Streptomycin has a storied history, and many uses - it is the treatment of choice for plague, and is also used to control algae in ponds.  Its place in statistics history, though, dates to 1946, when a study demonstrated its effectiveness in cases of tuberculosis.  This study - controlled, double blind with a placebo - is generally regarded as the first randomized controlled trial (RCT).  Learn the principles of designing and analyzing RCT's in our online course, "Introduction to Statistical Issues in Clinical Trials," with Dr. Vidyadhar Phadke at Statistics.com. For more details please visit http://www.statistics.com/ClinicalStats/.

This course covers the basic statistical principles in the design and analysis of randomized controlled trials. Participants will learn the basic principles for the design of trials, and sample size determination. They will also learn the appropriate statistical techniques associated with the major types of end points for trials (categorical, count, Normal, non-Normal). Participants will also be introduced to pharmacokinetics and the study of drug concentration data.

Who can take this course:
Analysts and statisticians at pharmaceutical companies and other health research organizations who need or want to become involved in the design, monitoring or analysis of clinical trials.

Course Program:

Course outline: The course is structured as follows
SESSION 1: The Domain
  • What is a clinical trial?
  • Historical remarks, some diseases and discoveries
  • Steps(phases)in drug development
  • Scope of clinical trials: new drugs, generics, devices, psychiatric therapy, alternative medicine.
  • Role of statistics

SESSION 2: Planning a Clinical Trial - Statistican's Inputs
  • Principles of design of experiments (replication, local control, randomization)
  • Power and sample size
  • Bias reduction (blinding)
  • Commonly used designs

SESSION 3: Statistical Analysis Plan (SAP) of Clinical Trial
  • Trial objectives, hypotheses, choice of techniques, nature of endpoints (illustrated with live cases)
  • End point Binary: A Randomizated Evaluation of First-Dollar Coverage for Post-MI Secondary Preventive Therapies (Post-MI FREEE)
  • End point - Normal: accuracy study of SoftTouch (a non-invasive device for measurement of peripheral blood biomarkers)
  • End point - count data: Pediatric Asthma Alert Intervention for Minority Children With Asthma (PAAL)
  • End point - non-Normal: TBTC Study 27/28 PK: Moxifloxacin Pharmacokinetics During TB Treatment

SESSION 4: Illustrative Statistical Analysis of Clinical Trial Data
  • One sample problem - reduction in blood pressure
  • Two sample problem - anorexia
  • K-sample problem - drowsiness due to antihistamines
  • Cochrane's Q test - allergic response
  • Analysis of Time-concentration data in pharmacokinetic study

HOMEWORK:
Homework in this course consists of short answer questions to test concepts.
In addition to assigned readings, this course also has supplemental readings available online, and an end of course data modeling project.

Dr. Vidyadhar Phadke is Senior Statistician at Cytel Statistical Software and Services, the leading contract research organization for advanced design of clinical trials.  Dr. Phadke has responsibility for Cytel's industry-leading software for adaptive trials (EaSt) and dose-ranging trials (Compass).

You will be able to ask questions and exchange comments with the instructors via a private discussion board throughout the course.   The courses take place online at statistics.com in a series of 4 weekly lessons and assignments, and require about 15 hours/week.  Participate at your own convenience; there are no set times when you must be online. You have the flexibility to work a bit every day, if that is your preference, or concentrate your work in just a couple of days.

We, the Center for eLearning and Training (C-eLT), Pune, partner with Statistics.com and offer these courses to Indian participants at special prices payable in INR.

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

Call: 020 6680 0300 / 322

Websites:

Friday, 2 May 2014

Introduction to Statistical Modeling

If you've had some statistics and feel that mathematical notation and formulas are not your friend, consider Dr. Vittorio Addona's online course Introduction to Statistical Modeling at statistics.com.

This course provides a solid introduction to the ideas and techniques of statistical modeling. Once you have completed this course, you will be able to construct and interpret linear statistical models involving multiple variables and co-variates, you will understand the implications of including or excluding explanatory variables, you will be able to conduct and interpret analysis of variance (ANOVA) and of covariance (ANCOVA), and you will have a solid theoretical foundation for understanding linear regression and experimental design. For more details please visit at http://www.statistics.com/ModelingIntro/.

Who Should Take This Course:
Students who are planning to take regression and other modeling courses at statistics.com. Analysts or educators who need to work with multiple variables but are not comfortable with the standard formula- and linear-algebra based approach generally taken.

Course Program:
Course outline: The course is structured as follows

SESSION 1: What is a Statistical Model?
  • Explanatory and response variables
  • Model terms
  • Reading model formulas
  • Fitting models to data
  • Introduction to R software

SESSION 2: The Logic Behind Models
  • Statistical adjustment
  • Introduction to the geometry of model fitting:
    • case space vs variable space
    • variables as vectors
    • simple projection and least squares
    • the model triangle
  • Correlation as a measure of alignment

SESSION 3: Randomness and Models
  • Geometry of multiple explanatory variables
  • Random walks and random directions
  • Confidence intervals
  • Collinearity

SESSION 4: Inference and Models
  • The F statistic
  • Decomposing variance into parts
  • Ambiguities introduced by collinearity
  • The virtues of orthogonality

Homework:
The homework in this course consists of short answer questions to test concepts, guided data analysis problems using software, and guided data modeling problems using software.

In addition to assigned readings, this course also has supplemental readings available online, and example software codes.

The Instructor, Dr. Vittorio Addona, teaches statistics at Macalaster College in Minnesota.  His research falls into three broad categories: survival analysis, sports statistics, and election audits.  His doctoral work was in survival analysis, a statistical field often employed in medical studies of time-to-event data. Vittorio teaches across the statistics curriculum: introductory modeling, probability, mathematical statistics, and an applied survival analysis course.

This course takes place online 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. Course participants will be given access to a private discussion board. In class discussions led by the instructor, you can post questions, seek clarification, and interact with your fellow students and the instructor.

The course typically requires 15 hours per week. At the beginning of each week, you receive the relevant material, in addition to answers to exercises from the previous session. During the week, you are expected to go over the course materials, work through exercises, and submit answers. Discussion among participants is encouraged. The instructor will provide answers and comments, and at the end of the week, you will receive individual feedback on your homework answers.

We, the Center for eLearning and Training (C-eLT), Pune, partner with Statistics.com and offer these courses to Indian participants at special prices payable in INR.

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

Call: 020 6680 0300 / 322

Websites:

Monday, 28 April 2014

Text Mining

Peter Bruce, President and Founder of Statistics.com, says, as I read about the frenzy of interest in mining Twitter data, I think of the 1949 Gold Rush, which boosted the settler population of California from under 1,000 to over 100,000 in two years.  Most miners made little money, but suppliers of tools and owners of technology did quite well.

"Text Mining" will introduce the essential techniques of text mining, understood here as the extension of data mining's standard predictive methods to unstructured text. This course will discuss these standard techniques, and will devote considerable attention to the data preparation and handling methods that are required to transform unstructured text into a form in which it can be mined.

Learn about text mining techniques in Nitin Indurkhya's online course, "Text Mining," at statistics.com. For more details please visit http://www.statistics.com/textmining.

Who can take this course?
IT professionals, web marketing analysts, data mining and statistical consultants. In general: analysts and researchers who need to pilot, implement or analyze data mining methods aimed at data containing unstructured text (forms, surveys, etc.).

Course Program:
Course outline: The course is structured as follows

 

SESSION 1: Introduction and Data preparation
  • Overview of text mining
  • Tokenization
  • Dictionary creation
  • Vector generation for prediction
  • Feature generation and selection
  • Parsing

SESSION 2: Predictive Models for Text
  • Document classification
  • Document similarity and nearest-neighbor
  • Decision rules
  • Probabilistic models
  • Linear models
  • Performance evaluation
  • Applications

SESSION 3: Retrieval and Clustering of Documents
  • Measuring similarity for retrieval
  • Web-based document search and link analysis
  • Document matching
  • Clustering by similarity
  • k-means clustering
  • Hierarchical clustering
  • The EM algorithm for clustering
  • Evaluation of clustering

SESSION 4: Information Extraction
  • Goals of information extraction
  • Finding patterns and entities
  • Entity Extraction: The Maximum Entropy method
  • Template filling
  • Applications

HOMEWORK:
Homework in this course consists of short answer questions to test concepts and guided data analysis problems using software. In addition to assigned readings, this course also has a get started guide, and supplemental readings available online.

Software:
Python is used in the course.

Instructor Dr. Nitin Indurkhya, co-author of "Text Mining" (Springer) and co-editor of the "Handbook of Natural Language Processing" (CRC), was also Principal Research Scientist at eBay and Professor at the School of Computer Science and Engineering, University of New South Wales (Australia), as well as the founder and president of Data-Miner Pty Ltd, an Australian company engaged in data-mining consulting and education.

You will be able to ask questions and exchange comments with the instructors via a private discussion board throughout the course.   The courses take place online at statistics.com in a series of 4 weekly lessons and assignments, and require about 15 hours/week.  Participate at your own convenience; there are no set times when you must be online. You have the flexibility to work a bit every day, if that is your preference, or concentrate your work in just a couple of days.

We, the Center for eLearning and Training (C-eLT), Pune, partner with Statistics.com and offer these courses to Indian participants at special prices payable in INR.

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

Call: 020 6680 0300 / 322

Websites:

Friday, 18 April 2014

Sample Size and Power Determination

"How many subjects do I need?" is a common question from researchers.  "It depends" is the common, unsatisfactory, response.  Learn what the answer depends on in Thomas Ryan's online course, “Sample Size and Power Determination,” at Statistics.com.
For more details please visit at http://www.statistics.com/samplesize/.   

"Sample Size and Power Determination" covers how to plan the appropriate sample size for a study, striking the optimal balance of feasible sample size, reasonable assumptions, and acceptable power. The power of a study (the study's ability to prove a treatment effect exists) is determined by such factors as the magnitude of the treatment effect, the sample size, alpha (the level of statistical significance required), and (for survival studies) the study duration.

Since some of these factors are under the researcher's control while others are not, the goal of power analysis is to balance them as a series of "What if's." For example "What sample size would we need if the treatment reduces the risk of death by 10%, and what sample size would we need if the treatment reduces the risk of death by 20%?" Or, "How would power be affected if the study followed patients for two years rather than three?" This process of finding a balance among factors is done most effectively with graphs that allow the researcher to grasp (and communicate) a range of options in a single picture, and find the one that strikes the optimal balance of feasible sample size, reasonable assumptions, and acceptable power.  Illustrations include examples from means, proportions, correlations, and survival analysis, and possibly from other procedures as well.

Course Program:
Course outline: The course is structured as follows

SESSION 1: Introduction to Sample Size Determination and Power, Including Useful Software
  • Hypothesis tests and confidence intervals
  • Factors that determine sample size
  • Sample size for estimating a population mean
  • Examples, including a study from the literature
  • External and internal pilot studies
  • Ways to estimate sigma
  • What should be avoided:  Retrospective power and standardized effect sizes
  • Ethical issues in power analysis
  • Recommended references
  • Software
SESSION 2: Tests on Population Means (continued)
  • T-Test or Z-Test for population mean?
  • Testing the normality assumption
  • Confidence Intervals on Power and/or Sample Size?
  • Two-sample study from the literature with unequal sample sizes
    • Sample sizes determined by scientist in two stages without software
    • Illustration of more efficient sample determination using software
  • Using coefficient of variation
  • Paired data
  • Additional examples

SESSION 3: Tests on Proportions and Variances
  • One proportion    
    • Software disagreement and rectification
  • Two proportions
  • Options, including transformations built into software, for tests of proportions
  • One variance  and two variances
  • Examples
 SESSION 4: Regression and Design
  • Simple linear regression
    • Complexity caused by what must be inputted
  • Multiple linear regression
  • Optional material:  Repeated measures designs, Logrank test for survival analysis
  • Literature references for sample size determination with more advanced
    statistical methods and some information on corresponding software
    capability
     
HOMEWORK:
Homework in this course consists of short answer questions to test concepts and guided data analysis problems using software.
In addition to assigned readings, this course also has supplemental readings available online

Who Should Take This Course?
Anyone responsible for the planning of a study, or its subsequent analysis. Investigators writing grant applications or other proposals in which sample size must be specified.

The instructor, Dr. Thomas P. Ryan, is the author of "Sample Size and Power Determination" (Wiley, 2103), a number of other books, plus numerous papers in peer-reviewed journals.  He is an elected Fellow of the American Statistical Association, American Society for Quality, and Royal Statistical Society. Participants can ask questions and exchange comments with Dr. Ryan via a private discussion board throughout the period of the course.

You will be able to ask questions and exchange comments with the instructors via a private discussion board throughout the course.   The courses take place online at statistics.com in a series of 4 weekly lessons and assignments, and require about 15 hours/week.  Participate at your own convenience; there are no set times when you must be online. You have the flexibility to work a bit every day, if that is your preference, or concentrate your work in just a couple of days.

We, the Center for eLearning and Training (C-eLT), Pune, partner with Statistics.com and offer these courses to Indian participants at special prices payable in INR.

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

Call: 020 6680 0300 / 322

Websites:

Wednesday, 16 April 2014

Practical Rasch Measurement - Core Topics

Surveys and tests produce prodigious quantities of data for diagnostic and assessment purposes, but how useful is that data for decision-making?  Rasch models help you optimize the utility of quantitative information from surveys and exams. Learn what the Rasch model involves by taking Dr. Everett V. Smith’s online course "Practical Rasch Measurement - Core Topics". For more details please visit at http://www.statistics.com/rasch1.

Rasch analysis constructs linear measures from scored observations, such as responses to multiple-choice questions, Likert scales and quality-of-life assessments. This course covers the practical aspects of data setup, analysis, output interpretation, fit analysis, differential item functioning, dimensionality and reporting. Simple test linking and equating designs are addressed. Supporting theory is presented conceptually.
 
Who can take this course:
Survey researchers, social scientists who use surveys or questionnaires in their work, education assessment analysts and managers.

Course Program:
Course outline: The course is structured as follows

SESSION 1: Basic Concepts and Operations
  • Winsteps software installation and operation
  • Basic measurement and Rasch concepts
  • Simple dichotomous analysis
  • Constructing data files

SESSION 2: Fit Analysis and Measurement Models
  • Rasch-Andrich Rating Scale Model
  • Quality-control fit statistics
  • Scalograms

SESSION 3: Rating Scales, Reliability and Anchoring
  • Partial Credit Model
  • Category Description
  • Standard errors and Reliability
  • Anchoring

SESSION 4: DTF, DIF, and dimensionality
  • Differential Test Functioning
  • Differential Item Functioning
  • Investigating Dimensionality

HOMEWORK:
Homework in this course consists of short answer questions to test concepts and end of course project.
In addition to assigned readings, this course also has supplemental readings available online, and an end of course data modeling project.

The Instructor, Dr. Everett V. Smith Jr., Professor of Educational Psychology at the University of Illinois at Chicago, is co-editor of “Introduction to Rasch Measurement: Theory, Models, and Applications” (2004), “Rasch Measurement: Advanced and Specialized Applications” (2007), and “Criterion-Reference Testing: Practice Analysis to Score Reporting using Rasch Measurement Models” (2009). He also serves as the Associate Editor for the “Journal of Applied Measurement” and is on the editorial boards of “Educational and Psychological Measurement and the Journal of Nursing Measurement.” Participants can ask questions and exchange comments directly with Dr. Smith via a private discussion board throughout the period.

You will be able to ask questions and exchange comments with the instructors via a private discussion board throughout the course.   The courses take place online at statistics.com in a series of 4 weekly lessons and assignments, and require about 15 hours/week.  Participate at your own convenience; there are no set times when you must be online. You have the flexibility to work a bit every day, if that is your preference, or concentrate your work in just a couple of days.

We, the Center for eLearning and Training (C-eLT), Pune, partner with Statistics.com and offer these courses to Indian participants at special prices payable in INR.

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

Call: 020 6680 0300 / 322

Websites: