| Statistical
Analyst Certificate
Curriculum
To earn
the Statistical Analyst Certificate, participants must successfully
complete each of the program's four modules:
Fundamentals
of Statistics
This
module is designed to give you an understanding of the use
of descriptive and inferential statistics. Applying techniques
of correlation and regression analysis are stressed, rather
than derivation or memorization of formulas. The module includes
a review of software packages commonly used to analyze data.
Microsoft Excel™ is used for initial exercises, and SAS JMP™
is used for calculations and analysis. Topics include
- Statistical
software overview, including Excel™, SAS JMP™, Minitab™,
and SAS Enterprise Guide™
- Basic
statistics review
- Graphical
techniques
- Hypothesis
testing
- Correlation
- Model
building
- Simple
linear regression
- Analysis
of variance
- Non-parametric
statistics
Design
of Experiments
This
hands-on computer workshop, conducted as a day and a half
seminar, provides an overview of design of experiments (DOE)
and applications using SAS JMP™. You will be introduced to
the benefits of DOE as you solve problems and gain increased
knowledge of your products and processes. The aim is to enable
you to use your statistical software to design an experiment,
analyze the results to understand your products/ processes
more completely, make predictions, and determine optimum settings.
Topics include
- Factorial
experiments
- Screening
designs—design and analysis
- Response
surface designs and models
- Predictions
and optimization
- Graphical
techniques
Statistical
Process Control
Measuring
and improving processes is a key application of statistics.
This module, which is conducted as a day and a half workshop,
focuses on a number of techniques used to measure process
capability and outputs. Topics include
- Quality
improvement and statistics
- Statistical
process control
- Control
charts
- Process
capability
- Measurement
systems capability
Analysis
of Historical Data
The statistical
analyst is often confronted with data that can be characterized
as massive, operational, and/or opportunistic in contrast
with data gleaned from well designed and focused experimental
efforts. The computational and analytical strategy for dealing
with this kind of data is multidisciplinary and creative in
nature. The primary goal for this type of statistical analysis
is to develop meaningful predictive models that yield useful
information for decision making. In addition to building on
the uses of regression analysis, this module introduces strategies
such as data mining and predictive modeling. The topics covered
include
- Historical
perspective of happenstance data
- Pitfalls
of analyzing historical data
- Regression
analysis
- Logistic
regression
- Data
mining
- Predictive
modeling
| If
you have previously completed coursework in the Data Management
and Statistical Analysis Certificate, please contact Mica
Corradin at 302/571-5239 or corradin@udel.edu
to determine completion requirements. |
|
