Fast Track your Knowledge of SPSS Inc. Software
with Our Training Courses

This session will show you the skills needed to build the "right" Web templates to display surveys created with Data Collection (formerly Dimensions). With Data Collection, you have the creative license to make surveys as engaging as possible for the respondent. This training session will touch upon all the key areas of Web template creation, introducing best practices and providing re-usable content that attendees will be able to take home with them. This hands-on session will introduce simple concepts and then build upon them to produce robust and efficient Web template designs. Topics include:

• Building and deploying custom survey templates
• Using styles to affect formatting
• Best practices for survey presentation

Pre-requisites:

Must have deployed at least two (2) Web based Data Collection surveys. No experience of HTML or Web Design is necessary. However, those with experience in any of these areas will benefit from attending this session.

In IBM SPSS Statistics 17 (formerly SPSS Statistics), a new feature was introduced that allows users to build new dialog boxes with relative ease. The feature, Custom Dialog Builder, provides the ability to create a Graphical User Interface for any IBM SPSS Statistics functionality. In addition, IBM SPSS Collaboration and Deployment Services 4.0 (formerly SPSS Predictive Enterprise Services), users gained the ability to deploy these dialogs via a Web-based portal for easy but controlled access across an entire organization. This course will walk you through the necessary steps to build a custom dialog and deploy it over the Web. Topics will include:

• Building and testing Custom Dialogs within IBM SPSS Statistics 18
• Deploying the dialogs on individual users desktops
• Deploying the dialog to an entire enterprise via the Collaboration and Deployment Services deployment portal

Pre-requisites:

Familiarity with construction of IBM SPSS Statistics Syntax will be helpful, but not required.

This course will focus on building and comparing Decision Tree and Logistic Regression models in IBM SPSS Modeler (formerly Clementine). You will see the steps involved in creating, validating, evaluating, and finally comparing the models to determine which model is performing best. During the session, you will also be introduced to the Analysis and Evaluation Nodes, which automatically allow you to validate, evaluate, and compare several models at once. This hands-on training will include the following topics:

• Comparison of Decision Tree techniques in Modeler
• Rule Induction using C5.0 and CHAID
• Logistic Regression
• Browsing the models
• Determining the accuracy of each model
• Comparing the models using the Analysis Node
• Comparing the models using the Evaluation Node

Pre-requisites:

Introduction to Clementine and Data Mining or Introduction to IBM SPSS Modeler and Data Mining or comparable experience with IBM SPSS Modeler or Clementine.

Have you ever wondered how to make IBM SPSS Modeler (formerly Clementine) streams more efficient? Or do you have repetitive data mining tasks which take up too much time? This course, led by an SPSS Inc. data mining expert, will show you the best ways to make your streams and workflow more efficient. From proper node sequencing and SQL pushback to sample scripts for automation, there are many techniques that can be used to improve stream creation and function. This hands-on training will include topics covering:

• Optimizing IBM SPSS Modeler streams
• Making use of Global and stream parameters
• Using scripts to streamline standard tasks
• Techniques for automating the creation of models
• Manipulating data sources

Pre-requisites:

Experience using IBM SPSS Modeler or Clementine for creation of data mining streams. The courses Introduction to Clementine and Data Mining or Introduction to IBM SPSS Modeler and Data Mining will also be beneficial.

This session provides a hands-on introduction detailing methods of conducting analysis on survey data. Appropriate methods of analysis are discussed for both categorical and continuous data. Steps to produce and interpret five procedures, with appropriate statistical tests, are presented. We will also discuss how to report the results using appropriate charts and tables. This hands-on training will include topics covering:

• Cross-tabulation, with Chi-square tests (including its limitations)
• Multiple Response analysis (check all that apply "questions")
• Comparing mean differences, including
• T-tests
• Analysis of Variance (ANOVA)
• Introduction to Regression

Pre-requisites:

Introduction to IBM SPSS Statistics (formerly Basics with SPSS for Windows) or comparable experience with IBM SPSS Statistics.

IBM SPSS Custom Tables (formerly SPSS Custom Tables) can be used to generate stub and banner tables as well as complex multi-page tables with multiple variables. This course focuses on how to create publication-quality tables using the Custom Tables module of IBM SPSS Statistics, including new features in version 18. This hands-on training will include the following topics:

• Creating tables from categorical and scale variables
• Creating summary statistics
• Displaying information with stacking, nesting, and layers
• Creating and displaying comparison test statistics
• Using the new post-compute feature to create new columns and rows
• Using syntax to automate the creation of custom tables

Pre-requisites:

Introduction to IBM SPSS Statistics (formerly Basics with SPSS for Windows) or comparable experience with IBM SPSS Statistics. Some knowledge of IBM SPSS Statistics syntax is also recommended.

This course is designed to introduce new users to IBM SPSS Modeler (formerly Clementine). The course reviews the basic operations and environment for this data mining software. You will learn how to read data into IBM SPSS Modeler, assess the quality of your data, manipulate data within IBM SPSS Modeler, and explore relationships among fields. The last sections will provide a general introduction to the different modeling techniques IBM SPSS Modeler has to offer. This hands-on training will cover topics including:

• Introduction to data mining
• The basics of using IBM SPSS Modeler
• Reading data files
• Auditing and exploring data quality
• Searching for anomalous data and outliers
• Sampling data
• Modeling techniques in IBM SPSS Modeler
• Evaluating and comparing model performance
• Deploying and using models

Pre-requisites:

Only an interest in learning the basics of data mining!

Do you have an interest in the Python language? Or have you ever found a state-of-the-art algorithm coded in R that you wanted to add to IBM SPSS Statistics (formerly SPSS Statistics)? In this course, we will show you how to make use of functions written in the Python and R languages within IBM SPSS Statistics 18 and distribute them to users who do not know anything about these languages. We will work through a complete end-to-end solution from designing custom dialog boxes, defining IBM SPSS Statistics-style syntax for them, integrating with R and Python functions, and packaging and deploying to your organization. Upon completion of this course, you will be able to tap into the rich library of R functions or build off of the plentiful Python language examples on SPSS Developer Central to add custom functionality and procedures to make IBM SPSS Statistics your own. This hands-on training will include the following topics:

• Building and testing custom dialogs within IBM SPSS Statistics 18
• Creating syntax for extension commands implemented in Python or R
• Integrating R and Python functions inside IBM SPSS Statistics
• Delivering custom output including pivot tables and graphics from external functions to the Statistics Viewer window
• Packaging the custom procedures for sharing with co-workers

Pre-requisites:

An understanding of IBM SPSS Statistics Syntax formulation and experience or interest in R and/or Python programming will be helpful. This course will not teach the basics of R or Python programming.