Silvermine House Steenberg Office Park, Tokai 7945 Cape Town, South Africa Telephone:

Transcription

1 SPSS-SA Silvermine House Steenberg Office Park, Tokai 7945 Cape Town, South Africa Telephone: SPSS-SA Training Brochure 2009

2 TABLE OF CONTENTS 1 SPSS TRAINING COURSES FOCUSING ON USING SPSS INTRODUCTION TO SPSS (FORMALLY SPSS BASICS) (2 DAYS) DATA MANAGEMENT AND MANIPULATION (FORMALLY INTERMEDIATE TOPICS) (2 DAYS) SPSS TRAINING COURSES FOCUSING ON STATISTICAL ANALYSIS INTRODUCTION TO SPSS AND STATISTICS (3 DAYS) INTRODUCTION TO STATISTICAL ANALYSIS USING SPSS (3 DAYS) ADVANCED STATISTICAL ANALYSIS (3 DAYS) MARKET SEGMENTATION USING SPSS (2 DAYS) INTRODUCTION TO AMOS (1 DAY) SURVEY ANALYSIS USING SPSS (3 DAYS) SPSS COURSES FOCUSSING ON SPECIFIC ADD-ON MODULES TIME SERIES ANALYSIS AND FORCASTING (3 DAYS) ADVANCED TECHNIQUES: REGRESSION (3 DAYS) ADVANCED TECHNIQUES: ANOVA (2 DAYS) PRESENTING DATA WITH SPSS TABLES: INTRODUCTION (1 DAY) PRESENTING DATA WITH SPSS TABLES: ADVANCED (1 DAY) INTRODUCTION TO SPSS DECISION TREES (1 DAY) SPSS SYNTAX FOR BEGINNERS (2 DAYS) SPSS SYNTAX FOR EXPERTS (1 DAY) INTRODUCTION TO SPSS TEXT ANALYSIS FOR SURVEYS (1 DAY) DATA MINING/ CLEMENTINE COURSES INTRODUCTION TO CLEMENTINE AND DATA MINING (2 DAYS) PREPARING DATA FOR DATA MINING (2 DAYS) PREDICTIVE MODELING WITH CLEMENTINE (2 DAYS) CLUSTERING AND ASSOCIATION MODELS WITH CLEMENTINE (1 DAY) INTRODUCTION TO TEXT MINING FOR CLEMENTINE (2 DAYS)

3 1 SPSS TRAINING COURSES FOCUSING ON USING SPSS 1.1 INTRODUCTION TO SPSS (FORMALLY SPSS BASICS) (2 days) Get up to speed in the use of SPSS quickly and easily in this two-day course. Learn the basics of data definition, data analysis and presentation of your results. See how easy it is to get your data into SPSS so that you can focus on analyzing the information. In addition to the fundamentals, learn shortcuts that will help you save time. This course is designed with the SPSS beginner in mind. Prerequisites: None, but trainees should be fully computer literate and have minimal statistical background 1. Introduction to SPSS 2. Using the Help System 3. Sources and Organisation of Data 4. Reading Data 5. Using the Data Editor 6. Working with Multiple Data Sources 7. Examining Summary Statistics for Individual Variables 8. Modifying Data Values 9. Crosstabulation Tables 10. Working with Output 11. Creating and Editing Charts 12. Working with SPSS Syntax 13. Multiple Response Variables 1.2 DATA MANAGEMENT AND MANIPULATION (FORMALLY INTERMEDIATE TOPICS) (2 days) The focus of this two-day course is on the use of a wide range of transformation techniques, ways to automate your work, manipulate your data files and results and send your output to other Windows applications. You will gain an understanding of the various options for operating SPSS and how to use syntax to perform data transformations efficiently. Prerequisites: Introduction to SPSS, or familiarity with SPSS 1. Automating SPSS using syntax and Production Mode 2. Further data transformations: Automatic Recode, Count, conditional transformations 3. Using Numeric Functions 4. Using System Variables 5. Computing Date, Time, and String variables 6. Helpful Data Management Features: Identify duplicate cases, Custom Attributes, Variable Sets 7. Aggregating Data 8. Merging Files - Adding cases 9. Merging Files - Adding variables 10. Editing Charts and Pivot Tables 11. Deploying SPSS results 12. Controlling the SPSS environment 13. Appendix A: Optimal Binning using SPSS Data Preparation Module (Add-on Module) 3

4 2 SPSS TRAINING COURSES FOCUSING ON STATISTICAL ANALYSIS 2.1 INTRODUCTION TO SPSS AND STATISTICS (3 days) This three-day course provides an introduction to using SPSS with particular regard to analysing quantitative information, data management and charting results. The training covers basic statistical theory and introduces many of the most popular statistical tests. The course focuses on how to use SPSS to enhance the typical data analysis process through informed statistical analysis and appropriate data presentation 1. Principles of Research Design 2. Introducing SPSS 3. Defining, Entering and Editing Data in SPSS 4. Using the Data Viewer II: Additional Features 5. Opening Data Files 6. Central Tendency & Dispersion 7. Summarising Data 8. The Output Viewer 9. Modifying Data Values 10. Making Inferences about Populations from Samples 11. Checking the Form of Distributions 12. Analysing Combinations of Categorical & Continuous Data using t-tests 13. Manipulating Files 14. Testing Relationships Between Categorical Variables 15. Improving Output 16. Editing Charts 17. Analysing Combinations of Continuous Variables using Correlations 2.2 INTRODUCTION TO STATISTICAL ANALYSIS USING SPSS (3 days) This is an application oriented course and the approach is practical. You'll take a look at several statistical techniques and discuss situations in which you would use each technique, the assumptions made by each method, how to set up the analysis using SPSS as well as how to interpret the results. Prerequisites: Completion of the courses, Introduction to SPSS and/or Data Management and Manipulation with SPSS or experience with SPSS; including familiarity with opening, defining, and saving data files and manipulating and saving output. Basic statistical knowledge or at least one introductory-level course in statistics is recommended. 1. Some Introductory Statistical Concepts 2. The Influence of Sample Size 3. Data Checking 4. Describing Categorical Data 5. Comparing Groups: Categorical Data 6. Exploratory Data Analysis: Interval Scale Data 7. Mean Differences Between Groups: Simple Case 8. One factor ANOVA 9. Two factor ANOVA 10. Bivariate Analysis 11. Introduction to Regression 4

5 2.3 ADVANCED STATISTICAL ANALYSIS (3 Days) In this three-day course you will learn some of the more advanced statistical procedures that are available in SPSS. Unlike the basic Introduction to Statistical Analysis course, this course also focuses on the syntax needed to generate the results you want. You will be introduced to several advanced statistical techniques and discuss situations when each may be used, the assumptions made by each method, how to set up the analysis using SPSS and how to interpret the results. This course is not recommended for delegates who have not attended the "Statistical Analysis using SPSS" course or covered similar content at some stage. Prerequisite: Statistical Analysis using SPSS, or similar experience/background 1. Introduction and Overview 2. Discriminant Analysis 3. Binary Logistic Regression 4. Multinomial Logistic Regression 5. Survival Analysis (Kaplan-Meier) 6. Cluster Analysis 7. Factor Analysis 8. Loglinear Analysis 9. Multivariate Analysis of Variance 10. Repeated Measures Analysis of Variance 2.4 MARKET SEGMENTATION USING SPSS (2 Days) In this two-day course you will focus on the statistical techniques most often used to support market segmentation. The course emphasizes the practical issues of setting up, running and interpreting the results of market segmentation analysis Prerequisite: Familiarity with SPSS, including variable definition, opening and saving data files, generation of basic exploratory statistics. The understanding of Central Tendency, Dispersion and Hypothesis Testing (including the t-test) is an essential prerequisite. 1. Overview of market segmentation methods 2. Cluster analysis basics 3. Running a cluster analysis 4. Factor analysis basics 5. Factoring methods and recommendations 6. Running a factor analysis 7. Response-based segmentation 8. Logistic regression 9. Discriminant analysis 10. CHAID Analysis 5

6 2.5 INTRODUCTION TO AMOS (1 Day) This course is an introduction to structural equation modelling (SEM) using Amos and its graphical interactive path modelling tools. During the course you will review the fundamentals of SEM. Modern advances in structural modelling and statistical methods are emphasized and demonstrated with practical examples drawn from a variety of application areas, such as customer satisfaction, healthcare, and education. 1. Overview of structural equation modelling 2. Simple regression models with Amos 3. Confirmatory factor analysis models 4. Specifying applied regression, factor analysis, and structural regression models 5. Tests of model adequacy and fit 6. Identification problems in factor analysis and structural equation models 7. Structural equation models with means and intercepts, for trend analysis and exact predictions 8. Multi-group models, with and without constraints across groups 9. Amos's efficient modelling approach for incomplete or missing data 10. Analysis of non-normal data: Applications of the bootstrap method to estimate empirical standard errors and confidence intervals of parameter estimates, and to obtain robust tests of model fit 11. Bayesian methods of estimation 2.6 SURVEY ANALYSIS USING SPSS (3 days) This three-day course reviews the standard methods that are used to analyze survey data, beginning with simple methods, such as crosstabulations and moving toward the advanced, such as logistic regression and decision tree methods. Appropriate methods of analysis are discussed for both categorical and continuous data. Also included are discussions of qualitative data analysis and the reporting and presentation of survey results. Prerequisites: Completion of the Introduction to SPSS and/or Data Management and Manipulation with SPSS courses or experience with SPSS, including familiarity with opening, defining, and saving data files and manipulating and saving output. Basic statistical knowledge or at least one introductory level course in statistics is recommended. 1. The Logic of Survey Analysis 2. Creating new Variables: Reliability and Validity 3. Relationships between Categorical Variables 4. Analyzing Interval Variables 5. Reporting Results 6. Analyzing Text Data 7. Clustering Respondents 8. Multivariate Analysis with Regression 9. Special Problems with Survey Data 6

7 3 SPSS COURSES FOCUSSING ON SPECIFIC ADD-ON MODULES 3.1 TIME SERIES ANALYSIS AND FORCASTING (3 Days) This three-day course will introduce you to a set of procedures for analyzing time series data. Learn how to forecast using a variety of models which take into account different combinations of trend, seasonality and prediction variables. Generate predicted values along with standard errors, confidence intervals and residuals. This course will also show you how to display your results graphically. Prerequisites: Attendees must be familiar with SPSS, have an understanding of basic statistics and hypothesis testing. It would be helpful to have a basic understanding of regression analysis. 1. What is Time Series Analysis? 2. Starting Time Series Analysis 3. Smoothing Time Series Data 4. Looking at the Smooth and the Rough 5. Using Moving Averages as Forecasts 6. Introduction to Exponential Smoothing 7. Measuring Model Performance 8. Fitting a Simple Curve to Time Series Data 9. Seasonal Decomposition 10. Multiple Regression and Autocorrelation 11. Autoregressive Models 12. Mixed Models and Outliers 13. Some Approaches to Modelling a Nonstationary Series 14. ARIMA Models for Seasonal Series 15. Regression with Autocorrelated Errors 3.2 ADVANCED TECHNIQUES: REGRESSION (3 days) This three-day course examines regression techniques used to explore the relationships between predictor variables and interval scale or categorical outcomes. You will develop an understanding of when and how to apply regression analysis and how to interpret the results. Additionally, the course will cover some preliminary data analysis steps, how to check the underlying assumptions and suggestions of how to proceed when your assumptions fail. Prerequisites: Familiarity with SPSS and an understanding of measures of central tendency and dispersion, inferential statistics, using interactive charts and editing and saving output. 1. Introduction to Regression 2. Examining data 3. Simple Regression 4. Multiple Regression 5. Stepwise Regression 6. Influential Points and Multicollinearity 7. Dummy variables 8. Logistic Regression 9. Multinomial Logistic Regression 10. Modelling Interactions 11. Polynomial Regression 12. Nonlinear Regression 7

8 3.3 ADVANCED TECHNIQUES: ANOVA (2 days) This two-day course focuses on the different Analysis of Variance techniques which allow you to test whether the means of several populations are the same. After discussing the basic assumptions for each technique you will check the assumptions, run the analysis and draw conclusions from the data. Prerequisites: Familiarity with SPSS and an understanding of Central Tendency, Dispersion and Hypothesis Testing (including the t-test) is an essential prerequisite. 1. Introduction to ANOVA 2. Examining data and testing assumptions 3. One-factor ANOVA 4. Multi-way Univariate ANOVA 5. Multivariate Analysis of Variance 6. Within-Subjects Designs: Repeated Measures 7. Between- and within-subjects ANOVA 8. Mixed Models ANOVA 9. Analysis of Covariance 10. Latin Square Designs 11. Random Effects Models 12. Hierarchical Linear Models 3.4 PRESENTING DATA WITH SPSS TABLES: INTRODUCTION (1 Day) In this one-day introductory course you will focus on using the SPSS Tables module to create publication quality tables. You will use Tables to generate stub and banner tables as well as complex multi-page tables with multiple variables and a variety of statistics, including the following significance tests: chi-square tests, t tests and z tests of proportions. Prerequisites: You must be familiar with the basics of operating SPSS and understand the difference between categorical and scale data types. 1. Visualization in exploring data (boxplots, pareto charts) 2. Deployment of models 3. Visualization in monitoring change over time (control charts) 4. Visualization of relationships (web graphs (Clementine), scatterplots, decision trees) 5. Automation (SPSS syntax, production mode, scripts, custom applications; Clementine scripts) 6. Deployment of results (SmartViewer Web Server, SPSS Viewer, SPSS Export function) 7. OLAP reporting 8. Getting Started with Custom Tables (the Table Builder) 9. Simple Categorical Tables 10. Stacking, Nesting, and Layers 11. Totals and Subtotals 12. Tables for Variables with Shared Categories 13. Summary Statistics 14. Tables Summarizing Scale Variables 15. Significance Testing 16. Multiple Response Tables 17. Missing Values 18. Formatting and Customising Tables 8

9 3.5 PRESENTING DATA WITH SPSS TABLES: ADVANCED (1 Day) In this new one-day advanced course, users of SPSS Tables will learn how to use the SPSS Tables module to build more complex and customized tables and produce them more efficiently. You will see options for handling missing values, formatting and editing tables and moving tables to other software, be introduced to SPSS Tables syntax for recurring analyses and learn time saving tips. Prerequisite: On-the-job experience with SPSS and SPSS Custom Tables, or completion of the courses "Presenting Data with SPSS Tables: Introduction" 1. Formatting and Editing Tables 2. Missing Values 3. Moving Tables to Other Software, Distributing Tables 4. Introduction to Tables Syntax 5. Using Syntax for Recurring Analyses 6. Special Purpose Tables I: Other Groupings 7. Special Purpose Tables II: Advanced Tables 8. Time Saving Features 3.6 INTRODUCTION TO SPSS DECISION TREES (1 Day) This one-day course covers the principles and practice of the tree-based classification and regression methods available in SPSS Classification Trees. A general introduction to the features of the SPSS Classification Trees module and an overview of decision tree based methods will be covered. These methods (CHAID, Exhaustive CHAID, CRT and QUEST) are used to perform classification, segmentation and prediction modelling in a wide range of business and research areas. The techniques are discussed and compared, analyses are performed and the results interpreted. 1. Overview of Features in SPSS Classification Trees 2. Overview and Comparison of Tree-Structured Methods 3. CHAID Analysis 4. Additional Features and CHAID Extensions 5. CRT Classification Trees 6. CRT Regression Trees 7. Tree-Structured Methods 8. QUEST Analysis 9. Recommendations and Tips 3.7 SPSS SYNTAX FOR BEGINNERS (2 Days) This two-day course, designed for current SPSS users of the graphical user interface, introduces the Syntax language on which SPSS is based. You will learn the rules of SPSS syntax, how to generate, write and modify it and how syntax is used to facilitate repeated SPSS analyses and perform operations not available through SPSS dialog boxes. Prerequisites: Attendees should also have basic familiarity with SPSS procedures including variable definition, entering and editing data, opening and saving data files, compute and recode procedures, dealing with output and saving output. 9

10 1. When SPSS syntax is helpful and why should it be used? 2. Syntax rules and structure 3. How to create and run syntax 4. Opening and saving SPSS Data Files 5. Structure and definition of variables 6. Introduction to transformation functions 7. String and date/time functions 8. Data transformations only available using syntax 9. Debugging syntax and reading error messages 3.8 SPSS SYNTAX FOR EXPERTS (1 Day) Following a brief Introduction, you will examine the difference between syntax, macros and scripting. Then you will be introduced to several programming concepts and commands and look at numerous practical examples for using advanced syntax programming to achieve difficult tasks: Prerequisites: Attendees should have completed the SPSS Syntax for Beginners course. Course Content 1. Introduction and syntax review 2. Basic SPSS programming concepts 3. Practical applications for advanced syntax 4. Introduction to Macros 5. Advanced Macros 6. SPSS Output Management System 3.9 INTRODUCTION TO SPSS TEXT ANALYSIS FOR SURVEYS (1 Day) This one-day course shows you how to analyze text or open-ended survey questions using SPSS Text Analysis for Surveys. You will see the steps involved in working with text data, from reading the text data to exporting the final categories for additional analysis. Topics include how to automatically and manually create and modify categories and how to edit synonym, type and exclude dictionaries. 1. Introduction and overview of SPSS Text Analysis for Surveys 2. Considerations before performing text analysis 3. Projects and help 4. Data access 5. Extracting terms 6. Category creation (automatic and manual) 7. Exporting categories 8. Editing dictionaries 9. Managing libraries and projects 10

11 4 DATA MINING/ CLEMENTINE COURSES 4.1 INTRODUCTION TO CLEMENTINE AND DATA MINING (2 days) This two-day course provides an overview of data mining and the fundamentals of using SPSS Clementine. Using the CRISP-DM methodology, the principles and practice of data mining are illustrated. The course structure follows the stages of a typical data mining project, from reading data, to data exploration, data transformation, modelling and effective interpretation of results. The course provides training in the basics of how to read, explore and manipulate data with Clementine and then create and use successful models. Prerequisites: General computer literacy. Attendees will also greatly benefit if they have an understanding of their organisation s data and knowledge of their organisation s business issues that are relevant to the use of data mining. No statistical background is necessary. 1. Introduction to Data Mining 2. The Basics of Using Clementine 3. Reading Data Files 4. Data Understanding 5. Introduction to Data Manipulation 6. Looking for Relationships in Data 7. Selecting and Partitioning Records 8. Modelling Techniques in Clementine 9. Rule Induction 10. Model Understanding 11. Comparing Models 12. Automating Models for Binary Outcomes 13. Deploying and Using Models 14. Other Topics: Suggestions, Automation and Deployment 4.2 PREPARING DATA FOR DATA MINING (2 Days) This two-day course reviews how to prepare data for a successful data mining project. Included are examples of appending and merging files, sampling and partitioning records from files, handling missing data and working with dates and sequence data. Prerequisite: General computer literacy. Some experience with using Clementine, including familiarity with the Clementine environment, creating streams, reading in data files and doing simple data exploration and manipulation. Prior completion of the Introduction to Clementine and Data Mining course is strongly encouraged. 1. Introduction to Data Preparation 2. Combining Data Files 3. Sampling Data 4. Missing Data 5. Outliers and Anomalous Data 6. Working with Dates 7. Working with String Data 8. Data Transformations 9. Working with Sequence Data 11

12 10. Aggregating Data 11. Exporting Data Files 12. Efficiency with Clementine 4.3 PREDICTIVE MODELING WITH CLEMENTINE (2 Days) This two-day course demonstrates how to develop models to predict categorical and continuous outcomes, using such techniques as neural networks, decision trees and logistic regression. Feature selection and detection of outliers are also discussed. Expert options for each modelling node are discussed in detail and advice is provided on when and how to use each model. You will also learn how to combine two or more models to improve prediction. Prerequisite: Experience using Clementine, including familiarity with the Clementine environment, creating streams, reading in data files, assessing data quality and handling missing data (including the Type and Data Audit nodes), basic data manipulation (including the Derive and Select nodes) and creation of models. Prior completion of the Introduction to Clementine and Data Mining course or the Preparing Data for Data Mining course is strongly encouraged. An introductory course in statistics, or equivalent experience, would be helpful for the statisticsbased modelling techniques. 1. Preparing data for modelling 2. Neural Networks 3. Decision Trees/Rule Induction 4. Linear Regression 5. Logistic Regression 6. Discriminant Analysis 7. Data Reduction: Principal Components 8. Time Series Analysis 9. Decision List 10. Finding the Best Model for Binary Outcomes 11. Getting the Most from Models 4.4 CLUSTERING AND ASSOCIATION MODELS WITH CLEMENTINE (1 Day) This course follows Introduction to Clementine and Data Mining or Preparing Data for Data Mining and is designed for anyone who wishes to become familiar with the full range of modelling techniques available in Clementine to segment (cluster) data and to create models with association or sequence data. If you want to successfully build such models using Clementine, this course is an essential part of the learning Prerequisites: General computer literacy. Experience using Clementine, including familiarity with the Clementine environment, creating streams, reading in data files, assessing data quality and handling missing data (including the type and data audit nodes), basic data manipulation (including the derive and select nodes), and creation of models. Prior completion of Introduction to Clementine and Data Mining is required and completion of Preparing Data for Data Mining is strongly encouraged. An introductory course in statistics, or equivalent experience, would be helpful for the statisticsbased modelling techniques. Overview: In this course you will learn how to segment or cluster data with all the clustering techniques available in Clementine. You will also discover how to create association models to 12

13 find rules describing the relationships among a set of items and create sequence models to find rules describing the relationships over time among a set of items. Following an overview of the main features and an introduction to essential terminology, you will proceed logically through the following topics: 1. Introduction to models for clustering and association 2. Preparing data for modelling 3. Clustering models 4. Association models 5. Sequence models 4.5 INTRODUCTION TO TEXT MINING FOR CLEMENTINE (2 Days) This course follows Introduction to Clementine and Data Mining and is designed for anyone who wishes to become familiar with the text mining capability of Clementine. For people wishing to successfully build such models using Clementine, this course is an essential part of the learning process. Prerequisites: General computer literacy. Experience using Clementine, including familiarity with the Clementine environment, creating streams, reading in data files, assessing data quality and handling missing data (including the type and data audit nodes), basic data manipulation (including the derive and select nodes), and creation of models. Prior completion of Introduction to Clementine and Data Mining is strongly encouraged. Overview: This two-day course shows how you can convert text to data for use in text mining and data mining applications. You will review the basic concepts of text analysis and learn how to extract and refine concepts from text, convert these concepts to data, and then perform text mining and data mining analyses. Both automation and deployment are discussed. Following an overview of the main features and an introduction to essential terminology, you will proceed logically through the following topics: 1. Introduction to text mining 2. Text Mining for Clementine 3. Extracting text in a field 4. The generated model 5. Analysis for concepts 6. Expert extraction options 7. Extracting text in documents 8. Text Mining Builder 9. Scoring new data 10. Linguistics and text mining 13