Data Analysis with IBM SPSS Statistics电子书

Title Page

Copyright

Data Analysis with IBM SPSS Statistics

Credits

About the Authors

Acknowledgement

About the Reviewers

www.PacktPub.com

Why subscribe?

Customer Feedback

Preface

What this book covers

What you need for this book

Who this book is for

Conventions

Reader feedback

Customer support

Downloading the example code

Errata

Piracy

Questions

Installing and Configuring SPSS

The SPSS installation utility

Installing Python for the scripting

Licensing SPSS

Confirming the options available

Launching and using SPSS

Setting parameters within the SPSS software

Executing a basic SPSS session

Summary

Accessing and Organizing Data

Accessing and organizing data overview

Reading Excel files

Reading delimited text data files

Saving IBM SPSS Statistics files

Reading IBM SPSS Statistics files

Demo - first look at the data - frequencies

Variable properties

Variable properties - name

Variable properties - type

Variable properties - width

Variable properties - decimals

Variable properties - label

Variable properties - values

Variable properties - missing

Variable properties - columns

Variable properties - align

Variable properties - measure

Variable properties - role

Demo - adding variable properties to the Variable View

Demo - adding variable properties via syntax

Demo - defining variable properties

Summary

Statistics for Individual Data Elements

Getting the sample data

Descriptive statistics for numeric fields

Controlling the descriptives display order

Frequency distributions

Discovering coding issues using frequencies

Using frequencies to verify missing data patterns

Explore procedure

Stem and leaf plot

Boxplot

Using explore to check subgroup patterns

Summary

Dealing with Missing Data and Outliers

Outliers

Frequencies for histogram and percentile values

Descriptives for standardized scores

The Examine procedure for extreme values and boxplot

Detecting multivariate outliers

Missing data

Missing values in Frequencies

Missing values in Descriptives

Missing value patterns

Replacing missing values

Summary

Visually Exploring the Data

Graphs available in SPSS procedures

Obtaining bar charts with frequencies

Obtaining a histogram with frequencies

Creating graphs using chart builder

Building a scatterplot

Create a boxplot using chart builder

Summary

Sampling, Subsetting, and Weighting

Select cases dialog box

Select cases - If condition is satisfied

Example

If condition is satisfied combined with Filter

If condition is satisfied combined with Copy

If condition is satisfied combined with Delete unselected cases

The Temporary command

Select cases based on time or case range

Using the filter variable

Selecting a random sample of cases

Split File

Weighting

Summary

Creating New Data Elements

Transforming fields in SPSS

The RECODE command

Creating a dummy variable using RECODE

Using RECODE to rescale a field

Respondent's income using the midpoint of a selected category

The COMPUTE command

The IF command

The DO IF/ELSE IF command

General points regarding SPSS transformation commands

Summary

Adding and Matching Files

SPSS Statistics commands to merge files

Example of one-to-many merge - Northwind database

Customer table

Orders table

The Customer-Orders relationship

SPSS code for a one-to-many merge

Alternate SPSS code

One-to-one merge - two data subsets from GSS2016

Example of combining cases using ADD FILES

Summary

Aggregating and Restructuring Data

Using aggregation to add fields to a file

Using aggregated variables to create new fields

Aggregating up one level

Preparing the data for aggregation

Second level aggregation

Preparing aggregated data for further use

Matching the aggregated file back to find specific records

Restructuring rows to columns

Patient test data example

Performing calculations following data restructuring

Summary

Crosstabulation Patterns for Categorical Data

Percentages in crosstabs

Testing differences in column proportions

Crosstab pivot table editing

Adding a layer variable

Adding a second layer

Using a Chi-square test with crosstabs

Expected counts

Context sensitive help

Ordinal measures of association

Interval with nominal association measure

Nominal measures of association

Summary

Comparing Means and ANOVA

SPSS procedures for comparing Means

The Means procedure

Adding a second variable

Test of linearity example

Testing the strength of the nonlinear relationship

Single sample t-test

The independent samples t-test

Homogeneity of variance test

Comparing subsets

Paired t-test

Paired t-test split by gender

One-way analysis of variance

Brown-Forsythe and Welch statistics

Planned comparisons

Post hoc comparisons

The ANOVA procedure

Summary

Correlations

Pearson correlations

Testing for significance

Mean differences versus correlations

Listwise versus pairwise missing values

Comparing pairwise and listwise correlation matrices

Pivoting table editing to enhance correlation matrices

Creating a very trimmed matrix

Visualizing correlations with scatterplots

Rank order correlations

Partial correlations

Adding a second control variable

Summary

Linear Regression

Assumptions of the classical linear regression model

Example - motor trend car data

Exploring associations between the target and predictors

Fitting and interpreting a simple regression model

Residual analysis for the simple regression model

Saving and interpreting casewise diagnostics

Multiple regression - Model-building strategies

Summary

Principal Components and Factor Analysis

Choosing between principal components analysis and factor analysis

PCA example - violent crimes

Simple descriptive analysis

SPSS code - principal components analysis

Assessing factorability of the data

Principal components analysis of the crime variables

Principal component analysis – two-component solution

Factor analysis - abilities

The reduced correlation matrix and its eigenvalues

Factor analysis code

Factor analysis results

Summary

Clustering

Overview of cluster analysis

Overview of SPSS Statistics cluster analysis procedures

Hierarchical cluster analysis example

Descriptive analysis

Cluster analysis - first attempt

Cluster analysis with four clusters

K-means cluster analysis example

Descriptive analysis

K-means cluster analysis of the Old Faithful data

Further cluster profiling

Other analyses to try

Twostep cluster analysis example

Summary

Discriminant Analysis

Descriptive discriminant analysis

Predictive discriminant analysis

Assumptions underlying discriminant analysis

Example data

Statistical and graphical summary of the data

Discriminant analysis setup - key decisions

Priors

Pooled or separate

Dimensionality

Syntax for the wine example

Examining the results

Scoring new observations

Summary