Data Analytics using IBM SPSS Statistics

From Survey Data into Paper Publications

Author

Kamarul Ariffin

General Information

Description

This is a full day beginner to intermediate level workshop on how to analyze survey data recorded from a structured questionnaire using IBM SPSS Statistics.

Expectations and Goals

At the end of the session, participant will be able to know how to handle survey data and prepare the data for further analysis using statistical software IBM SPSS Statistics (any version). In addition, participant will know how to analyze data with respect to specific research questions or objectives, and eventually present the result in proper way in papers or articles for publication purposes.

Workshop Materials

Required Materials

  • IBM SPSS Statistics (any version – IBM SPSS Statistics version 26 will be provided if participant don’t have one installed in his or her computer)
  • Presentation slides (provided by instructor)
  • Data set (provided by instructor or use own data set)

Optional Materials

Will be provided during the workshop if any.

Required Text

Provided by instructor

Workshop Schedule

Time Activity
08:00 – 08:15 Registration
08:15 – 10:15 Slot 1
10:15 – 10:30 Break
10:30 – 12:30 Slot 2
12:30 – 14:00 Lunch
14:00 – 16:00 Slot 3
16:00 – 16:30 Q&A
16:30 Session End
Item Topic Duration Exercise
Slot 1

Pre-works

- Data preparation

- Code and recode variables

- Missing values

- Normality

- Compute new variables

- Outliers

- etc.

 2 – 2 ½ hours Step by step approach preparing survey data for analysis using IBM SPSS Statistics
Slot 2

Descriptive Statistics

- Categorical data

- Numerical data

- Frequency distribution

- Data visualization

- Handling of Likert Scale data

Inferential Statistics (Basic)

- t-test

- one way ANOVA

- chi-square test of independence

 2 – 2 ½ hours

How to report demographic profile in papers?

How to report descriptive analysis in paper?

Create and edit basic data visualization.

Analyze and present Likert Scale data

How to run basic inferential statistics analysis?
Slot 3

Inferential Statistics (Intermediate)

- Correlation

- Regression

- Moderation & Mediation Analysis (if time permits)

 2 – 2 ½ hours

Testing hypothesis on relationship between variables.

How to report in papers for publication purpose (APA 7th edition)

Instructor

Kamarul Ariffin Mansor (M.Sc.) is a senior lecturer at Faculty of Computer Science and Mathematics, Universiti Teknologi MARA (UiTM), Kedah Branch Campus, Malaysia. His research interests include the application of structural equation modelling and statistical applications in other field of studies, data analytics and visualization using IBM SPSS Statistics, Excel, R, Google Data Studio, Tableau, etc.

Personal websites: https://ariff118.github.io/kamansor.github.io/
CV: https://ariff118.github.io/kamansor.github.io/files/cv-kamarul.pdf

Fundamentals of Data Analysis

3 Most Common Basic Analysis in Research

1. DESCRIPTIVE ANALYSIS

PURPOSE:

  • Describe the distribution of the variable of interest.

TECHNIQUES:

  • Frequencies and Cross-tabulations for Nominal or Categorical Variables
  • Means and Means by sub-groups for Continuous Data

WHEN DO WE USE THEM IN THE RESEARCH?

  • Describing the Sample Profile
  • Issue of Representativeness - Non-Response Bias

2. TEST OF DIFFERENCES

PURPOSE:

  • To test whether a variable of interest differ significantly across 3 or more sub-groups of the population, or
  • To test whether 2 or more subgroups of the population differ in terms of one or more variable of interest, or
  • To test whether 2 or more variables are rated differently by the population.

WHEN:

  • To establish whether two or more groups are statistically significantly different in terms of a particular variable of interest.
  • To establish whether two or more variables are rated significantly different by the population. This is to establish definite ranking/ordering

TECHNIQUES:

  • Parametric Techniques: t-test; paired t-test, 1-way ANOVA, 2-way ANOVA
  • Non-Parametric Techniques: Mann-Whitney/ Wilcoxon rank sum test; Wilcoxon signed rank sum test, Kruskal Wallis; Friedman test

3. ESTABLISHING RELATIONSHIPS

PURPOSE:

  • To establish dependence (cause-effect) relationships between two or more variables
  • To establish the inter-relationships between two or more variables.

TECHNIQUES:

  • Dependence Relationships
    • Correlation
    • Multiple Regression
    • Discriminant Analysis
  • Non-dependence Relationships
    • Correlation – Canonical Correlations
    • Factor Analysis

This work is licensed under a Creative Commons Attribution 4.0 International License.