Data collected from the field either for academic thesis/dissertation or for consultancy work needs to be analyzed to make it meaningful to the readers. There are two types of data we collect from the field: Numerical and Narrative. Each of this type of data is analyzed using different software. This course is about analysis of numerical data or data that is data in numbers. The most user-friendly software to analyze numerical data is IBM SPSS statistics software.

This course is thus intended to develop your skills and competencies in IBM SPSS Statistics so that you are able to analyze and make appropriate interpretation of your data. This course is offered once a week on Thursday from 7-9pm (EAT). However, arrangements can be made to adjust the time if not appropriate for all the trainees. There is an assignment after every module that is submitted the following Tuesday after class. For ease of understanding and practice, trainer will email you the power point notes for the module. Please note that data analysis requires an understanding of Statistics and Research Methods.

The assumption therefore is that as you register for this course, you have already gone through Statistics and Research Methods course units. This course will not take you through Statistical Methods Course or Research Methods Course. 

Target Audience

This course is appropriate for:

i) Undergraduate and postgraduate students

ii) Practitioners in Research organizations

iii) Consultants in Monitoring and Evaluation

iv) Anyone with an interest in data collection, analysis and interpretation.

Course Outline

Module 1 / Week 1: Basic Concepts in Data Analysis

This is an introduction lesson that lays the foundation for data analysis. This lesson is key because it ensures that before defining variables and entering data into SPSS, the researcher is aware of the relationship between scale of measurement and the selection of the statistical tool. The lesson covers the main concepts in data analysis including:

i) Research, types of research and the designs
ii) Variables; definition and types
iii) Population and sampling techniques
iv) Data and types of Data,
v) Quantitative analysis, types of statistics, test for hypotheses and statistical tests
vi) Scales of measurement.

Module 2 / Week 2: IBM SPSS Environment

This is a core lesson because without understanding the SPSS environment, then you cannot enter data. The is a practical lesson where the learner is expected to enter data into the data editor. This is the data that we shall use as we practically analyze data in week 3 and 4. This lesson takes the learner through

i) The components of the SPSS environment both in the data editor and the output.
ii) How to define variables
iii) How to enter data into the data editor.

Module 3 / Week 3: Descriptive Analysis / Statistics

Real analysis using SPSS software and interpretation of data i.e. the output of the analysis starts in this lesson. In Module 1, we have said that there are two types of data analysis; descriptive and inferential. Data analysis always starts with descriptive statistics. This is a practical oriented lesson where the learner will use the data entered in week 2 to analyze data descriptively. This lesson Covers the three forms of descriptive analysis; these are:

i) Meaning of descriptive statistics
ii) Explain why analysis should start with descriptive before inferential
iii) Forms of descriptive analysis: Tabular, Graphical and Numerical
iv) Tabular Analysis: Frequency Distribution Tables and Crosstabulation
v) Graphical Analysis: Pie charts, bar charts, Histogram, Scatter graphs, Frequency polygon
vi) Numerical Analysis: Measures of Central Tendency and Measures of Variability

Module 4 / Week 4: Inferential Analysis / Statistics

The second type of statistics is inferential statistics. Inferential statistics give confidence to the descriptive statistics by allowing us to make predictions about the population parameter based on the sample statistic. We are able to predict the population parameter because we use probability to test hypothesis. In this module, we are going to learn:

i) Relationship between descriptive and inferential statistics
ii) Hypotheses testing, decision that determine rejecting and failing to reject hypotheses
iii) Statistical tests: parametric and non-parametric.
iv) Forms of inferential analysis: Correlation, Regression and Comparison Tests
v) Correlation: Pearson Product Moment Correlation Coefficient and Chi-Square
vi) Regression: Simple Linear regression and Multiple Linear Regression
vii) Comparison Tests: t-test and ANOVA

Module 5 / Week 5: Likert Scale

Many researchers construct Likert scale kind of questions to measure variables. A scale has a number of statements and the researcher expects each respondent to score the statement on a scale of 1-5. However, the debate on whether scale data collects ordinal or interval data has ranged for a long time. This lesson will thus explain the following:

i) Types of data that can be collected using Likert Scale: is it ordinal data or categorical data?
ii) How to construct Likert scale Myths about Likert Scale
iii) How to enter Likert Data in the SPSS data editor
iv) How to analyze Likert Scale data using descriptive and inferential statistics
v) How to interpret the Likert Data