Faculty of Engineering

INTRODUCTION TO DATA ANALYSIS

IE 204

Contents

• INTRODUCTION

• LEARNING OUTCOMES

• RESEARCH PROCESS

• QUALITATIVE ANALYSIS

• QUANTITATIVE ANALYSIS

• DATA ANALYSIS

Introduction

Welcome to the data analysis presentation. The presentation covers both qualitative and quantitative approaches to data analysis.

Data analysis is an important stage of the research process. This presentation includes a summary of that process and explores specific areas of data analysis that might be applicable to learners studying at undergraduate and post graduate levels.

It aims to provide a definition of qualitative and quantitative data analysis and opportunities to explore textual and numerical data analysis through providing worked examples and further opportunities for learners to develop knowledge and skills in data analysis.

Research Process

Definition

Researchers who are attempting to answer a research question employ the research process. Though presented in a linear format, in practice the process of research can be less straightforward. This said, researchers attempt to follow the process and use it to present their research findings in research reports and journal articles.

Research Question

The specific question that guides the research process.

Research Process

The process undertaken by researchers to answer research questions/hypotheses.

Learning Outcomes

The presentation aims to achieve the following learning outcomes:

• An awareness of the situation of qualitative data analysis within the inductive paradigm

• An awareness of the situation of quantitative data analysis within the deductive paradigm

• Skills in critically appraising the data analysis component of research studies

• An appreciation of the different approaches to qualitative data analysis

• An appreciation of the different approaches to quantitative data analysis

• Skills in undertaking basic qualitative and quantitative data analysis

Research Process Stages

Identifying research problemsResearch problems need to be researchable and can be generated from practice, but must be grounded in the existing literature. They may be local, national or international problems, that need addressing in order to develop the existing evidence base.

Searching the existing literature baseA thorough search of the literature using data bases, internet, text and expert sources should support the need to research the problem. This should be broad and in depth, showing a comprehensive search of the problem area.

Critical review of the literatureA critical review framework should be employed to review the literature in a systematic way.

Developing the questions/ and or hypothesisA more specific research question and /or hypothesis may be developed from the literature review, that provides the direction for the research, which aims to provide answers to the question /hypothesis posed.

Theoretical baseThe research may employ a theoretical base to examining the problem, especially seen in masters level research and in many research studies.

Research Process Stages

Sampling strategiesSampling is the method for selecting people, events or objects for study in research. Non-probability and probability sampling strategies enable the researcher to target data collection techniques. These may need to be of a specific size (sometimes determined by a power calculation) or composition.

Data collection techniquesThese are the tools and approaches used to collect data to answer the research question/hypothesis. More than one technique can be employed, the commonest are questionnaires, interviews and surveys.

Approaches to qualitative and quantitative data analysisThis component involves qualitative and quantitative approaches, dependent on the type of data collected.

Interpretation of resultsThe results are interpreted, drawing conclusions and answering the research question/hypothesis. Implications for practice and further research are drawn, which acknowledge the limitations of the research.

Dissemination of researchThe research and results can be presented through written reports, articles, papers and conferences, both in print and electronic forms.

Qualitative Data

Qualitative data is extremely varied in nature. It includes virtually any information that can be captured that is not numerical in nature. Here are some of the major categories or types:

• In-Depth Interviews

These can be individual interviews of group interviews sometimes referred to as ‘focus groups’. The data can be recorded in many ways. The purpose of the interview is to understand the ideas of the interviewees.

• Direct Observation

• Written Documents

Qualitative Data

What types of questions produce qualitative data?

• Questions with textual responses (i.e where the answers are not in numerical format)• Open ended questions; where the subject is expected to provide an answer in textual or written form.

Therefore, the nature of qualitative data and quantitative data is different. Qualitative data usually comes in the form of words whereas quantitative data consists of numbers.

However, qualitative data, can be coded numerically.

Explanation

• Assign numerical values to all responses received to any given question.• Thereafter, the qualitative data is in numerical form and can be processed as quantitative data.

Qualitative Data

A Simple Example

Population Size: 10

Open Ended Question:

-What topic of books are your favorite to read?

A) History B) Sports C) Science D) Islam E) Other ________

All responses received:- History (2)- Sports (1)- Science (0)- Islam (3)- Novels (2)- I do not read any books. (2)

From a population size of 10, we have received

6 different responses. The responses are

qualitative in nature. We now have to work

in order to quantify the data. ‘Other’ Responses

Qualitative Data

Now we have to work to translate the qualitative data into numerical format, which is easier to tabulate and interpret.

First, we have to assign each received response a label, which is easier to understand that words or phrases.

We can refer to this as a ‘key’ , as it simplifies the process of representing the data and understanding it.

KEY DESIGN

For this example, the word ‘theme’ will be used in order to translate the data numerically. The word itself is interchangeable and therefore letters (A, B, C), numbers (1, 2, 3) or any other identifying scale could be used. As we have received 6 different responses to our open ended question, we will now have ‘6 themes’.

Qualitative Data

EXAMPLE KEY

Theme 1 = HistoryTheme 2 = SportsTheme 3 = ScienceTheme 4 = IslamTheme 5 = NovelsTheme 6 = I do not read any books

Now that we have our key in place, we can continue to produce tables on the results received to our open ended question.

Within the cells of the table we use numbers to signify the type of response received, e.g:

1= positive response2= negative response3= no response

Qualitative Data

RESULTING TABLEDon’t Read

Novels Islam Science Sports History Person

0 0 0 0 0 1 1

0 0 0 0 1 0 2

0 0 1 0 0 0 3

0 0 1 0 0 0 4

0 0 1 0 0 0 5

0 1 0 0 0 0 6

0 0 0 0 0 1 7

0 1 0 0 0 0 8

1 0 0 0 0 0 9

1 0 0 0 0 0 10

2 2 3 0 1 2 Total

‘Other’ ResponsesProvided Responses

Qualitative Data

GRAPHICAL REPRESENTATION – BAR GRAPH

Using the above table, we can now work to translate our results into graphical format.

History Sports Science Islam Novels Don't Read

0

0.5

1

1.5

2

2.5

3

3.5

Qualitative Data

GRAPHICAL REPRESENTATION – PIE CHART

HistorySportsScienceIslamNovelsDon't Read

Qualitative Data

GRAPHICAL REPRESENTATION – LINE GRAPH

History Sports Science Islam Novels Don't Read

0

0.5

1

1.5

2

2.5

3

3.5

Quantitative Data

As stated earlier, quantitative data is numerical in nature. Typically questions that provide quantitative are not open ended questions, unless otherwise stated.

Typically quantitative questions are multiple choice in nature, providing the subject with numerical answers to select from.

A Simple Example

Population Size : 10

-How many news papers do you read daily?• 0 – 1 reply • 1 – 2 replies • 2 – 3 replies• 3 – 1 reply• 4 – 1 replies• 5 – 2 replies

As the data is already numeric in nature, there is no need for us to

design a key. The data, as is, can be tabulated.

Quantitative Data

6 5 3 2 1 0 Person

0 0 0 0 1 0 1

0 0 0 1 0 0 2

0 0 0 1 0 0 3

0 0 0 1 0 0 4

1 0 0 0 0 0 5

0 0 0 0 0 1 6

0 0 0 0 1 0 7

0 0 1 0 0 0 8

0 1 0 0 0 0 9

1 0 0 0 0 0 10

2 1 1 3 2 1 Total

Quantitative Data

0 1 2 3 4 50

0.5

1

1.5

2

2.5

3

3.5

Newspapers Read

Replies

Quantitative Data

012345

Newspapers Read

Quantitative Data

0 1 2 3 4 50

0.5

1

1.5

2

2.5

3

3.5

Newspapers Read

Replies

Data Analysis

Now that we have successfully created our tables and graph, we can now begin to analyze the data.

With regards to data analysis, the main statistical analysis we wish to consider are as follows:

• Mean = being the average of the results

• Median = being the middle value, when all the numbers are in numerical order from lowest to highest

• Mode = being the number that is repeated the most often

• Range = being the difference between the highest number and the lowest

• Standard Deviation = showing how much variation or difference there is within the results from the mean.

Data Analysis

Given that our results from the quantitative analysis are as follows:

1, 2, 3, 1, 2, 2

The mean, median and mode can be calculated as follows:

MEAN – take the average of the results

(1 + 2 + 3 + 1 + 2 + 2)/6 = 1.67 papers read

MEDIAN – put the numbers in numerical order from lowest to highest and select the middle number

1, 1, 2, 2, 2, 3 – as there are an even amount of numbers, take the average of the middle two (2+2)/2 = 2 papers read

MODE – the number that appears the most, therefore MODE = 2 papers read

RANGE – 3 – 1 = 2 papers read

Data Analysis

Standard Deviation

Consider our results from our quantitative question:

1, 2, 3, 1, 2, 2

With the mean (average) being = 2

To calculate the Standard Deviation, from the difference of each data point from the mean and then square the result, then find the average of all the results, finishing by finding the square root:

(1 – 2)₂ = (-1)₂ = 1(2 – 2)₂ = (0)₂ = 0(3 – 2)₂ = (1)₂ = 1(1 – 2)₂ = (-1)₂ = 1(2 – 2)₂ = (0)₂ = 0(2 – 2)₂ = (0)₂ = 0

√(1 + 0 + 1 + 1 + 0 + 0)/6 = √0.5

Standard Deviation = 0.707

Data Analysis

What does this result tell us?

Assuming a normal distribution, as shown above, the red area accounts for approximately 68% of the population. The standard deviation is a statistic that tells you how tightly all the various examples are clustered around the mean in a set of data. When the examples are pretty tightly bunched together and the bell-shaped curve is steep, the standard deviation is small. When the examples are spread apart and the bell curve is relatively flat, that tells you have a relatively large standard deviation.

Therefore, for our qualitative question, regarding how many newspapers people read a day, 68% of our population reads between 2.707 – 1.293 papers a day.

Data Analysis

THEREFORE, from the quantitative question asked, and from the tables and graphsProduced, we have the following results:

MEAN = 1.67

MEDIAN = 2

MODE = 2

RANGE = 2

STANDARD DEVIATION = 0.707

NOTE: This process would be repeated for all the meaningful questions you have.

Thank You

To help you with your data analysis, you may visit

www.download.com

Where you can find the following data analysis software:

• SAS• Minitab• Lotus• Others…

To download the presentation, please visit the TLSU website

http://lsueng.kau.edu.sa

Go to Files and then Forms