Data analysis and interpretation

This part of the document explains how data in the next chapter will be analysed. According to Kothari (2004:18) after the data has been collected, the researcher turns to the task of analysis. Since the study adopted both the quantitative and qualitative approaches, for the quantitative approach, the thematic analysis was used to analyse the qualitative responses. For the quantitative responses, data analysis included counting of answers, tabulating the data, and coding the answers.

5.3.6.1 Quantitative data analysis and interpretation

In statistical analysis, it is important to identify the variables under study. Great care is required in measuring variables (Ragin & Amoroso 2011:174). The name ‘variable’ refers to the fact that this data will differ between units and this deferring data is called attributes (Singh 2013:7). The variables that are studied in this study include gender, age, race, level of study and the type of study. For example, this research studied the gender of students as a variable attributed to both female and male students. This means in other words that gender is a variable, and that female and male are attributes of this variable.

Bless, Higson-Smith and Sithole (2013:395) mentioned that a variable is an empirical property that is observed to change by taking more than one value or being of more than one kind. They further differentiate between an independent variable as well as the dependent variable where by the former is observed and measured to determine the effect on it of the independent variable while the latter is measured, manipulated or selected by the researcher to determine its relationship to an observed phenomenon (the dependent variable).

In this study, the demographic characteristics of the respondents are regarded as the independent variables. The empirical statements are regarded as the dependent variables. The demographic characteristics of the respondents vary according to individual’s choices or decisions (e.g. type of study) and nature (e.g. age).

Data will be analysed through the Pearson Chi-Square to determine the significance of difference between the respondents’ demographic characteristics. The chi-square test will be used to determine the 5% level of significance between the variables. The research results are presented in the form of the frequency distribution tables. After counting, data will be presented in tables. Data should necessarily be condensed into a few manageable groups and tabled for further analysis (Kothari 2004:18). This will include tables presenting all parts of the questionnaire, as per the study research instrument. After presenting data in tabular formats, the researcher will classify the raw data into some purposeful and usable categories (Kothari 2004:18).

According to Singh (2013:316), descriptive statistics, together with simple graphics analysis, form the basis of virtually every quantitative analysis of data and provide simple summaries about the sample and the measures. Since data will be coded by turning the raw data into numerical representations, after coding there may be possible errors. Such errors will be cleaned through a process called data cleaning. Data cleaning is the process of detecting and correcting coding errors (Babbie 2001:392).

For the purpose of statistical data analysis, the following hypothesis was formulated:

H0 (null hypothesis): There is no significance difference between the interview questions or

empirical statements and the respondents’ demographic characteristics

H1 (alternative hypothesis): There is a significance difference between the interview

questions or empirical statements and the respondents’ demographic characteristics

The researcher sought to determine the most effective demographic characteristic that may contribute to the establishment of an integrated communication strategy as an enabling tool for increasing graduate employment potential based on the tested empirical statements and the interview questions.

Data was collected through empirical statements and the interview questions according to the first 5 research objectives as follows:

 identify factors contributing to graduate unemployment – 15 empirical statements;

 clarify the role of media in addressing unemployment challenges – 6 empirical statements;

 identify types of media that are used to disseminate information about factors contributing to graduate unemployment – 4 interview questions;

 confirm if unemployment is a challenge faced by the graduates at the university of technology – 4 interview questions;

 confirm a media that is relevant for disseminating information about unemployment factors – 6 empirical statements and 1 question.

It should be noted that the 6th _{research objective was used for qualitative data analysis.}

5.3.6.2 Qualitative data analysis and interpretation

While the quantitative research methodology allows for deductive analysis and qualitative methodology allows for inductive analysis, the thematic analysis provides flexibility for approaching research patterns in two ways, i.e. inductive and deductive (Alhojailan 2012:39). Thematic analysis is capable of detecting and identifying, for example, such factors or variables as may influence any issue generated by the participants. Therefore, the participants‟ interpretations are significant in terms of giving the most appropriate explanations for their behaviours, actions and thoughts (Alhojailan 2012:11).

The steps that are followed for applying thematic analysis are outline by Braun and Clarke (2006: 16) as follows:

1. Familiarizing yourself with your data: transcribing data (if necessary), reading and rereading the data, noting down initial ideas.

2. Generating initial codes: coding interesting features of the data in a systematic fashion across the entire data set, collating data relevant to each code.

3. Searching for themes: collating codes into potential themes, gathering all data relevant to each potential theme.

4. Reviewing themes: checking in the themes work in relation to the coded extracts (Level 1) and the entire data set (Level 2), generating a thematic ‘map’ of the analysis.

5. Defining and naming themes: On-going analysis to refine the specifics of each theme, and the overall story the analysis tells, generating clear definitions and names for each theme.

6. Producing the report: the final opportunity for analysis. Selection of vivid, compelling extract examples, final analysis of selected extracts, relating the analysis back to the research question and literature, producing a scholarly report of the analysis.

The practical application of thematic analysis for this study is presented in chapter 6, under the heading “qualitative data analysis for the proposed communication strategy”.

Based on the above information, data will be analysed in a four-section approach, namely:  Section A - is the analysis and interpretation of demographic profile of the respondents  Section B – is the analysis and interpretation of the first 5 objectives of the study

according to the descriptive statistics

 Section C – is the quantitative analysis and the descriptive statistics based on the 5 objectives of the study according to the Pearson Chi-Square.

 Section D – is the qualitative analysis of the 6th _{objective of the study. The 6}th _objective

required the respondents to provide comments about the establishment of the strategy.