CHAPTER 1: INTRODUCTION AND BACKGROUND
3.6 DATA ANALYSIS
Data analysis is a body of methods that help to describe facts, detect patterns, develop explanations, and test hypotheses. It is used in all of the sciences. It is used in business, in administration and in policy (Macintosh, 1997). Data analysis refers to the process of generating value from the raw data (Johnson and Christensen 2004; Wamundila 2004). Data analysis is a practice in which raw data is ordered and organised so that useful information can be extracted from it. Raw data can take a variety of forms, including measurements, survey responses, and observations. In its raw form, this information can be incredibly useful, but also overwhelming. Over the course of the data analysis process, the raw data are ordered in way which will be useful (Hardy and Bryman, 2004). For example, survey results may be tallied, so that people can see at a glance how many people answered the survey, and how people responded to specific questions.
According to van den Hoonaard & van den Hoonhaard (2008), data analysis is an integral part of qualitative research and constitutes an essential stepping-stone toward both gathering data and linking one’s findings with higher order concepts. There are many variants of qualitative research involving many forms of data analysis, including interview transcripts, field notes, conversational analysis, and visual data, whether photographs, film, or observations of internet occurrences (Pampel, 2004). Since this study employed a triangulation method to data collections, both the survey and the interviews data were analysed using appropriate data analysis techniques. Qualitative data analysis was represented through analytic text or narratives, explanations and descriptions. As Tylor-Powell and Renner (2003) explains, this requires creativity, discipline and a systematic approach.
Quantitative research techniques generate a mass of numbers that need to be summarised, described and analysed. Characteristics of the data may be described and explored by drawing graphs and charts, doing cross tabulations and calculating means and standard deviations (Lacey and Luff, 2001). So it is with qualitative data analysis. The mass of words generated by interviews or observational data needs to be described and summarised. The question may require the researchers to seek relationships between various themes that have been identified, or to relate behavior or ideas to biographical characteristics of respondents such as age or gender.
There are no ‘quick fix’ techniques in quantitative analysis. Just as a software package such as the Statistical Package for the Social Sciences (SPSS) won’t tell you which of the myriad statistical tests available to use to analyse numerical data, so there are probably as many different ways of
analysing qualitative data as there are qualitative researchers doing it (Pope and Mays, 1996). “For Taylor–Powell and Renner (2003), the analysis process involves the following steps:
Get to know your data; Focus the analysis; Categorise information;
Identify patterns and connections within and between categories; and Interpretation-bring it all together
In essence there are a number of specialised qualitative data analysis softwares that researchers can use to analyse data (Hodson, 1999). Among them includes ATLAS, NUDIST, The Ethnograph, and NVivo. Computerised qualitative data analysis programs do not transform qualitative data for statistical analysis; instead they leave the data in their original qualitative form. The programs allow the marking of passages in the original textual data as representative of certain concepts or ideas. Researchers can the pull these passages together for easy comparison and analysis (Hodson, 1999).
Because quantitative data is usually voluminous, application of computer software that aids the analysis process has been in the use for a long time. The most commonly employed software is the SPSS. The great advantage of using a package like SPSS® is that it enables the researcher to score and to analyse quantitative data very quickly. In other words, it will help researcher eliminate those long hours spent working out scores, carrying out involved calculations, and making those inevitable mistakes that so frequently occur while doing this (Bryman and Cramer, 2005). There is, of course, what may seem to be a strong initial disadvantage in using computer programs to analyse data and that is the researcher will have to learn how to run these programs. The time spent doing this however, will be much less than doing these same calculations by hand.
Having considered the above mentioned reasons and challenges associated using computerised methods of analysing data, the researcher chose to analyse data at hand manually in this study. What inspired the manual process was the simplicity of tally sheet which drew its design from the questionnaire content design (Laws, Harper and Marcus, 2003). This process allowed the researcher to read in data provided for each question in the questionnaire (Desai and Potter, 2006). Tally sheet, also called a check sheet, is used as a form for collecting information through observation and counting. Tally sheets can be simple as using a sheet of paper and pencil, they are simple and
tempted to conduct the data analysis using the computerised software, as it was equally easier and accurate to read in data to the tally sheet. The process was a bit tiresome to read in considering the high number of questionnaires and interview responses received. But it would have not helped as the researcher did not have enough time to enroll to classes in pursuit of learning how to use the SPSS software program. Fearing errors experienced as a result of the method being a novelty to researcher that’s why the project embarked on the simple data tally sheet for analysis.
Interview data was recorded through field notes to ensure complete capture of discussions and members were asked to relate views and answers as relaxed as possible for the researcher to capture the correct inputs as narrated by the respondent. Thus after such a process data was recorded onto tally sheet.
After tally completion, and verifying that each category’s data was included to the sheet, calculations for average to each question were made. The calculated figures were then captured on to MS Excel® spread-sheet database for average figures as depicted from tally sheet. In short tally sheet helped extract important qualitative data indicating the patterns of knowledge existence in DOD and extent of knowledge held by DOD personnel about knowledge management. Graphic representation of the patterns was established and was then transferred or copied to Chapter Four using MS Word® document for proper analysis. Quantitative data analysis was depicted by use of graphs and tables to support text analysis with visual reading (Laws, Harper and Marcus 2003; Desai and Potter 2006; van den Hoonaard & van den Hoonhaard 2008). Easley and Kleinberg (2010) alludes that graphs are useful because they serve as mathematical models for specifying relationships among a collection of items. They further state that graphs are simple in describing data. After analysing submitted data, complex results were given, as such the use of graphs and tables made it easier to make such data readable. The researcher then followed the process by giving meaning to the presentations.