**CHAPTER-3: METHODOLOGY**

3-1 Research Methodology

The main objective of this chapter is to identify how the chosen research methodologies that will match the main objective of the dissertation question and how it will be achieved. Given the two types of research methodology between qualitative and quantitative research, this paper has to make a choice of one over the other or a combination of both. This paper admits that the quantitative research is carried out through obtaining primary data such as questionnaire, while qualitative research is a research that may make use of qualitative information through interviews and observations. Given the fact that the purpose of this research is to test the relationship of accounting numbers with the equity valuation, quantitative research is more of the required type for this kind of work. This does not however exclude the use of qualitative research as could be observed in content analysis from statements of various authors. Therefore, a quantitative approach is used here that it will enable the researcher to make use of the numerical and to explore the details of individual perceptions over phenomena. As complement to quantitative research this paper will also use qualitative methods particularly in expounding on the merits of one model over the other for it is in this context that qualitative approach assumes undeniable significance. This paper therefore first uses the quantitative approach by using both the small sample size and large sample size analysis to confirm or the deny the thesis of this dissertation the accounting numbers are good and reliable predictor for stock valuation and to under stand the finer points of the research qualitative research will be used.

Under the large sample size, the researcher used about more than 180 registered companies in UK by extracting relevant accounting numbers such as net income , total assets, etc in relation to total equity valuation of the firms . This paper has chosen multiple regressions to test of degree of relationships for the dependent variable to the independent variables

Under the small sample size approach, the researcher tried to reduce the large sample size from 180 to 50 until it reached 25. The basis for bringing the l80 sample size to 50 is to get only those that have R&D values of £10,000 or more. To get to 25, only those whose balance sheet date was December, 2004 were considered.

The paper will compare the results of analysis between the large and small sample size on whether there is basis to confirm the validity of finding. As a rule if the result of the first is confirmed by the second, then such would be a good sign of the characteristics of the models using accounting numbers.

Before the discussion of the application of the small size sample and large sample size, further discussion of the methodology will also be further discuss to enlighten the reader of this paper.