Get Complete Project Material File(s) Now! »

**CHAPTER 3 ****RESEARCH METHODOLOGY**

** Introduction**

In the preceding chapters, the thesis provided a discussion of conceptual definitions such as entrepreneurs, entrepreneurial characteristics and small enterprises. Founder entrepreneurs versus other business owners, an overview and brief history of small enterprises in Ethiopia and the parameters used for the analysis were also discussed.

In addition, Micro and Small Enterprise Development Strategy in Ethiopia, the rationale for the development of small enterprises, theories of growth and the measurement of the growth of small enterprises were discussed. Chapter Three provides a discussion of the type of research conducted, the data collected in the study, sample size and sampling procedures, methods of data collection, tools for data analysis and ethical considerations

**Types of Research**

The researcher used descriptive approaches to interpret and reduce the data into a summary form in tabulations, charts, bar graphs and measures of central tendency (mean and standard deviation). He also conducted an investigation of the underlying motives, desires, feelings or thoughts of people regarding a particular situation or institution, using research methods such as in-depth interviews and focus group discussions (Silverman (1993: 78–79). This approach is commonly applied when people are the focus of the study, particularly in small groups or with individuals, but it can also be used when dealing with beliefs or customs in a community (Bernard 2000: 103–104).

The main purpose of descriptive research is to describe the state of affairs, as it exists at the present time. The distinguishing feature of this method is that the researcher has no control over the variables, but only reports what has happened or what is happening. Survey methods of all kinds, including comparative methods, can be used in descriptive research. This type of research is also concerned with predictions and the narration of facts about a particular individual or a group (Bernard 2000: 28; Bryman 2004: 18–19; Ghosh 1982: 70; Silverman 1993: 35).

Thus this study explores and describes the various challenges that have a direct bearing on operators of small enterprises, using descriptive narrations and concurrent triangulation strategies. These difficulties include access to credit, training, market information and government rules and regulations affecting small enterprises

**Data Types**

The study used mainly qualitative data, both primary and secondary, collected from the study sites. Miles and Huberman (1994: 329–330) and Silverman (1993: 213–214) explain that qualitative data deals with phenomena that relate to qualities or types. It is based on information expressed in words, descriptions, accounts and on the opinions and feelings of people. Albert (1961: 43–44) and Bernard (2000: 45–46) argue that qualitative data is generated either in non-quantitative form or in forms that are not subjected to rigorous quantitative analysis

**Sampling Procedures and Sample Size**

In order to increase the validity and reliability of the data, the study used both probability and non-probability sampling techniques. Probability sampling is known as „random sampling‟ or „chance sampling‟, where every item of the population has an equal chance of inclusion in the sample (Ghosh 1982: 89–90).

It is, so to say, a lottery method in which individual units are picked from the whole group, not deliberately but by some mechanical process. For instance, one can write the names of a finite population on slips of paper and, after mixing the slips of paper thoroughly, can draw the required number of slips one after the other without duplication (Odum and Jocher 1929: 125–126; Preece 1994: 65– 66). In doing so, each of the elements of the population has the same chance of being selected. In research, population does not necessarily mean the number of people; it may consist of objects, people or even events (e.g. schools, miners, revolutions) that describe the total quantity of things (or cases) or of types that are the subject of the study (Bryman 2004: 23–24).

In this way, the results obtained from the random sampling technique can be assured in terms of probability: i.e., one can measure the errors of estimation or the significance of the results obtained from a random sample (Allen 1978: 18– 19). This method ensures that the sample has the same composition and characteristics as the population.

Non-probability sampling is known by various names such as deliberate sampling, purposive and judgment sampling, where the choice of the researcher concerning the items to be included in the sample remains supreme (Gopal 1964: 56–57). In other words, in non-probability sampling, the organisers of the inquiry purposefully choose the particular units of the population to constitute a sample on the basis that what they select will be typical or representative of the whole population (Preece 1994: 65–66).

In this study, purposive sampling was used to select the region and the specific study sites (Mekelle and Adigrat) as they are cities with a relatively high concentration of small enterprises.

Secondly, in the case of the study districts, Keddamay-Wayyane was purposively selected from Mekelle to enable the researcher to describe the challenges and prospects of each sector of small enterprises in detail. In fact, this district has a high concentration of the small enterprises represented in Mekelle. In contrast, all districts of Adigrat were surveyed as there are relatively small numbers of small enterprises scattered throughout these districts.

Thirdly, different small enterprise sectors (trade, service, urban agriculture, construction and manufacturing) were taken purposefully as strata; strata can be illustrated, for instance, by a business enterprise whose workforce is divided into categories based on income level, age, sex and religion. The required sample was selected from each stratum to represent the whole population, using a stratified proportional random sampling technique. A stratified sampling technique is generally applied in order to obtain a representative sample if the population from which it is to be drawn does not constitute a homogeneous group (Nicholas 2006: 93–94). A stratum in which the population is divided into several sub-populations is individually more homogeneous than the total population and is usually formed based on the common characteristics of the items to be put in each stratum (Tandon 1979: 103–104).

The relationship between the characteristics of the population and the characteristics to be estimated are used to define the strata from which items are selected to constitute the sample (Cothari 2004: 91–92). A stratum or a sector of small enterprises ensures elements that are homogeneous within each stratum (sector) and heterogeneous among the different strata in terms of capital size, the number of employees and other characteristics. In this way, a representative sample from which reliable and detailed information about the total population is inferred can be achieved.

Fourthly, in order to determine the number of small enterprises (proportions) from each stratum, proportional allocation methods are employed in which the size of the samples from the different strata are kept proportional to the size of the strata. Sharma et al. (1983: 378–379) illustrate this method as follows:

If P_{i} represents the proportion of population included in stratum „i‟, and „n‟ represents the total sample size, the number of elements selected from stratum „i‟ is n*P_{i.} To illustrate this, let us suppose that we want a sample of size n = 30 to be drawn from a population of three strata of size N1 = 4000, N2= 2400 and N3= 1600. Adopting proportional allocation, we shall get the sample sizes as shown below for the different strata: For strata with N1= 4000, we have P_{i}= 4000/8000 and hence n_{1} = n.P_{1} = 30 (4000/8000) = 15. Similarly, for strata with N_{1} = 2400, we have n_{2 }P_{2} = 30 (2400/8000) = 9, and for strata with N = 1600, we have n_{3} = n.P_{3} = 30 (1600/8000) = 6.

Thus, according to this illustration, using proportional allocation in this study resulted in the sample size from each stratum being 15, 9 and 6 respectively, proportional to the size of the strata, that is, 4000, 2400 and 1600. Proportional allocation is considered efficient and an optimal design when the cost of selecting an item is equal for each stratum. Furthermore, it is used when there is no difference in stratum variance, and the purpose of sampling happens to estimate the population characteristics (Kvale 1996: 87–89).

Using these techniques, 154 respondents from all small enterprise sectors were randomly selected from the two study sites. That is, the sample respondents were randomly selected from each small enterprise sector (stratum) with the help of the lottery method or a simple random sampling technique. In other words, chance alone determined whether one item or another was selected.

With regard to sample size, a simplified formula provided by Yamane (as cited in Yilma 2005: 42) was used to determine the minimum sample size at 95% level of confidence, 0.5 degrees of variability and 9% precision level (e):

**n = N **

**1+ N (e)**

^{2}where „n‟ is the minimum sample size, „N‟ is the total number of the study population and „e‟ is the level of precision

#### Confidence Level

The confidence level indicates the degree to which the sample size falls within the required intervals. It gives an estimated range of values, which are likely to include the unknown population parameter (Cothari 2004: 65–66; Sharma 1983: 201–202). Therefore, for a confidence level of 95%, 95 out of 100 samples will have a true population value within the confidence interval and 95% is the proportion of the population covered by ±2 standard deviations from the mean in a normal distribution. The wider we allow the confidence interval to be, the more confident we can be that the real answer lies within the range (Bryman 2004: 45– 46).

Degree of Sampling Variability

The degree of variability describes the distribution of attributes in the population, while the sampling variability of a statistic refers to how much the statistic varies from sample to sample and is usually measured by its standard error. The smaller the standard error, the less the sampling variability will be (Anderson 1958: 25–26). For example, the standard error of the mean is a measure of the sampling variability of the mean. The more heterogeneous the population, the larger the sample size required to obtain a given level of precision; the more homogeneous the population, the smaller the sample size required.

Level of Precision/Significance

The level of precision sometimes referred to as the confidence interval or sampling error, is the range in which the population‟s actual value is estimated to exist (Anderson 1958: 208). For instance, if one finds that 60% of a sample has adopted a specific practice with a precision rate of ±5%, then it can be concluded that the actual number of samples in the total population that has adopted the practice lies in the range of 55–65%.

The minimum sample size required in Kaddamay-Wayyane of Mekelle, according to the above formula, was 106 small enterprises. However, for greater precision and accuracy, the total number of respondents taken from this study site was purposefully determined as 114 operators. In Adigrat, the total number of respondents, based on the formula given above, was 40 operators. In this way, the size of the samples from each sector was kept proportional to the size of the strata, as shown in Table 3.2 and 3.4 below

Declaration

Acknowledgements

INTRODUCTION

1.1 Background to the Study

1.2 Statement of Problem

1.3 Objectives of the Study

1.4 Significance of the Study

1.5 Scope and Limitations

1.6 Structure of the Thesis

1.7 Description of the Study Areas

1.8 Conclusion

CHAPTER 2 REVIEW OF LITERATURE

2.1 Introduction

2.2 Entrepreneur and Entrepreneurship

2.3 An Overview of Small Enterprises

2.4 Definition of Small Enterprises

2.5 The National Small Enterprise Development Strategy in Ethiopia

2.6 Rationale for Small Enterprises‟ Growth and Development

2.7 Theories of Growth of Small Enterprises

2.8 Measurement of Small Enterprises‟ Growth

2.9 Demographic Characteristics of Entrepreneurs

2.10 Characteristics of Small Enterprises

2.11 Challenges to Small Enterprises

2.12 Theoretical Framework

2.13 Studies of Small Enterprise in Developing Countries

2.14 Previous Research on Small Enterprises in Ethiopia

2.15 Previous Research on Small Enterprises in Tigray Region

2.16 Socio-Political Context of Small Enterprise in Ethiopia

2.17 Conclusion

CHAPTER 3 RESEARCH METHODOLOGY

3.1 Introduction

3.2 Types of Research

3.3 Data Types

3.4 Sampling Procedures and Sample Size

3.5 Method of Data Collection .

CHAPTER 4 DATA PRESENTATION, ANALYSIS AND INTERPRETATION

4.1 Introduction

4.2 Demographic Characteristics and Prospects of Entrepreneurs

4.3 Characteristics and Prospects of Small Enterprises

4.4 Challenges and Prospects of Small Enterprises

4.5 Conclusion

CHAPTER 5 RATING CHALLENGES ACROSS SMALL ENTERPRISES

5.1 Introduction

5.2 Rating Financial Challenges across Small Enterprises

5.3 Rating Market Challenges across Small Enterprises

5.4 Rating Linkage Challenges across Small Enterprises

5.5 Rating Policy Challenges across Small Enterprises

5.6 Conclusion

CHAPTER 6 . SUMMARY, CONCLUSIONS AND RECOMMENDATIONS

6.1 Introduction

6.2 Summary and Conclusion

6.3 Recommendations

BIBLIOGRAPHY

GET THE COMPLETE PROJECT