CHAPTER THREE Joy

CHAPTER THREE
RESEARCH METHODOLOGY
3.1 Introduction
This chapter describes procedures and methods which were used in the study in order to
satisfy the objectives. These include: the research design, target population, data collection
methods and data analysis.
3.2 Research Design
The study adopted a descriptive research design. A descriptive research design determines
and reports the way things are (Mugenda & Mugenda, 2003). The design also has enough
provision for protection of bias and maximized reliability (Kothari, 2008). Descriptive
design uses a preplanned design for analysis (Mugenda and Mugenda, 2003). In this study,
inferential statistics and measures of central, dispersion and distribution will be applied.
Descriptive research is a method of collecting information by interviewing or administering
a questionnaire to a sample of individual (Orodho, 2003). The research will focus on the
performance of SMEs over a three (3) year period from 2011 to 2013.
3.3 Population
The target population for the study was 1050 manufacturing SMEs, registered in Baringo
County that would be in various strata: light manufacturing, commercial and trade,
services, with specific attention to the owners and staff of the small and medium
enterprises. Light manufacturing SMEs will include steel, aluminum industries, commercial
and trade comprise detergents, plastic bottles and plastic water companies and services
comprises of printing among others.
3.4 Sample
The study employed stratified random sampling, with a target of 200 manufacturing
registered small and medium enterprises within Baringo County. The number represented
18% of the total number of registered SMEs within Baringo County which is 1050 (NCC,
2013) SME Register Baringo. Mugenda & Mugenda (2003) argues that if well chosen,
samples of between 10% and 30% of a population can often give good reliability.
Table 3.1 Target population and sample size
Type of SMEs Target Population Sample Size Sample size

Light Manufacturing 480 20% 84
Commercial and 170 10% 17
Trade manufacturing
Services 400 20% 80
Total 1050 180
Source: NCC (2013)
3.5 Data Collection
Data collection will involve self-administered questionnaires as the main instrument for data
collection. Primary data will be collected from the owners of the manufacturing SMEs in
Baringo County using the questionnaires. The questionnaire to be used is divided into three
sections with section A meant to get the general information about the SME including the
area of operation, age, size and profitability trends. Section B is intended to gather
information on the effect of innovation within the firm whereas section C is to get data on
the impact of innovations on the financial performance of the firms
3.5.1 Data Validity and Reliability

Reliability refers to the extent to which findings can be replicated by another researcher
(Saunders, 2009). To test the internal consistency of the items listed on the instrument used,
the Cronbach’s alpha coefficient was computed. Cronbach’s alpha is a statistic coefficient (a
value between 0 and 1) that is used to rate the reliability of an instrument such as a
questionnaire. This method randomly splits the data set into two and a score for each
participant calculated from each half of the scale. The advantage with using Cronbach’s
alpha is that the data is split into every possible way and the correlation coefficient for
each split computed. The average of these coefficients is the value equivalent to this alpha
(Cronbach, 1951).
3.6 Data Analysis
Data collected will be analyzed using descriptive statistics (frequencies and percentages)
and inferential statistics. The descriptive statistical tools helped in describing the data and
determining the respondents’ degree of agreement with the various statements under each
factor.
Data analysis will done using statistical tools SPSS and Microsoft excel. The findings will
be presented using tables and charts, percentages, means and other central tendencies. For
this study, the researcher will be interested in establishing the effects of innovations on the
performance of SMEs in Baringo County, Kenya.
3.6.1 Analytical Model

In addition, multiple linear regression model will be used to analysis the independent
variables represent types of innovations and dependent variable represent profit. The
following analytical model will be used in analyzing the relationship between the dependent
and independent variables:
Y= α + β1X1+β2X2+β3X3+ ε
Where:
Y- Is the SMEs financial performance as a dependent variable measured by

ROA β1– is the co-efficient of product innovations
β2– is the co-efficient of process
innovations β3 – is the coefficient of
market innovations X1 – value of product
innovation
X2 – value of process
innovation X3 - value of
market innovation ε = error
or random term
α- constant
3.6.2 Operationalization of the
Study Independent Variables
The independent variable in this study was divided into product innovation, process
innovation and market innovation. Product innovation included three items, namely the
introduction of new product/ service, technological newness in product and product/service
differentiation. Process innovation comprised of application of new technology and new
combination of materials in production. Market innovation consists of application of online
transaction, innovative marketing and promotion and ability to find new markets. All
these items were adapted from Rosli and Sidek (2013).
Dependent variable
The dependent variable to be used is return on assets (ROA). Return on assets measures the
efficiency of business in using assets to generate net income.
ROA= Annual Net Income

Average Total Assets
Annual net income is the after tax income while average total assets is calculated by
dividing the sum total of assets at the beginning and end of the financial year by 2.
3.6.3 Test of Significance

The test of significance to be used in this study is Regression Analysis. The linear regression
analysis will show the relationship between the dependent variable which is performance
and independent variable which is the various types of innovations. The coefficient of
determination R2 and correlation coefficient r will show the degree of association between
effects of adopting innovations and performance of manufacturing SMEs in Baringo
County. The results of the linear regression Y= α + β1X1+β2X2+β3X3+ε will indicate
whether there is a strong relationship between the variables under study using the results of
r2 and R. The findings will then be generalized to the population of interest. ANOVA as a
statistical tool will also be used in determining the variance among the grouped data for
statistical significance in determining the impact of the independent variables on the
dependent variable in a regression analysis.

CHAPTER THREE Joy

Uploaded by

Copyright:

Available Formats

CHAPTER THREE Joy

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

CHAPTER THREE Joy

Uploaded by

Copyright:

Available Formats

CHAPTER THREE

3.2 Research Design

Table 3.1 Target population and sample size

Type of SMEs Target Population Sample Size Sample size

3.5 Data Collection

3.5.1 Data Validity and Reliability

3.6 Data Analysis

3.6.1 Analytical Model

Y- Is the SMEs financial performance as a dependent variable measured by

ROA= Annual Net Income

3.6.3 Test of Significance

You might also like