The study adopted a stratified random sampling with a target sample of 30

# The study adopted a stratified random sampling with a

• 43

This preview shows page 22 - 25 out of 43 pages.

Mugenda, 2003). The study adopted a stratified random sampling, with a target sample of 30 registered SMEs within Baringo County. To achieve the intended objective of the study random sampling was used to collect secondary data from SMEs in Baringo town. The Yamane (2003) used the formula below to determining the sample size: n=N/1+N (a) 2 Where n=sample N=population a=margin of error. 22
Using a confidence level of 95% and a total population of 110 employees the sample size was 65 calculated as follows 110/1+110(0.05) 2 =65 Table 3.1 2 sample size NATURE OF THE BUSINESS POPULATION SAMPLE SIZE PERCENTAGE RESTAURANT 30 20 31 SACCO 50 30 46 SMALL ENTERPRISE 20 10 15 BOUTIQUE 10 5 8 TOTAL 110 65 100 3.5 Data Collection instruments Primary data was gathered through structured questionnaires with the respondents. Secondary data was collected from textbooks, newspapers, journals and magazines as well as other sources such as the MFI’s annual reports. A semi-structured questionnaire was used to collect primary data. In order to ensure uniformity in response and to encourage participation, the questionnaire was kept short and structured with mostly multiple-choice selections in a Likert scale. The questionnaires was preferred in this study because respondents of the study are literate and quite able to answer questions asked adequately. According to Mugenda and Mugenda (2003), questionnaires are commonly used to obtain important information about a population under study. The researcher obtained an introductory letter from the University to collect data then personally deliver the questionnaires to the respondents and have them filled in and then collect later: the drop and pick later method. 23
3.6.1 Reliability of Research instruments. The reliability of a research instrument concerns the extent to which the instrument yields the same results on repeated trials. Although unreliability was always present to a certain extent, there will generally be a good deal of consistency in the results of a quality instrument gathered at different times. The tendency toward consistency found in repeated measurements was referred to as reliability (Carmines and Zeller, 1979). 3.6.2 Validity Validity was defined as the extent to which the instrument measures what it purports to measure (Allen and Yen, 1979). Content validity pertains to the degree which the instrument fully assesses or measure the construct of interest. The questionnaire was carefully designed and tested with a few members of the population for further improvements. This was done in order to enhance its validity and accuracy of data to be collected for the study 3.7 Pilot study According to Rigard and James, (2010), pilot study is pre-test study which is carried before the actual study to ensure suitability and reliability. The pilot study was done by administering the questionnaires to 30 respondents who was chosen from the population and was included in the actual study. This enable the researcher to determine the time that a respondent would take to