The study will use a quantitative research design. A quantitative research design allows for a faster collection of data compared to a qualitative design. It is also suitable for studying large population because it allows the researcher to use inferential statistics (Rubin, 2012). Therefore, the findings from a sample can be used to generalize information about the whole population. This study seeks to assess whether the high prices that Starbucks charges for its coffee drive consumers to its competitors. Therefore, the study is interested in all consumers of coffee at Starbucks. The population of interest is large.
A survey method, which will be implemented by the use of questionnaires, will be used to collect data from the respondents. The questionnaire will contain closed ended questions. The questionnaire will seek to assess whether the current customers of Starbucks are satisfied with the prices that are being charged. Questions for the primary variables of interest will be closed-ended. Respondents will be given affirmative statements with five multiple choices that are in line with the 5-point Likert scale. Closed-ended questions will be preferable because they allow for a quantitative analysis (Trochim & Donnelly, 2008). Besides, it restricts the answers that can be received. Therefore, the analysis is easier compared to data from open ended questions. The scale of the choices will range from ‘completely disagree’ to ‘completely agree’. The questionnaire will also include questions on the respondent’s demographic profile. The questions will allow the researcher to describe the profile of the respondents. The study will be implemented purely through survey method. Therefore, the instruments that will be required for data collection will be the questionnaire and pens that will be used to fill them.
The population of interest is the current customers of Starbucks who consume coffee. The study will use a sample of 300 respondents. The sample size is informed by financial and time restrictions. The sample size is also large enough to allow for robust results that can be generalized to the entire population. The sample will be selected from Starbucks shops in five different cities. Different cities will be used to ensure geographical representatives. There may be differences in responses based on geography or background. The setting is Starbucks shops because it will be easier to identify the respondents who meet the two key characteristics of the targeted population: they are current customers of Starbucks and they consume coffee. Therefore, those who are in Starbucks stores and are consuming coffee with being the targets. A random sample will be selected from the target population. Random sampling ensures that the sample is a representation of the population of interest (JHA, 2014). Random sampling is also a requirement for inferential statistics (Jackson, 2012). Besides, random sampling ensures that the research is objective both factually as well as in appearance.
The selected respondents will be approached and will be informed of the intention of the study. They will then be requested to participate. The participants will be informed that it is voluntary to participate. They will be required to sign a consent form to show they participated willing. They will be informed that they will be entered into a raffle draw will have a chance to win an iPad. The raffle draw will be included to encourage participation. Therefore, zero percent attrition rate is expected. In case of attrition, the respondent will be replaced using random re-sampling. The information that will be collected will be used solely for the purposes of the study and it will be kept confidential in line with ethical and professional standards of research. The information will be destroyed after three months.
Respondents will take about fifteen minutes to fill in the questionnaires. After they have filled in all the questionnaires, the data will be stored in table form in excel. The nominal data will be stored using codes. The main nominal data that will be collected during the study is gender (male and female).
Data analysis will be conducted using Excel. The data analysis will be done in two stages. In the first stage, descriptive statistics will be applied. Descriptive statistics will be used to provide an overview of the respondents and responses. Frequency tables will be used for nominal and categorical data. Bar graphs and pie charts will also be used to provide a visual representation of the data. The demographic data that will be collected includes age, income level, employment, and ethnicity and education level. Ethnicity, employment and education level will be measured using the dummy variable representation. Income level will be measured in dollars per year and age will be measured in years. Income level and age will be described using central tendency measures and dispersion.
One-sample t-test will be used to answer the primary research question for this study. The primary research question is whether the prices charged by Starbucks drive customers away. The respondents will be given a statement to the effect “The prices charged by Starbucks are fair”. Respondents were required to agree or disagree with the statement using a Likert scale. If customers are uncomfortable will the prices, then they will completely disagree with the statement. Therefore, the null hypothesis for the study will be that the sample mean is one and the alternate hypothesis will be that the sample mean is greater than one. The hypothesis will be tested as a one-tailed test at five percent significance level.
The study is also interested in assessing whether there are differences in the responses based on ethnicity, education and employment. Therefore, a Chi-square test of independence will also be used to analyze the data. Chi-square test of independence will be a two-tailed test at five percent significance level (95 percent confidence interval). The null hypothesis will be that the distribution of the responses is independent from the respondent profile (ethnicity, income level and education level). The alternate hypothesis will be that the distribution of the responses is dependent from the respondent profile
References
Babbie, E. (2009). The Practice of Social Research. London: Cengage Learning.
Jackson, S. (2012). Research Methods and Statistics: A Critical Thinking Approach. London: Cengage Learning.
JHA. (2014). Social Research Methods. New Delhi: McGraw Hill Education (India) Pvt Ltd.
Rubin, A. (2012). Statistics for Evidence-Based Practice and Evaluation. London: Cengage Learning.
Trochim, W., & Donnelly, J. (2008). The Research Methods Knowledge Base. London: Cengage Learning.
