Research Design
This chapter described the methodology that has been used to conduct this research. It included the research approaches, research design, population and sampling, data collection techniques, research instrument, data analysis, validity and reliability test, pilot study, and the ethics related to this research.
Research Approaches
There are three types of approaches to conduct research; which are
* Qualitative
* Quantitative
* Mixed
In this research quantitative approach has been used because the researcher had determined the relationship between variables. Quantitative research approach is used when it is important to establish out the relationship between one thing (an independent variable) and another (a dependent or outcome variable) in a population. Hopkins (2000) had defined quantitative research that precisely measure variables and that aim to determine the relationship between dependent and independent variables to determine an association. Quantitative research design is an outstanding way of finalizing results and proving or disproving a hypothesis. The structure has not changed for centuries, so is standard across many scientific fields and disciplines.
Research Design
There are three types of research design:
* Descriptive
* Correlational
* Causal-comparative
* Experimental
correlational research design is used to relate two or more variables and correlation results show whether the relationship exists among variables or not. After analyzing the correlations results the regression describe the variability in dependent variable due to the explanatory variables. The over all reasoning for using correlation was to analyze the relationship and regression to analyze how well the prediction can be made. In this research multiple regression analysis has been used.
The reason for using correlational design in this research was to analyze the relationship between product’s new features and brand choice and Correlation coefficients was used to provide the degree and direction of relationship between the product new features and brand choice. In this research regression analysis described that how much variability in brand choice was caused by new features.
Population and sampling
Statisticians define a population as the entire collection of items that is the focus of concern. Sampling is indispensable technique of behavioral research; the research work cannot be undertaken without use of sampling. (David S.Fox) suggested that “In the social sciences, it is not possible to collect data from fractional part of the respondents to our study but only from some fractional part of the respondents. The process of selecting the fractional part is called sampling”.
In this research Karachi has been taken as the population and Business University students selected as sample. The sample size was 150. There are two types of sampling “Random” and “Non-Random Sampling” in this research “Simple Random Sampling” has been used. Simple random sampling is defined by Castillo, Joan Joseph (2009) “In this technique, each member of the population has an equal chance of being selected as subject. The entire process of sampling is done in a single step with each subject selected independently of the other members of the population.”
In this research simple random sampling was used because it represents whole population and covered different demographics which were needed. Moreover, it is unbiased selection and important to draw conclusion from the results of study.
Data collection
For conducting any research it is very important to collect relevant data that suits the methodology and research design. Mark Saunders et. Al (2006) explained that in primary data collection different methods are used such as survey, observation, focus group. There are two types of data collection techniques “Primary and Secondary Data Collection”. In this research primary data has been used.
Data that never gathered before is called primary data. The reason for selecting primary data source was that through primary data the needed information could be gathered that suited the purpose of research as it is not published.
Research instrument
Research instrument is a testing device for measuring a given phenomenon. In this research, questionnaires were used to gather information which are the most widely used survey data collection techniques. Through questionnaire each person (respondent) is asked to respond to the same set of questions, it provides efficient way of collecting responses from a large sample prior to quantitative analysis.
This research involved survey with structured questionnaire to gather complete details. Although people generally use the term survey and questionnaire interchangeably, the term survey is used as a general category with questionnaire and interviews as specific methodologies to conduct survey research (Gay, 1992). The reason for using structured questionnaire was the questions asked were precisely decided in advance. Close-ended questions are particularly useful where the study topic concerns to factual issues with a limited range of responses.The overall reason for using structured questionnaire and close ended questions was that it supported the research technique that have been used in this research for the testing.
Validity and Reliability
Reliability is used to measure the consistency of the data which is used to analyze the instrument whether it provides the same results if it is used in the same way and same conditions with the same objects repeatedly. One thing that is very important to remember that reliability is not measured, it is estimated.
Shuttleworth, Martyn (2008) suggested that before analyzing any data, however, and even before testing any subjects, the issues of variable selection and control, reliability, and validity must be addressed. The simplest definition of validity is that degree to which a test measures what it is supposed to measure Gay (1992).
Validity is the accuracy of the results and the strength of the conclusions. Cook and Campbell (1979) define it as the “best available approximation to the truth or falsity of a given inference, proposition or conclusion”. Each type of validity would highlight a different aspect of the relationship between treatment and observed outcome.
There are four types of validity Conclusion, Internal, Construct and External validity. In this research internal validity was used as it analyzed the relationship between the program and the outcome and causal relationship. Validity is more important than reliability because if an instrument does not accurately measure there is no reason to use it even if it measures consistently. The objective of analyzing the reliability and the validity of the data is to check how much accurate relationship between the measure and underlying trait it is trying to measure.
Pilot study
Pilot study is the small scale rehearsal of the larger research design. This technique refers to a smaller scale version of the experiment and equipment tests are the important part of sub-group of experiments.
Pilot studies can be based on quantitative and/or qualitative methods and large-scale studies might employ a number of pilot studies before the main survey is conducted. Thus researchers may start with “qualitative data collection and analysis on a relatively unexplored topic, using the results to design a subsequent quantitative phase of the study” (Tashakkori & Teddlie 1998: 47).
In this study the reasons for using pilot testing was to develop and test adequacy of research instruments. It was also used for assessing the feasibility of full scale study, designing research protocol, analyzing the sample frame and research technique and collecting preliminary data.
In this study 30 out of 150 respondents were used for the purpose of pilot study.
Ethical Consideration
Ethics refers to the appropriateness of researcher behavior in relation to the right of subject of work which is affected by research. Wells (1994) defines “ethics in terms of a code of behavior appropriate to academics and the code of conduct of research “.
In this research by following rules of ethics, all details of participants were remained confidential and they were completely informed related to the nature of the study, they were given fair consideration and personal biasness didn’t hamper the way of research, and the results were accurately represented as they were told and observed.