Finally the paper concludes with the statement of present research's variables and describe the types of reliability and validity that is intended to be used in respect of such variables. The target object of the proposed research is to evaluate service quality performance versus customer expectations of the same.
A variable is a data that can assume one or more attributes called its values. The level of measurement refers to the relationship among the values that are assigned to the attributes for a variable. Level of measurement is important as it helps researcher to decide how to interpret the data from that variable. It also helps the researcher to decide what statistical analysis is most appropriate on the values that were assigned. As is typically posited four levels of measurements are identified i.e nominal(here the numerical values just "name" the attribute uniquely; no ordering of the cases is implied),ordinal( here measurement of the attributes can be rank-ordered and distances between attributes do not have any meaning),interval(in such measures distances between attributes do have meaning) and ratio(in such measurement there is always an absolute zero that is meaningful; this means that you can construct a meaningful fraction (or ratio) with a ratio variable).(Trochim,2006-a). These measurements have to be reliable and valid in an integrated manner and based on true score theory of measurement. to ensure high quality (Trochim, 2006-b). Unobtrusive measures are measures that don't require the researcher to intrude in the research context. Direct and participant observation requires that the researcher be physically present.Reseracher presence can affect respondent behavior and response. Three kinds of unobtrusive measures are normally used in social science research: Indirect Measures, Content Analysis and Secondary Analysis of Data(Trochim,2006-c).In short, unobtrusive measurement work to reduce the bias caused by researcher's presence but result in lesser control over the data.
The earlier paper on relationships had identified the primary constructs as: reliability, responsiveness, assurance, empathy, tangibles, and business success in relation to services' quality. Construct validity refers to the degree to which inferences can legitimately be made from the operationalizations in your study to the theoretical constructs on which those operationalizations were based. Construct validity involves generalizing from the program or measures to the concept of such program or measures (Trochim, 2006-d). Threats to construct validity may be caused by not properly defining operationally the constructs; using only one version of your treatment; inadequacy of using a single measure to look at a particular concept; interactions between different treatments; interaction of the testing and the treatment; unanticipated consequences etc.( Driebe ) It is posited here that answers to the proposed