1. Describe the terms “Unit of analysis”, “Characteristics of Interest” and
“Decision-Making Unit”. Why is there confusion between the first two?
Ans One of the most important ideas in a research project is the unit of analysis. The unit of analysis is the major entity that you are analyzing in your study. For instance, any of the following could be a unit of analysis in a study:
Individuals groups artifacts (books, photos, newspapers) geographical units (town, census tract, state) social interactions (dyadic relations, divorces, arrests)
Why is it called the 'unit of analysis' and not something else (like, the unit of sampling)? Because it is the analysis you do in your study that determines what the unit is. For instance, if you are comparing the children in two classrooms on achievement test scores, the unit is the individual child because you have a score for each child. On the other hand, if you are comparing the two classes on classroom climate, your unit of analysis is the group, in this case the classroom, because you only have a classroom climate score for the class as a whole and not for each individual student. For different analyses in the same study you may have different units of analysis. If you decide to base an analysis on student scores, the individual is the unit. But you might decide to compare average classroom performance. In this case, since the data that goes into the analysis is the average itself (and not the individuals' scores) the unit of analysis is actually the group. Even though you had data at the student level, you use aggregates in the analysis. In many areas of social research these hierarchies of analysis units have become  particularly important and have spawned a whole area of statistical analysis sometimes referred to as hierarchical modeling. This is true in education, for instance, where we often compare classroom performance but collected achievement data at the individual student level

Decision-making unit" (DMU) often comes into play in defining the units of the universe. But the DMU is usually difficult to define in an unambiguous manner. A purchase that is a wife's decision in one family may be a husband's decision in  another and a joint decision in third. How does one cope with this problem? A two step procedure is a possibility. The first stage units are families; within each family the decision maker is identified. The units of the problem universe are the DMU's. Any compromise research universe must be evaluated against that concept, including the possibility that the DMU is a group. The following example from marketing will clarify the concepts.
The specification of the appropriate DMU for industrial products is more difficult than it is for consumer products. The number of persons who have potential involvement is greater. Job designations do not have the same meaning for all organisations. Responsibilities for ultimate decisions vary with size of organization, organizational structure, philosophy of decentralization, plus the personalities involved. The question is further complicated by the fact that some characteristics of interest refer to the organization-for example, size, geographic location, and past purchases-while others, such as preferences education, and attitudes, uniquely refer to specific individuals.
The problem definition, whether for a consumer product or an industrial product, must specify the units of analysis. It is better to err at this stage by specifying conceptually correct units that pose difficult problems in implementations. Compromises in the transition to operational definitions can then be better evaluated. This approach also permits the possibility of using different procedures with different market segments or a multistage approach in identifying the relevant DMU's.
The characteristics of interest identify what there is about the units that is of concern to the decision maker. These characteristics fall into two categories: the dependent variables and the independent variables. The dependent variables are those of interest for their own sake. For example, in marketing, they often refer to behaviour or attitude towards a firm's offering. Examples are purchases, awareness, opinions, or profits associated with consumer behaviour attitudes. The independent variables included in the problem definition are those characteristics thought to be related to the dependent variables. These variables may either be within the control of the firm (endogenous) - such as advertising, pricing or personnel changes -or beyond the control of the firm (exogenous). Exogenous variables of potential interest cover a multitude of possibilities, varying from competitor and government actions to economic conditions to individual consumer characteristics.
It is impossible to give a complete list of various characteristics that may be of interest to the manager. In order to overcome this impossibility, many practitioners and theorist have suggested a multitude of classification schemes. Indeed it seems that all managers and researchers feel compelled to establish their own classification scheme-and often more than one. No system is optimal for all projects and all discussions; but the 2 * 2 matrix developed by Frank, Massy, and Wind has two principal merits: simplicity and the highlighting of measurement assumptions. This matrix is presented in Table below. The 2 * 2 matrix, of course, yields four cells. Discussion of the separate cells with example from the field of marketing helps clarify the general classification scheme.






Situation Specific








Cell (1)-General objective measures. Cell (1) for example may contain two different types of variables: demographic and socio-economic. The demographic are illustrated by age, sex, stage of life cycle, marital status, tenure, geographic location, and rare or ethnic group. The socio-economic variables, usually stress income, education, and occupation either singly or in some combination assumed to be a measures of social class.
These variables do not relate to specific products or market activity. They typically enter marketing research projects as potential explanatory variables for the characteristics of direct interest to the marketing manager rather than as variables of direct interest themselves. Does age - a variable of cell (1) - help discriminate between product users and nonusers? At what age of fife cycle are the families most interested in condominium living? Neither age nor stage of life cycle would of interest in these examples apart from its potential relationship to specific products or companies.