# Presentation On Discriminant Analysis, Factor Analysis & Conjoint Analysis Presented By Sandip Magar

Discriminant Analysis Idea & Purpose Objective is to find a linear combination of independent variables that make the mean scores across categories of dependent variables on this linear combination maximally different. Used to classify objects into two or more alternative groups on the basis of a set of measurements. .

Submit the training sample to a Discriminant Analysis and obtain a set of discriminant functions. The information on these functions is stored in a dataset that is created within the program. used implicitly by for example SPSS or SAS. so you do not need to see or know them. The same procedure allows a true validation of the classification functions by using a file that contains objects of known membership to be classified using only the information on the variables and the classification functions developed with the training or learning sample    . sample. These functions are functions. program.Discriminant Analysis Procedure  Obtain a random sample of objects from each class (these are objects whose membership is known) This is known as the training or learning sample. them.

Factor Analysis Factor:  A variable or a construct that is not directly observable but needs to be inferred from input variables Eigenvalue:  Amount of variance in the original variables that are associated with the factor .

Factor Score: Value of each factor for all respondents . level.Factor Analysis Percentage of Variance Criteria: The number of Criteria: factors extracted is determined so that the cumulative percentage of variance extracted by the variance reaches a satisfactory level.

Disadvantages of Factor Analysis  Subjective Does not make use of any standard Statistical tests   .

Conjoint Analysis Measure joint effects of two or more independent variables on the ordering of a dependent variable Quantitative measure of relative importance of one attribute over another .

attributes. unless the attribute naturally occurs in binary form (two levels). stimuli.     . levels). A typical conjoint analysis study involves six or seven attributes. The researcher should take into account the attribute levels prevalent in the marketplace and the objectives of the study.Conducting Conjoint Analysis Formulate the Problem  Identify the attributes and attribute levels to be used in constructing the stimuli. actionable. The attributes selected should be salient in influencing consumer preference and choice and should be actionable. At least three levels should be used. study.

the use of ratings has become increasingly common. the conjoint methodology is flexible and can accommodate a range of other dependent variables.     . independently. rankevaluations. The dependent variable is usually preference or intention to buy. In this case. In the metric form. including actual purchase or choice. However.Conducting Conjoint Analysis Decide on the Form of Input Data  For non-metric data. choice. common. respondents were required to provide preference. In recent years. buy. the respondents provide ratings. In evaluating sneaker profiles. rather than rankings. independently. the respondents are typically required to nonprovide rank-order evaluations. preference. the judgments are typically made rankings.

partunique. particularly if a large number of attributes are involved and the model must be estimated at the individual level. Another limitation is that data collection may be complex. The tradeoff model may not be a good representation of the choice process.     . tradeoffs. The part-worth functions are not unique. process. identified. level. It assumes that consumers evaluate the choice alternatives in terms of these attributes and make tradeoffs.Assumptions and Limitations of Conjoint Analysis  Conjoint analysis assumes that the important attributes of a product can be identified.