Team C Day 10 (Rahat Dhir)

Day 10 – Team C

Today we started with the revision of Dicriminant with Bank loan file. It is an imperative tool in SPSS that helps in the prediction of the outcome. It can thus have a descriptive or a predictive objective.

Discriminant function analysis is used to determine which continuous variables discriminate between two or more naturally occurring groups. For example, a researcher may want to investigate which variables discriminate between fruits eaten by (1) primates, (2) birds, or (3) squirrels. For that purpose, the researcher could collect data on numerous fruit characteristics of those species eaten by each of the animal groups. Most fruits will naturally fall into one of the three categories. Discriminant analysis could then be used to determine which variables are the best predictors of whether a fruit will be eaten by birds, primates, or squirrels.

We follow the following procedure:

Analysis-> Classify-> discriminant

·         Select grouping variable as default.

·         Select rest as independent.

·         Select means in statistics and summary table in classify.

·         Save with all 3 option checked.

Go to the data view, we observe 4 new columns added, which signifies:

1.       Dis_1: What we predicted

2.       Dis1_1: Scores

3.       Dis1_2: Probability of not defaulting

4.       Dis2_2: Probability of defaulting

Now, in the output file we compare canonical discriminant function table with functions at group centroids table to see the effect of various variables on grouping variable.

Then we studied the Gss93 file. Choose respondent sex as the independent variable, while music type as independent. Follow similar steps like before and save file also. In the output file we compare canonical discriminant function table with functions at group centroids table to see the effect of various variables on grouping variable.

Second half of the class was covered under Conjoint topic. It is a method to find what people actually want. Here we use several combination of opinion answers, and ask people to rate them and provide ranking to them. Based on this we calculate their preference for an individual aspect (using highest utility difference).

The objective of conjoint analysis is to determine what combination of a limited number of attributes is most influential on respondent choice or decision making. A controlled set of potential products or services is shown to respondents and by analyzing how they make preferences between these products, the implicit valuation of the individual elements making up the product or service can be determined. These implicit valuations (utilities or part-worths) can be used to create market models that estimate market share, revenue and even profitability of new designs.

Advantages:

§  Estimates psychological tradeoffs that consumers make when evaluating several attributes together.

§  measures preferences at the individual level

§  uncovers real or hidden drivers which may not be apparent to the respondent themselves

§  realistic choice or shopping task

§  able to use physical objects

§  if appropriately designed, the ability to model interactions between attributes can be used to develop needs based segmentation

Disadvantages:

§  designing conjoint studies can be complex

§  with too many options, respondents resort to simplification strategies

§  difficult to use for product positioning research because there is no procedure for converting perceptions about actual features to perceptions about a reduced set of underlying features

§  respondents are unable to articulate attitudes toward new categories, or may feel forced to think about issues they would otherwise not give much thought to

§  poorly designed studies may over-value emotional/preference variables and undervalue concrete variables

§  does not take into account the number items per purchase so it can give a poor reading of market share

Then we use SPSS and go to: (food priority example)

Data-> Orthogonal designs-> Generate

Start adding factor name eg type and add. Click on type and define values with lables and continue. Click file when you are done with all factors and click save. Now for ranking:

Data-> Orthogonal designs-> Display

Select all apart from status and card. Select, listing and profile, and OK. You will receive a card table, copy paste in excel and give ranking as per your preference. 1-16 ranks, with 1 being most preferable and 16 meaning least.

Next part will be followed in the next class.

Rahat S. Dhir