Reference no: EM132271258
Resolution the first question on factor analysis as follows
A) What are the key assumption for conducting exploratory factor analysis (EFA) ? Does the metropolitan areas dataset adhere to them (please refer only to what we can see in the output reports)?
B) Describe briefly the key statistical findings of the factor solution (you can skip over the assumption test result and focus on the actual solution ). Please particularly focus on the eigenvalues , scree plot and unrotated /rotated factor matrices )
C) how could you re-run the analysis in SPSS in order to try finding an improved factor solution ?
D) Interpret the table labelled 'communalities ' in the SPSS output report . why are the initial values for each variable all smaller than 1.0?
E) SPSS has chosen by default to extract 4 factors from the metropolitan areas data set . how many factors would you decide to retain ? how would you label each chosen factor in your own solution?
F) How could a researcher practically use the obtained factor solution for conducting further research?
The second question on discriminant analysis as follows
What are the key assumptions about the quality of the underlying data set when performing discriminant analysis ? does the data set satisfy them(please only comment on what you can infer from the output reports)?
Describe briefly the key statistical findings the discriminant analysis solution ( you can skip over the assumption test results and focus on the actual solution ) Please only focus on the eigenvalues .wilk's Lambda and the structure matrix)
Please interpret the meaning pf the SPSS output in particular , do you believe it is a good solution? Is school D significantly different from the other business schools ? what types of students does school D attract?
What is your best guess, based on the analysis above, that this student will enroll in school D please make a prediction and state any assumption that you need to make.
How well are you able to discriminate MBA graduates using the information available in the study? explain briefly by interpreting the classification matrix.
In the table labeled as 'prior probabilities for groups ' you can see that the initial prior are 0.5. what does this mean ? what could we try out in order to see if we can improve the discriminant analysis solution?