Summary

Summary of all lectures

2 purchases

Course
Marketing Research Methods

Institution
Rijksuniversiteit Groningen (RuG)

This summary helped me a lot studying for the MRM exam. I took a lot of time summarizing everything and used mainly this document to study and get an 8.4 as a result. The screenshots are from the lecture. If you know the content lectures, in my opinion you know enough to pass this course. There are...

[Show more]

Preview 3 out of 23 pages

View example

Uploaded on November 29, 2018
Number of pages 23
Written in 2018/2019
Type Summary

malhotra
marketing statistics
marketing research methods

Institution
Rijksuniversiteit Groningen (RuG)
Education
Marketing
Course
Marketing Research Methods

$4.43

Also available in package deal from $5.54

Add to cart

Save

100% satisfaction guarantee
Immediately available after payment
Both online and in PDF
No strings attached

Also available in package deal (1)

Marketing research essentials to get an 8 (like me:)

$ 7.75 $ 5.54

3x sold

2 items

1. Summary - Summary of all lectures
2. Class notes - Summary and transcripts of last (and most important) lecture
Show more

● Factor analysis
1. You use it for more complicated issues than issues you can use a one-item scale for. So multi-item
scales needed.

The purpose is reduction of much data by finding common variance. The ultimate goal is using
dimensions in further analysis. Data can be interval- or ratio scaled. Or assumed interval which is
ordinal (Likert). Usually IV, no causal relation. n items will be p factors.

- use it for parsimony
- use it to reduce multicollinearity
Check correlation matrix first.

After putting them into factors, you have dimensions which are now uncorrelated with each other.

- Items = variables = survey questions
- Dimensions = factors = components
2. Is FA appropriate?
Barlett’s test
- H0: variables are uncorrelated, i.e. the identity matrix

KMO
- If KMO <0.5, drop variable with lowest individual KMO statistics

NOTE also check the communalities. Common rule: >.4

The communalities measure the percent of variance in a given variable explained by all the extracted
factors. This is < 1, since we have fewer factors than variables.

3. Select factor model to get the weights wij
- See how the variables combine into factors: PCA (Principal Component Analysis)
4. Select best number of factors

,5. Orthogonal rotation prevents that all variables load on one factor. Does not change the variance
explained.

Common factor analysis: factors are estimated based only on the common variance.
Eigenvalues are in decreasing order of magnitude as we go from factor 1 to factor 6. Eigenvalue of a
factor indicates the total variance attributed to that factor, so should be as high as possible. See p.
641. Eigenvalue divided by number of factors is % of variance.
Deciding how many factors you should choose can be done by:
o A priori determination
o Determination based on eigenvalues
o Determination based on a scree plot
o Determination based on percentage of
variance
o Determination based on split-half reliability
o Determination based on significance tests
6. interpreting and labeling factors.

The ones of F3 are as highest around .4 but that is not high enough. Should be 0.5 or higher. X14 is
not really clear if it belongs to F1 or F2. Exclude these variables and do factor analysis again.
7. Subsequent use of factors. Use obtained factors as new variables. Calculate factor scores for each
respondent or use reliability analysis. Internal consistency (reliability):

, >> p-value
would go from
0.589 to 0.601
if item
deleted.

• Cluster analysis

Gap in brands and also a cluster of
people in this gap? Then you could
make a new brand there. This can
be done by combining cluster and
factor analysis.

Dividing a heterogeneous sample in
homogeneous groups based on a
set of (active) variables.

-Making groups that are internally
as similar as possible, but are as
different as possible from other
groups

Active variables: used for clustering

Passive variables: used for group identification, e.g. demographics)

1. segmentation basis (active variables).

2. Scores on each variable can be transformed / standardized, e.g., to have a mean of 0 and a
variance of 1 (Z-scores). Do this in SPSS when performing analysis.

3. Hierarchical :

- -Can be agglomerative (most often) or divisive
- -Based on pairwise distances
- -Preferred: Ward’s method
- -Uses Squared Euclidean Distance
- -Produces tree (dendrogram)

Non Hierarchical:
- -Pre-specify #clusters
- -Start with certain clusters (centres) and add other observations

The benefits of buying summaries with Stuvia:

Guaranteed quality through customer reviews

Stuvia customers have reviewed more than 700,000 summaries. This how you know that you are buying the best documents.

Quick and easy check-out

You can quickly pay through credit card or Stuvia-credit for the summaries. There is no membership needed.

Focus on what matters

Your fellow students write the study notes themselves, which is why the documents are always reliable and up-to-date. This ensures you quickly get to the core!

Frequently asked questions

What do I get when I buy this document?

You get a PDF, available immediately after your purchase. The purchased document is accessible anytime, anywhere and indefinitely through your profile.

Satisfaction guarantee: how does it work?

Our satisfaction guarantee ensures that you always find a study document that suits you well. You fill out a form, and our customer service team takes care of the rest.

Who am I buying these notes from?

Stuvia is a marketplace, so you are not buying this document from us, but from seller verawillems. Stuvia facilitates payment to the seller.

Will I be stuck with a subscription?

No, you only buy these notes for $4.43. You're not tied to anything after your purchase.

Can Stuvia be trusted?

4.6 stars on Google & Trustpilot (+1000 reviews)

66184 documents were sold in the last 30 days

Founded in 2010, the go-to place to buy study notes for 15 years now

Start selling