Measuring familiarity

[Mbaye Fall Diallo]

Dear all,

I would like to analyse the moderating effect of store familiarity in a CFA model. So, I intend to measure the Familiarity construct (FAM) with the store from two other constructs : Experience (EXP) and Frequence (FRE). For this, I intend to conduct principal component analysis yielding a standardised factor score for Familiarity. Then, I plan to broke data into quartiles based on Familiarity. 

- The first quartile will comprise ‘‘low-familiar users’’, those users having the least amount of accumulated experiences with the store, i.e. having purchased most 
   infrequently and/or started frequenting store only recently.
- The second and the third quartiles will comprise the category ‘‘moderately familiar users’’.
- The fourth quartile will represente ‘‘highly familiar users’’.

Questions :
               Does anyone know how to broke data into quartiles with Spss?
               Can you provide your comments about this methodology?

Thanks in advance.

Best,
Mbaye,

---

Hotmail débarque sur votre téléphone ! Paramétrez Hotmail sur votre téléphone! Gratuit !

[Art Kendall]

Does anyone know how to broke data into quartiles with Spss?

Once you have the new variable use the RANK command specifying /ntiles(4).

Can you provide your comments about this methodology?

A lot depends on what you want to do with the new variable. Ntiles can be useful in some presentation contexts. For modeling you would usually want to leave the new variable as continuous.

I don't follow what you would be doing with PCA. Please give more detail.

Art Kendall
Social Research Consultants


On 3/4/2010 6:48 AM, Mbaye Fall Diallo wrote:

Dear all,

I would like to analyse the moderating effect of store familiarity in a CFA model. So, I intend to measure the Familiarity construct (FAM) with the store from two other constructs : Experience (EXP) and Frequence (FRE). For this, I intend to conduct principal component analysis yielding a standardised factor score for Familiarity. Then, I plan to broke data into quartiles based on Familiarity.

- The first quartile will comprise ‘‘low-familiar users’’, those users having the least amount of accumulated experiences with the store, i.e. having purchased most
infrequently and/or started frequenting store only recently.
- The second and the third quartiles will comprise the category ‘‘moderately familiar users’’.
- The fourth quartile will represente ‘‘highly familiar users’’.

Questions :
Does anyone know how to broke data into quartiles with Spss?
Can you provide your comments about this methodology?

Thanks in advance.

Best,
Mbaye,

---

Hotmail débarque sur votre téléphone ! Paramétrez Hotmail sur votre téléphone! Gratuit !

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD