1

I'm compiling a survey that will have several questions which would lend to the creation of an index of a main dependent variable (level of engagement in sucession planning). The questions will involve topics like:

  • PROCESS: linking strategic planning to succession planning, identifying critical positions that need to be filled,identifying competencies, identifying high potential employees, coaching and mentoring, providing leadership development;
  • ROLE IDENTIFICATION: identifying roles (several options); and
  • RESULTS: zero people ready for each position, 1 or 2 people ready for each position, or a pool of people ready for each position.

I'm not sure how to start. Any suggestions?

Jeromy Anglim
  • 42,044
  • 23
  • 146
  • 250
Tim
  • 11
  • 2
  • 1
    It sounds as if you already have decided the 10 or so items that will feed into (comprise) your scale score. (You use the term "dependent variable" as if this scale score is going to be eventually explained or predicted by some other variables, but as I read you you have not indicated what they are--only the components of the dependent variable itself. Is that right?) Further, are you looking for help designing the survey; computing your Engagement scale; or explaining/predicting it? – rolando2 Apr 26 '11 at 01:43

1 Answers1

1

Check out some of the following:

Community
  • 1
Jeromy Anglim
  • 42,044
  • 23
  • 146
  • 250
  • question about your blog on scale construction: You wrote about factor analysis, "The more items per factor, the fewer participants required." Can you explain? How far would you carry this principle? btw I've read in 1 idiosyncratic source that what counts is the ratio not of items to participants but of obtained factors to participants (should be just 20:1) - any comment? Thx. – rolando2 May 03 '11 at 14:20
  • @rolando2 The words you quote come from an a set of notes I wrote in 2006 http://web.psych.unimelb.edu.au/jkanglim/Anglim2006-SPSSIntroductionWorkshop.pdf. Thinking back, I took the idea from a lecture on factor analysis that summarised the findings of Velicer, W.F., and Fava J.L. (1987) An evaluation of the effects of variable sampling on component, image, and factor analysis. Multivariate Behavioral Research, 22, 193-209. – Jeromy Anglim May 03 '11 at 15:34
  • @rolando2 perhaps this site needs a question on sample size and factor analysis and role of various factors like loadings, number of items, etc. – Jeromy Anglim May 03 '11 at 15:36