I'm currently designing a questionnaire for measuring a variable. There are 5 questions related to the variable and 4 of them are in 5-point and 1 one of them is in 6-point Likert scale (based on literature review). Will it be a problem for further analysis on this variable? For your information, this variable will be a mediating one in the main model.
That is perfectly possible especially if they are just scores. They can be collapsed into one score eventually and used for further analysis. However, you dont mention whether the scales have real values. If one scale uses 1-5 rating while another uses values like $0-100, 101-200 etc, then you may find difficulty mixing apples with oranges.
It is usually best if you have all scales of similar number of data points. If you convert their score on each of the five scales to percentages (including the 1-6 one inversely) then you can plot or carry out tests easily that data entered as say .38 or .5 and so on.
I agree that all the variables, regardless of length, are "just scores," so what will matter is how well they correlate.
Having said that, I do prefer to keep all of the variables on the same response format, if only because it makes things easier for the respondent.
Dear All thanks for your responses.
Regarding my scales, all of them are ordinal. 4 of them (5-point) are agree-disagree questions and one of them (6-point) measures the respondent's intensity of a feeling. and all of them refer to one variable measurement.
I understood from the comments above that it's best to have all of them in one format. However, since they are just scores it's possible to run analyses like validity and reliability for the variable. Please confirm if I am correct.
The usual approach in scripting a scale from Likert-scored items is to assess their reliability using Cronbach's alpha, which uses correlations. In this regard, it doesn't matter how many response points you have (i.e., how the variables are scored), because that does not affect the ability to calculate correlations.
Because there have been so many questions here about Likert-scored items, I have compiled a set of resources on this topic:
https://www.researchgate.net/post/How_can_one_help_people_create_simple_scales_from_Likert-scored_items
