+ Reply to Thread
Results 1 to 11 of 11

Thread: Problem with Data analysis on Likert Scale!

  1. #1
    Points: 3,343, Level: 35
    Level completed: 96%, Points required for next Level: 7

    Posts
    1
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Thumbs up Problem with Data analysis on Likert Scale!




    Hello John,
    Im a student of Business studies and am working on a research project titled as "Impact of Physical environment on Employee Committment". In our model designed for this topic we have a general catagory named physical environment that contains sub-catagory(independent variables namely: Adequacy,architectiral arrangement and outlook) each of this independent variable has several determining factors like in adequacy there is cooling,,heating, ventilation etc. The dependent variable is employee Committment.
    We designed the questionnaire on a 5-scale Likert scale. with strongly agree and strongly disagree at its 2 continums. We got responses from 80 respondents. Now that we have gathered data we want to analyse it using statistical tools like Regression and correlation. The problem we are facing is that how should we run these methods. Like if take the 3 independent variables as X1, X2 and X3 and dependent variable as Y, then how shall we analyse the data and the responses.
    please help really stuck up at this stage
    Thanks in advance

  2. #2
    Points: 3,797, Level: 38
    Level completed: 98%, Points required for next Level: 3

    Location
    Barbados
    Posts
    132
    Thanks
    0
    Thanked 0 Times in 0 Posts
    Hi

    Given that the variables are continuous, and you are looking at multiple independent variables and their impact on a dependent variable, conduct a multiple regression analysis to determine which variables are related to the dependent variable.
    You can do correlational analysis among all variables first, then do the regression distinguishing the independent and dependent variables.

  3. #3
    alicccccc
    Guest

    Help please..

    Thanks John for your feedback...

    I am facing very similar problem... as follows:

    same data set to be collected - 5 points: SA/A/DoNotKnow/DA/SDA

    independent variables are:

    assessment structure
    e-learning platform
    supportive services

    hypothesis is that these factors contributing to the effectiveness of the e-learning platform, dependent factor.

    But I designed data collection to collect datasets about the independent variables only... true...

    NOW, I can not understand how to use Multiple regression mainly when you say:

    "We designed the questionnaire on a 5-scale Likert scale. with strongly agree and strongly disagree at its 2 continums"


    what is this exactly, and how can apply multiple regression on it in SPSS, it seems with no M.Reg...I have another application, MedCalc which has it... but yet, I do not know how to input data from the questions.. are they frequencies or means ... or what?

    Many thanks for your efforts...

  4. #4
    Points: 2,935, Level: 33
    Level completed: 24%, Points required for next Level: 115

    Posts
    15
    Thanks
    0
    Thanked 0 Times in 0 Posts
    hi Asma i guess u have to do a coding of your variable before entering into regression and method as stepwise. i suggest to do a scale reliability test before doing regression

  5. #5
    Points: 1,759, Level: 24
    Level completed: 59%, Points required for next Level: 41

    Posts
    1
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Similar Problem

    Hi there,
    I have a similar issue with having create a Quadrant analysis graph using 1 criterion variable (job satisfaction) and 8 predictor variables to see which one has the most impact on Job satisfaction. However, I don't know how to lay out the responses from the survey (which used likert scales) on a spreadsheet to calculate the standardized regression coefficients or what data to select if I were to do it on SPSS. Also I don't have the raw data (as in the exact answers of each person for every question). I only have the percentages for how many people picked Strongly Agree, Somewhat Agree, Somewhat Disagree etc. Do I need the raw data, or can I use what I have and still get a weighting for the 8 variables?

  6. #6
    Points: 238, Level: 4
    Level completed: 76%, Points required for next Level: 12

    Posts
    5
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Problem with Data analysis on Likert Scale!

    My research instrument(questionnaire) consists of one dependent variable(7 point Likerscale, 4 items) and seven independent variables. Each independent variable has 3 items, all measured in 7 point Likerscale. My sample size is limited to 50. My question is can I treat my dependent and independent variables (Likert scale as interval) and proceed with multiple regression? If yes, Can anyone please suggest how can i use multiple regression for Likertscale in spss? I need to generate multiple regression model. I am a beginner in stat and data analysis. Really appreciate your help in this regard.

  7. #7
    Human
    Points: 12,676, Level: 73
    Level completed: 57%, Points required for next Level: 174
    Awards:
    Master Tagger
    GretaGarbo's Avatar
    Posts
    1,362
    Thanks
    455
    Thanked 462 Times in 402 Posts

    Re: Problem with Data analysis on Likert Scale!

    My question is can I treat my dependent and independent variables (Likert scale as interval) and proceed with multiple regression?
    I would do that.

    I think you can find it under: Analyze/regression or Analyze/linear model

  8. #8
    Points: 238, Level: 4
    Level completed: 76%, Points required for next Level: 12

    Posts
    5
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Problem with Data analysis on Likert Scale!

    Hello,

    If I can use dependent variable likertscale(4 Items) as an Interval variable then can anyone please tell me how can I convert those 4 items data(7 point likertscale) into inverval data in SPSS? Also, I have 7 independent variables(7 point likertscale, each containing 3 items) which also need to be used as interval data for multiple regression. Please help me how can i use these items data as interval data for multiple regression in SPSS?

  9. #9
    TS Contributor
    Points: 17,773, Level: 84
    Level completed: 85%, Points required for next Level: 77
    Karabiner's Avatar
    Location
    FC Schalke 04, Germany
    Posts
    2,541
    Thanks
    56
    Thanked 640 Times in 602 Posts

    Re: Problem with Data analysis on Likert Scale!

    The score for the scale (the dependent variable) is calculated by just summing up the scores of the 4 items
    (as long that there are nowhere missing values). Use the Transform => Compute menue.

    With kind regards

    K.

  10. #10
    Points: 238, Level: 4
    Level completed: 76%, Points required for next Level: 12

    Posts
    5
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Problem with Data analysis on Likert Scale!

    Quote Originally Posted by Karabiner View Post
    The score for the scale (the dependent variable) is calculated by just summing up the scores of the 4 items
    (as long that there are nowhere missing values). Use the Transform => Compute menue.

    With kind regards

    K.
    Hello Sir,

    Somewhere I found that to summarize likert scale data we need to use median value of all the items in the scale. Some people also use average of all items ie mean but in one article they have mentioned to use median than the mean value. Could you please tell me will it be okay for me to summarize my likert scale data (4 items, dependent variable) as a median and like so for all independent variables (3 items, likertscale)? Can i proceed with these median values as interval data and carry on multiple regression? I am a beginner in data analysis, your suggestions will help me a lot in my study. Thanks in advance.

    Regards,
    Amrita

  11. #11
    TS Contributor
    Points: 17,773, Level: 84
    Level completed: 85%, Points required for next Level: 77
    Karabiner's Avatar
    Location
    FC Schalke 04, Germany
    Posts
    2,541
    Thanks
    56
    Thanked 640 Times in 602 Posts

    Re: Problem with Data analysis on Likert Scale!


    Could you please tell me will it be okay for me to summarize my likert scale data (4 items, dependent variable) as a median and like so for all independent variables (3 items, likertscale)?
    For summarizing Likert-type items, their values are summed up (which is equivalent to calculating the mean). The resulting value for the Likert scale is ususally treated as interval scaled.

    With Kind regards

    K.

+ Reply to Thread

           




Similar Threads

  1. Analysis of Likert Scale data
    By Servellen in forum Statistics
    Replies: 0
    Last Post: 04-03-2011, 07:59 AM
  2. Replies: 3
    Last Post: 10-07-2010, 08:03 PM
  3. Data analysis for Likert scale means
    By AnnEarley in forum Statistics
    Replies: 0
    Last Post: 03-30-2010, 04:57 PM
  4. Analysis of 5 point Likert Scale Data
    By AAA in forum Statistical Research
    Replies: 1
    Last Post: 12-15-2009, 08:47 PM
  5. Likert scale analysis problem
    By nma in forum Statistics
    Replies: 4
    Last Post: 06-24-2008, 04:54 AM

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats