Discussion: View Thread

  • 1.  Methodological Help!

    Posted 04-21-2008 17:47

    Friends,
     
    I have been challenged to find published use of either of the following two procedures:
     
    (1).  The use of a single-item to measure a "global" attitude (e.g., "Overall, how satisfied are you with the proposed pay raise?"         Not at All Satisfied   1    2    3    4    5    6    7   Extremely Satisfied).  The intent is to get a summary evaluation, not explore or identify those elements that may contribute to one's opinion.
     
    (2).  The creation of 2 "groups" from continuous data by eliminating the middle SD.  For example, in the question above, calculate the mean and then eliminate plus and minus 1/2 SD so that you are comparing the top third with the bottom third (essentially).
     
    Thanks in advance for any leads you can suggest!  Coffee, bagels, and possibly a little "crow" is at stake.
     
    Cheers,
     
    GL
     
    G. L. Forward, PhD
    Professor of Organizational Communication
    Point Loma Nazarene University
    3900 Lomaland Dr., San Diego, CA 92106
    T: 619.849.2561     F: 619.849.7015
    *******************************************
    "The limits of my language are the limits of my world."
                                                              --Wittgenstein
    *******************************************
     

    My e-mail address has changed to GLForward@pointloma.edu.



  • 2.  Methodological Help!

    Posted 04-21-2008 19:35
    G. L.:

    I know that Highhouse & Becker (1993) compared facet measures to a
    single item measure of job satisfaction in the Journal of Business and
    Psychology ("Facet measures and global job satisfaction"). Scarpello
    and Campbell's (1983) Personnel Psychology article "Job satisfaction:
    Are all the parts there?" also discussed this and found it to be
    applicable. Don't know if that addresses your point #1 or not...

    I'm not entirely sure about the splitting of data into thirds, but from
    some of the medical journal articles I've read (which are very few), I
    think I've seen them employ that practice relatively often. But, again,
    I could be mistaken.

    Hope this helps some. Cheers!

    Beth A. Livingston
    PhD Candidate
    Department of Management
    Warrington College of Business Administration
    University of Florida
    Office Phone: 352.846.2691
    Email: beth.livingston@cba.ufl.edu
    Email: bethlivi@ufl.edu


    On Apr 21, 2008, at 5:46 PM, GL Forward wrote:

    > Friends,
    >  
    > I have been challenged to find published use of either of the
    > following two procedures:
    >  
    > (1).  The use of a single-item to measure a "global" attitude (e.g.,
    > "Overall, how satisfied are you with the proposed pay raise?"        
    > Not at All Satisfied   1    2    3    4    5    6    7   Extremely
    > Satisfied).  The intent is to get a summary evaluation, not explore or
    > identify those elements that may contribute to one's opinion.
    >  
    > (2).  The creation of 2 "groups" from continuous data by eliminating
    > the middle SD.  For example, in the question above, calculate the mean
    > and then eliminate plus and minus 1/2 SD so that you are comparing the
    > top third with the bottom third (essentially).
    >  
    > Thanks in advance for any leads you can suggest!  Coffee, bagels, and
    > possibly a little "crow" is at stake.
    >  
    > Cheers,
    >  
    > GL
    >  
    > G. L. Forward, PhD
    > Professor of Organizational Communication
    > Point Loma Nazarene University
    > 3900 Lomaland Dr., San Diego, CA 92106
    > T: 619.849.2561     F: 619.849.7015
    > Email: GLForward@pointloma.edu
    > *******************************************
    > "The limits of my language are the limits of my world."
    >                                                          
    > --Wittgenstein
    > *******************************************
    >  
    >
    > My e-mail address has changed to GLForward@pointloma.edu.


  • 3.  Methodological Help!

    Posted 04-21-2008 19:42

    GL,

     

    Although you may find examples (people can make mistakes), there are several important reasons for not engaging in either of the practices noted below. First, a single-item scale is a coarse way to measure the underlying construct of overall satisfaction (or other attitudes). Consequently, the resulting correlation between the scores gathered using this type of coarse scale and other variables will be artificially deflated (i.e., smaller observed correlation than its population counterpart). For a detailed description of this issue and a computer program available for free online that corrects for correlations computed using coarse scales, please see:

     

    Aguinis, H., Pierce, C. A., & Culpepper, S. A. (in press). Scale coarseness as a methodological artifact: Correcting correlation coefficients attenuated from using coarse scales. Organizational Research Methods. [available online at http://carbon.cudenver.edu/~haguinis/; please click on the "refereed journal articles" link]

     

    Second, it seems that the comparison between the two groups that you are trying to do is in relation to some other variable(s). This practice, labeled "artificial dichotomization" is also not recommended because it reduces the chances that you will find statistically significant differences (i.e., it reduces statistical power). This issue is discussed in detail in Aguinis (2004), Regression Analysis for Categorical Moderators, NY: Guilford [see http://www.guilford.com/cgi-bin/cartscript.cgi?page=research/aguinis.htm&cart_id=]. Let me know if you don't have access to this book and I could scan and email the appropriate pages to you.

     

    I hope this helps.

     

    All the best,

     

    --Herman.

    ******************************************
    Herman Aguinis, Ph.D.
    Mehalchin Term Professor of Management
    The Business School, University of Colorado Denver

    http://carbon.cudenver.edu/~haguinis

    Past Editor, Organizational Research Methods
    http://orm.sagepub.com
    ******************************************


    From: Organizational Behavior Division Listserv [mailto:OB@AOMLISTS.pace.edu] On Behalf Of GL Forward
    Sent: Monday, April 21, 2008 3:47 PM
    To: OB@AOMLISTS.pace.edu
    Subject: Methodological Help!

     

    Friends,

     

    I have been challenged to find published use of either of the following two procedures:

     

    (1).  The use of a single-item to measure a "global" attitude (e.g., "Overall, how satisfied are you with the proposed pay raise?"         Not at All Satisfied   1    2    3    4    5    6    7   Extremely Satisfied).  The intent is to get a summary evaluation, not explore or identify those elements that may contribute to one's opinion.

     

    (2).  The creation of 2 "groups" from continuous data by eliminating the middle SD.  For example, in the question above, calculate the mean and then eliminate plus and minus 1/2 SD so that you are comparing the top third with the bottom third (essentially).

     

    Thanks in advance for any leads you can suggest!  Coffee, bagels, and possibly a little "crow" is at stake.

     

    Cheers,

     

    GL

     

    G. L. Forward, PhD

    Professor of Organizational Communication

    Point Loma Nazarene University

    3900 Lomaland Dr., San Diego, CA 92106

    T: 619.849.2561     F: 619.849.7015

    Email: GLForward@pointloma.edu

    *******************************************

    "The limits of my language are the limits of my world."

                                                              --Wittgenstein

    *******************************************

     

    My e-mail address has changed to GLForward@pointloma.edu.



  • 4.  Methodological Help!

    Posted 04-21-2008 20:10
    Hi GL,

    For your first question, the following paper is relevant:

    Wanous, J. P., Reichers, A. E., & Hudy, M. J. (1997). Overall job
    satisfaction: How good are single-item measures? Journal of Applied
    Psychology, 82, 247-252.


    For your second question, the following paper is something you do not
    want to miss:

    Preacher, K. J., Rucker, D. D., MacCallum, R. C., & Nicewander, W. A.
    (2005). Use of the extreme groups approach: A critical reexamination and
    new recommendations. Psychological Methods, 10, 178-192.

    Cheers,

    Fan


    >>> GLForward@POINTLOMA.EDU 04/21/08 5:46 PM >>>
    Friends,

    I have been challenged to find published use of either of the following
    two procedures:

    (1). The use of a single-item to measure a "global" attitude (e.g.,
    "Overall, how satisfied are you with the proposed pay raise?"
    Not at All Satisfied 1 2 3 4 5 6 7 Extremely
    Satisfied). The intent is to get a summary evaluation, not explore or
    identify those elements that may contribute to one's opinion.

    (2). The creation of 2 "groups" from continuous data by eliminating the
    middle SD. For example, in the question above, calculate the mean and
    then eliminate plus and minus 1/2 SD so that you are comparing the top
    third with the bottom third (essentially).

    Thanks in advance for any leads you can suggest! Coffee, bagels, and
    possibly a little "crow" is at stake.

    Cheers,

    GL

    G. L. Forward, PhD
    Professor of Organizational Communication
    Point Loma Nazarene University
    3900 Lomaland Dr., San Diego, CA 92106
    T: 619.849.2561 F: 619.849.7015
    Email: GLForward@pointloma.edu
    *******************************************
    "The limits of my language are the limits of my world."
    --Wittgenstein
    *******************************************


    My e-mail address has changed to GLForward@pointloma.edu.


  • 5.  Methodological Help!

    Posted 04-21-2008 20:24
    It might be worth having a look at Nagy (2003) in the Journal of Occupational and Organizational Psychology for an answer to Part (1). He made a strong case for single item measures over multi-faceted ones.

    Hope this helps,

    Jon


    Jon Billsberry
    The Open University

    ________________________________

    From: Organizational Behavior Division Listserv on behalf of GL Forward
    Sent: Mon 21/04/2008 22:46
    To: OB@AOMLISTS.pace.edu
    Subject: Methodological Help!



    Friends,

    I have been challenged to find published use of either of the following two procedures:

    (1). The use of a single-item to measure a "global" attitude (e.g., "Overall, how satisfied are you with the proposed pay raise?" Not at All Satisfied 1 2 3 4 5 6 7 Extremely Satisfied). The intent is to get a summary evaluation, not explore or identify those elements that may contribute to one's opinion.

    (2). The creation of 2 "groups" from continuous data by eliminating the middle SD. For example, in the question above, calculate the mean and then eliminate plus and minus 1/2 SD so that you are comparing the top third with the bottom third (essentially).

    Thanks in advance for any leads you can suggest! Coffee, bagels, and possibly a little "crow" is at stake.

    Cheers,

    GL

    G. L. Forward, PhD
    Professor of Organizational Communication
    Point Loma Nazarene University
    3900 Lomaland Dr., San Diego, CA 92106
    T: 619.849.2561 F: 619.849.7015
    Email: GLForward@pointloma.edu
    *******************************************
    "The limits of my language are the limits of my world."
    --Wittgenstein
    *******************************************


    My e-mail address has changed to GLForward@pointloma.edu.


    ---------------------------------
    The Open University is incorporated by Royal Charter (RC 000391), an exempt charity in England & Wales and a charity registered in Scotland (SC 038302).


  • 6.  Methodological Help!

    Posted 04-22-2008 02:16
    Hi:

    On another note, apart from potential attenuation due to short test length discussed by others, regarding (1) individuals cannot discrimate well between global and specific dimensions of performance (they can do the global rating well, but not the specific dimension ratings). See:

    Mount, M. K., & Scullen, S. E. (2001). Multisource feedback ratings: What do they really measure? In M. London (Ed.), How people evaluate others in organizations (pp. 155-176). Mahwah, NJ: Lawrence Erlbaum.

    Scullen, S. E., Mount, M. K., & Goff, M. (2000). Understanding the latent structure of job performance ratings. Journal of Applied Psychology, 85(6), 956-970.

    Regarding (2), it is now established practice not to dichotomize, trichotomize etc. data. You loose information and of course power, and the consequences can result in a failure to detect significant differences (or do detect differences when there are none).

    Best,
    J.

    At 14:46 21.04.2008 -0700, you wrote:

    Friends,
     
    I have been challenged to find published use of either of the following two procedures:
     
    (1).  The use of a single-item to measure a "global" attitude (e.g., "Overall, how satisfied are you with the proposed pay raise?"         Not at All Satisfied   1    2    3    4    5    6    7   Extremely Satisfied).  The intent is to get a summary evaluation, not explore or identify those elements that may contribute to one's opinion.
     
    (2).  The creation of 2 "groups" from continuous data by eliminating the middle SD.  For example, in the question above, calculate the mean and then eliminate plus and minus 1/2 SD so that you are comparing the top third with the bottom third (essentially).
     
    Thanks in advance for any leads you can suggest!  Coffee, bagels, and possibly a little "crow" is at stake.
     
    Cheers,
     
    GL
     
    G. L. Forward, PhD
    Professor of Organizational Communication
    Point Loma Nazarene University
    3900 Lomaland Dr., San Diego, CA 92106
    T: 619.849.2561     F: 619.849.7015
    Email: GLForward@pointloma.edu
    *******************************************
    "The limits of my language are the limits of my world."
                                                              --Wittgenstein
    *******************************************
     

    My e-mail address has changed to GLForward@pointloma.edu.
    <x-sigsep></x-sigsep>

    ______________________________________

    Prof. John Antonakis
    Associate Dean, Executive Education
    Faculty of Business and Economics
    University of Lausanne
    Internef #527
    CH-1015 Lausanne-Dorigny
    Switzerland

    Tel: ++41 (0)21 692-3438
    Fax: ++41 (0)21 692-3305

    http://www.hec.unil.ch/people/jantonakis&cl=en
    ______________________________________



  • 7.  Methodological Help!

    Posted 04-22-2008 02:54
    Hi GL and all,



    Single item measure:



    The use of single-item measures in the behavioral sciences is generally discouraged, but this should not be perceived as a 'fatal error' in the process (Wanous et al 1997). In a relatively recent study I used unique setting enabled further validation of some single item measures by comparing them to the comprehensive sets of items in asub-sample. The single items used were clearly validated (Baruch, 2005). In addition, single item measures were successfully used to evaluate non-standard variables such as 'perceived probability that effort leads to performance' (Ilgen et al 1981). Of course, the use of single item measures is not new. Those for attitudes such as antecedents of organizational commitment (Morris et al 1993) and job satisfaction were extensively applied in the past and published in leading journals (Greenberg & Barling 1999).



    Overall, the single-item performance rating is not uncommon in the literature (Erez & Judge, 2001), but less desired, and may reduce the strength of your findings (see Aguinis e-mail).



    Yours,



    Yehuda



    References mentioned:



    Baruch, Y. (2005). Bullying on the net: adverse behaviour on e-mail and its impact. Information & Management, 42(2): 361-371.



    Erez, A., & Judge, T. A. 2001. Relationship of Core Self-Evaluations to Goal Setting,

    Motivation, and Performance. Journal of Applied Psychology, 86: 1270-1279.





    Morris, T. J. Lydka, H. Fenton-O'Creevy, M. P. (1993). Can Commitment be Managed? A Longitudinal Analysis of Employee Commitment and Human Resource Policies, Human Resource Management Journal, 3(3), 21-42.



    Greenberg, L. & Barling, J. (1999). Predicting employee aggression against coworkers, subordinates and supervisors: The role of person behaviors and perceived workplace factors Journal of Organizational Behavior, 20, 897-913.



    Ilgen, D. R. Nebeker, D. M. & Pritchard, R. D. (1981). Expectancy theory measures: an empirical comparison in an experimental simulation Organizational Behavior and Human Performance, 28, 189-223



    Wanous, J. P. Reichers, A. E. Hudy, M. J. (1997). Overall job satisfaction: how good are single-item measures? Journal of applied Psychology, 82, 247-252.






    Professor Yehuda Baruch
    Editor, Group & Organization Management
    Norwich Business School, UEA, UK
    Tel -44-1603-593341
    Fax -44-1603-593343

    ________________________________

    From: Organizational Behavior Division Listserv on behalf of GL Forward
    Sent: Mon 21/04/2008 22:46
    To: OB@AOMLISTS.pace.edu
    Subject: Methodological Help!



    Friends,

    I have been challenged to find published use of either of the following two procedures:

    (1). The use of a single-item to measure a "global" attitude (e.g., "Overall, how satisfied are you with the proposed pay raise?" Not at All Satisfied 1 2 3 4 5 6 7 Extremely Satisfied). The intent is to get a summary evaluation, not explore or identify those elements that may contribute to one's opinion.

    (2). The creation of 2 "groups" from continuous data by eliminating the middle SD. For example, in the question above, calculate the mean and then eliminate plus and minus 1/2 SD so that you are comparing the top third with the bottom third (essentially).

    Thanks in advance for any leads you can suggest! Coffee, bagels, and possibly a little "crow" is at stake.

    Cheers,

    GL

    G. L. Forward, PhD
    Professor of Organizational Communication
    Point Loma Nazarene University
    3900 Lomaland Dr., San Diego, CA 92106
    T: 619.849.2561 F: 619.849.7015
    Email: GLForward@pointloma.edu
    *******************************************
    "The limits of my language are the limits of my world."
    --Wittgenstein
    *******************************************


    My e-mail address has changed to GLForward@pointloma.edu.