Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Laura Maria Schwirz <schwirzl@tcd.ie> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: Mokken scaling procedure - output |
Date | Tue, 12 Feb 2013 15:42:32 +0000 |
Apologies. I had some trouble sending the email and I thought the Stata output caused the problem. Here's the output. I am actually just reading van Schur's article and find it quite helpful. . msp econ1 trust1 like1 energy1 Scale: 1 ---------- Significance level: 0.008333 The two first items selected in the scale 1 are econ1 and trust1 (Hjk=0.7016) Significance level: 0.006250 The item like1 is selected in the scale 1 Hj=0.5953 H=0.6273 Significance level: 0.005556 The item energy1 is selected in the scale 1 Hj=0.5535 H=0.5882 Significance level: 0.005556 There is no more items remaining. Observed Expected Number Mean Guttman Guttman Loevinger H0: Hj<=0 of NS Item Obs Score errors errors H coeff z-stat. p-value Hjk --------------------------------------------------------------------------------------------------- energy1 3072 0.5949 553 1238.52 0.55350 56.4588 0.00000 0 like1 3072 0.5278 527 1195.19 0.55907 58.9920 0.00000 0 econ1 3072 0.5197 351 1003.71 0.65030 60.3237 0.00000 0 trust1 3072 0.5763 495 1240.05 0.60082 62.5854 0.00000 0 --------------------------------------------------------------------------------------------------- Scale 3072 963 2338.74 0.58824 84.2721 0.00000 On 12 February 2013 15:39, JVerkuilen (Gmail) <jvverkuilen@gmail.com> wrote: > On Tue, Feb 12, 2013 at 10:09 AM, Laura Maria Schwirz <schwirzl@tcd.ie> wrote: >> Dear Statalist Users >> >> I have a set of variables that look at party leader traits. For >> example, on a scale from 0 to 5 how well does trait X describe leader >> Y? I would like to examine whether these traits form a scale or not. >> Is Mokken scaling procedure the right approach for this and if so, >> what does the actual output tell me? See below for an example where >> traits are knows how to manage economy, likeable, energetic, >> trustworthy. > > There's no below to see. ;) > > I'm the resident psychometrician. In general I find that Mokken > scaling is a good approach for many practical scale analyses, but I > recommend that you read at least a few articles on it. You also should > do a thorough job of missing data analysis and descriptive statistics, > including correlations. > > Here are citations to the two articles I assign in my IRT course on > nonparametric IRT: > > Meijer, R. R. & Baneke, J. J. (2004). Analyzing psychopathology items: > a case for nonparametric item response modeling. Psychological > Methods, 9, 354-368. > van Schuur, W. (2003). Mokken scaling: between the Guttman scale and > parametric item response theory. Political Analysis, 11, 139-163. > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/faqs/resources/statalist-faq/ > * http://www.ats.ucla.edu/stat/stata/ > -- Laura Schwirz PhD Candidate and IRCHSS Scholar Department of Political Science Trinity College Dublin Dublin 2 Republic of Ireland Email: schwirzl@tcd.ie On 12 February 2013 15:39, JVerkuilen (Gmail) <jvverkuilen@gmail.com> wrote: > On Tue, Feb 12, 2013 at 10:09 AM, Laura Maria Schwirz <schwirzl@tcd.ie> wrote: >> Dear Statalist Users >> >> I have a set of variables that look at party leader traits. For >> example, on a scale from 0 to 5 how well does trait X describe leader >> Y? I would like to examine whether these traits form a scale or not. >> Is Mokken scaling procedure the right approach for this and if so, >> what does the actual output tell me? See below for an example where >> traits are knows how to manage economy, likeable, energetic, >> trustworthy. > > There's no below to see. ;) > > I'm the resident psychometrician. In general I find that Mokken > scaling is a good approach for many practical scale analyses, but I > recommend that you read at least a few articles on it. You also should > do a thorough job of missing data analysis and descriptive statistics, > including correlations. > > Here are citations to the two articles I assign in my IRT course on > nonparametric IRT: > > Meijer, R. R. & Baneke, J. J. (2004). Analyzing psychopathology items: > a case for nonparametric item response modeling. Psychological > Methods, 9, 354-368. > van Schuur, W. (2003). Mokken scaling: between the Guttman scale and > parametric item response theory. Political Analysis, 11, 139-163. > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/faqs/resources/statalist-faq/ > * http://www.ats.ucla.edu/stat/stata/ > -- Laura Schwirz PhD Candidate and IRCHSS Scholar Department of Political Science Trinity College Dublin Dublin 2 Republic of Ireland Email: schwirzl@tcd.ie * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/