Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Comparative Study
. 2016 Jun;30(2):92-102.
doi: 10.1007/s40211-016-0180-3. Epub 2016 Jun 13.

The importance of statistical modelling in clinical research : Comparing multidimensional Rasch-, structural equation and linear regression models for analyzing the depression of relatives of psychiatric patients

Rainer W Alexandrowicz  1 , Rebecca Jahn  2 , Fabian Friedrich  2 , Anne Unger  2
Affiliations
Comparative Study

The importance of statistical modelling in clinical research : Comparing multidimensional Rasch-, structural equation and linear regression models for analyzing the depression of relatives of psychiatric patients

Rainer W Alexandrowicz et al. Neuropsychiatr. 2016 Jun.

Abstract
in English, German

Background: Various studies have shown that caregiving relatives of schizophrenic patients are at risk of suffering from depression. These studies differ with respect to the applied statistical methods, which could influence the findings. Therefore, the present study analyzes to which extent different methods may cause differing results.

Methods: The present study contrasts by means of one data set the results of three different modelling approaches, Rasch Modelling (RM), Structural Equation Modelling (SEM), and Linear Regression Modelling (LRM).

Results: The results of the three models varied considerably, reflecting the different assumptions of the respective models.

Conclusions: Latent trait models (i. e., RM and SEM) generally provide more convincing results by correcting for measurement error and the RM specifically proves superior for it treats ordered categorical data most adequately.

Hintergrund: In zahlreichen Studien konnte gezeigt werden, dass die Betreuung schizophrener Patienten durch Angehörige eine große Belastung für die Angehörigen darstellen und zu Depressionen der Angehörigen führen kann. Allerdings unterscheiden sich diese Studien in ihrer statistischen Herangehensweise, was einen Einfluss auf die Ergebnisse haben kann.

Methodik: Die vorliegende Studie vergleicht daher drei verschiedene statistische Modelle, das Rasch-Modell (RM), das Strukturgleichungsmodell (SEM) und das lineare Regressionsmodell an einem Datensatz.

Ergebnisse: Es zeigten sich zum Teil deutliche Unterschiede zwischen den drei untersuchten Modellen, die sich durch deren spezifischen Annahmen erklären lassen.

Schlussfolgerungen: Latent-trait-Modelle (d. h. das RM und das SEM) führen im Allgemeinen zu überzeugenderen Ergebnissen, da sie den Messfehler korrigieren. Das RM erweist sich darüber hinaus als überlegen gegenüber den anderen Modellen, da es ordinalskalierte Daten am angemessensten verarbeiten kann.

Keywords: Latent regression; Linear Regression Model; Model comparison; Rasch Model; Structural Equation Model.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
Outline of the MRCMLM- and the SEM-approach
Fig. 2
Fig. 2
Outline of the LRM-approach
Fig. 3
Fig. 3
Item-based fit-measures for the five scales; circles: outfit indices of the MRCMLM; “x”: factor loadings of the SEM; bullets: corrected item-total-correlation
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Flyckt L, Fatouros-Bergman H, Koernig T. Determinants of subjective and objective burden of informal caregiving of patents with psychotic disorders. Int J Soc Psych. 2015;61(7):684–692. doi: 10.1177/0020764015573088. - DOI - PMC - PubMed
    1. Wilms H-U, Mory C, Angermeyer MC. Erkrankungsbedingte Kosten für Partner psychisch Kranker: Ergebnisse einer Mehrfacherhebung. Psychiat Prax. 2004;31:177–183. doi: 10.1055/s-2003-812600. - DOI - PubMed
    1. Young SR, Young HY, Sohee P, Dong OS, Kwang ML, Han JY, Jeong HK, Soon OK, Ran L, Youn OL, Nam SK. Depression in family Caregivers of cancer patients: the feeling of burden as a predictor of depression. J Clin Oncol. 2008;26:5890–5895. doi: 10.1200/JCO.2007.15.3957. - DOI - PubMed
    1. Magliano L, Fadden G, Madianos M, Caldas de Almeida J, Held T, Marasco C, Tosini P, Maj M. Burden on the families of patients with schizophrenia: results of the BIOMED-1 study. Soc Psychiatry Psychiatr Epidemiol. 1998;33:405–412. doi: 10.1007/s001270050073. - DOI - PubMed
    1. Jungbauer J, Mory C, Angermeyer MC. Ist die Betreuung eines schizophrenen Familienmitglieds mit einem Gesundheitsrisiko verbunden? Psychische und psychosomatische Beeintraechtigungen bei Angehoerigen schizophrener Patienten. Fortschr Neurol Psychiat. 2002;70:548–554. doi: 10.1055/s-2002-34669. - DOI - PubMed

Publication types

LinkOut - more resources