Quality of Life Research

, Volume 6, Issue 2, pp 0–0 | Cite as

Factor analysis, causal indicators and quality of life

  • P. M. Fayers
  • D. J. Hand


Exploratory factor analysis (EFA) remains one of the standard and most widely used methods for demonstrating construct validity of new instruments. However, the model for EFA makes assumptions which may not be applicable to all quality of life (QOL) instruments, and as a consequence the results from EFA may be misleading. In particular, EFA assumes that the underlying construct of QOL (and any postulated subscales or ‘factors’) may be regarded as being reflected by the items in those factors or subscales. QOL instruments, however, frequently contain items such as diseases, symptoms or treatment side effects, which are ‘causal indicators.’ These items may cause reduction in QOL for those patients experiencing them, but the reverse relationship need not apply: not all patients with a poor QOL need be experiencing the same set of symptoms. Thus a high level of a symptom item may imply that a patient's QOL is likely to be poor, but a poor level of QOL need not imply that the patient probably suffers from that symptom. This is the reverse of the common EFA model, in which it is implicitly assumed that changes in QOL and any subscales ‘cause’ or are likely to be reflected by corresponding changes in all their constituent items; thus the items in EFA are called ‘effect indicators.’ Furthermore, disease-related clusters of symptoms, or treatment-induced side-effects, may result in different studies finding different sets of items being highly correlated; for example, a study involving lung cancer patients receiving surgery and chemotherapy might find one set of highly correlated symptoms, whilst prostate cancer patients receiving hormone therapy would have a very different symptom correlation structure. Since EFA is based upon analyzing the correlation matrix and assuming all items to be effect indicators, it will extract factors representing consequences of the disease or treatment. These factors are likely to vary between different patient subgroups, according to the mode of treatment or the disease type and stage. Such factors contain little information about the relationship between the items and any underlying QOL constructs. Factor analysis is largely irrelevant as a method of scale validation for those QOL instruments that contain causal indicators, and should only be used with items which are effect indicators.

Causal indicators construct validity factor analysis quality of life instruments 


  1. 1.
    Zigmond AS, Snaith RP. The Hospital Anxiety and Depression Scale. Acta Psychiatr Scand 1983; 67: 361-370.Google Scholar
  2. 2.
    Spearman C. General intelligence objectively determined and measured. Am J Psychol 1904; 15: 201-293.Google Scholar
  3. 3.
    MacCallum RC, Wegener DT, Uchino BN, Fabrigar LR. The problem of equivalent models in applications of covariance structure-analysis. Psychol Bull 1993; 114: 185-199.Google Scholar
  4. 4.
    Holroyd KA, Holm JE, Keefe FJ, et al.A multi-center evaluation of theMcGill Pain Questionnaire: Results from more than 1700 chronic pain patients. Pain 1992; 48: 301-311.Google Scholar
  5. 5.
    de Haes JCJM, van Knippenberg FCE, Neijt JP. Measuring psychological and physical distress in cancer patients: Structure and application of the Rotterdam Symptom Checklist. Br J Cancer 1990; 62: 1034-1038.Google Scholar
  6. 6.
    Watson M, Law M, Maguire GP, et al.Further development of a quality of life measure for cancer patients: the Rotterdam Symptom Checklist (revised). Psych Oncol 1992; 1: 35-44.Google Scholar
  7. 7.
    Paci E. Assessment of validity and clinical application of an Italian version of the Rotterdam Symptom Checklist. Qual Life Res 1992; 1: 129-134.Google Scholar
  8. 8.
    de Haes JCJM, Olschewski M, Fayers PM, et al. The Rotterdam Symptom Checklist (RSCL): A Manual. Groningen: Northern Centre for Healthcare Research, 1996.Google Scholar
  9. 9.
    World Health Organization. Constitution of the World Health Organization. Geneva, Switzerland: WHO Basic Documents, 1948.Google Scholar
  10. 10.
    Aaronson NK, Ahmedzai S, Bergman B, et al.The European Organization for Research and Treatment of Cancer QLQ-C30: A quality-of-life instrument for use in international clinical trials in oncology. J Natl Cancer Inst 1993; 85: 365-376.Google Scholar
  11. 11.
    Cella DF, Tulsky DS, Gray G, et al.The Functional Assessment of Cancer Therapy scale: development and validation of the general measure. J Clin Oncol 1993; 11: 570-579.Google Scholar
  12. 12.
    Schipper H, Clinch J, McMurray A, Levitt M. Measuring the quality of life of cancer patients: the Functional Living Index-Cancer: development and validation. J Clin Oncol 1984; 2: 472-483.Google Scholar
  13. 13.
    Hopwood P, Howell A, Maguire P. Screening for psychiatric morbidity in patients with advanced breast cancer: Validation of two self-report questionnaires. Br J Cancer 1991; 64: 353-356.Google Scholar
  14. 14.
    Ibbotson T, Maguire P, Selby P, Priestman TJ, Wallace L. Screening for anxiety and depression in cancer patients: The effects of disease and treatment. Eur J Cancer 1994; 30: 37-40.Google Scholar
  15. 15.
    Bergman B, Sullivan M, Sorenson S. Quality of life during chemotherapy for small cell lung cancer. I. An evaluation with generic health measures. Acta Oncol 1991; 30: 947-957.Google Scholar
  16. 16.
    Maguire P, Selby P. Assessing quality of life in cancer patients. Br J Cancer 1989; 60: 437-440.Google Scholar
  17. 17.
    Seymour MT, Slevin ML, Kerr DJ, et al.A randomized trial assessing the addition of interferon alpha2a to 5-fluorouracil and leucovorin in advanced colorectal cancer. J Clin Oncol 1996; 14: 2280-2288.Google Scholar
  18. 18.
    StataCorp. Stata Reference Manual: Release 4.0. College Station, TX (USA): Stata Corporation, 1995.Google Scholar
  19. 19.
    Bentler PM. EQS Structural Equations Program Manual. Encino, CA (USA): Multivariate Software, Inc., 1995.Google Scholar
  20. 20.
    Hendrickson AE, White PO. Promax: a quick method for rotation to oblique simple structure. Br J Statist Psychol 1964; 17: 65-70.Google Scholar
  21. 21.
    Moorey S, Greer S, Watson M, et al.The factor structure and factor stability of the hospital anxiety and depression scale in patientswith cancer [see comments]. Br J Psychiatry 1991; 158: 255-259.Google Scholar
  22. 22.
    Armitage P, Berry G. Statistical Methods in Medical Research. Oxford, UK: Blackwell Scientific Publications, 1994.Google Scholar
  23. 23.
    Bentler PM, Stein JA. Structural equationmodels inmedical research. Stat Methods Med Res 1992; 1: 159-181.Google Scholar
  24. 24.
    Blacock HM. Causal Inferences in Nonexperimental Research. Chapel Hill, CA (USA): University of North Carolina Press, 1964.Google Scholar
  25. 25.
    Bollen KA. Multiple indicators: internal consistency or no necessary relationship? Qual Quan 1984; 18: 377-385.Google Scholar
  26. 26.
    Bollen K, Lennox R. Conventional wisdom on measurement: a structural equation perspective. Psychol Bull 1991; 110: 305-314.Google Scholar
  27. 27.
    MacCallum RC, Browne MW. The use of causal indicators in covariance structure models- some practical issues. Psychol Bull 1993; 114: 533-541.Google Scholar
  28. 28.
    Nunnally JC, Bernstein IH. Psychometric Theory, 3rd Edition. New York, NY: McGraw-Hill, 1994.Google Scholar
  29. 29.
    Juniper EF, Guyatt GH, King DR. Comparison of methods for selecting items for a disease-specific quality-of-life questionnaire -importance versus factor-analysis. Qual Life Res 1994; 3: 52-53.Google Scholar
  30. 30.
    Steiger JH. Factor indeterminacy in the 1930's and the 1970's: some interesting parallels. Psychometr 1979; 50: 253-264.Google Scholar
  31. 31.
    McDonald RP, Mulaik SA. Determinacy of common factors: a nontechnical review. Psychol Bull 1979; 86: 297-308.Google Scholar
  32. 32.
    Steiger JH. Some additional thoughts on components, factors, and factor-indeterminacy. Multivar Behav Res 1990; 25: 41-45.Google Scholar
  33. 33.
    Bentler PM, Bonett DG. Significance tests and goodness of fit in the analysis of covariance structures. Psychol Bull 1980; 88: 588-606.Google Scholar
  34. 34.
    Marsh HW, Balla J. Goodness-of-fit in confirmatory factor-analysis — the effects of sample-size and model parsimony. Qual Quan 1994; 28: 185-217.Google Scholar
  35. 35.
    Kaplan D. Statistical power in structural equation modelling. In:Hoyle RH, ed. Structural Equation Modelling: Concepts, Issues and Applications. CA (USA): Sage Publications, 1995: 100-117.Google Scholar
  36. 36.
    Watson M, Zittoun R, Hall E, Solbu G, Wheatley K. A modular questionnaire for the assessment of long-term quality of life in leukaemia patients: The MRC/EORTC QLQ-LEU. Qual Life Res 1996; 5: 15-19.Google Scholar
  37. 37.
    Carlsson M, Hamrin E. Measurement of quality of life in women with breast cancer. Development of a life satisfaction questionnaire (LSQ-32) and a comparisonwith the and EORTC QLQ-C30. Qual Life Res 1996; 5: 265-274.Google Scholar
  38. 38.
    Meadows K, Steen N, McColl E, et al.The diabetes health profile (DHP): A new instrument for assessing the psychosocial profile of insulin requiring patients - Development and psychometric evaluation. Qual Life Res 1996; 5: 242-254.Google Scholar
  39. 39.
    Valenti L, Lim L, Heller RF, Knapp J. An improved questionnaire for assessing quality of life after acutemyocardial infarction. Qual Life Res 1996; 5: 151-161.Google Scholar
  40. 40.
    Essink-Bot ML, Krabbe PFM, van Agt HME, Bonsel GJ. NHP or SIP -Acomparative study in renal insufficiency associated anemia. Qual Life Res 1996; 5: 91-100.Google Scholar

Copyright information

© Chapman and Hall 1997

Authors and Affiliations

  • P. M. Fayers
    • 1
  • D. J. Hand
    • 2
  1. 1.Unit for Clinical Research and Epidemiology, Faculty of MedicineNorwegian University of Science and TechnologyTrondheimNorway
  2. 2.Department of StatisticsOpen UniversityMilton KeynesUK

Personalised recommendations