Bias and heteroscedastic memory error in self-reported health behavior: an investigation using covariance structure analysis

BMC Medical Research Methodology

Emil Kupek¹ 

[1] Universidade Federal de Santa Catarina, Departamento de Saúde Pública – CCS, Campus Universitario, Trindade, 88.040-900 Florianópolis-SC, Brazil

关键词: memory error;    sexual behavior;    validity;    measurement errors;    covariance structure analysis;    heteroscedasticity;    bias;   

Others  :  1143443
DOI  :  10.1186/1471-2288-2-14

 received in 2002-06-13, accepted in 2002-11-18,  发布年份 2002

【 摘 要 】

Background

Frequent use of self-reports for investigating recent and past behavior in medical research requires statistical techniques capable of analyzing complex sources of bias associated with this methodology. In particular, although decreasing accuracy of recalling more distant past events is commonplace, the bias due to differential in memory errors resulting from it has rarely been modeled statistically.

Methods

Covariance structure analysis was used to estimate the recall error of self-reported number of sexual partners for past periods of varying duration and its implication for the bias.

Results

Results indicated increasing levels of inaccuracy for reports about more distant past. Considerable positive bias was found for a small fraction of respondents who reported ten or more partners in the last year, last two years and last five years. This is consistent with the effect of heteroscedastic random error where the majority of partners had been acquired in the more distant past and therefore were recalled less accurately than the partners acquired more recently to the time of interviewing.

Conclusions

Memory errors of this type depend on the salience of the events recalled and are likely to be present in many areas of health research based on self-reported behavior.

【 授权许可】

   
2002 Kupek; licensee BioMed Central Ltd. This is an Open Access article: verbatim copying and redistribution of this article are permitted in all media for any purpose, provided this notice is preserved along with the article's original URL.

【 图 表 】

Figure 1.

Figure 2.

【 参考文献 】

• [1]Boulton M: The methodological imagination. In Challenge and innovation: Methodological advances in social research on HIV/AIDS. Edited by Boulton M. London, Taylor & Francis; 1994:1-21.
• [2]Wadsworth J, Johnson AM, Wellings K, Field JJ: What is in a mean – an examination of the inconsistency between men and women reporting sexual partnerships. J R Statis Soc A 1996, 159:111-123.
• [3]Catania JA, Gibson DR, Chitwood DD, Coates DJ: Methodological problems in AIDS behavioural research: Influences of measurement error and participation bias in studies of sexual behaviour. Psychol Bull 1990, 108:339-362.
• [4]Friedman WJ: Memory for the time of past events. Psychol Bull 1993, 113:44-66.
• [5]Gaskell G, Wright D, O'Muirchaertaigh C: Reliability of surveys. Psychologist 1993, 6(11):500-503.
• [6]Krosnick JA: Response strategies for coping with the cognitive demands of attitude measures in surveys. Appl Cognit Psychol 1991, 5:213-236.
• [7]Nadeau R, Niemi RG: Educated guesses: The process of answering factual knowledge questions in surveys. Public Opinion Quart 1995, 59:323-346.
• [8]Johnson AM, Wadsworth J, Wellings K, Field J: Sexual Attitudes and Lifestyles. Oxford, Blackwell Scientific Publications 1994.
• [9]Hoyt TW: Rater bias in psychological research: When is it a problem and what can we do about it? Psy Method 2000, 5:64-86.
• [10]Hoyt WT, Kerns MD: Magnitude and moderators of bias in observer ratings: a meta-analysis. Psy Method 1999, 4:403-424.
• [11]Kupek E: Determinants of item non-response in a large national sex survey. Arch Sex Behav 1998, 27:581-594.
• [12]Kupek E: Estimation of the number of sexual partners for the non-respondents to a large national survey. Arch Sex Behav 1999, 28:233-242.
• [13]Wadsworth J, Field J, Johnson AM, Bradshaw S, Wellings K: Methodology of the National Survey of Sexual Attitudes and Lifestyles. J R Stat Soc Ser A Stat Soc 1993, 156:407-421.
• [14]Dunn G, Everitt B, Pickles A: Modelling covariances and latent variables using EQS. London, Chapman & Hall 1993.
• [15]Joreskog KG, Sorbom D: LISREL VI. Uppsala, Uppsala University Press 1981.
• [16]Scott Long J: Covariance Structure Models: An Introduction to LISREL. London, Sage Publications 1990.
• [17]Johnson RA, Wichern DW: Applied multivariate statistical analysis. Englewood Cliffs, Prentice Hall Int 1988.
• [18]Sharma S: Applied multivariate techniques. New York, John Wiley & Sons 1996.
• [19]Institute SAS: Proc CALIS. In SAS/STAT (R) User's Guide. Version 6. Volume 2. Edited by SAS Institute. Cary, NC, SAS Institute; 1989::245-366.
• [20]Maddala GS: Econometrics. New York, McGraw-Hill 1977.
• [21]Heckman J, Robb R: Alternative methods for solving the problem of selection bias in evaluating the impact of treatment on outcomes. In Drawing inferences from self-selected samples. Edited by Wainer H. Berlin, Springer-Verlag; 1986.
• [22]Bartholomew DJ: Foundation of factor analysis: Some practical implications. British J Math Statist Psych 1985, 38:1-10.
• [23]Wood PW: The effect of unmeasured variables and their interactions on structural models. In Latent variables analysis. Edited by von Eye A, Clogg CC. London, Sage Publications; 1994:109-130.
• [24]Bollen KA, Stine RA: Bootstrapping goodness-of-fit measures in structural equation models. In Testing structural equation models. Edited by Bollen KA, Scott Long J. Newbury Park, Sage Publications; 1993:111-135.
• [25]Browne MW, Cudeck R: Alternative ways of assessing model fit. In Testing structural equation models. Edited by Bollen KA, Scott Long J. Newbury Park, Sage Publications; 1993:136-162.
• [26]Chou CP, Bentler PM, Satorra A: Scaled test statistics and robust standard errors for non-normal data in covariance structure analysis: A Monte Carlo study. British J Math Statist Psych 1993, 44:347-357.
• [27]MacCallum RC, Roznowski M, Mar CM, Reith JV: Alternative strategies for cross-validation of covariance structure models. Multivariate Behav Res 1994, 29:1-32.
• [28]Gonzalez R, Griffin D: Testing parameters in structural equation modeling: every "one" matters. Psy Method 2001, 6:258-269.
• [29]MacCallum RC, Roznowski M, Necowitz LB: Model modification in covariance structure analysis: the problem of capitalization on chance. Psychol Bull 1992, 111:490-504.
• [30]Browne MW: Asymptotically distribution-free methods for the analysis of covariance structures. British J Math Statist Psych 1984, 37:62-83.
• [31]Boomsma A: The robustness of maximum likelihood estimation in structural equation models. In Structural Modelling by Example. Edited by Cuttance P, Ecob R. Cambridge, Cambridge University Press; 1987:160-188.
• [32]Browne MW, Shapiro A: Robustness of normal theory methods in the analysis of linear latent variable models. British J Math Statist Psych 1988, 41:193-208.
• [33]Satorra A, Bentler PM: Model conditions for asymptotic robustness in the analysis of linear relations. Comput Stat Data Analysis 1990, 10:235-249.
• [34]Satorra A, Bentler PM: Corrections to tests statistics and standard errors in covariance structure analysis. In Latent variables analysis. Edited by von Eye A, Clogg CC. London, Sage Publications; 1994:399-419.
• [35]Bentler PM, Newcomb MD: Linear structural modeling with nonnormal continuous variables. Application: Relations among social support, drug use, and health in young adults. In Statistical models for longitudinal studies of health. Edited by Dwayer JH, Feinlieb M, Lippert P, Hoffmeister H. Oxford, Oxford University Press; 1992:132-160.
• [36]Gerbing DW, Anderson JC: Monte Carlo evaluations of goodness-of-fit indices for structural equation models. In Testing structural equation models. Edited by Bollen KA, Scott Long J. Newbury Park, Sage Publications; 1993:40-65.
• [37]Muthen BO: Goodness of fit with categorical and other nonnormal variables. In Testing structural equation models. Edited by Bollen KA, Scott Long J. Newbury Park, Sage Publications; 1993:205-234.
• [38]Tanaka JS: Multifaceted conceptions of fit in structural equation models. In Testing structural equation models. Edited by Bollen KA, Scott Long J. Newbury Park, Sage Publications; 1993:10-39.
• [39]Kupek E: Sexual attitudes and number of partners in young British men. Arch Sex Behav 2001, 30:13-27.
• [40]Fendrich M, Vaughn CM: Diminished lifetime substance use over time: an inquiry into differential underreporting. Public Opinion Quart 1994, 58:96-123.
• [41]Pickles A, Pickering K, Taylor C: Reconciling recalled dates of developmental milestones, events and transitions: a mixed generalized linear model with random mean and variance functions. J R Statist Soc A 1996, 159:225-234.
• [42]Saris WE, Satorra A: Power evaluations in structural equation models. In Testing structural equation models. Edited by Bollen KA, Scott Long J. Newbury Park, Sage Publications; 1993:181-204.
• [43]Raftery AE: Bayesian model selection in structural equation models. In Testing structural equation models. Edited by Bollen KA, Long JS. Newbury Park, Sage Publications; 1993:163-180.
• [44]Goldstein H, Spiegelhalter D: League tables and their limitations: Statistical issues in comparisons of institutional performance. J R Statist Soc A 1996, 159(3):385-443.
• [45]Cameron AC, Trivedi PK: Regression analysis of count data. Cambridge, Cambridge University Press 1998.
• [46]Muthen LK, Muthen B: Mplus user's guide. Los Angeles, Muthen & Muthen 1998.
• [47]Heckman J: Comment. J Amer Statist Assoc 1996, 91:459-462.
• [48]Angrist JD, Imbens GW, Rubin DB: Identification of causal effects using instrumental variables. J Amer Statist Assoc 1996, 91:444-455.
• [49]Wothke W: Nonpositive definite matrices in structural modeling. In Testing structural equation models. Edited by Bollen KA, Long JS. Newbury Park, Sage Publications; 1993:256-293.
• [50]Dunn G: Design and analysis of reliability studies. Stat Methods Med Res 1992, 1:123-157.
• [51]Plummer MT, Clayton DG: Measurement error in dietary assessment: an investigation using covariance structure models. Stat Med 1993, 12:925-948.
• [52]Joereskog KG: Testing structural equation models. In Testing structural equation models. Edited by Bollen KA, Scott Long J. Newbury Park, Sage Publications; 1993:294-316.