Joost R. van Ginkel

SPSS Syntax for Missing Value Imputation in Test and Questionnaire Data

A well-known problem in the analysis of test and questionnaire data is that some item scores may be missing. Advanced methods for the imputation of missing data are available, such as multiple imputation under the multivariate normal model and imputation under the saturated logistic model (Schafer, 1997). Accompanying software was made available by, for example, Schafer (1998a, 1998b) and in SOLAS (2001) and S-Plus 6 for Windows (2001). However, these methods and software may be too complicated for a typical psychological researcher, and for the imputation of his or her missing data, he or she depends on the help of a trained statistician. If available, this statistician may not always have enough time or may not be an experienced software user, so the researcher may decide to simply delete all incomplete observations. To help researchers impute scores using simple methods, two SPSS subroutines were written. The aim of these subroutines is that researchers can apply them easily within SPSS and without experienced help. The subroutine “tw” performs two-way imputation, and the subroutine “rf” performs responsefunction imputation. Two-way imputation and response-function imputation are described by Sijtsma and Van der Ark (2003). Simulation studies by Van der Ark and Sijtsma (in press) indicate that these imputation methods work rather well when applied to an approximately unidimensional set of items (i.e., the items measure the same construct). The subroutines allow the researcher to transform an SPSS data file with missing values (an incomplete data file) into an SPSS data file without missing values (a completed data file). The researcher can use the completed data file for further analysis. To run the subroutines, one must select the variables containing the missing scores that need to be imputed, and some optional arguments also can be specified. For two-way imputation, the most important optional argument pertains to changing or removing the random error that is added to the imputed values by default. For response-function imputation, the most important optional argument pertains to changing the minimum group size used for estimating the response function (see Sijtsma & Van der Ark, 2003).

Multiple Imputation of Item Scores in Test and Questionnaire Data, and Influence on Psychometric Results.

The performance of five simple multiple imputation methods for dealing with missing data were compared. In addition, random imputation and multivariate normal imputation were used as lower and upper benchmark, respectively. Test data were simulated and item scores were deleted such that they were either missing completely at random, missing at random, or not missing at random. Cronbachs alpha, Loevingers scalability coefficient H, and the item cluster solution from Mokken scale analysis of the complete data were compared with the corresponding results based on the data including imputed scores. The multiple-imputation methods, two-way with normally distributed errors, corrected item-mean substitution with normally distributed errors, and response function, produced discrepancies in Cronbachs coefficient alpha, Loevingers coefficient H, and the cluster solution from Mokken scale analysis, that were smaller than the discrepancies in upper benchmark multivariate normal imputation.

Analysis of Variance of Multiply Imputed Data

As a procedure for handling missing data, Multiple imputation consists of estimating the missing data multiple times to create several complete versions of an incomplete data set. All these data sets are analyzed by the same statistical procedure, and the results are pooled for interpretation. So far, no explicit rules for pooling F tests of (repeated-measures) analysis of variance have been defined. In this article we outline the appropriate procedure for the results of analysis of variance (ANOVA) for multiply imputed data sets. It involves both reformulation of the ANOVA model as a regression model using effect coding of the predictors and applying already existing combination rules for regression models. The proposed procedure is illustrated using 3 example data sets. The pooled results of these 3 examples provide plausible F and p values.

Is the ideal mother a sensitive mother? Beliefs about early childhood parenting in mothers across the globe

In this article, we test the hypothesis that beliefs about the ideal mother are convergent across cultures and that these beliefs overlap considerably with attachment theory’s notion of the sensitive mother. In a sample including 26 cultural groups from 15 countries around the globe, 751 mothers sorted the Maternal Behavior Q-Set to reflect their ideas about the ideal mother. The results show strong convergence between maternal beliefs about the ideal mother and attachment theory’s description of the sensitive mother across groups. Cultural group membership significantly predicted variations in maternal sensitivity belief scores, but this effect was substantially accounted for by group variations in socio-demographic factors. Mothers living in rural versus urban areas, with a low family income, and with more children, were less likely to describe the ideal mother as highly sensitive. Cultural group membership did remain a significant predictor of variations in maternal sensitivity belief scores above and beyond socio-demographic predictors. The findings are discussed in terms of the universal and culture-specific aspects of the sensitivity construct.

Two-way imputation: A Bayesian method for estimating missing scores in tests and questionnaires, and an accurate approximation

Previous research has shown that method two-way with error for multiple imputation in test and questionnaire data produces small bias in statistical analyses. This method is based on a two-way ANOVA model of persons by items but it is improper from a Bayesian point of view. Proper two-way imputations are generated using data augmentation. Simulation results show that the resulting method two-way with data augmentation produces unbiased results in Cronbachs alpha, the mean of squares in ANOVA, the item means, and small bias in the mean test score and the factor loadings from principal components analysis. The data with imputed scores result in statistics having a slightly larger standard deviation than the original complete data. Method two-way with error produces results that are only slightly more biased, especially for low percentages of missingness. Thus, it may serve as an accurate approximation to the more involved method two-way with data augmentation.

Epidemiology and outcome of infections with carbapenem-resistant Gram-negative bacteria treated with polymyxin B-based combination therapy

Abstract Introduction: Infections with carbapenem-resistant Gram-negative bacteria (CRGNB) are increasing and are associated with a high mortality. Synergistic effects of combination therapy with a polymyxin, carbapenem, and rifampin have been observed in in vitro studies. Clinical data are limited to retrospective studies. Methods: We performed an observational cohort study of patients over 18 y of age who were treated with polymyxin B combination therapy. Results: One hundred and four patients were studied. The mean age was 77 y; 73% had recently received antibiotics, 67% had recently been hospitalized, and 47% lived in a nursing facility. The most common infections were pneumonia and urinary tract infection due to Acinetobacter baumannii (33%), Klebsiella pneumoniae (24%), and Pseudomonas aeruginosa (11%). Treatment regimens included polymyxin B with a carbapenem in 48%, with additional rifampin in 23%. Clinical success was achieved in 50% and reinfection occurred in 25%. Treatment-related acute renal failure occurred in 14.4%. No treatment-related hemodialysis was needed. All-cause hospital mortality was 47% and mortality after 6 months was 77%. No significant difference was found between treatment regimens. Age (odds ratio (OR) 10.4 per 10 y, p = 0.04), severity of acute illness (OR 2.2 per point, p < 0.001), and Charlson score (OR 1.12 per point, p = 0.04) were associated with hospital mortality. K. pneumoniae was associated with increased hospital survival compared to other CRGNB (p = 0.03). Conclusion: CRGNB infections are associated with previous antibiotic and health care exposure. Mortality is related to age and the severity of chronic and acute illness.

Missing data in principal component analysis of questionnaire data: a comparison of methods

Principal component analysis (PCA) is a widely used statistical technique for determining subscales in questionnaire data. As in any other statistical technique, missing data may both complicate its execution and interpretation. In this study, six methods for dealing with missing data in the context of PCA are reviewed and compared: listwise deletion (LD), pairwise deletion, the missing data passive approach, regularized PCA, the expectation-maximization algorithm, and multiple imputation. Simulations show that except for LD, all methods give about equally good results for realistic percentages of missing data. Therefore, the choice of a procedure can be based on the ease of application or purely the convenience of availability of a technique.

Trauma Exposure in Primary School Children: Who Is at Risk?

In order to direct efforts to prevent children from being exposed to trauma and its psychosocial consequences, more knowledge is needed about which children are at risk. Therefore, we examined demographic risk factors for trauma exposure in a sample of Dutch primary school children in the general population (N = 1,770, mean age 10.24 years). Fourteen percent of the children reported exposure. Age was positively associated with exposure while sex, ethnicity, and region of residence did not emerge as significant risk factors. These results imply that prevention measures should be provided not only to groups of children who are traditionally considered vulnerable but broadly.

Web-Based Fully Automated Self-Help With Different Levels of Therapist Support for Individuals With Eating Disorder Symptoms: A Randomized Controlled Trial.

Background Despite the disabling nature of eating disorders (EDs), many individuals with ED symptoms do not receive appropriate mental health care. Internet-based interventions have potential to reduce the unmet needs by providing easily accessible health care services. Objective This study aimed to investigate the effectiveness of an Internet-based intervention for individuals with ED symptoms, called “Featback.” In addition, the added value of different intensities of therapist support was investigated. Methods Participants (N=354) were aged 16 years or older with self-reported ED symptoms, including symptoms of anorexia nervosa, bulimia nervosa, and binge eating disorder. Participants were recruited via the website of Featback and the website of a Dutch pro-recovery–focused e-community for young women with ED problems. Participants were randomized to: (1) Featback, consisting of psychoeducation and a fully automated self-monitoring and feedback system, (2) Featback supplemented with low-intensity (weekly) digital therapist support, (3) Featback supplemented with high-intensity (3 times a week) digital therapist support, and (4) a waiting list control condition. Internet-administered self-report questionnaires were completed at baseline, post-intervention (ie, 8 weeks after baseline), and at 3- and 6-month follow-up. The primary outcome measure was ED psychopathology. Secondary outcome measures were symptoms of depression and anxiety, perseverative thinking, and ED-related quality of life. Statistical analyses were conducted according to an intent-to-treat approach using linear mixed models. Results The 3 Featback conditions were superior to a waiting list in reducing bulimic psychopathology (d=−0.16, 95% confidence interval (CI)=−0.31 to −0.01), symptoms of depression and anxiety (d=−0.28, 95% CI=−0.45 to −0.11), and perseverative thinking (d=−0.28, 95% CI=−0.45 to −0.11). No added value of therapist support was found in terms of symptom reduction although participants who received therapist support were significantly more satisfied with the intervention than those who did not receive supplemental therapist support. No significant differences between the Featback conditions supplemented with low- and high-intensity therapist support were found regarding the effectiveness and satisfaction with the intervention. Conclusions The fully automated Internet-based self-monitoring and feedback intervention Featback was effective in reducing ED and comorbid psychopathology. Supplemental therapist support enhanced satisfaction with the intervention but did not increase its effectiveness. Automated interventions such as Featback can provide widely disseminable and easily accessible care. Such interventions could be incorporated within a stepped-care approach in the treatment of EDs and help to bridge the gap between mental disorders and mental health care services. Trial Registration Netherlands Trial Registry: NTR3646; http://www.trialregister.nl/trialreg/admin/ rctview.asp?TC=3646 (Archived by WebCite at http://www.webcitation.org/6fgHTGKHE)

Using Generalized Procrustes Analysis for Multiple Imputation in Principal Component Analysis

Multiple imputation is one of the most highly recommended procedures for dealing with missing data. However, to date little attention has been paid to methods for combining the results from principal component analyses applied to a multiply imputed data set. In this paper we propose Generalized Procrustes analysis for this purpose, of which its centroid solution can be used as a final estimate for the component loadings. Convex hulls based on the loadings of the imputed data sets can be used to represent the uncertainty due to the missing data. In two simulation studies, the performance of Generalized Procrustes approach is evaluated and compared with other methods. More specifically it is studied how these methods behave when order changes of components and sign reversals of component loadings occur, such as in case of near-equal eigenvalues, or data having almost as many counterindicative items as indicative items. The simulations show that other proposed methods either may run into serious problems or are not able to adequately assess the accuracy due to the presence of missing data. However, when the above situations do not occur, all methods will provide adequate estimates for the PCA loadings.