Methods for Handling Missing Secondary Respondent Data

Secondary respondent data are underutilized because researchers avoid using these data in the presence of substantial missing data. The authors reviewed, evaluated, and tested solutions to this problem. Five strategies of dealing with missing partner data were reviewed: (a) complete case analysis, (b) inverse probability weighting, (c) correction with a Heckman selection model, (d) maximum likelihood estimation, and (e) multiple imputation. Two approaches were used to evaluate the performance of these methods. First, the authors used data from the National Survey of Fertility Barriers (n = 1,666) to estimate a model predicting marital quality based on characteristics of women and their husbands. Second, they conducted a simulation testing the 5 methods and compared the results to estimates where the true value was known. They found that the maximum likelihood and multiple imputation methods were advantageous because they allow researchers to utilize all of the available information as well as produce less biased and more efficient estimates.     

HOW TO IMPUTE INTERACTIONS, SQUARES, AND OTHER TRANSFORMED VARIABLES

Researchers often carry out regression analysis using data that have missing values. Missing values can be filled in using multiple imputation, but imputation is tricky if the regression includes interactions, squares, or other transformations of the regressors. In this paper, we examine different approaches to imputing transformed variables; and we find one simple method that works well across a variety of circumstances. Our recommendation is to transform, then impute —i.e., calculate the interactions or squares in the incomplete data and then impute these transformations like any other variable. The transform-then-impute method yields good regression estimates, even though the imputed values are often inconsistent with one another. It is tempting to try and "fix" the inconsistencies in the imputed values, but methods that do so lead to biased regression estimates. Such biased methods include the passive imputation strategy implemented by the popular ice command for Stata.     

Handling Missing Values in Longitudinal Panel Data With Multiple Imputation

This article offers an applied review of key issues and methods for the analysis of longitudinal panel data in the presence of missing values. The authors consider the unique challenges associated with attrition (survey dropout), incomplete repeated measures, and unknown observations of time. Using simulated data based on 4 waves of the Marital Instability Over the Life Course Study (n = 2,034), they applied a fixed effect regression model and an event‐history analysis with time‐varying covariates. They then compared results for analyses with nonimputed missing data and with imputed data both in long and in wide structures. Imputation produced improved estimates in the event‐history analysis but only modest improvements in the estimates and standard errors of the fixed effects analysis. Factors responsible for differences in the value of imputation are examined, and recommendations for handling missing values in panel data are presented.     

Handling missing data in numeric analyses

ABSTRACT

Social science datasets usually have missing cases, and missing values. All such missing data has the potential to bias future research findings. However, many research reports ignore the issue of missing data, only consider some aspects of it, or do not report how it is handled. This paper rehearses the damage caused by missing data. The paper then briefly considers eight different approaches to handling missing data so as to minimise that damage, their underlying assumptions and the likely costs and benefits. These approaches include complete case analysis, complete variable analysis, single imputation, multiple imputation, maximum likelihood estimation, default replacement values, weighting, and sensitivity analyses. Using only complete cases should be avoided wherever possible. The paper suggests that the more complex, modelling approaches to replacing missing data are based on questionable methodological and philosophical assumptions. And they may anyway not have clear advantages over simpler approaches like default replacements. It makes sense to report all possible forms of missing data, report everything that is known about the characteristics of cases missing values, conduct simple sensitivity analyses of the potential impact of missing data on the substantive results, and retain the knowledge of missingness when using any form of replacement value.     

Toward Best Practices in Analyzing Datasets with Missing Data: Comparisons and Recommendations

Although several methods have been developed to allow for the analysis of data in the presence of missing values, no clear guide exists to help family researchers in choosing among the many options and procedures available. We delineate these options and examine the sensitivity of the findings in a regression model estimated in three random samples from the National Survey of Families and Households (n = 250–2,000). These results, combined with findings from simulation studies, are used to guide answers to a set of 10 common questions asked by researchers when selecting a missing data approach. Modern missing data techniques were found to perform better than traditional ones, but differences between the types of modern approaches had minor effects on the estimates and substantive conclusions. Our findings suggest that the researcher has considerable flexibility in selecting among modern options for handling missing data.     

Multiple imputation for missing data in a longitudinal cohort study: a tutorial based on a detailed case study involving imputation of missing outcome data

Multiple imputation (MI), a two-stage process whereby missing data are imputed multiple times and the resulting estimates of the parameter(s) of interest are combined across the completed datasets, is becoming increasingly popular for handling missing data. However, MI can result in biased inference if not carried out appropriately or if the underlying assumptions are not justifiable. Despite this, there remains a scarcity of guidelines for carrying out MI. In this paper we provide a tutorial on the main issues involved in employing MI, as well as highlighting some common pitfalls and misconceptions, and areas requiring further development. When contemplating using MI we must first consider whether it is likely to offer gains (reduced bias or increased precision) over alternative methods of analysis. Once it has been decided to use MI, there are a number of decisions that must be made during the imputation process; we discuss the extent to which these decisions can be guided by the current literature. Finally we highlight the importance of checking the fit of the imputation model. This process is illustrated using a case study in which we impute missing outcome data in a five-wave longitudinal study that compared extremely preterm individuals with term-born controls.     

REGRESSION WITH MISSING YS: AN IMPROVED STRATEGY FOR ANALYZING MULTIPLY IMPUTED DATA

When fitting a generalized linear model—such as linear regression, logistic regression, or hierarchical linear modeling—analysts often wonder how to handle missing values of the dependent variable Y . If missing values have been filled in using multiple imputation, the usual advice is to use the imputed Y values in analysis. We show, however, that using imputed Y s can add needless noise to the estimates. Better estimates can usually be obtained using a modified strategy that we call multiple imputation, then deletion (MID). Under MID, all cases are used for imputation but, following imputation, cases with imputed Y values are excluded from the analysis. When there is something wrong with the imputed Y values, MID protects the estimates from the problematic imputations. And when the imputed Y values are acceptable, MID usually offers somewhat more efficient estimates than an ordinary MI strategy.     

Tracking poverty with coarse data: evidence from South Africa

Household surveys often contain coarse data, which consist of a mixture of missing values, interval-censored values and point (fully-observed) values, making it difficult to construct a continuous money-metric measure of wellbeing. This paper assesses the sensitivity of poverty and inequality estimates to the multiple imputation of coarse earnings data and reported zero values using the 2001?C2006 South African Labour Force Surveys. Estimates of poverty amongst the employed are shown not to be sensitive to multiple imputation of missing and interval-censored data, but are sensitive to the treatment of workers reporting zero earnings. Poverty trends are generally robust to the choice of method, and a significant decline in poverty is evident. Inequality estimates, on the other hand, appear more sensitive to the treatment of zero values and the choice of imputation methods, and, overall, no particular trends in inequality could be discerned.     

MULTIPLE IMPUTATION OF INCOMPLETE CATEGORICAL DATA USING LATENT CLASS ANALYSIS

We propose using latent class analysis as an alternative to log-linear analysis for the multiple imputation of incomplete categorical data. Similar to log-linear models, latent class models can be used to describe complex association structures between the variables used in the imputation model. However, unlike log-linear models, latent class models can be used to build large imputation models containing more than a few categorical variables. To obtain imputations reflecting uncertainty about the unknown model parameters, we use a nonparametric bootstrap procedure as an alternative to the more common full Bayesian approach. The proposed multiple imputation method, which is implemented in Latent GOLD software for latent class analysis, is illustrated with two examples. In a simulated data example, we compare the new method to well-established methods such as maximum likelihood estimation with incomplete data and multiple imputation using a saturated log-linear model. This example shows that the proposed method yields unbiased parameter estimates and standard errors. The second example concerns an application using a typical social sciences data set. It contains 79 variables that are all included in the imputation model. The proposed method is especially useful for such large data sets because standard methods for dealing with missing data in categorical variables break down when the number of variables is so large.     

Audience success or art for art's sake? Efficiency evaluation of dance companies in the United States

Our aim is to evaluate the performance of American dance companies, considering that the production process may be subdivided into consecutive stages consisting of fundraising, artistic production, and social impact. A three‐stage network‐Data Envelopment Analysis model is applied which takes account of the links between stages in the form of intermediate inputs/outputs and provides an overall indicator of efficiency together with partial performance indicators in the stages. Given the lack of information for some variables, we previously undertook a process to impute missing values following MICE (multiple imputation by chained equations) procedures. Results show that the highest levels of efficiency are achieved during the cultural creation stage, whereas the lowest correspond to social impact, indicating that dance companies pursue artistic excellence in their cultural programming, irrespective of their activity's commercial outcomes. Moreover, public and private funds are seen to be channeled following this guideline, thereby justifying the non‐profit status of these entities.     

Multiple imputation for missing edge data: A predictive evaluation method with application to Add Health

Recent developments have made model-based imputation of network data feasible in principle, but the extant literature provides few practical examples of its use. In this paper, we consider 14 schools from the widely used In-School Survey of Add Health (Harris et al., 2009), applying an ERGM-based estimation and simulation approach to impute the network missing data for each school. Add Health's complex study design leads to multiple types of missingness, and we introduce practical techniques for handing each. We also develop a cross-validation based method – Held-Out Predictive Evaluation (HOPE) – for assessing this approach. Our results suggest that ERGM-based imputation of edge variables is a viable approach to the analysis of complex studies such as Add Health, provided that care is used in understanding and accounting for the study design.     

Sexual Rehabilitation After Prostate Cancer Through Assistive Aids: A Comparison of Gay/Bisexual and Heterosexual Men

The use of assistive aids in sexual rehabilitation after prostate cancer (PCa) was examined in 124 gay, bisexual, and other men who have sex with men (GBM) and 225 heterosexual men. GBM were significantly more likely to use assistive aids (79% versus 56%), to try multiple assistive aids (M = 1.65 versus M = 0.83) including medication, penile injection, penile implant, vacuum pump, and nonmedical sex aids, and to seek information about sexual rehabilitation on the Internet, through counseling, or in a support group. There were no differences between the groups in satisfaction with the use of assistive aids. However, use of aids was a significant negative predictor of sexual functioning for GBM and a significant positive predictor for heterosexual men. Interview accounts described satisfaction with assistive aids in terms of maintaining erectile functioning and relationships. The majority of men in the study also described hindrances, both physical and social, resulting in discontinuation of assistive aids, including perceived artificiality, loss of sexual spontaneity, side effects, failure to achieve erectile response, cost, and lack of access to information and support. It is concluded that the specific needs and concerns of GBM and heterosexual men regarding sexual rehabilitation after PCa need to be addressed by clinicians.     

Addressing Three Common Issues in Research on Youth Activities: An Integrative Approach for Operationalizing and Analyzing Involvement

Youth activity involvement has been operationalized and analyzed using a wide range of approaches. Researchers face the challenges of distinguishing between the effects of involvement versus noninvolvement and intensity of involvement in a particular activity, accounting simultaneously for cumulative effects of involvement, and addressing multiple unique effects of individual activities. In the present work, we review and illustrate the conceptual and empirical implications of these issues using data from a study of activity involvement and successful development in early adolescence (N=537; M age=11.56, 52% female). An integrative solution is introduced based on a latent composite variable (LCV) model ( Bollen & Lennox, 1991 ), which can be used to address all three issues simultaneously. Using this approach, we show that of the aggregate indices examined, breadth of involvement was uniquely and positively associated with multiple indices of successful development. Of the individual activities, a dichotomous score and residual frequency rating for involvement in out‐of‐school clubs were both uniquely associated with less positive development indicators. We concluded that an LCV approach provides a novel method for addressing several fundamental operational and analytic issues facing researchers who investigate youth activity involvement as a context for positive development.     

Family group conferences: from Maori culture to decision-making model in work with late modern families in Norway†

Models and methods within social work and child protection services are disseminated across cultural and national borders. The family group conference (FGC), with its origins in traditional Maori culture, is one example of this. The application of this model presupposes an ‘extended family’. Based on sociological theory, we highlight and problematise the explicit inattention to relevant cultural differences. The assumed existence of the extended family is implied in the direct translation of the term. The family in late modern society is often described as diversified, elective and shifting. We argue that FGC is relevant to such families. In our conclusion, we point out that despite changes, the family remains associated with traditional family values as solidarity and joint obligations, responsibilities and continuity. FGC vitalise traditional family values and facilitate for modern families performing traditional family practices. From our exploration of discourses and analyses on how FGC may be transformed from supporting Maori traditional culture to become a decision model in a CPS of a society such as Norway, we find there is a compliance with two fundamental factors: the late modern family's negotiating practices and the revitalisation of traditional family values.     

Familism Values,Perspective Taking,and Prosocial Moral Reasoning: Predicting Prosocial Tendencies Among Mexican American Adolescents

Mexican American youth often engage in relatively high levels of prosocial behaviors. We theorize that this may be due to a cultural value system that encourages familism values, which, in turn, may foster the development of sociocognitive processes that promote prosocial behaviors. Two hundred and five Mexican American early adolescent youth (M_age = 10.9 years, SD = 0.84; 51% girls) reported their familism values, perspective taking, prosocial moral reasoning, and six types of prosocial behaviors. The results indicated that perspective taking partially mediated the relation between familism values and the specific prosocial tendencies theoretically linked to the Mexican American culture. The study demonstrated the utility of integrating cultural and traditional developmental mechanisms in attempting to explain prosocial behaviors.     

Ambiguous Loss Research,Theory, and Practice: Reflections After 9/11

This article contains an overview of three decades of research, theory development, and clinical application about ambiguous loss. Although the work includes both physical and psychological types of ambiguous loss, the focus is the aftermath of 9/11 (September 11, 2001), when the World Trade Center collapsed following terrorist attacks. On the basis of her previous work, the author was asked to design an intervention for families of the missing. She reflects on what she learned from this unexpected test and presents new propositions and hypotheses to stimulate further research and theory that is more inclusive of diversity. She suggests that scholars should focus more on universal family experience. Ambiguous loss is just one example. Encouraging researchers and practitioners to collaborate in theory development, she concludes that research‐based theory is essential to inform interventions in unexpected times of terror, and in everyday life.     

Inter-rater Agreement Indices for Multiple Informant Methodology

This paper addresses the potential applications of multiple informant methodology (MIM) to family research. The MIM is used when data on the same unit of analysis are collected from more than one informant, and when the researchers’ purpose requires a dyadic or group level of analysis. The MIM relies on inter-rater agreement (IRA) indices, which are needed to both estimate agreement among informants and aggregate scores from different informants. This review describes the main IRA indices: reliability within-group index (r_WG), agreement within-group index (a_WG), average deviation indices (AD_M and AD_Md), intra-class correlation coefficient (ICC), and random group index (r_WG). For each index, we describe the aim, application contexts, formula(s), ranges, cutoffs, requirements to apply the index, and its possible application to family research.     

Graduate Social Work Students’ Approaches and Ways of Thinking in Child Protection Assessment: Case Vignette Reflections from Estonia

This article examines Estonian graduate social work students’ (MSW, n = 41) assessment approaches (deficit-based versus strengths-based) in the context of a child protection assessment through a case vignette format. The study found that students tend to focus more on a traditional deficit-based approach in their responses to a presented case, and less on capabilities and resources. The study indicates the need to find ways to promote more client-friendly approaches (for a shift in the way of thinking) in social work education to empower families through developing a respectful and effective helping relationship that promotes comprehensive assessment guided by social work values. Practice implications are discussed and recommendations for future research are outlined.     

Linking maternal psychopathology to children's excessive crying and sleeping problems in a large representative German sample—The mediating role of social isolation and bonding difficulties

Attaining self-regulation is a major developmental task in infancy, in which many children show transient difficulties. Persistent, clinically relevant difficulties in self-regulation include excessive crying or sleeping disorders. Many families with affected children are burdened with multiple psychosocial risk. This suggests that regulatory problems are best conceptualized as the maladaptive interplay of overly burdened parents and a dysfunctional parent–child interaction. The current study examines whether social isolation and bonding difficulties function as mediating mechanisms linking maternal psychopathology to (1) children's excessive crying and (2) sleeping problems. The sample comprised N = 6598 mothers (M = 31.51 years) of children between zero to three years of age (M = 14.08 months, 50.1% girls). In addition to socio demographic data, the written questionnaire included information on maternal depression/anxiety, isolation, bonding, and children's regulatory problems. Hypotheses were tested with a mediation model controlling for psychosocial risk and child characteristics. As expected, maternal symptoms of depression/anxiety were linked to infants‘ excessive crying and sleeping problems. Social isolation and bonding difficulties mediated this association for excessive crying as well as for sleeping problems, but social isolation was a single mediator for sleeping problems only. The findings provide important insights in the mediating pathways linking maternal psychopathology to children's regulatory problems.