PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “missing data”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 289 records · Page 16Linked to original sources
PubMed1999

Estimation and comparison of rates of change in longitudinal studies with informative drop-outs.

Many cohort studies and clinical trials have designs which involve repeated measurements of disease markers. One problem in such longitudinal studies, when the primary interest is to estimate and to compare the evolution of a disease marker, is that planned data are not collected because of missing data due to missing visits and/or withdrawal or attrition (for example, death). Several methods to analyse such data are available, provided that the data are missing at random. However, serious biases can occur when missingness is informative. In such cases, one needs to apply methods that simultaneously model the observed data and the missingness process. In this paper we consider the problem of estimation of the rate of change of a disease marker in longitudinal studies, in which some subjects drop out prematurely (informatively) due to attrition, while others experience a non-informative drop-out process (end of study, withdrawal). We propose a method which combines a linear random effects model for the underlying pattern of the marker with a log-normal survival model for the informative drop-out process. Joint estimates are obtained through the restricted iterative generalized least squares method which are equivalent to restricted maximum likelihood estimates. A nested EM algorithm is applied to deal with censored survival data. The advantages of this method are: it provides a unified approach to estimate all the model parameters; it can effectively deal with irregular data (that is, measured at irregular time points), a complicated covariance structure and a complex underlying profile of the response variable; it does not entail such complex computation as would be required to maximize the joint likelihood. The method is illustrated by modelling CD4 count data in a clinical trial in patients with advanced HIV infection while its performance is tested by simulation studies.

Biomarkers↗
PubMed2003

Preliminary experience with a prospective, multi-centered evaluation of out-of-hospital endotracheal intubation.

STUDY OBJECTIVE: Previous out-of-hospital airway management data are limited by small, single-site designs. We sought to evaluate the feasibility of performing a prospective, multi-centered evaluation of out-of-hospital endotracheal intubation (ETI) using a standardized data collection tool. METHODS: We designed a prospective multi-centered observational study involving 45 advanced life support (ALS) services from a mid-Atlantic state. Using a standardized data form, prehospital personnel reported details of each attempted ETI, including patient demographics, methods used, difficulties encountered, and initial patient outcomes. We calculated and assessed data form return rates (using independent queries of the number of ETI attempted by each EMS service) and missing data entry rates. We also performed preliminary cross-sectional assessments of factors of current interest in out-of-hospital ETI. Accuracy and validity of responses were not evaluated. Data were stored centrally and analyzed using descriptive techniques. RESULTS: Participants included 8 urban, 15 suburban, 20 rural, and 2 air medical services. Data forms were received on 783 adults receiving ETI attempts during the study period June 1, 2001-November 30, 2001. The pooled data form return rate was 72.7%. Per-service return rates ranged from 0 to 100% and the median per-service return rate was 75%. Non-response (data form not returned for attempted intubation) was problematic, with nine services demonstrating data return rates less than 50%. Data return rates could not be calculated for an additional nine services. The missing data entry rate was 0.5-22.2%. The overall reported ETI success rate was 86.8% (92.8% for cardiac arrests and 76.8% for non-arrests) and did not appear to vary between population settings. There were two cases of delayed recognition of esophageal intubation, one case of unrecognized esophageal intubation, and 22 cases of tube dislodgement during patient care or transport. Bag-valve-mask ventilation was used as the rescue airway technique in the majority of failed ETI. When stratified for cardiac arrests vs. non-arrests, ETI success was not associated with field or initial ED survival. CONCLUSIONS: We successfully obtained complete data for the majority of ETI attempted across multiple EMS services. Our data also indicate the need to address problems with non-response. Preliminary cross-sectional data highlight areas of current interest in out-of-hospital airway management.

Emergency Medical Services↗
PubMed1996

Short-term compliance with peak flow monitoring: results from a study of inner city children with asthma.

The objective of the study was to assess the feasibility of initiating daily peak flow monitoring in a research study of asthma in inner city children. We performed a descriptive study of patterns of peak flow monitoring in children randomized to receive a simple mini-Wright (SM) or an electronic recording meter (ERM). The ERM served as a "covert" meter, providing objective documentation of actual peak flow use. Sixty-five Hispanic or African-American children, ages 5-9 years, with a history of physician-diagnosed asthma participated in the study. All children resided in census tracts with 40% or more of the population living at or below the poverty level. Subjects were instructed to use a peak flow meter (the SM or ERM) at least twice daily over a 3 week period, and to record peak flow values in a paper diary. Subjects who received the ERM were not made aware that measurements were also recorded electronically. Differences in patterns of use of the SM and ERM were assessed with the Wilcoxon signed rank test and Wilcoxon sum rank test. Adherence to peak flow monitoring was evaluated by comparing the percent days with missing values in the manually completed diary with those obtained by computer record. The Friedman statistic was used to compare changes in compliance (percent of days with missing peak flow entries) over time. Accuracy of peak flow readings was assessed by comparing the manual and electronic recordings with paired and unpaired t-tests and with Pearson product moment correlations. The percent of days with missing peak flow entries on diaries increased from 1.4% to 10.6% from the first to third week of monitoring (P < 0.004). The ERMs indicated a significantly greater percent of missing data than did the manual records (P < 0.0002). The difference in the percent of missing data for the electronic and manual records was most notable during the third study week, when the ERM and the manually completed records indicated that 52% and 15% of days, respectively, were without peak flow measures. Large inter-subject variations in the relationship between manually and electronically recorded peak flow measurements were observed, suggesting that errors in reading and transcribing peak flow rates occur in a subset of asthmatics. We conclude that children and caretakers in the inner city may have considerable difficulty initiating and maintaining peak flow recordings. Data obtained by manual records may considerably overestimate actual use. Compliance with monitoring decreases markedly between the first and third week of monitoring.

Black or African American↗
PubMed1997

Demonstration of accuracy and clinical versatility of mutual information for automatic multimodality image fusion using affine and thin-plate spline warped geometric deformations.

This paper applies and evaluates an automatic mutual information-based registration algorithm across a broad spectrum of multimodal volume data sets. The algorithm requires little or no pre-processing, minimal user input and easily implements either affine, i.e. linear or thin-plate spline (TPS) warped registrations. We have evaluated the algorithm in phantom studies as well as in selected cases where few other algorithms could perform as well, if at all, to demonstrate the value of this new method. Pairs of multimodal gray-scale volume data sets were registered by iteratively changing registration parameters to maximize mutual information. Quantitative registration errors were assessed in registrations of a thorax phantom using PET/CT and in the National Library of Medicine's Visible Male using MRI T2-/T1-weighted acquisitions. Registrations of diverse clinical data sets were demonstrated including rotate-translate mapping of PET/MRI brain scans with significant missing data, full affine mapping of thoracic PET/CT and rotate-translate mapping of abdominal SPECT/CT. A five-point thin-plate spline (TPS) warped registration of thoracic PET/CT is also demonstrated. The registration algorithm converged in times ranging between 3.5 and 31 min for affine clinical registrations and 57 min for TPS warping. Mean error vector lengths for rotate-translate registrations were measured to be subvoxel in phantoms. More importantly the rotate-translate algorithm performs well even with missing data. The demonstrated clinical fusions are qualitatively excellent at all levels. We conclude that such automatic, rapid, robust algorithms significantly increase the likelihood that multimodality registrations will be routinely used to aid clinical diagnoses and post-therapeutic assessment in the near future.

Abdomen↗
PubMed2000

Corticosteroids for acute severe asthma in hospitalised patients.

BACKGROUND: Corticosteroids are currently used routinely in the management of acute severe asthma. The optimal dose and route of administration continues to be debated. Some investigators have reported a greater benefit of higher doses of corticosteroids in the management of severe asthma, while others have not. OBJECTIVES: To determine whether higher doses of systemic corticosteroids (oral, intravenous or intramuscular) are more effective than lower doses in the management of patients with acute severe asthma requiring hospital admission. SEARCH STRATEGY: Randomised controlled trials were identified from the Cochrane Airways Group Asthma Register. In addition, primary authors and content experts were contacted to identify eligible studies. Bibliographies from included studies, known reviews and texts were also searched. SELECTION CRITERIA: Studies were selected for inclusion in the review if they met the following broad inclusion criteria: described as randomised controlled trials, included patients with acute severe asthma, compared different doses of corticosteroids (any route) in 2 or more treatment arms, and had a minimum period of follow up of 24 hours. Two reviewers independently assessed the studies for inclusion and disagreement was resolved by third party adjudication. DATA COLLECTION AND ANALYSIS: Data were extracted independently by two reviewers if the authors were unable to verify the validity of information. Missing data were obtained from authors or calculated from other data presented in the paper. The data were analysed as weighted mean differences (WMD) for primary pulmonary function outcomes using a fixed effects model. For the purposes of the review, three broad categories of corticosteroid dose (equivalent dose of methylprednisolone in 24 hours) were defined in advance: low dose (< or = 80 mg), medium dose (> 80 mg and < or = 360 mg) and high dose (> 360 mg). There were thus 3 main comparison groups: low versus medium dose, medium versus high dose and low versus high dose. MAIN RESULTS: Nine trials were included; a total of 344 adult patients have been studied (96 with low dose, 85 with medium dose and 163 with high dose corticosteroids). Only 6 trials provided sufficient data for the meta-analysis. There were no clinically or statistically significant differences detected in % predicted FEV1 among comparison groups after 24, 48 or 72 hours. At 48 hours, the weighted mean difference was -3.3% predicted (95% confidence interval -12.4 to + 5.8) for the low vs medium dose comparison, -1. 9% predicted (95% CI -8.1 to + 4.3) for the medium vs high dose comparison and + 0.5% predicted (95% CI - 7.8 to + 8.8) for the low vs high dose comparison. There appeared to be no significant differences in side effects or rates of respiratory failure among the varying doses of corticosteroids. REVIEWER'S CONCLUSIONS: No differences were identified among the different doses of corticosteroids in acute asthma requiring hospital admission. Low dose corticosteroids (< or = 80 mg/day of methylprednisolone or < or = 400 mg/day of hydrocortisone) appear to be adequate in the initial management of these adult patients. Higher doses do not appear to offer a therapeutic advantage.

Acute Disease↗
PubMed2000

Oral beta-blockers for mild to moderate hypertension during pregnancy.

BACKGROUND: Hypertension is a common complication of pregnancy. Antihypertensive drugs are widely used in the belief these will improve outcome for both the woman (such as decreasing the risk of stroke or eclampsia) and her baby (such as decreasing the risk of preterm birth and its complications). Beta-blockers are a popular choice of antihypertensive agent during pregnancy; other choices include methyldopa and calcium channel blockers. OBJECTIVES: The aim of this review is to assess whether oral beta-blockers are overall better than placebo, or no beta-blocker, for women with mild-moderate hypertension during pregnancy, and to assess whether oral beta-blockers have any advantages over other antihypertensive agents for women with mild-moderate hypertension during pregnancy. Both maternal outcomes (e.g., the incidence of severe hypertension) and perinatal outcomes (e.g., mortality) were of interest. SEARCH STRATEGY: Register of trials maintained by the Cochrane Pregnancy and Childbirth Group, MEDLINE 1966-97, bibliographies of retrieved papers, personal files. Date of last search: June 2000. SELECTION CRITERIA: Trials comparing beta-blockers with (i) placebo or no therapy, or (ii) other antihypertensive agents, for women with mild-moderate pregnancy hypertension (i.e., blood pressure under 170 mm Hg systolic, or 110 mm Hg diastolic). DATA COLLECTION AND ANALYSIS: All data were extracted independently by two investigators, who were not blinded to outcome or other trial characteristics. Whenever possible, missing data were obtained by personal communication with authors. Discrepancies were resolved by discussion. The overview was divided into two comparisons: (i) beta-blockers versus placebo or no therapy, and (ii) beta-blockers versus other antihypertensives. MAIN RESULTS: Twenty-seven trials, involving just under 2400 women, are included in this review. Fourteen trials (1516 women) compared beta-blockers with placebo/no beta blocker. Oral beta-blockers decrease the risk of severe hypertension (relative risk (RR) 0.37, 95% confidence interval (CI) 0.26-0.53) and the need for additional antihypertensive drugs (RR 0.44, 95% CI 0.31-0.62). There are insufficient data for any conclusions about the effect on perinatal mortality or preterm delivery. Beta-blockers seem to be associated with an increase in small for gestational age infants (RR 1.34, 95% CI 1.01-1.79). Maternal hospital admission may be decreased, neonatal bradycardia increased and respiratory distress syndrome decreased, but these outcomes are only reported in a very small proportion of trials. Eleven trials (787 women) compared beta-blockers with methyldopa. Beta-blockers appear to be no more effective and probably equally as safe (from maternal and perinatal perspectives) as methyldopa. Single small trials have compared beta-blockers with hydralazine and with nicardipine. It is unusual for women to change drugs due to side effects. REVIEWER'S CONCLUSIONS: The improvement in control of maternal blood pressure with use of beta-blockers would be worthwhile only if it were reflected in other more substantive benefits for the mother and/or baby, and none have yet been clearly demonstrated. The effect of beta-blockers on perinatal outcome is uncertain, given that the worrying trend to an increase in small for gestational age infants is partly dependent on one small outlying trial. Large, randomised controlled trials are needed to determine whether antihypertensive therapy in general (rather than beta-blocker therapy specifically) results in benefits that outweigh the risks for treatment of mild-moderate pregnancy hypertension. If so, then it would be appropriate to look at which antihypertensive is best. Beta-blockers would remain a candidate class of agents.

Administration, Oral↗
PubMed1988

Estimation of missing cone data in three-dimensional electron microscopy.

The range of tilt angles for which projected images of two-dimensionally periodic specimens can be obtained in electron microscopy is limited both by technical aspects, such as goniometer design, and by the more fundamental limitation of object thickness. The lack of a full set of projections causes a missing cone in the reciprocal space data for the object, which will give an anisotropic resolution in a three-dimensional reconstruction and may cause the quality to be impaired by spurious features. The problem is governed by a linear operator which maps the three-dimensional object onto the set of projections. The eigenvalue spectrum of this operator is determined by the range of tilt angles and the spatial extent of the object. If the object is spatially restricted, the eigenvalues are all positive, and it is in principle possible to retrieve experimentally unavailable structure data from those that are measured. However, with restricted angle data, some of the eigenvalues are extremely small, so the problem is 'ill-conditioned' or sensitive to small perturbations in the data, such as noise, and it is necessary to regularize the solution. We applied two methods of band-limited extrapolation and inference on electron microscope data. Alternating projections onto convex sets regularized by a regularization parameter and a least squares estimation regularized by the Shannon entropy functional yield similar results if a close object extent constraint is available. The criterion of maximum entropy, however, allows a relaxation of this constraint.

Bacteria↗
PubMedDate not supplied

Statistical analysis of cost outcomes in a randomized controlled clinical trial.

This paper suggests an approach to deal with an estimation problem which is often encountered in analyzing the longitudinal cost data gathered in a clinical trial. The source of that estimation problem is twofold: 1) a considerable number of missing data due to treatment-related withdrawal of severely affected patients with high health care costs in only one the treatment groups and 2) a heavily skewed cost distribution due to rare high-cost events. The approach is illustrated using data from a trial comparing 3 different drug regimes. In order to calculate costs per patient-year in case of selectively missing data we extrapolated the costs of patients with incomplete follow-up. Due to the skewness and the associated large variance in costs per patient-year, these costs cannot be analyzed using common parametric statistical methods relying on underlying normal distributions. A logarithmic transformation was performed to approximate a normal distribution, reduce the impact of extreme values and create similar size variances in the treatment groups. An ordinary least squares regression analysis of transformed data then standardized for differences in patient characteristics between the groups. For the retransformation, the so-called smearing estimate was used. This 'transformation-standardization-retransformation' approach enabled us to provide more consistent and efficient estimates of cost differences that were shown to be statistically significant and judged to be important.

Adolescent↗
PubMed1988

Compliance in clinical trials: impact on design, analysis and interpretation.

A positive association between compliance and clinical outcome has been observed in several randomized, controlled, clinical trials. This association, seen in the placebo-treated group as well as the active-treatment group, clarifies the possibility that data analyses incorporating estimates of protocol adherence are potentially biased. In the presence of non-compliance, or missing data from any cause, several statistical analyses may seem plausible, with none clearly superior to the others. These may include an analysis of all patients randomized, with imputed values for missing data, and an analysis restricted to protocol-adherent patients. The recommended approach is a conservative one that examines consistency among the plausible analyses. Using compliance data in trial conduct can also introduce bias into trial results by inducing differential treatment of compliers and non-compliers. This possibility arises, for instance, when adherence is affected by the randomized treatment. Non-compliance can have a substantial impact on statistical power and sample size requirements in a clinical trial. Under certain assumptions, required sample sizes are doubled with 30% non-compliance and tripled with 40% non-compliance.

Clinical Trials as Topic↗
PubMed2002

Comparative study of noninvasive cerebrovascular monitoring methods in cardiac surgery.

Unfavorable incidents during cardiac operations due to inadequate cerebral perfusion can be avoided by the utilization of noninvasive blood flow monitoring methods. The purpose of this study was to evaluate monitoring systems for cebrovascular perfusion. We compared currently available blood flow monitoring devices including transcranial Doppler (TCD), central retinal artery color Doppler (CRAD) and near-infrared spectroscopy (NIRS). The maximum flow velocity (Vmax) of the right central retinal artery was measured with a 7.5 MHz Doppler system. The Vmax of the right middle cerebral artery was measured with a TCD system. Regional tissue oxygen saturation (rSO2) was continuously measured with a NIRS system. The total number of individual data for each monitoring method collected from 25 patients was 184. The CRAD-Vmax was correlated more closely with the corresponding maximum blood pressure than the TCD-Vmax (r = 0.742 and 0.607, respectively). No missing data were seen in CRAD, but 20 missing data were seen in TCD, mostly during the period of cardiopulmonary bypass with lowered blood pressure. All 184 data were divided into two groups: Group 1 (rSO2 > or = 60 %, n=175) and Group 2 (rSO2 <60 %, n=9 data). The CRAD-Vmax was significantly lower in Group 2 (5.2+/-2.4 cm/s versus 3.0+/-0.4 cm/s, p<0.001). However, there was no significant difference in the TCD-Vmax between these two groups. Thus, CRAD may be superior to TCD in detecting insufficiency of cerebral blood flow correlating to rSO2, and could be used as the first choice monitoring system of cerebral blood flow during cardiac surgery.

Adolescent↗
PubMedDate not supplied

Incomplete quality of life data in randomized trials: missing forms.

Analysing quality of life (QOL) data may be complicated for several reasons, such as: repeated measures are obtained; data may be collected on ordered categorical responses; the instrument may have multidimensional scales, and complete data may not be available for all patients. In addition, it may be necessary to integrate QOL with length of life. The major undesirable effects of missing data, in QOL research, are the introduction of biases due to inadequate modes of analysis and the loss of efficiency due to reduced sample sizes. Currently, there is no standard method for handling missing data in QOL studies. In fact, there are very few references to methods of handling missing data in this context. The aim of this paper is to provide an overview of methods for analysing incomplete longitudinal QOL data which have either been presented in the QOL literature or in the missing data literature. These methods of analysis include complete case, available case, summary measures, imputation and likelihood-based approaches. We also discuss the issue of bias and the need for sensitivity analyses.

Bias↗
PubMed2000

Psychoeducation for schizophrenia.

BACKGROUND: Schizophrenia can be a severe and chronic illness characterised by lack of insight and poor compliance with treatment. Psychoeducational approaches have been developed to increase patients' awareness of their illness and its treatment. OBJECTIVES: To assess the effects of psychoeducational interventions compared to standard levels of knowledge provision. SEARCH STRATEGY: Electronic searches of CINAHL (1982-1999), The Cochrane Library CENTRAL (Issue 1, 1999), The Cochrane Schizophrenia Group's Register (January 1999), EMbase (1980-1999), MEDLINE (1966-1999), PsycLit (1974-1999), and Sociofile (1974-1999) were undertaken. These were supplemented with reference searching and personal contact with authors of all included studies. SELECTION CRITERIA: All relevant randomised controlled trials focusing on psychoeducation for schizophrenia or related serious mental illnesses, involving individuals or groups. Quasi-randomised trials were excluded. DATA COLLECTION AND ANALYSIS: Data were extracted independently by at least two reviewers from included papers. Authors of trials were contacted for additional and missing data. Relative risks (RR) and 95% confidence intervals (CI) of homogeneous dichotomous data were calculated. A random effects model was used for heterogeneous dichotomous data. Where possible the numbers needed to treat (NNT) were also calculated. Weighted or standardised means were calculated for continuous data. MAIN RESULTS: Ten studies are included in this review. All studies of group education included family members. Compliance with medication was significantly improved in a single study using brief group intervention (at one year) but other studies produced equivocal or skewed data. Any kind of psychoeducational intervention significantly decreased relapse or readmission rates at nine to 18 months follow-up compared with standard care (RR 0.8 CI 0.7-0.9 NNT 9 CI 6-22). Several of the secondary outcomes (knowledge gains, mental state, global level of functioning, status of high expressed emotion family members) were measured using scales that are difficult to interpret. Generally, however, findings were consistent with the possibility that psychoeducation has a positive effect on a persons' well being. No impact was found on insight, medication related attitudes or on overall satisfaction with services of patients or relatives but these findings rested on very few studies. Health economic outcome was only measured in one study and data were skewed. It was not possible to analyse whether different duration or formats of psychoeducation influenced effectiveness. REVIEWER'S CONCLUSIONS: Evidence from trials suggests that psychoeducational approaches are useful as a part of the treatment programme for people with schizophrenia and related illness. That the interventions are brief and inexpensive should make them attractive to managers and policy makers. More well-designed, conducted and reported randomised studies investigating the efficacy of psychoeducation are needed.

Family↗
PubMed1995

Application of a method for estimating day of ovulation using urinary estrogen and progesterone metabolites.

Longitudinal epidemiologic studies of menstrual and reproductive function are more informative if one can identify day of ovulation. We previously developed a method for estimating day of ovulation that is feasible for epidemiologic studies. The method relies on the relative concentrations of estrogen and progesterone metabolites in daily first-morning urine specimens and does not require creatinine adjustment. This paper describes results of applying this method to a large study with 724 menstrual cycles from 217 women. The method estimated a credible day of ovulation in 88% of cycles. Missing data accounted for most of the failures. When we excluded anovulatory cycles (1%) and cycles with missing data, the method estimated a day of ovulation in 97% of cycles. Variance in luteal phase length was small for our sample, suggesting that this method of identifying a day of ovulation introduces no more measurement error than when day of ovulation is determined by plasma luteinizing hormone (LH), the standard clinical method.

Adult↗
PubMed1996

The effects of non-response on statistical inference.

Surveys have been, and will most likely continue to be, the source of data for many empirical articles. Likewise, the difficulty of making valid statistical inferences in the face of missing data will continue to plague researchers. In an ideal situation, all potential survey participants would respond; in reality, the goal of an 80 to 90% response rate is very difficult to achieve. When nonresponse is systematic, the combination of low response rate and systematic differences can severely bias inferences that are made by the researcher to the population. It is important for the researcher to assess the potential causes of nonresponse and the differences between the observed values in the sample compared to what may have been gained if the sample was complete, particularly when the response rate is low. There are methods available that substitute imputed values for missing data, but these methods are useless if the researcher lacks knowledge of how the responders and nonresponders may differ. With regard to statistical inference, the researcher also should be aware of the difference between a convenient sample and a probability sample. Valid statistical inference assumes that the probability of characteristics observed in the sample bear some relationship to their occurrence in the population. For example, in a simple random sample each member of the accessible population has an equal chance of inclusion in the sample. A convenient sample lacks the statistical properties of a probability sample that allow the validity of its inferences to be assessed strictly from a mathematical framework. The context of the research and the type of data being gathered greatly affect the validity of any generalizations the researcher makes with regard to the population the convenient sample attempts to represent.

Bias↗
PubMed1999

Improving the rate of classification of patients with the multidimensional pain inventory (MPI): clarifying the meaning of "significant other".

OBJECTIVE: The Multidimensional Pain Inventory (MPI) has been used widely to assess the psychosocial adaptation in chronic pain patients. The MPI can also be used to classify patients into one of three primary subgroups. However, studies have reported that anywhere from 3% to 30% of patients are unclassifiable, mostly attributable to an excessive number of missing responses to questions. The purpose of this study was to examine the reasons for the large number of missing responses and subsequently to reduce the number of patients who cannot be classified within one of the three primary MPI subgroups. DESIGN: Two versions of the MPI were evaluated on two samples of patients (N = 147; and N = 143) with persistent pain being evaluated by the Workers Compensation Board of British Columbia, Canada. One version used the published MPI instructions and the second modified the instructions to clarify the meaning of the term "significant other." In addition, patients were required to designate a significant other who would serve as the anchor for all responses related to a significant other. RESULTS: Approximately 18% of patients could not be classified within one of the three primary profiles and were determined to be unanalyzable using the MPI standard classification procedure. Most patients who could not be classified had excessive missing data to those questions asking about support received from "significant other." Almost all of these patients with missing data were unmarried and living alone. Modifying the instructions of the MPI to specify the meaning of the term "significant other" resulted in an almost threefold (6.3% vs. 18%) reduction in the percentage of patients whose responses could not be analyzed and consequently classified into one of the three primary MPI subgroups. The revised instructions did not lead to any difference in the actual distribution of patients assigned to one of the three profiles. Thus, using the modified instruction did not alter the proportion of patients assigned to one of the three primary groups. CONCLUSION: Modification of the MPI instructions clarifying the definition of a significant other can greatly reduce the number of patients who are classifiable within one of the three primary MPI profiles. Thus, the modified instructions of the MPI (hence the MPI-M) have a significant advantage over the original version. The mean scores on the individual scales of the MPI and the MPI-M are comparable. Moreover, the results demonstrate that the proportion of the previously unanalyzable patients classified within one of the three primary subgroups is comparable to the original proportion of patients assigned to each of the primary subgroups. Thus, it may not be necessary to reestablish the norm scores based on the modified instructions. Future studies and clinicians who wish to use the MPI for the purpose of classifying patients on the basis of psychosocial and behavioral factors should make use of the MPI-M that incorporates the clarification of the meaning of "significant other."

Adaptation, Psychological↗
PubMed1994

A PC program for diagnosing abnormal growth, growth velocity and acceleration from longitudinal observations.

A PC program, written in GAUSS386i, implementing Zerbe's (Growth, 43 (1979) 263-272) procedure for diagnosis on the basis of longitudinal data is described, illustrated and made available to interested readers. Given longitudinal observations on N normal individuals, this technique can be used to characterize normal growth, velocity and acceleration, and to determine whether or not a new individual can be considered normal with respect to any or all of these parameters. Missing data are allowed, and there is no requirement that the variable whose growth is being monitored has a normal distribution. The method and program are illustrated using a data set with a substantial amount of missing data. Information on obtaining a copy of the program and hardware requirements are given in the Appendix.

Algorithms↗
PubMed1991

Source of bias in prenatal care utilization indices: implications for evaluating the Medicaid expansion.

BACKGROUND: Recent expansions in eligibility for coverage of prenatal care services by the Medicaid program reflect national initiatives to improve pregnancy outcomes. This study investigates the potential impact that completeness of reporting of prenatal care and gestational age variables and strategies to impute missing data may have on evaluations of the Medicaid expansion. METHODS: This study, examining 15 years of vital record data from a single state and comparing 1 year of data from four mid-Atlantic states, selected single live births to resident mothers for analyses. The "day 15" and the "preceding case" methods were used to impute missing gestational age data. RESULTS: Considerable temporal and geographic variation was detected in completeness of reporting of variables used to construct prenatal care indices. After imputing values for cases with missing data, the proportion of cases for which adequacy of prenatal care utilization could not be determined ranged from 3% to 24% among the states investigated. For those cases where gestational age data could be imputed, the distribution of prenatal care utilization was not markedly disparate from those cases with complete reporting of gestational age. CONCLUSIONS: The results indicate that variations in reporting, decisions regarding the treatment of missing data, and the choice of the denominator can alter prenatal care utilization percentages and have implications for evaluations of the impact of the recent Medicaid expansion on prenatal care utilization.

Bias↗