SEARCH · Search PubMed

Results for “missing data”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

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

At least 1,081 records · Page 60Linked to original sources

PubMedDate not supplied

Increased psychiatric morbidity in female outpatients with skin lesions on visible parts of the body.

Psychiatric disorders are frequent among patients with skin diseases. We aimed at identifying factors associated with psychiatric morbidity in dermatological outpatients. All adults attending the outpatient clinics of a dermatological hospital on predetermined days were given the 12-item General Health Questionnaire. The dermatologists indicated the diagnosis and location of skin lesions and rated the disease severity. A total of 1389 patients were asked to take part in the study. Of the 722 who accepted, 389 had a complete set of data and were included in the analysis. To verify the representativeness of our sample, we used the administrative registries to compare participants with the total population of patients who attended the clinics during the same period, and we examined the distribution of missing data. There was a tendency towards a younger age in the sample studied, but no evidence of substantial selection bias. The prevalence of psychiatric morbidity was 20.6%. We found higher probability of psychiatric disorders in women, controlling for age, clinical severity and localization of lesions. In women, but not in men, the prevalence of psychiatric morbidity was higher in patients with lesions on the face or hands. Given that the identification and appropriate management of psychiatric morbidity are important, it seems that the dermatologist should be particularly alert to the possibility of a concurrent psychiatric disorder in women with lesions on the face or hands.

Adult↗

PubMed1992

A longitudinal analysis of factors related to survival in old age.

Data from a longitudinal study of the elderly in rural North Wales are used in an exploratory study of the relationships between very broadly defined social circumstances and longevity. A statistical modeling approach is adopted and has some nonroutine features necessitated by missing data on dates of death. A variety of demographic, socioeconomic, social network, quality-of-life, dependence, and health variables are found, individually, to be related to survival. Multivariate analysis demonstrated that many of these relationships are spurious and, in particular, there is no prima facie evidence that survival is affected by social networks or quality-of-life factors. However, socioeconomic factors emerge as important for the old elderly.

Aged↗

PubMed1989

Temporal trends of human immunodeficiency virus type 1 (HIV-1) infection among inmates entering a statewide prison system, 1985-1987.

Acquired immune deficiency syndrome (AIDS) became the leading cause of death among Maryland State prisoners in 1985. To identify the prevalence, risk factors, and temporal trends for infection with the human immunodeficiency virus type 1 (HIV-1) in the statewide prison system, excess sera were obtained from incoming male inmates during specified periods between April and June 1985, 1986, and 1987. Correctional medical personnel also provided demographic variables of age, race, offense category, sentence, jurisidiction, and an indicator of intravenous drug use. Once rendered anonymous, specimens were assayed for antibody to HIV-1, using ELISA and Western blot techniques. For data from April to June 1985, 1986, and 1987, the crude prevalence of anti-HIV-1 was 7.1, 7.7, and 7.0%, respectively. Although one-third of incoming inmates were identified as intravenous drug users (IVDUs), the drug use variable was missing for 70% of the 1985 sample, and 40% of the 1986 sample. Several strategies were used to examined temporal trends in the context of missing data. Univariate analyses suggested no substantial change over time for either HIV-1 seroprevalence or risk of infection among IVDUs.(ABSTRACT TRUNCATED AT 250 WORDS)

Acquired Immunodeficiency Syndrome↗

PubMedDate not supplied

The Manton-Woodbury model for longitudinal data with dropouts.

Often in longitudinal studies one is not able to obtain a complete set of measurements of the variable recorded over time for each person in the study. This could be caused by some of the persons dying (or leaving the study for some other reasons) while the study is going on. If there is any concern that such missing data (which have been termed dropouts) and the variables measured over time affect each other, a model for the joint distribution is needed. For a review of several such models see Hogan and Laird (in this volume). A model of the same kind was proposed by Woodbury and Manton and developed further later on. In this model it is possible to describe the evolution of the distribution of the variable measured over time when exposed to mortality selection. In contrast to other models, this allows for an explicit description of the interaction between the variable measured over time and the time to dropout. We describe the model and propose some generalizations. The theory is illustrated by some Monte Carlo simulations.

Adult↗

PubMed2006

Small-incision versus open cholecystectomy for patients with symptomatic cholecystolithiasis.

BACKGROUND: Cholecystectomy is one of the most frequently performed operations. Open cholecystectomy has been the gold standard for over 100 years. Small-incision cholecystectomy is a less frequently used alternative. OBJECTIVES: To compare the beneficial and harmful effects of small-incision versus open cholecystectomy for patients with symptomatic cholecystolithiasis. SEARCH STRATEGY: We searched TheCochrane Hepato-Biliary Group Controlled Trials Register (6 April 2004), The Cochrane Library (Issue 1, 2004), MEDLINE (1966 to January 2004), EMBASE (1980 to January 2004), Web of Science (1988 to January 2004), and CINAHL (1982 to January 2004) for randomised trials. SELECTION CRITERIA: All published and unpublished randomised trials in patients with symptomatic cholecystolithiasis comparing any kind of small-incision or other kind of minimal incision cholecystectomy versus any kind of open cholecystectomy. No language limitations were applied. DATA COLLECTION AND ANALYSIS: Two authors independently performed selection of trials and data extraction. The methodological quality of the generation of the allocation sequence, allocation concealment, blinding, and follow-up was evaluated to assess bias risk. Analyses were based on the intention-to-treat principle. Authors were requested additional information in case of missing data. Sensitivity and subgroup analyses were performed if appropriate. MAIN RESULTS: Seven trials randomised 571 patients. Bias risk was high in the included trials. No mortality was reported. The total complication proportions are respectively 9.9% and 9.3% in the small-incision and open group, which is not significantly different (risk difference all trials, random-effects 0.00, 95% confidence interval (CI) -0.06 to 0.07). There are also no significant differences considering severe complications and bile duct injuries. However, small-incision cholecystectomy has a shorter hospital stay (weighted mean difference, random-effects -2.8 days (95% CI -4.9 to -0.6)) compared to open cholecystectomy. AUTHORS' CONCLUSIONS: Small-incision and open cholecystectomy seem to be equivalent regarding risks of complications, but the latter method is associated with a significantly longer hospital stay. The quicker recovery of small-incision cholecystectomy compared with open cholecystectomy confirms the existing preference of this technique over open cholecystectomy.

Cholecystectomy↗

PubMed2006

Laparoscopic versus small-incision cholecystectomy for patients with symptomatic cholecystolithiasis.

BACKGROUND: Cholecystectomy is one of the most frequently performed operations. Open cholecystectomy has been the gold standard for over 100 years. Small-incision cholecystectomy is a less frequently used alternative. Laparoscopic cholecystectomy was introduced in the 1980s. OBJECTIVES: To compare the beneficial and harmful effects of laparoscopic versus small-incision cholecystectomy for patients with symptomatic cholecystolithiasis. SEARCH STRATEGY: We searched TheCochrane Hepato-Biliary Group Controlled Trials Register (6 April 2004), The Cochrane Library (Issue 1, 2004), MEDLINE (1966 to January 2004), EMBASE (1980 to January 2004), Web of Science (1988 to January 2004), and CINAHL (1982 to January 2004) for randomised trials. SELECTION CRITERIA: All published and unpublished randomised trials in patients with symptomatic cholecystolithiasis comparing any kind of laparoscopic cholecystectomy versus small-incision or other kind of minimal incision open cholecystectomy. No language limitations were applied. DATA COLLECTION AND ANALYSIS: Two authors independently performed selection of trials and data extraction. The methodological quality of the generation of the allocation sequence, allocation concealment, blinding, and follow-up was evaluated to assess bias risk. Analyses were based on the intention-to-treat principle. Authors were requested additional information in case of missing data. Sensitivity and subgroup analyses were performed if appropriate. MAIN RESULTS: Thirteen trials randomised 2337 patients. Methodological quality was relatively high considering the four quality criteria. Total complications of laparoscopic and small-incision cholecystectomy are high: 26.6% versus 22.9%. Total complications (risk difference, random-effects -0.01, 95% confidence interval (CI) -0.07 to 0.05), hospital stay (weighted mean difference (WMD), random-effects -0.72 days, 95% CI -1.48 to 0.04), and convalescence were not significantly different. High-quality trials show a quicker operative time for small-incision cholecystectomy (WMD, high-quality trials 'blinding', random-effects 16.4 minutes, 95% CI 8.9 to 23.8) while low-quality trials show no significant difference. AUTHORS' CONCLUSIONS: Laparoscopic and small-incision cholecystectomy seem to be equivalent. No differences could be observed in mortality, complications, and postoperative recovery. Small-incision cholecystectomy has a significantly shorter operative time. Complications in elective cholecystectomy are prevalent.

Cholecystectomy↗

PubMed2006

Laparoscopic versus open cholecystectomy for patients with symptomatic cholecystolithiasis.

BACKGROUND: Cholecystectomy is one of the most frequently performed operations. Open cholecystectomy has been the gold standard for over 100 years. Laparoscopic cholecystectomy was introduced in the 1980s. OBJECTIVES: To compare the beneficial and harmful effects of laparoscopic versus open cholecystectomy for patients with symptomatic cholecystolithiasis. SEARCH STRATEGY: We searched TheCochrane Hepato-Biliary Group Controlled Trials Register (April 2004), The Cochrane Library (Issue 1, 2004), MEDLINE (1966 to January 2004), EMBASE (1980 to January 2004), Web of Science (1988 to January 2004), and CINAHL (1982 to January 2004) for randomised trials. SELECTION CRITERIA: All published and unpublished randomised trials in patients with symptomatic cholecystolithiasis comparing any kind of laparoscopic cholecystectomy versus any kind of open cholecystectomy. No language limitations were applied. DATA COLLECTION AND ANALYSIS: Two authors independently performed selection of trials and data extraction. The methodological quality of the generation of the allocation sequence, allocation concealment, blinding, and follow-up was evaluated to assess bias risk. Analyses were based on the intention-to-treat principle. Authors were requested additional information in case of missing data. Sensitivity and subgroup analyses were performed when appropriate. MAIN RESULTS: Thirty-eight trials randomised 2338 patients. Most of the trials had high bias risk. There was no significant difference regarding mortality (risk difference 0,00, 95% confidence interval (CI) -0.01 to 0.01). Meta-analysis of all trials suggests less overall complications in the laparoscopic group, but the high-quality trials show no significant difference ('allocation concealment' high-quality trials risk difference, random effects -0.01, 95% CI -0.05 to 0.02). Laparoscopic cholecystectomy patients have a shorter hospital stay (weighted mean difference (WMD), random effects -3 days, 95% CI -3.9 to -2.3) and convalescence (WMD, random effects -22.5 days, 95% CI -36.9 to -8.1) compared to open cholecystectomy. AUTHORS' CONCLUSIONS: No significant differences were observed in mortality, complications and operative time between laparoscopic and open cholecystectomy. Laparoscopic cholecystectomy is associated with a significantly shorter hospital stay and a quicker convalescence compared with the classical open cholecystectomy. These results confirm the existing preference for the laparoscopic cholecystectomy over open cholecystectomy.

Cholecystectomy↗

PubMed1996

Effect of maternal age and parity on the risk of uteroplacental bleeding disorders in pregnancy.

OBJECTIVE: To examine the risk of placental abruption, placenta previa, and uterine bleeding of unknown etiology in relation to advanced maternal age and parity in a large, population-based study. METHODS: Data for this study were derived from the Nova Scotia Atlee perinatal provincial data base, Canada, an ongoing project on human reproduction. Women who delivered between 1980 and 1993 (n = 123,941) in the province of Nova Scotia were included in the study, with the exception of pregnancies resulting in multiple births (n = 2859) and those missing data on maternal age or parity (n = 14). Multivariable logistic regression models based on the method of generalized estimating equations were used to generate odds ratios after adjustment for multiple confounders. RESULTS: The frequency of abruption was increased slightly among younger women (relative risk [RR] 1.3, 95% confidence interval [CI] 1.0-1.7), compared with women ages 25-29 years, but there was no increase with advancing maternal age. In contrast, the risk of placenta previa increased dramatically with advancing maternal age, with women older than 40 years having a nearly ninefold greater risk than women under the age of 20, after adjustment for potential confounders, including parity. Uterine bleeding of unknown etiology was not associated with advanced maternal age, except for a slight increase among women over 40 (RR 1.3, 95% CI 1.0-1.6). The risk of placenta previa and placental abruption was increased with higher parity among younger women only, but uterine bleeding of unknown etiology was more weakly associated with higher parity. In addition, an analysis of the joint effects of age and parity on placental abruption indicated a strong parity effect for women under 30 years, whereas the risk of placenta previa increased with increasing parity up to age 35 years. Uterine bleeding of unknown etiology also indicated a parity effect that was restricted to women under 25 years. CONCLUSION: Multiparity is associated with the risk of placenta previa and, to a lesser extent, placental abruption, but not with other uterine bleeding. Increasing maternal age is associated independently with the risk of placenta previa, but not with either of the other two conditions. Finally, the increased risks of uteroplacental bleeding disorders with advanced parity among the younger women (ie, 20-25 years, parity 3+) may reflect effects of close pregnancy spacing, or confounding by unmeasured factors that characterize women who have many pregnancies at a relatively young age. Overall, the findings suggest that the three uteroplacental bleeding disorders do not share a common etiology in relation to maternal age and parity, and that placenta previa is linked to aging of the uterus and the effects of repeated pregnancies.

Abruptio Placentae↗

PubMed2006

Alignment of optical maps.

We introduce a new scoring method for calculation of alignments of optical maps. Missing cuts, false cuts, and sizing errors present in optical maps are addressed by our alignment score through calculation of corresponding likelihoods. The size error model is derived through the application of Central Limit Theorem and validated by residual plots collected from real data. Missing cuts and false cuts are modeled as Bernoulli and Poisson events, respectively, as suggested by previous studies. Likelihoods are used to derive an alignment score through calculation of likelihood ratios for a certain hypothesis test. This allows us to achieve maximal descriminative power for the alignment score. Our scoring method is naturally embedded within a well known DP framework for finding optimal alignments.

Algorithms↗

PubMed1993

Multi method approach to the assessment of data quality in the Finnish Medical Birth Registry.

OBJECTIVE: To assess comprehensively the validity of the data in the Finnish Medical Birth Registry (MBR) by the combined use of several controls and internal analysis of the data. DESIGN: The MBR data were individually linked to a medical record sample (n = 775) and to all perinatal death certificates in 1987. The data were also compared with annual hospital statistics. The distributions of birth weights and gestational ages were examined. SUBJECTS: All stillborn and liveborn babies registered in the MBR in 1987 (n = 59,370). SETTING: The nationwide MBR data were compared with medical records from one third of the Finnish hospitals, with statistics for all hospitals, and with nationwide cause of death registry data. MEASUREMENTS AND MAIN RESULTS: With regard to most variables, the data quality was good or satisfactory (agreement with medical records 95% or more). Allowing for minor deviations in variables with continuous scales improved the agreement rates further. Explanations could be deduced for items with poor agreement values. For most variables, the amount of missing data was less than 1%. With the exception of caesarean sections, medical procedures were registered in only 30 to 72% of the cases, and the proportion varied strongly between the hospitals. Common diagnoses (32 to 86%) and primary causes of death (59 to 78%) were also poorly recorded. CONCLUSIONS: Combined use of several control materials and internal analyses was successful in investigating the whole data content. The data in the MBR were generally valid but diagnoses and most data on medical procedures were not of sufficiently good quality.

Birth Certificates↗

PubMed1998

Health-related quality of life in the general Norwegian population assessed by the European Organization for Research and Treatment of Cancer Core Quality-of-Life Questionnaire: the QLQ=C30 (+ 3).

PURPOSE: To obtain reference data on health-related quality of life (HRQOL) for the functional and symptom scales and single items of the European Organization for Research and Treatment of Cancer Core Quality-of-Life Questionnaire (EORTC QLQ-C30 [+ 3]) in a representative sample of the Norwegian general population. PATIENTS AND METHODS: A randomly selected sample of 3,000 people from the Norwegian population, aged 18 to 93 years, who represent geographic diversity, took part in this postal survey. The EORTC QLQ-C30 (+ 3) and a questionnaire about demographic data and health were sent by mail. A new questionnaire package was sent as a reminder after 3 weeks. RESULTS: The survey yielded a high response rate with 1,965 of 2,892 eligible persons responding (68%). There was a low amount of missing data (1.8%). Internal consistency was highly satisfactory and yielded Cronbach's alpha coefficients greater than 0.70 for all but two functional scales and one symptom scale. The sensitivity of the questionnaire was shown by the excellent discrimination between age and sex groups. Clinical validity was shown by the distinct differences according to age and sociodemographic characteristics. Women reported lower functional status and global quality of life (mean scale scores from 71.7 to 91.0) than men (mean scale scores from 75.4 to 94.4), and also more symptoms and problems. This was remarkably consistent across age groups, as was a decline in functional status with an increase in age. CONCLUSION: This is the first study that presented reference data from the EORTC QLQ-C30 (+ 3) in a sample from a general population and seems to provide valid measures of HRQOL within different age groups. The results may serve as a guideline for clinicians when interpreting HRQOL in their own groups of patients, and contributes to a better understanding of the significance of mean scores and their clinical relevance.

Adult↗

PubMed1994

Time series models of individual substance abusers.

Time series analysis is a statistical procedure appropriate for repeated observations on a single subject or unit. The goal of the analysis may be to determine the nature of the process that describes an observed behavior or to evaluate the effects of a treatment or intervention. Model identification involves specifying which of several alternative Autoregressive Integrated Moving Average (ARIMA) models best describes the series and may be used to investigate basic processes. This is illustrated by an example involving selecting the model of nicotine regulation that best represents smokers. Intervention analysis involves determining if there are any changes in level or direction for the series as a result of the intervention. Two types of applications have potential for the substance abuse area: (1) evaluation of the effects of an intervention on a single individual, and (2) evaluation of organizational-level changes (i.e., program evaluation). This is illustrated by an example that examines the effect of relaxation therapy on blood pressure. Pooled time series procedures are employed to combine the data from several different individuals or units, either by cross-sectional analysis or meta-analysis. In addition, several other issues are discussed that are critical to performing a time series analysis: selection of an appropriate computer program, alternative procedures for handling missing data, procedures for multiple observations at each occasion, and corrections for seasonal data.

Humans↗

PubMed2003

Outcome prediction in a surgical ICU using automatically calculated SAPS II scores.

The objective of this study was to establish a complete computerized calculation of the Simplified Acute Physiology Score (SAPS) II within 24 hours after admission to a surgical intensive care unit (ICU) based only on routine data recorded with a patient data management system (PDMS) without any additional manual data entry. Score calculation programs were developed using SQL scripts (Structured Query Language) to retrospectively compute the SAPS II scores of 524 patients who stayed in ICU for at least 24 hours between April 1, 1999 and March 31, 2000 out of the PDMS database. The main outcome measure was survival status at ICU discharge. Score evaluation was modified in registering missing data as being not pathological and using surrogates of the Glasgow Coma Scale (GCS). Computerized score calculation was possible for all investigated patients. The 459 (87.6%) survivors had a median SAPS II of 28 (interquartile range (IQR) 13) whereas the 65 (12.4%) decreased patients had a median score of 43 (IQR 16; P < 0.001). Of the physiological variables for SAPS II score calculation, bilirubin was missing in 84%, followed by PaO2/FiO2 ratio (34%), and neurological status (34%). Using neurological diagnoses and examinations as surrogates for the GCS, a pathological finding was seen in only 8.8% of all results. The discriminative power of the computerized SAPS II checked with a receiver operating characteristic (ROC) curve was 0.81 (95% confidence interval (CI): 0.74-0.87). The Hosmer-Lemeshow goodness-of-fit statistics showed good calibration (H = 5.55, P = 0.59, 7 degrees of freedom; C = 5.55, P = 0.68, 8 degrees of freedom). The technique used in this study for complete automatic data sampling of the SAPS II score seems to be suitable for predicting mortality rate during stay in a surgical ICU. The advantage of the described method is that no additional manual data recording is required for score calculation.

Adult↗

PubMed1999

Semiparametric methods for multiple exposure mismeasurement and a bivariate outcome in HIV vaccine trials.

Exposure to infection information is important for estimating vaccine efficacy, but it is difficult to collect and prone to missingness and mismeasurement. We discuss study designs that collect detailed exposure information from only a small subset of participants while collecting crude exposure information from all participants and treat estimation of vaccine efficacy in the missing data/measurement error framework. We extend the discordant partner design for HIV vaccine trials of Golm, Halloran, and Longini (1998, Statistics in Medicine, 17, 2335-2352.) to the more complex augmented trial design of Longini, Datta, and Halloran (1996, Journal of Acquired Immune Deficiency Syndromes and Human Retrovirology 13, 440-447) and Datta, Halloran, and Longini (1998, Statistics in Medicine 17, 185-200). The model for this design includes three exposure covariates and both univariate and bivariate outcomes. We adapt recently developed semiparametric missing data methods of Reilly and Pepe (1995, Biometrika 82, 299 314), Carroll and Wand (1991, Journal of the Royal Statistical Society, Series B 53, 573-585), and Pepe and Fleming (1991, Journal of the American Statistical Association 86, 108-113) to the augmented vaccine trial design. We demonstrate with simulated HIV vaccine trial data the improvements in bias and efficiency when combining the different levels of exposure information to estimate vaccine efficacy for reducing both susceptibility and infectiousness. We show that the semiparametric methods estimate both efficacy parameters without bias when the good exposure information is either missing completely at random or missing at random. The pseudolikelihood method of Carroll and Wand (1991) and Pepe and Fleming (1991) was the more efficient of the two semiparametric methods.

AIDS Vaccines↗

PubMed1997

Exploring the effects of age of alcohol use initiation and psychosocial risk factors on subsequent alcohol misuse.

OBJECTIVE: This study examines whether the age of initiation of alcohol use mediates the effects of other variables that predict alcohol misuse among adolescents and also whether the age of initiation of alcohol use accounts for known gender differences in the severity of alcohol misuse. METHOD: Data were taken from an ethnically diverse sample of 808 (412 male) students who were recruited in grade 5 at age 10-11 and followed prospectively on an annual basis for the next 7 years to age 17-18. State-of-the-art missing data methodology was used to address nonresponse due to noninitiation of alcohol use. Structural equation modeling was used to examine hypotheses for the prediction of alcohol misuse. RESULTS: A younger age of alcohol initiation was strongly related to a higher level of alcohol misuse at age 17-18 and fully mediated the effects of parent drinking, proactive parenting, school bonding, peer alcohol initiation and ethnicity, all measured at age 10-11, and perceived harmfulness of alcohol use, measured at age 10-11 and age 11-12. However, age of alcohol initiation did not fully account for gender differences in the level of alcohol misuse at age 17-18. To further examine the role of gender, interactions between gender and school bonding, and gender and friend's alcohol initiation, were evaluated. However, neither of the interaction terms had direct effects on either age of initiation or level of alcohol-related problems. CONCLUSIONS: Most measured risk factors for alcohol misuse were mediated through age of alcohol initiation. Only gender differences in alcohol misuse at age 17-18 were not mediated by age of alcohol initiation. Variables associated with these differences require further study. The results of this study indicate the importance of prevention strategies to delay the age of initiation of alcohol use.

Adolescent↗

PubMed2006

[Quality of socioeconomic and demographic data in relation to infant mortality in the Brazilian Mortality Information System (1996/2001)].

This study aimed to evaluate the quality of socioeconomic and demographic data in the Brazilian Mortality Information System (SIM), in relation to infant mortality. The article assesses the system's potential for monitoring inequalities in infant mortality in various States in the country. Accessibility, timeliness, methodological clarity, incompleteness, and consistency were explored as quality indicators. Selected variables were: race, birth weight, gestational age, medical care, parity, and maternal schooling, age, and occupation. The study also reviewed the system's working documentation and the scientific literature on infant mortality. Proportions of data incompleteness were calculated by region and State, identifying factors that might influence (in)completeness using logistic regression. Despite the database's accessibility and the relevance of most of its variables, the system has serious quality problems: confusing instructions in the information manual concerning missing data, misclassification of maternal occupation, lack of data on the informant's race/ethnicity, and high proportions of incomplete information. The system does not appear to be a reliable source for monitoring, evaluating, and planning measures to minimize infant health inequalities.

Brazil↗

PubMed2003

Hypothesis testing of a change point during cognitive decline among Alzheimer's disease patients.

In this paper, we present a statistical hypothesis test for detecting a change point over the course of cognitive decline among Alzheimer's disease patients. The model under the null hypothesis assumes a constant rate of cognitive decline over time and the model under the alternative hypothesis is a general bilinear model with an unknown change point. When the change point is unknown, however, the null distribution of the test statistics is not analytically tractable and has to be simulated by parametric bootstrap. When the alternative hypothesis that a change point exists is accepted, we propose an estimate of its location based on the Akaike's Information Criterion. We applied our method to a data set from the Neuropsychological Database Initiative by implementing our hypothesis testing method to analyze Mini Mental Status Exam scores based on a random-slope and random-intercept model with a bilinear fixed effect. Our result shows that despite large amount of missing data, accelerated decline did occur for MMSE among AD patients. Our finding supports the clinical belief of the existence of a change point during cognitive decline among AD patients and suggests the use of change point models for the longitudinal modeling of cognitive decline in AD research.

Aged↗

PubMed2001

A robust multipoint linkage statistic (tlod) for mapping complex trait loci.

Classical parametric two-point linkage analysis is a powerful analysis tool, however there are clear disadvantages too, including the sensitivity to allele frequency mis-specification. Conversely, multipoint linkage analysis is not sensitive to allele frequency mis-specification, but it is sensitive to genetic model mis-specification. Göring and Terwilliger [Am J Hum Genet 66:1095-106, 2000] proposed a new robust multipoint statistic that increased the robustness of multipoint analyses. In this paper we have referred to this new statistic as the tlod. We applied this new statistic to the Genetic Analysis Workshop (GAW) 12 data using affected status (AFF) as the phenotype of interest. The heterogeneity tlod and two-point hlod scores correlated highly across the genome (p < 0.0001), as expected, but the het-tlod had a lower number false positives. In addition, the tlod analysis handled missing data better, as would be expected for a multipoint method. When one-third of the genotype data was removed (dead people) the tlod analysis was less affected than the two-point analysis. When tlod scores were compared with multipoint lod scores in true gene locations, the robustness of the tlod to model mis-specification was clearly evident. When the "best" replicate from the general population was analyzed, a borderline genome-wide significant two-point hlod result (3.6) was found 4 cM from MG6 and MG7 on chromosome 6. The heterogeneity tlod score was lower than the two-point hlod score (1.8), but greater than the heterogeneity multipoint lod score (0.4). However, when replicate 1 of the isolated population was analyzed none of the true gene locations were identified with either statistic.

Chromosome Mapping↗