Data from longitudinal surveys give rise to many statistical challenges. They often come from a vast, heterogeneous population and from a complex sampling design. Further, they are usually collected retrospectively at intermittent interviews spaced over a long period of time, which gives rise to missing information and loss to follow-up. As a result, duration data from this kind of surveys are subject to dependent censoring, which needs to be taken into account to prevent biased analysis. Methods for point and variance estimation are developed using Inverse Probability of Censoring (IPC) weights. These methods account for the random nature of the IPC weights and can be applied in the analysis of duration data in survey and non-survey settings. The IPC estimation techniques are based on parametric estimating function theory and involve the estimation of dropout models. Survival distributions without covariates are estimated via a weighted Kaplan-Meier method and regression modeling through the Cox Proportional Hazards model and other models is based on weighted estimating functions. The observational frameworks from Statistics Canada's Survey of Labour and Income Dynamics (SLID) and the UK Millenium Cohort Study are used as motivation, and durations of jobless spells from SLID are analyzed as an illustration of the methodology. Issues regarding missing information from longitudinal surveys are also discussed.

Background: Across North America, smoking prevalence is highest among young adults (YAs). Understanding the cessation behaviours of YAs is critical given their higher smoking rates; however, there is a paucity of prospective studies on YA cessation from a population-based sample of smokers. Objectives: This study characterizes younger and older adult smokers as well as identifies the rate of making a quit attempt (QA) and smoking cessation among a representative sample of younger and older adult smokers. Guided by the Social Cognitive Theory (SCT), this study also examines the interpersonal predictors of moving toward smoking cessation among YAs. Methods: Self-report data on 592 YA and 2777 older adult smokers were compiled from the Ontario Tobacco Survey baseline and six-month follow-up interviews. Smoking cessation behaviour was measured as an ordinal variable: made no attempt to quit, made a QA that lasted for less than 30 days, and successfully quit for 30 days or longer. Design-based analyses examined the characteristics of young and older adult smokers. Making a QA and smoking cessation during a six-month follow-up period were modeled according to the SCT constructs while accounting for the complex study design. Results: Young adult smokers were more likely to be men with lower levels of addiction but greater self-efficacy and an intention to quit than their older counterparts. While YA smokers were more likely to make a QA than their older counterparts (25% vs. 17%, respectively), they were no more likely to succeed (14% vs. 10%, respectively). Having an intention to quit smoking and having made two or more lifetime number of QAs predicted making a QA; the use of smoking cessation aids or resources and having knowledge that stop smoking medications make quitting a lot easier also contributed to making an attempt to quit. Self-efficacy, use of smoking cessation aids or resources and having someone to support one‘s QA were positive predictors of quitting whereas having high levels of addiction was a negative predictor of cessation. Conclusions: Young and older adults are distinct types of smokers with different personal and smoking characteristics. Different factors predicted making a QA and smoking cessation among YAs. Smoking cessation interventions for YAs should provide social support and skills to build and maintain self-efficacy to quit. It is critical to ensure YA smokers have effective smoking cessation aids and services that are easily accessible and appropriate for this population. Future research is needed to understand long-term smoking cessation and relapse in this vulnerable population.

Data obtained from longitudinal surveys using complex multi-stage sampling designs contain cross-sectional dependencies among units caused by inherent hierarchies in the data, and within subject correlation arising due to repeated measurements. The statistical methods used for analyzing such data should account for stratification, clustering and unequal probability of selection as well as within-subject correlations due to repeated measurements. <p>The complex multi-stage design approach has been used in the longitudinal National Population Health Survey (NPHS). This on-going survey collects information on health determinants and outcomes in a sample of the general Canadian population. <p>This dissertation compares the model-based and design-based approaches used to determine the risk factors of asthma prevalence in the Canadian female population of the NPHS (marginal model). Weighted, unweighted and robust statistical methods were used to examine the risk factors of the incidence of asthma (event history analysis) and of recurrent asthma episodes (recurrent survival analysis). Missing data analysis was used to study the bias associated with incomplete data. To determine the risk factors of asthma prevalence, the Generalized Estimating Equations (GEE) approach was used for marginal modeling (model-based approach) followed by Taylor Linearization and bootstrap estimation of standard errors (design-based approach). The incidence of asthma (event history analysis) was estimated using weighted, unweighted and robust methods. Recurrent event history analysis was conducted using Anderson and Gill, Wei, Lin and Weissfeld (WLW) and Prentice, Williams and Peterson (PWP) approaches. To assess the presence of bias associated with missing data, the weighted GEE and pattern-mixture models were used.<p>The prevalence of asthma in the Canadian female population was 6.9% (6.1-7.7) at the end of Cycle 5. When comparing model-based and design- based approaches for asthma prevalence, design-based method provided unbiased estimates of standard errors. The overall incidence of asthma in this population, excluding those with asthma at baseline, was 10.5/1000/year (9.2-12.1). For the event history analysis, the robust method provided the most stable estimates and standard errors. <p>For recurrent event history, the WLW method provided stable standard error estimates. Finally, for the missing data approach, the pattern-mixture model produced the most stable standard errors <p>To conclude, design-based approaches should be preferred over model-based approaches for analyzing complex survey data, as the former provides the most unbiased parameter estimates and standard errors.

none

In optical disk systems, a semiconductor laser is used to read out the data recorded on the disc. Since the laser is the first noise source, there are strictly rated values for laser's noise in various optical disk systems to ensure the normal operation of the system. Among different laser noises, the worst one is the optical feedback noise. The feedback light will disturb the longitudinal modes of the laser and induce huge fluctuation in Laser's output. In our work, we study the effect of optical feedback on Laser's modes and relative intensity noises under various driving current and chop temperature. We try to find out methods that can suppress the Laser's noise and try to give some suggestions for the design of disc driven. Some experiments about a commercialized optical disk driver are also reported as well.

In this day and age, information technology to daily life is now universal. The Internet is a global system that provides innovative services. This study focused on treating the feelings and intentions of new users that has not been used at the hedonic website. As well as expectations and intentions during and after a month of usage. Through this study, the self-developed innovative website has created called iMemory. During the first survey, the subjects were on display for users. After measuring the hearts of users show the expected feelings and intentions.A month later, the same measure by measuring the extent of use, the use of feelings and intentions. In this study, based on technology acceptance model, by adding perceived enjoyment that the period of one month longitudinal study. To compare the differences between two results. The results showed that the second measurement of the use of feelings and intentions are will be the first to use measurements of the feelings and intentions significant impact on the use of the past month and the remarkable degree of influence. The second measure of perceived ease of use and perceived usefulness of intent with the impact is not significant, but perceived enjoyment of intent are still significantly affected. Finally, this study based on data analysis for discussion.

Thesis--University of Oklahoma. / Bibliography: leaves 101-104.

Thesis (Ph. D.)--University of Washington, 2002. / Vita. Includes bibliographical references (p. 174-179).

Sociologists are generally in agreement that the closing decades of the twentieth century involved striking changes in the landscape against which British young people grew up. Transformations in education and the labour market had the potential to dramatically alter and re-shape patterns of social inequality. This thesis addresses the importance of family effects upon educational attainment, early career prospects and, in turn, the post-16 trajectories of young adults against the contextual changes of this period. Recently, youth researchers have been keen to argue that we are continuing to progress towards a ‘post-modern era’, which centres on the ‘individualisation’ or ‘detraditionalisation’ arguments of Beck and Giddens; where structural factors, such as gender and social class are diminishing as the defining elements of the pathway a young person will take. In this study, the British Household Panel Survey (BHPS), a contemporary source of longitudinal data from the early 1990s onwards, is used to demonstrate a lack of evidence of detraditionalisation, or the weakening of structural factors in determining the outcomes of young people. To the contrary, the gap between those from advantaged and less advantaged backgrounds remains wide. Furthermore, this research augments and extends previous studies of educational and early labour market outcomes by providing more comprehensive and integrated statistical analyses of household, family and parental effects, using techniques for longitudinal data analysis which give insight into patterns of social inequality being replicated in current contexts. Evidence using 17 years of longitudinal panel data indicate that, over time, family effects on school attainment and early labour market outcomes remain strong.

This longitudinal study examined factors that contribute to change in attachment anxiety and attachment avoidance over the transition to parenthood. Participants were a community sample of 98 heterosexual couples expecting their first child who were recruited through maternity resources in the Victoria, B.C. area. Specifically, this study considered whether prenatal perceived stress levels predicted change in adult attachment security. For men, higher stress levels predicted more change in attachment security. We also examined whether increases in stress levels from the prenatal to the postnatal period predicted changes in attachment security and found that increases in stress from the prenatal to postnatal period were associated with more change in attachment for men; results were marginally significant for women. In addition to examining the impact of stress on the absolute value of change in attachment, this study considered perceived support and perceived anger as moderators of the relationship between stress and directional change in attachment. Measures of general support and perceived anger did not moderate this relationship. Observational ratings of partner’s positive and negative support behaviours during support-seeking interactions were examined as potential moderators. The interaction between stress and positive emotional support predicted decreasing avoidance for women. Interactions between stress and negative affect marginally predicted increasing anxiety for men and women. Dyadic analyses were also used to clarify how changes in participants’ attachment security over time were influenced by their partners’ prenatal attachment security. For women, partner levels of attachment avoidance at the prenatal period predicted increasing attachment anxiety. These findings emphasize that adult attachment exists in the context of interpersonal relationships, and demonstrate the importance of using dyadic and longitudinal data to study attachment. Implications for attachment theory and intervention are discussed. / Graduate / 0451 / 0621 / 0622 / taracg@uvic.ca