Spelling suggestions: "subject:"aregression analysis"" "subject:"bregression analysis""
81 
Theory and algorithms for finding optimal regression designsYin, Yue 25 July 2017 (has links)
In this dissertation, we investigate various theoretical properties of optimal regression designs and develop several numerical algorithms for computing them. The results can be applied to linear, nonlinear and generalized linear models.
Our work starts from how to solve the design problems for A, As, c, I and Loptimality criteria on oneresponse model. Theoretical results are hard to derive for many regression models and criteria, and existing numerical algorithms can not compute the results efficiently when the number of support points is large. Therefore we consider to solve the design problems based on SeDuMi program in MATLAB. SeDuMi is developed to solve semidefinite programming (SDP) problems in optimization. To apply it, we derive a general transformation to connect the design problems with SDP problems, and propose a numerical algorithm based on SeDuMi to solve these SDP problems. The algorithm is quite general under the least squares estimator (LSE) and weighted least squares estimator (WLSE) and can be applied to both linear and nonlinear regression models.
We continue to study the optimal designs based on oneresponse model when the error distribution is asymmetric. Since the secondorder least squares estimator (SLSE) is more efficient than the LSE when the error distribution is not symmetric, we study optimal designs under the SLSE. We derive expressions to characterize A and Doptimality criteria and develop a numerical algorithm for finding optimal designs under the SLSE based on SeDuMi and CVX programs in MATLAB. Several theoretical properties are also derived for optimal designs under SLSE. To check the optimality of the numerical results, we establish the KieferWolfowitz equivalence theorem and apply it to various applications.
Finally, we discuss the optimal design problems for multiresponse models. Our algorithm studied here is based on SeDuMi and CVX, and it can be used for linear, nonlinear and generalized linear models. The transformation invariance property and dependence on the covariance matrix of the correlated errors are derived. We also correct the errors in the literature caused by formulation issues.
The results are very useful to construct optimal regression designs on discrete design space. They can be applied to any oneresponse and multiresponse models, various optimality criteria, and several estimators including LSE, maximum likelihood estimator, best linear unbiased estimator, SLSE and WLSE. / Graduate

82 
Monotone regression functionsZuo, Yanling January 1990 (has links)
In some applications, we require a monotone estimate of a regression function. In others, we want to test whether the regression function is monotone. For solving the first problem, Ramsay's, Kelly and Rice's, as well as pointwise monotone regression
functions in a spline space are discussed and their properties developed. Three monotone estimates are defined: leastsquare regression splines, smoothing splines and binomial regression splines. The three estimates depend upon a "smoothing parameter":
the number and location of knots in regression splines and the usual [formula omitted] in smoothing splines. Two standard techniques for choosing the smoothing parameter, GCV and AIC, are modified for monotone estimation, for the normal errors case. For answering the second question, a test statistic is proposed and its null distribution conjectured. Simulations are carried out to check the conjecture. These techniques are applied to two data sets. / Science, Faculty of / Statistics, Department of / Graduate

83 
Regression Analysis of Swedens Power ConsumptionMoloisel, Victor, Lind, CarlFredrik January 2022 (has links)
Energy Consumption is a topic of great interest, especially since a surge in prices in late 2021 has caused a considerable increase in discussion around the topic. Data from the Swedish Central Bureau of statistics (SCB) and the Swedish Meteorological Institute (SMHI) were provided for macroscopic regressors. These regressors are temperature, population, GDP, day length, electricity price, electricity production, production of variable renewable energy and average income in order to predict electricity consumption. Four models were created, a full multiple linear regression model using all regressors. A reduced multiple linear regression model using a subset of the regressors determined by cross validation. A ridge model and a LASSO model. These were then used to attempt to predict the power consumption of 20% of the data set that were left out when creating the models. The LASSO model was most successful in this as it had the smallest cumulative residual and the ridge model was the worst. Since the reduced and the full model both had very high multicollinearity the conclusion was that the LASSO model is the best model out of the four.

84 
Predicting the power of an intraocular lens implant : an application of model selection theoryDiodatiNolin, Anna C. January 1985 (has links)
No description available.

85 
Distributionfree test for the equality of several regression lines /Smith, Theodore MacDonald January 1977 (has links)
No description available.

86 
Poisson regression /Koo, Joo Ok January 1978 (has links)
No description available.

87 
Confidence intervals for inverse regression with applications to blood hormone analysisDavid, Richard. January 1974 (has links)
No description available.

88 
An ordinal logistic regression model with misclassification of the outcome variable and categorical covariate.Shirkey, Beverly Ann. Waring, Stephen Clay, January 2009 (has links)
Source: Dissertation Abstracts International, Volume: 7003, Section: B, page: 1743. Advisers: Wenyaw Chan; Glasser H. Jay. Includes bibliographical references.

89 
Characterization of the association between shortterm variations in daily mortality and adverse environmental conditions using time series methodologyGuzman, Martha Elva Ramierez January 1990 (has links)
No description available.

90 
An analysis of primary military occupational specialties on retention and promotion of midgrade officers in the U.S. Marine CorpsPerry, Tracy A. 03 1900 (has links)
The purpose of this thesis is to identify and evaluate factors that affect retention and promotion of midgrade officers in the U.S. Marine Corps. The analysis includes evaluation of survival patterns to tenyears of commissioned service and promotion patterns to O4 and O5. The primary goal is to explain the effect of an officersÃ¢ primary military occupational specialty (PMOS) on retention and promotion. The Marine Corps Commissioned Officer Accession Career (MCCOAC) data file contains cohort information from FY 1980 through FY 1999 and includes 27,659 observations. Using data from the MCCOAC data file, logistic regression and Cox Proportional Hazard models are used to estimate the effects of an officerÃ¢ s PMOS on survival and promotion patterns of Marine Corps officers. The findings indicate that an officers PMOS is significantly associated with whether an officer stays until 10 YCS or is promoted to O4 or O5. Logistic regression results show that pilot PMOSs are positively correlated with surviving until 10 YCS, but are negatively correlated with promotion to O4, when compared to Infantry. The results also find that the remaining PMOSs are negatively correlated with whether and officer survives until 10 YCS, when compared to Infantry. In addition, only three PMOSs (0402, 7202, and 7523) are positively correlated with whether an officer is promoted to O4 or O5. Finally, the Cox Proportional Hazard results show the effect of having a particular PMOS or occupational field on the hazards of separation and promotion.

Page generated in 0.1537 seconds