Abstract. In general, the parameter estimation of GWOLR model uses maximum likelihood method, but it constructs a system of nonlinear equations, making it difficult to find the solution. Therefore, an approximate solution is needed. There are two popular numerical methods: the methods of Newton and Quasi-Newton (QN). Newton's method requires largescale time in executing the computation program since it contains Jacobian matrix (derivative). QN method overcomes the drawback of Newton's method by substituting derivative computation into a function of direct computation. The QN method uses Hessian matrix approach which contains Davidon-Fletcher-Powell (DFP) formula. The Broyden-FletcherGoldfarb-Shanno (BFGS) method is categorized as the QN method which has the DFP formula attribute of having positive definite Hessian matrix. The BFGS method requires large memory in executing the program so another algorithm to decrease memory usage is needed, namely Low Memory BFGS (LBFGS). The purpose of this research is to compute the efficiency of the LBFGS method in the iterative and recursive computation of Hessian matrix and its inverse for the GWOLR parameter estimation. In reference to the research findings, we found out that the BFGS and LBFGS methods have arithmetic operation schemes, including and .

The blended learning was a learning model that combines offline and online learning. There are two types of blended learning models used in this research, namely the flipped classroom model and the station rotation model. In these models, the teacher would use WhatsApp as a media for online learning. The purpose of this research was to determine the effect of blended learning models on mathematical creative thinking skills and math anxiety of public junior high school students in Sukoharjo Regency, Central Java Province. The research method used was quasi-experimental by sampling using stratified cluster random sampling techniques. There were three schools selected as research samples, namely Mojolaban 1 Public Junior High School, Mojolaban 2 Junior High School, and Grogol 3 Public Junior High School. The data collection used a written test and questionnaires methods which were carried out after the treatment was given. The data analysis technique used a one-way multivariate analysis of variance. This research shows that the blended learning models were better than the direct learning model on mathematical creative thinking skills, but judging from the magnitude of math anxiety, the direct learning model was better than the station rotation learning model.

This study aims to determine the effect of REACT learning strategies on mathematics learning ac hievement in terms of the learning styles of eighth grade students of public junior high schools in S ragen district. This study was a quasi-experimental study with a 2x3 fac torial design. The population of this study was eighth grade students of the public junior high schools in S ragen Regency in the 2015/2016 ac ademic year. The sample was taken by stratified cluster random sampling. The instrument used to collect data is by distributing questionnaire to test the mathematics learning ac hievement and student learning style. Data analysis techniques use two-way variance analysis with unequal cells. The results show that REACT learning strategies produc e mathematics learning ac hievements that are better than direct learning in material relations and functions. Moreover, mathematics learning ac hievement of students who have a visual learning style as well as students with auditory learning styles, students with visual learning styles have better learning achievement than students with kinesthetic learning styles, while students with auditory learning styles have the same ac hievement with those with kinesthetic learning styles. In addition, in the category of visual, auditory, and kinesthetic learning styles, students who were treated with REACT learning strategies had better mathematics learning ac hievement than students who were treated with direct learning. Lastly, in each REACT learning and direct learning, students with visual learning styles have mathematics learning achievements that are as good as students who have auditory learning styles. S tudents with visual learning styles have better mathematics learning ac hievement than students with kinesthetic learning sty les, while students with auditory learning styles have mathematics learning ac hievements that are as good as students who have kinesthetic learning styles.

No abstract

Spatial relationship models often use dependence relationships into covariance structures through the autoregressive model. The autoregressive process is shown through the dependence relationship between a set of observations or a location from now on called the dependent spatial model. The Spatial dependent model is divided into two categories: spatial lag and spatial error. The spatial lag regression model is a model that considers dependent variables on an area with other areas associated with it, and the spatial error regression model is a model that takes into account the dependency of error values of an area with errors in other areas associated with it. Models with both dependencies are expressed as spatial autoregressive models with a spatial autoregressive error term (SAR-SAR). These dependencies resulted in the estimation of parameters by the ordinary least square method (OLS) resulting in inconsistent estimators. Therefore a special estimation method is required which results in a consistent estimate of the generalized spatial two-stage least square (GS2SLS). In this paper, we review the parameter estimation of SAR-SAR model with GS2SLS. To complete this paper, we also applicate of SAR-SAR model in dengue hemorrhagic fever (DHF) case in Surakarta, Central Java.