Regression Analysis of Count Data

Students in both social and natural sciences often seek regression methods to explain the frequency of events, such as visits to a doctor, auto accidents, or new patents awarded. This book, now in its second edition, provides the most comprehensive and up-to-date account of models and methods to interpret such data. The authors combine theory and practice to make sophisticated methods of analysis accessible to researchers and practitioners working with widely different types of data and software in areas such as applied statistics, econometrics, marketing, operations research, actuarial studies, demography, biostatistics and quantitative social sciences. The new material includes new theoretical topics, an updated and expanded treatment of cross-section models, coverage of bootstrap-based and simulation-based inference, expanded treatment of time series, multivariate and panel data, expanded treatment of endogenous regressors, coverage of quantile count regression, and a new chapter on Bayesian methods.

Students in both social and natural sciences often seek regression methods to explain the frequency of events, such as visits to a doctor, auto accidents, or new patents awarded. This book, now in its second edition, provides the most comprehensive and up-to-date account of models and methods to interpret such data. The authors combine theory and practice to make sophisticated methods of analysis accessible to researchers and practitioners working with widely different types of data and software in areas such as applied statistics, econometrics, marketing, operations research, actuarial studies, demography, biostatistics and quantitative social sciences. The new material includes new theoretical topics, an updated and expanded treatment of cross-section models, coverage of bootstrap-based and simulation-based inference, expanded treatment of time series, multivariate and panel data, expanded treatment of endogenous regressors, coverage of quantile count regression, and a new chapter on Bayesian methods.

Aim. This descriptive study was conducted to determine and compare the emotional intelligence levels of senior students receiving education in different fields of Ataturk University.Methods. The population of the study consisted of senior students receiving education in different fields of Atatürk University. The sample group of study consisted of 305 senior students receiving education in different fields (health, social, and natural) and they were selected by using the simple random sampling method. Three faculties from three different fields were selected. Data of the study were obtained by using the personal information form, which was prepared by researchers in the light of the literature and involved sociodemographic characteristics and the “Emotional Intelligence Evaluation Scale.”Results. It was determined that while natural science students had the lowest total mean score of emotional intelligence scale, students of social sciences had the highest total mean score according to departments. Examining the difference between the mean scores of three different educational fields, it was determined that this difference was statistically significant.Conclusion. Consequently, the emotional intelligence level was determined to be lower in natural science students and moderate in students of health and social sciences.

This research aims to investigate the attitude of natural science and social science students toward their English class, as well as the evaluative language employed in expressing their opinions toward English class. The study employs Martin & White's (2005) appraisal framework to analyze the language used. The participants in the study consist of 60 high school students, with 30 students from the Natural Science major and 30 students from the Social Sciences major, who were selected using the purposive sampling method. The students were requested to write a narrative text outlining their experiences and perceptions of the English class they attended for one semester. The analysis result show that both science and social science students tend to give positive evaluations towards the English class they attend. However, science students are more inclined to give positive evaluations compared to social science students.

The purposes of this study are to investigate the substantial difference in public speaking abilities between students with a natural science and social science background in their high school, and to investigate the students’ point of view related to this issue. This study is a case study approach that is naturally qualitative, which involved 163 students of English Education Study Program, at one state university on North Sumatera province. Semi-structured techniques were used for data collection. The data collected in this study then were inspected out by using two methods; statistical count for quantitative data related to students’ senior high school educational background, and particular substances analysis for qualitative data related to students’ performance in their public speaking. Questionnaire and interview were conducted to assemble the data related to students’ experiences and involvements in taking the public speaking subject and its practice based on their educational background in senior high school, and to collect the students’ opinion related to this difference. The analysis resulted that natural science students in average achieve score 3.58, meanwhile social science students in average achieve score 3.51. The difference is 0.07 point or 1.4%. The average score between the students in natural science and social science can be stated as not significantly different. In addition, generally, all the students who were interviewed believed that public speaking competency is not correlated with majoring in senior high school.

1. Introduction 2. Binary regression: the logit model 3. Generalized linear models 4. Modeling of binary data 5. Alternative binary regression models 6. Regularization and variable selection for parametric models 7. Regression analysis of count data 8. Multinomial response models 9. Ordinal response models 10. Semi- and nonparametric generalized regression 11. Tree-based methods 12. The analysis of contingency tables: log-linear and graphical models 13. Multivariate response models 14. Random effects models 15. Prediction and classification Appendix A. Distributions Appendix B. Some basic tools Appendix C. Constrained estimation Appendix D. Kullback-Leibler distance and information-based criteria of model fit Appendix E. Numerical integration and tools for random effects modeling.

The generalized Poisson distribution has been found useful in fitting over-dispersed as well as under-dispersed count data. Since a number of models and methods have been proposed for the regression analysis of count data either with under-dispersion or with over-dispersion, we define and study a generalized Poisson regression (GPR) model which is useful in predicting a response variable affected by one or more covariates. This regression model is suitable for both types of dispersions. The methods of maximum likelihood and moments are given for the estimation of parameters. Approximate tests for the adequacy of the model are considered. Asymptotic tests are given for the significance of regression parameters. The GPR model has been applied to four observed data sets to which other regression models were applied earlier.

The article argues the choice of the interdisciplinary approach as an effective method for increasing the motivation and engagement of students in natural sciences – biology, chemistry, physics, as well as geography, by connecting knowledge from different general education disciplines into a single meaningful whole. The interdisciplinary approach is associated with the active participation of students in the process of discovering interrelationships between scientific, humanitarian and artistic knowledge. It is considered a key tool in modern education, which encourages critical thinking, creativity and a complex understanding of real problems. Its implementation unites different topics from the curriculum, in particular in natural sciences and geography. The main stages of the implementation of an interdisciplinary approach in combination with project-based learning are related to: formulating a current problem or topic; researching and creating a final product and presenting the results obtained. The article has a methodological nature, related to the development, specifics, implementation and application of the interdisciplinary approach in Bulgarian schools.

Contributors

Mechanistic or dynamical models based on governing equations are ubiquitous throughout science and engineering. Such models, also referred to as “simulators”, are typically characterized by a forward mapping from some set of inputs or parameters to one or more output quantities of interest. In many cases, the inputs required for the forward model are either unknown or represent approximations of unresolved processes. Bayesian inference provides a natural framework for constraining this model uncertainty using observed data. Such a framework is especially valuable in cryospheric application domains such as permafrost research, where direct observations of many quantities of interest, e.g. subsurface temperature and soil moisture, are only sparsely available. Mechanistic models based on known physics therefore play an indispensable role in filling these gaps. However, virtually all methods for Bayesian inference require repeated evaluation of the forward model which is often computationally challenging, especially for dynamical systems. As a result, computational requirements of statistical inference very quickly become intractable even for systems of only moderate complexity. The burgeoning field of “simulation-based inference” (SBI) aims to leverage modern computational methods from machine learning (ML) and data assimilation (DA) to overcome these challenges and facilitate large scale uncertainty quantification in complex scientific models. In this work, we show how SBI can be seen as a unifying theoretical framework that bridges the gap between existing DA methods (e.g. variants of the ensemble Kalman filter) and full-fledged Bayesian inference with the goal of facilitating hybrid statistical-physical modeling of complex systems. We present a novel set of software tools for making SBI more accessible to researchers along with benchmarks of several methods drawn from both the ML and DA literature. Two of these benchmarks are based on use cases from Arctic land surface modeling: degree day approximation of snowmelt and geothermal inversion of historical climate change from boreholes in Arctic permafrost. We highlight the contributions that SBI can make to solving such inverse problems and discuss further potential applications in the cryosphere and beyond.

The teaching of IPAS (Integrated Science and Social Studies), particularly in the topic of map recognition, often still relies on traditional methods that are less effective in enhancing student learning outcomes. Problem-Based Learning (PBL) offers a more engaging and effective alternative by encouraging active student participation and deeper conceptual understanding through real-world problem-solving. This study aims to improve fourth-grade students' understanding of maps specifically, their knowledge of what maps are and how to read them by implementing the PBL model. The research was conducted using a classroom action research approach. In the pre-cycle, the average student score was 71.15, with only 34.61% (9 students) achieving a score of 75 or higher. After the first cycle, the average increased to 77.5, with 50% (13 students) meeting or exceeding the benchmark. In the second cycle, the average score rose significantly to 93.65, with 96.15% (25 students) scoring above 75. These findings indicate that the use of PBL, supported by map-based learning media and PowerPoint presentations, significantly improves student learning outcomes in the topic of map recognition.

Learning strategies are considered capable of greatly helping learners improve their proficiency in English and assist them to be more independent. The purpose of the study is to investigate language learning strategies used by secondary school students in Indonesia related to their field of specialization and gender. One hundred and eighty-six eleventh grade students from one of senior high schools in Pekanbaru, Indonesia participated in the survey. This was conducted using the Strategy Inventory for Language Learning (SILL) adopted from (Oxford, 1990) and the Strategy Questionnaire (SQ) adopted from Embi (2000). The collected data were analyzed using descriptive statistics and an independent sample t-test. The findings show that the most frequently used strategy is metacognitive and affective, followed by cognitive and compensation strategies. The least frequently used strategies are social and memory strategies. Besides, it was also found that there were significant differences in the use of strategies between natural and social science students, and there were no significant differences between the two groups of students based on their gender. The study implies that students are aware of language learning strategies, however students still need to be trained to be a successful language learner.

Throughout history, mankind has been almost constantly involved in an immigration movement. Almost all countries on earth are affected by migration. People sometimes have to leave by their own will and sometimes forced to migrate as well. The factors that cause this situation are natural, economic, social and political. In Turkey, the migration gained pace especially since the 1950s. The causes of this phenomenon are increased mechanization in agriculture, rapid urbanization and civil service assignments. The purpose of this study is to examine the determining factors of internal immigration between the provinces of Turkey through development indicators in the period of 2008-2015 with count data regression analysis and artificial neural network. In addition, using count data analysis and artificial neural networks are used to determine the best estimation method for performing internal migration forecasting in Turkey.

Education is a crucial foundation for shaping a generation with strong character, faith, intelligence, and responsibility as mandated by Law Number 20 of 2003. In the 21st century, one of the most essential competencies to be developed is critical thinking, which can be effectively nurtured through Project Based Learning (PjBL). This approach actively engages students in planning, inquiry, problem-solving, and reflection within project-based tasks, making learning more meaningful. This study examines the effect of PjBL on the critical thinking skills of fifth-grade students in Natural and Social Sciences (IPAS) at SD Islam Istiqomah, Ungaran Barat, Semarang Regency. Employing a quantitative method with a quasi-experimental Nonequivalent Control Group Design, the study involved 76 students divided into experimental and control groups. Data were collected using a validated and reliable essay test on critical thinking skills. Results showed that the experimental group achieved a higher mean posttest score (84.16) than the control group (74.74). The point-biserial correlation was rpb = 0.676, and the t-test result (tcount 7.891 > ttable 1.993, p < 0.05) confirmed a significant difference. These findings demonstrate that PjBL substantially improves students’ critical thinking and emphasize its continued implementation to foster contextual and meaningful IPAS learning.

Purpose – This study aimed to develop and assess the effectiveness of Smart Apps Creator (SAC)-based interactive learning media to enhance critical thinking skills among fifth-grade students in Natural and Social Sciences (IPAS) learning.Methodology – Employing the ADDIE model (Analysis, Design, Development, Implementation, Evaluation), the study employed a quasi-experimental design with purposive sampling for the needs analysis (20 teachers, 24 students) and random sampling for the trials (54 experimental and 57 control group students across four elementary schools). The experimental group engaged in six offline SAC-based learning sessions, while the control group used conventional methods (lectures, worksheets, static images). Data were collected through classroom observations, media feasibility questionnaires, and pre- and post-tests of critical thinking skills, and analyzed using descriptive statistics, paired t-tests, and N-Gain scores.Findings – The SAC-based media achieved high feasibility (expert validation: 82.3%-86.5%). They significantly improved critical thinking, with the experimental group recording an N-Gain of 0.75 (high) and a t-value of -30.556 (p = 0.000), outperforming the control group’s N-Gain of 0.42 (moderate) and a t-value of -18.070 (p = 0.000). Interactive elements, such as quizzes and animations, fostered student-centered learning, although challenges included limited hardware and teacher training needs. The offline SAC media effectively addressed connectivity constraints, enhancing analytical skills.Contribution – This study offers a scalable, offline educational technology solution for rural areas, promoting 21st-century skills such as critical thinking and suggesting the broader implementation and exploration of additional skills, including collaboration and communication.