Pub Date : 2023-03-27DOI: 10.1080/00031305.2023.2226184
Rolf Larsson
The notion of confidence distributions is applied to inference about the parameter in a simple autoregressive model, allowing the parameter to take the value one. This makes it possible to compare to asymptotic approximations in both the stationary and the non stationary cases at the same time. The main point, however, is to compare to a Bayesian analysis of the same problem. A non informative prior for a parameter, in the sense of Jeffreys, is given as the ratio of the confidence density and the likelihood. In this way, the similarity between the confidence and non-informative Bayesian frameworks is exploited. It is shown that, in the stationary case, asymptotically the so induced prior is flat. However, if a unit parameter is allowed, the induced prior has to have a spike at one of some size. Simulation studies and two empirical examples illustrate the ideas.
{"title":"Confidence Distributions for the Autoregressive Parameter","authors":"Rolf Larsson","doi":"10.1080/00031305.2023.2226184","DOIUrl":"https://doi.org/10.1080/00031305.2023.2226184","url":null,"abstract":"The notion of confidence distributions is applied to inference about the parameter in a simple autoregressive model, allowing the parameter to take the value one. This makes it possible to compare to asymptotic approximations in both the stationary and the non stationary cases at the same time. The main point, however, is to compare to a Bayesian analysis of the same problem. A non informative prior for a parameter, in the sense of Jeffreys, is given as the ratio of the confidence density and the likelihood. In this way, the similarity between the confidence and non-informative Bayesian frameworks is exploited. It is shown that, in the stationary case, asymptotically the so induced prior is flat. However, if a unit parameter is allowed, the induced prior has to have a spike at one of some size. Simulation studies and two empirical examples illustrate the ideas.","PeriodicalId":342642,"journal":{"name":"The American Statistician","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123582788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-21DOI: 10.1080/00031305.2023.2183257
Per Gösta Andersson
Abstract When teaching we usually not only demonstrate/discuss how a certain method works, but, not less important, why it works. In contrast, the Wald confidence interval for a binomial p constitutes an excellent example of a case where we might be interested in why a method does not work. It has been in use for many years and, sadly enough, it is still to be found in many textbooks in mathematical statistics/statistics. The reasons for not using this interval are plentiful and this fact gives us a good opportunity to discuss all of its deficiencies and draw conclusions which are of more general interest. We will mostly use already known results and bring them together in a manner appropriate to the teaching situation. The main purpose of this article is to show how to stimulate students to take a more critical view of simplifications and approximations. We primarily aim for master’s students who previously have been confronted with the Wilson (score) interval, but parts of the presentation may as well be suitable for bachelor’s students.
{"title":"The Wald Confidence Interval for a Binomial p as an Illuminating “Bad” Example","authors":"Per Gösta Andersson","doi":"10.1080/00031305.2023.2183257","DOIUrl":"https://doi.org/10.1080/00031305.2023.2183257","url":null,"abstract":"Abstract When teaching we usually not only demonstrate/discuss how a certain method works, but, not less important, why it works. In contrast, the Wald confidence interval for a binomial p constitutes an excellent example of a case where we might be interested in why a method does not work. It has been in use for many years and, sadly enough, it is still to be found in many textbooks in mathematical statistics/statistics. The reasons for not using this interval are plentiful and this fact gives us a good opportunity to discuss all of its deficiencies and draw conclusions which are of more general interest. We will mostly use already known results and bring them together in a manner appropriate to the teaching situation. The main purpose of this article is to show how to stimulate students to take a more critical view of simplifications and approximations. We primarily aim for master’s students who previously have been confronted with the Wilson (score) interval, but parts of the presentation may as well be suitable for bachelor’s students.","PeriodicalId":342642,"journal":{"name":"The American Statistician","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133861694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-14DOI: 10.1080/00031305.2023.2192746
A. Vexler, Alan D. Hutson
Data-driven most powerful tests are statistical hypothesis decision-making tools that deliver the greatest power against a fixed null hypothesis among all corresponding data-based tests of a given size. When the underlying data distributions are known, the likelihood ratio principle can be applied to conduct most powerful tests. Reversing this notion, we consider the following questions. (a) Assuming a test statistic, say T, is given, how can we transform T to improve the power of the test? (b) Can T be used to generate the most powerful test? (c) How does one compare test statistics with respect to an attribute of the desired most powerful decision-making procedure? To examine these questions, we propose one-to-one mapping of the term 'Most Powerful' to the distribution properties of a given test statistic via matching characterization. This form of characterization has practical applicability and aligns well with the general principle of sufficiency. Findings indicate that to improve a given test, we can employ relevant ancillary statistics that do not have changes in their distributions with respect to tested hypotheses. As an example, the present method is illustrated by modifying the usual t-test under nonparametric settings. Numerical studies based on generated data and a real-data set confirm that the proposed approach can be useful in practice.
{"title":"A Characterization of Most(More) Powerful Test Statistics with Simple Nonparametric Applications","authors":"A. Vexler, Alan D. Hutson","doi":"10.1080/00031305.2023.2192746","DOIUrl":"https://doi.org/10.1080/00031305.2023.2192746","url":null,"abstract":"Data-driven most powerful tests are statistical hypothesis decision-making tools that deliver the greatest power against a fixed null hypothesis among all corresponding data-based tests of a given size. When the underlying data distributions are known, the likelihood ratio principle can be applied to conduct most powerful tests. Reversing this notion, we consider the following questions. (a) Assuming a test statistic, say T, is given, how can we transform T to improve the power of the test? (b) Can T be used to generate the most powerful test? (c) How does one compare test statistics with respect to an attribute of the desired most powerful decision-making procedure? To examine these questions, we propose one-to-one mapping of the term 'Most Powerful' to the distribution properties of a given test statistic via matching characterization. This form of characterization has practical applicability and aligns well with the general principle of sufficiency. Findings indicate that to improve a given test, we can employ relevant ancillary statistics that do not have changes in their distributions with respect to tested hypotheses. As an example, the present method is illustrated by modifying the usual t-test under nonparametric settings. Numerical studies based on generated data and a real-data set confirm that the proposed approach can be useful in practice.","PeriodicalId":342642,"journal":{"name":"The American Statistician","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127477126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-10DOI: 10.1080/00031305.2023.2216252
Stijn Hawinkel, W. Waegeman, Steven Maere
Out-of-sample prediction is the acid test of predictive models, yet an independent test dataset is often not available for assessment of the prediction error. For this reason, out-of-sample performance is commonly estimated using data splitting algorithms such as cross-validation or the bootstrap. For quantitative outcomes, the ratio of variance explained to total variance can be summarized by the coefficient of determination or in-sample $R^2$, which is easy to interpret and to compare across different outcome variables. As opposed to the in-sample $R^2$, the out-of-sample $R^2$ has not been well defined and the variability on the out-of-sample $hat{R}^2$ has been largely ignored. Usually only its point estimate is reported, hampering formal comparison of predictability of different outcome variables. Here we explicitly define the out-of-sample $R^2$ as a comparison of two predictive models, provide an unbiased estimator and exploit recent theoretical advances on uncertainty of data splitting estimates to provide a standard error for the $hat{R}^2$. The performance of the estimators for the $R^2$ and its standard error are investigated in a simulation study. We demonstrate our new method by constructing confidence intervals and comparing models for prediction of quantitative $text{Brassica napus}$ and $text{Zea mays}$ phenotypes based on gene expression data.
{"title":"Out-of-sample R2: estimation and inference","authors":"Stijn Hawinkel, W. Waegeman, Steven Maere","doi":"10.1080/00031305.2023.2216252","DOIUrl":"https://doi.org/10.1080/00031305.2023.2216252","url":null,"abstract":"Out-of-sample prediction is the acid test of predictive models, yet an independent test dataset is often not available for assessment of the prediction error. For this reason, out-of-sample performance is commonly estimated using data splitting algorithms such as cross-validation or the bootstrap. For quantitative outcomes, the ratio of variance explained to total variance can be summarized by the coefficient of determination or in-sample $R^2$, which is easy to interpret and to compare across different outcome variables. As opposed to the in-sample $R^2$, the out-of-sample $R^2$ has not been well defined and the variability on the out-of-sample $hat{R}^2$ has been largely ignored. Usually only its point estimate is reported, hampering formal comparison of predictability of different outcome variables. Here we explicitly define the out-of-sample $R^2$ as a comparison of two predictive models, provide an unbiased estimator and exploit recent theoretical advances on uncertainty of data splitting estimates to provide a standard error for the $hat{R}^2$. The performance of the estimators for the $R^2$ and its standard error are investigated in a simulation study. We demonstrate our new method by constructing confidence intervals and comparing models for prediction of quantitative $text{Brassica napus}$ and $text{Zea mays}$ phenotypes based on gene expression data.","PeriodicalId":342642,"journal":{"name":"The American Statistician","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127156188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-07DOI: 10.1080/00031305.2023.2250401
Lin Ge, Yuzi Zhang, L. Waller, R. Lyles
Epidemiologic screening programs often make use of tests with small, but non-zero probabilities of misdiagnosis. In this article, we assume the target population is finite with a fixed number of true cases, and that we apply an imperfect test with known sensitivity and specificity to a sample of individuals from the population. In this setting, we propose an enhanced inferential approach for use in conjunction with sampling-based bias-corrected prevalence estimation. While ignoring the finite nature of the population can yield markedly conservative estimates, direct application of a standard finite population correction (FPC) conversely leads to underestimation of variance. We uncover a way to leverage the typical FPC indirectly toward valid statistical inference. In particular, we derive a readily estimable extra variance component induced by misclassification in this specific but arguably common diagnostic testing scenario. Our approach yields a standard error estimate that properly captures the sampling variability of the usual bias-corrected maximum likelihood estimator of disease prevalence. Finally, we develop an adapted Bayesian credible interval for the true prevalence that offers improved frequentist properties (i.e., coverage and width) relative to a Wald-type confidence interval. We report the simulation results to demonstrate the enhanced performance of the proposed inferential methods.
{"title":"Enhanced Inference for Finite Population Sampling-Based Prevalence Estimation with Misclassification Errors","authors":"Lin Ge, Yuzi Zhang, L. Waller, R. Lyles","doi":"10.1080/00031305.2023.2250401","DOIUrl":"https://doi.org/10.1080/00031305.2023.2250401","url":null,"abstract":"Epidemiologic screening programs often make use of tests with small, but non-zero probabilities of misdiagnosis. In this article, we assume the target population is finite with a fixed number of true cases, and that we apply an imperfect test with known sensitivity and specificity to a sample of individuals from the population. In this setting, we propose an enhanced inferential approach for use in conjunction with sampling-based bias-corrected prevalence estimation. While ignoring the finite nature of the population can yield markedly conservative estimates, direct application of a standard finite population correction (FPC) conversely leads to underestimation of variance. We uncover a way to leverage the typical FPC indirectly toward valid statistical inference. In particular, we derive a readily estimable extra variance component induced by misclassification in this specific but arguably common diagnostic testing scenario. Our approach yields a standard error estimate that properly captures the sampling variability of the usual bias-corrected maximum likelihood estimator of disease prevalence. Finally, we develop an adapted Bayesian credible interval for the true prevalence that offers improved frequentist properties (i.e., coverage and width) relative to a Wald-type confidence interval. We report the simulation results to demonstrate the enhanced performance of the proposed inferential methods.","PeriodicalId":342642,"journal":{"name":"The American Statistician","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114532117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-30DOI: 10.1080/00031305.2023.2173294
Peng Wang, Yi-lei Ma, Siqi Xu, Yixin Wang, Yu Zhang, Xiangyang Lou, Ming Li, Baolin Wu, Guimin Gao, P. Yin, Nianjun Liu
Abstract Developing a confidence interval for the ratio of two quantities is an important task in statistics because of its omnipresence in real world applications. For such a problem, the MOVER-R (method of variance recovery for the ratio) technique, which is based on the recovery of variance estimates from confidence limits of the numerator and the denominator separately, was proposed as a useful and efficient approach. However, this method implicitly assumes that the confidence interval for the denominator never includes zero, which might be violated in practice. In this article, we first use a new framework to derive the MOVER-R confidence interval, which does not require the above assumption and covers the whole parameter space. We find that MOVER-R can produce an unbounded confidence interval, just like the well-known Fieller method. To overcome this issue, we further propose the penalized MOVER-R. We prove that the new method differs from MOVER-R only at the second order. It, however, always gives a bounded and analytic confidence interval. Through simulation studies and a real data application, we show that the penalized MOVER-R generally provides a better confidence interval than MOVER-R in terms of controlling the coverage probability and the median width.
{"title":"MOVER-R and Penalized MOVER-R Confidence Intervals for the Ratio of Two Quantities","authors":"Peng Wang, Yi-lei Ma, Siqi Xu, Yixin Wang, Yu Zhang, Xiangyang Lou, Ming Li, Baolin Wu, Guimin Gao, P. Yin, Nianjun Liu","doi":"10.1080/00031305.2023.2173294","DOIUrl":"https://doi.org/10.1080/00031305.2023.2173294","url":null,"abstract":"Abstract Developing a confidence interval for the ratio of two quantities is an important task in statistics because of its omnipresence in real world applications. For such a problem, the MOVER-R (method of variance recovery for the ratio) technique, which is based on the recovery of variance estimates from confidence limits of the numerator and the denominator separately, was proposed as a useful and efficient approach. However, this method implicitly assumes that the confidence interval for the denominator never includes zero, which might be violated in practice. In this article, we first use a new framework to derive the MOVER-R confidence interval, which does not require the above assumption and covers the whole parameter space. We find that MOVER-R can produce an unbounded confidence interval, just like the well-known Fieller method. To overcome this issue, we further propose the penalized MOVER-R. We prove that the new method differs from MOVER-R only at the second order. It, however, always gives a bounded and analytic confidence interval. Through simulation studies and a real data application, we show that the penalized MOVER-R generally provides a better confidence interval than MOVER-R in terms of controlling the coverage probability and the median width.","PeriodicalId":342642,"journal":{"name":"The American Statistician","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125420368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-11DOI: 10.1080/00031305.2022.2163689
Serveh Sharifi Far, Vanda Inácio, D. Paulin, M. de Carvalho, Nicole Augustin, Mike Allerhand, Gail S Robertson
Abstract In this article, we chronicle the development of the consultancy style dissertations of the MSc program in Statistics with Data Science at the University of Edinburgh. These dissertations are based on real-world data problems, in joint supervision with industrial and academic partners, and aim to get all students in the cohort together to develop consultancy skills and best practices, and also to promote their statistical leadership. Aligning with recently published research on statistical education suggesting the need for a greater focus on statistical consultancy skills, we summarize our experience in organizing and supervising such consultancy style dissertations, describe the logistics of implementing them, and review the students’ and supervisors’ feedback about these dissertations.
{"title":"Consultancy Style Dissertations in Statistics and Data Science: Why and How","authors":"Serveh Sharifi Far, Vanda Inácio, D. Paulin, M. de Carvalho, Nicole Augustin, Mike Allerhand, Gail S Robertson","doi":"10.1080/00031305.2022.2163689","DOIUrl":"https://doi.org/10.1080/00031305.2022.2163689","url":null,"abstract":"Abstract In this article, we chronicle the development of the consultancy style dissertations of the MSc program in Statistics with Data Science at the University of Edinburgh. These dissertations are based on real-world data problems, in joint supervision with industrial and academic partners, and aim to get all students in the cohort together to develop consultancy skills and best practices, and also to promote their statistical leadership. Aligning with recently published research on statistical education suggesting the need for a greater focus on statistical consultancy skills, we summarize our experience in organizing and supervising such consultancy style dissertations, describe the logistics of implementing them, and review the students’ and supervisors’ feedback about these dissertations.","PeriodicalId":342642,"journal":{"name":"The American Statistician","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122887517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-06DOI: 10.1080/00031305.2022.2161637
Jiaqi Gu, Y. Zhang, G. Yin
Abstract Comparison of two survival curves is a fundamental problem in survival analysis. Although abundant frequentist methods have been developed for comparing survival functions, inference procedures from the Bayesian perspective are rather limited. In this article, we extract the quantity of interest from the classic log-rank test and propose its Bayesian counterpart. Monte Carlo methods, including a Gibbs sampler and a sequential importance sampling procedure, are developed to draw posterior samples of survival functions and a decision rule of hypothesis testing is constructed for making inference. Via simulations and real data analysis, the proposed Bayesian log-rank test is shown to be asymptotically equivalent to the classic one when noninformative prior distributions are used, which provides a Bayesian interpretation of the log-rank test. When using the correct prior information from historical data, the Bayesian log-rank test is shown to outperform the classic one in terms of power. R codes to implement the Bayesian log-rank test are also provided with step-by-step instructions.
{"title":"Bayesian Log-Rank Test","authors":"Jiaqi Gu, Y. Zhang, G. Yin","doi":"10.1080/00031305.2022.2161637","DOIUrl":"https://doi.org/10.1080/00031305.2022.2161637","url":null,"abstract":"Abstract Comparison of two survival curves is a fundamental problem in survival analysis. Although abundant frequentist methods have been developed for comparing survival functions, inference procedures from the Bayesian perspective are rather limited. In this article, we extract the quantity of interest from the classic log-rank test and propose its Bayesian counterpart. Monte Carlo methods, including a Gibbs sampler and a sequential importance sampling procedure, are developed to draw posterior samples of survival functions and a decision rule of hypothesis testing is constructed for making inference. Via simulations and real data analysis, the proposed Bayesian log-rank test is shown to be asymptotically equivalent to the classic one when noninformative prior distributions are used, which provides a Bayesian interpretation of the log-rank test. When using the correct prior information from historical data, the Bayesian log-rank test is shown to outperform the classic one in terms of power. R codes to implement the Bayesian log-rank test are also provided with step-by-step instructions.","PeriodicalId":342642,"journal":{"name":"The American Statistician","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122762360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-03DOI: 10.1080/00031305.2022.2164054
D. Rügamer, Chris Kolb, N. Klein
{"title":"Semi-Structured Distributional Regression","authors":"D. Rügamer, Chris Kolb, N. Klein","doi":"10.1080/00031305.2022.2164054","DOIUrl":"https://doi.org/10.1080/00031305.2022.2164054","url":null,"abstract":"","PeriodicalId":342642,"journal":{"name":"The American Statistician","volume":"9 16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124349615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-03DOI: 10.1080/00031305.2023.2232006
Vojtech Kejzlar, Jingchen Hu
Probabilistic models such as logistic regression, Bayesian classification, neural networks, and models for natural language processing, are increasingly more present in both undergraduate and graduate statistics and data science curricula due to their wide range of applications. In this paper, we present a one-week course module for studnets in advanced undergraduate and applied graduate courses on variational inference, a popular optimization-based approach for approximate inference with probabilistic models. Our proposed module is guided by active learning principles: In addition to lecture materials on variational inference, we provide an accompanying class activity, an texttt{R shiny} app, and guided labs based on real data applications of logistic regression and clustering documents using Latent Dirichlet Allocation with texttt{R} code. The main goal of our module is to expose students to a method that facilitates statistical modeling and inference with large datasets. Using our proposed module as a foundation, instructors can adopt and adapt it to introduce more realistic case studies and applications in data science, Bayesian statistics, multivariate analysis, and statistical machine learning courses.
{"title":"Introducing Variational Inference in Statistics and Data Science Curriculum","authors":"Vojtech Kejzlar, Jingchen Hu","doi":"10.1080/00031305.2023.2232006","DOIUrl":"https://doi.org/10.1080/00031305.2023.2232006","url":null,"abstract":"Probabilistic models such as logistic regression, Bayesian classification, neural networks, and models for natural language processing, are increasingly more present in both undergraduate and graduate statistics and data science curricula due to their wide range of applications. In this paper, we present a one-week course module for studnets in advanced undergraduate and applied graduate courses on variational inference, a popular optimization-based approach for approximate inference with probabilistic models. Our proposed module is guided by active learning principles: In addition to lecture materials on variational inference, we provide an accompanying class activity, an texttt{R shiny} app, and guided labs based on real data applications of logistic regression and clustering documents using Latent Dirichlet Allocation with texttt{R} code. The main goal of our module is to expose students to a method that facilitates statistical modeling and inference with large datasets. Using our proposed module as a foundation, instructors can adopt and adapt it to introduce more realistic case studies and applications in data science, Bayesian statistics, multivariate analysis, and statistical machine learning courses.","PeriodicalId":342642,"journal":{"name":"The American Statistician","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127092154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：