Recent uclastat_papers items

Converting Statistical Literacy Resources to Data Science Resources

Tue, 15 Aug 2023 00:00:00 +0000

Data Science is considered a pseudonym for handling big data, machine learning, statistics, computing and mathematics. It is no uncommon for learners to think that all that requires a radical change in their education and even a change in the name of their Statistics major. However, it is not too difficult for a program promoting statistical literacy to at the same time use its resources as data science resources. It takes translation, some acquaintance with what all practitioners of data science usually do, and a willingness to edit the resources to make learners feel that they are immersed in the data science world.

Discussing the Role of the Instructor and the Instructional designer in a Fully Asynchronous Statistics Course

Tue, 6 Jun 2023 00:00:00 +0000

Discussing the Role of the Instructor and the Instructional designer in a Fully Asynchronous Statistics Course

CGM and insulin pump data to introduce classical and machine learning time series analysis concepts to students

Tue, 10 Aug 2021 00:00:00 +0000

The case study engages students and makes them use the tools they know to investigate a complex process. At the same time, they learn basic time-series concepts using only their intro stats tools.

Show Me the Missing Data

Tue, 8 Dec 2020 00:00:00 +0000

Show Me the Missing Data

Women mathematicians in data-centric occupations (with a context)

Thu, 19 Mar 2020 00:00:00 +0000

Texas State University, Women Doing Math and Talk Math 2 Me Joint Statistics Seminar

R&D, Attrition and Multiple Imputation in The Business Research and Development and Innovation Survey (BRDIS)

Wed, 27 Sep 2017 00:00:00 +0000

R&D, Attrition and Multiple Imputation in The Business Research and Development and Innovation Survey (BRDIS)

Sensitivity of Econometric Estimates to Item Non-response Adjustment

Thu, 6 Oct 2016 00:00:00 +0000

Non-response in establishment surveys is a very important problem that can bias results of statistical analysis. The bias can be considerable when the survey data is used to do multivariate analysis that involve several variables with different response rates, which can reduce the effective sample size considerably. Fixing the non-response, however, could potentially cause other econometric problems. This paper uses an operational approach to analyze the sensitivity of results of multivariate analysis to multiple imputation procedures applied to the U.S. Census Bureau/NSF‘s Business Research and Development and Innovation Survey (BRDIS) to address item non-response. Multiple imputation is first applied using data from all survey units and periods for which there is data, presenting scenario 1. A scenario 2 involves separate imputation for units that have participated in the survey only once and those that repeat. Scenario 3 involves no imputation. Sensitivity analysis is done...

Identification Strategies for Models of Innovation,R&D, and Productivity

Wed, 26 Aug 2015 00:00:00 +0000

Identification Strategies for Models of Innovation,R&D, and Productivity

New Methods for Test Reliabiltity based on Structural Equation Modeling

Wed, 3 Jun 2015 00:00:00 +0000

New Methods for Test Reliabiltity based on Structural Equation Modeling

Innovation Output Choices and Characteristics of Firms in the U.S.

Wed, 8 Oct 2014 00:00:00 +0000

This paper uses new business micro data from the Business Research and

Development and Innovation Survey (BRDIS) for the years 2008-2011 to relate

the discrete innovation choices made by U.S. companies to features of the com-

pany that have long been considered to be important correlates of innovation.

We use multinomial logit to model those choices. Bloch and Lopez-Bassols

(2009) used the Community Innovation Surveys (CIS) to classify companies

according dual, technological or output-based innovation constructs. We found

that for each of those constructs of innovation combinations considered, man-

ufacturing and engaging in intellectual property transfer increase the odds

of choosing innovation strategies that involve more than one type of cate-

gories (for example, both goods and services, or both tech and non-tech) and

radical innovations, controlling for rm size, productivity, time and type of

R&D....

Non-technological and Mixed Modes of Innovation in the United States. Evidence from the Business Research and Development and Innovation Survey, 2008-2011

Mon, 22 Sep 2014 00:00:00 +0000

This paper presents a novel empirical study of innovation practices of U.S. com-

panies and their relation to productivity levels using new business micro data from

the Business Research and Development and Innovation Survey (BRDIS) for the years

2008-2011. The paper follows the work of Frenz and Lambert, who use factor analysis

to reduce a set of inputs and outputs of innovation activities into four latent unob-

served innovation modes or practices for OECD countries using Community Innovation

Surveys (CIS). Patterns obtained with BRDIS data are very similar to those found by

those authors in some OECD countries. Companies are grouped according to their

scores across the four factors to see that in large, small and medium companies more

than one mode of innovation practices prevails. The next step in the analysis links dif-

ferent types of innovation practices to levels of productivity using regression analysis.

The...

Transportability from Multiple Environments with Limited Experiments

Wed, 29 Jan 2014 00:00:00 +0000

Transportability from Multiple Environments with Limited Experiments

Linear Models: A Useful \Microscope" for Causal Analysis

Thu, 19 Dec 2013 00:00:00 +0000

Linear Models: A Useful \Microscope" for Causal Analysis

Meta-Transportability of Causal Eects: A Formal Approach

Thu, 19 Dec 2013 00:00:00 +0000

Meta-Transportability of Causal Eects: A Formal Approach

Causal Transportability with Limited Experiments

Thu, 19 Dec 2013 00:00:00 +0000

Causal Transportability with Limited Experiments

The mathematics of causal inference

Mon, 16 Dec 2013 00:00:00 +0000

The mathematics of causal inference

Comment on `Causal inference, probability theory, and graphical insights' (by Stuart G. Baker)

Mon, 16 Dec 2013 00:00:00 +0000

Comment on `Causal inference, probability theory, and graphical insights' (by Stuart G. Baker)

Graphical models for inference with missing data

Mon, 16 Dec 2013 00:00:00 +0000

Graphical models for inference with missing data

Structural counterfactuals: A brief introduction

Mon, 16 Dec 2013 00:00:00 +0000

Structural counterfactuals: A brief introduction

Reflections on Heckman and Pinto's `Causal analysis after Haavelmo'

Mon, 16 Dec 2013 00:00:00 +0000

Reflections on Heckman and Pinto's `Causal analysis after Haavelmo'

Comments on `Surrogate measures and consistent surrogates' (by Tyler VanderWeele)

Mon, 16 Dec 2013 00:00:00 +0000

Comments on `Surrogate measures and consistent surrogates' (by Tyler VanderWeele)

Recoverability and testability of missing data: Introduction and summary of results

Mon, 16 Dec 2013 00:00:00 +0000

Recoverability and testability of missing data: Introduction and summary of results

Reply to Commentary by Imai, Keele, Tingley, and Yamamoto, concerning Causal Mediation Analysis

Mon, 16 Dec 2013 00:00:00 +0000

Reply to Commentary by Imai, Keele, Tingley, and Yamamoto, concerning Causal Mediation Analysis

Determination of the Accuracy of the Observations

Thu, 21 Nov 2013 00:00:00 +0000

Determination of the Accuracy of the Observations

Gauss's Least Squares Conjecture

Thu, 21 Nov 2013 00:00:00 +0000

Gauss's Least Squares Conjecture

Role of Science and Engineering Education and R&D in U.S. State Growth and Innovation

Tue, 1 Oct 2013 00:00:00 +0000

Our research explores the feasibility and challenges of using composite indicators (defined as indicators that combine answers to several questions) based on National Center for Science and Engineering Statistics data and multivariate statistical methods to explain the redistribution of innovation and economic performance across the states in the US. Composite indicators examine a number of relevant factors as a way to capture a more detailed picture of the growth strategy of the states and the diversity of regional economic performance than a single indicator such as the proportion of the labor force in science and engineering or the R&D intensity of the state. Composite indicators address several broad issues characterizing economic performance such as: (a) R&D trends; (b) Science and Engineering composition of the labor force; (c) Science and Engineering education; (d) Sources of R&D funding. Those are items for which there exist appropriate indicators published...

Statistical Hypothesis Generation: Determining the Most Probable Subset

Mon, 20 May 2013 00:00:00 +0000

This article develops an axiomatic theory for statistical hypothesis generation that is based on the ideas of Gauss’ Theoria Motus. At the core of the theory is Bernoulli’s fifth axiom: Between two, the one that seems more probable should always be chosen. Under supplementary assumptions well-known special cases appear, such as regression analysis and principal component analysis. Through rigor, the abstracted theory provides clarity as to how different statistical hypothesis generation methods are interrelated, how they differ, and which method that should be used in a given situation.

The Gauss-Pearson Decomposition and the Link Between Classical Philosophy and Modern Statistics

Mon, 20 May 2013 00:00:00 +0000

This article discusses the mathematical and philosophical premises of Gauss’ and Pearson’s methods for advancing science through empirical observation. At the core is the notion that an observation can be decomposed into an ideal part and a random part, and that the relation between the observation and its two parts is known. The premise, named the Gauss-Pearson decomposition, is formalized in an algebraic framework that is as general as possible. Examples illustrate how the decomposition fits naturally into the body of statistical methodology and how it can facilitate understanding of statistical methods.

Jakob Bernoulli's Theory of Inference

Tue, 30 Apr 2013 00:00:00 +0000

This review of Ars Conjectandi, written on the eve of its 300th anniversary, discusses an aspect of Bernoulli’s magnum opus which hitherto has not received the attention it merits. Bernoulli envisioned a theory for the advancement of science based on the idea of pairing empirical evidence with the then-novel concept of probability. This theory of inference, which he termed “ars conjectandi”, was intended to complement the predominant axiomatic-deductive method where the latter could not be applied successfully. In the 300 years since its publication, Bernoulli’s idea went through ups and downs, but eventually ended up as the deﬁning characteristic of statistical science and a cornerstone of modern science. This review discusses the historical context from which Bernoulli’s idea was conceived, his sources of inspiration, and provides a detailed account of his theory of inference.

Single-Factor Polynomial Component Analysis

Thu, 4 Apr 2013 00:00:00 +0000

Polynomial component and factor analysis are deﬁned. Algorithms, based on multidimensional array approximation methods, to ﬁt a model with a single common factor to observed multivariate cumulants are described and applied to a psychometric example. Software in R is included.

On Statistical Criteria: Theory, History, and Applications

Thu, 4 Apr 2013 00:00:00 +0000

A statistical criterion is a convention by which certain values are considered relatively probable and others considered relatively improbable. Statistical criteria play a crucial role in the theory of statistics and were originally introduced by Daniel Bernoulli and later independently proposed by Karl Pearson and Ronald Fisher. This article discusses the theory and history of statistical criteria, in particular the density criterion and the distance criterion. Applications for statistical hypothesis generation and testing are discussed. The pedagogical value of statistical criteria is illustrated through a concise and simple explanation of statistical classiﬁcation. This article also contains discussions on Gauss’ least squares conjecture and Fisher ’s maximum likelihood.

MAJORIZING A MULTIVARIATE POLYNOMIAL OVER THE UNIT SPHERE, WITH APPLICATIONS

Thu, 4 Apr 2013 00:00:00 +0000

MAJORIZING A MULTIVARIATE POLYNOMIAL OVER THE UNIT SPHERE, WITH APPLICATIONS

Designing a "Cyber-Based" Article Bank to Enhance Statistics Education

Thu, 4 Apr 2013 00:00:00 +0000

Designing a "Cyber-Based" Article Bank to Enhance Statistics Education

Quantile Lower Bounds to Reliability Based on Splits

Thu, 4 Apr 2013 00:00:00 +0000

Extending the theory of lower bounds to reliability based on splits given by Guttman (1945), this paper introduces quantile lower bound coefficients λ_{4(Q )}that refer to cumulative proportions of potential “split-half” coefficients that are below a particular point Q in the distribution of split-halves based on different partitions of variables into two sets. Interesting quantile values are Q=.05,.50,.95,1.00 with λ_4(.05)≤λ_4(.50)≤λ_4(.95)≤λ_4(1.0) . Only λ_4(1.0), Guttman’s maximal λ₄, has previously been considered to be interesting, but in small samples it substantially overestimates population reliability ρ. The three coefficients λ_4(.05), λ_4(.50), and λ_4(.95) provide new lower bounds to reliability. The smallest, λ_4(.05), provides the most protection against capitalizing on chance associations and thus overestimation, λ_4(.50) approximates coefficient...

History of Nonlinear Principal Component Analysis

Thu, 4 Apr 2013 00:00:00 +0000

We discuss several forms of Nonlinear Principal Component Analysis (NLPCA) that have been proposed over the years: Linear PCA with optimal scaling, aspect analysis of correlations, Guttman’s MSA, Logit and Probit PCA of binary data, and Logistic Homogeneity Analysis. They are compared with Multiple Correspondence Analysis (MCA), which we also consider to be a form of NLPCA.

On Inverse Multidimensional Scaling

Thu, 4 Apr 2013 00:00:00 +0000

We discuss Inverse Multidimensional Scaling, clarifying and extending some results of De Leeuw and Groenen [1997]. R code for all computations is also provided.

Multivariate Cumulates in R

Thu, 4 Apr 2013 00:00:00 +0000

We give algorithms and R code to compute all multivariate cumulants up to order p of m variables.

Fertility and Female Spirituality Among Gloucestershire Baptists, 1800-1837: a Quantitative, Local Study

Thu, 4 Apr 2013 00:00:00 +0000

This paper examines quantitatively the comparative importance of female age-at-first marriage and age-at-conversion (adult baptism) among a sample of married female members of the Shortwood Baptist Church, located in Gloucestershire’s Nailsworth valley c. 1800-1837. English historical demographic studies usually decline to treat Protestant nonconformity separately from the Anglican laity; nor do they treat cultural phenomenon like religious affect as a variable in analyzing reproductive behavior, but rather emphasize socio-economic effects. The paper here is based on recent findings from my forthcoming family reconstitution monograph and based on a sample of 100 Baptist families, the profiles of which I have pieced together from an array of fragmentary sources. The data include the standard demographic indices but additionally contain data on the timing of religious conversion, the effects of which may be measured quantitatively through multiple regression analyses. Here female...

KICKING AND SCREAMING ABOUT STATISTICS: HOW SOCCER DATA CAN POTENTIALLY ALLEVIATE STATISTICAL ANXIETY

Wed, 3 Apr 2013 00:00:00 +0000

GAISE and many school curriculum reforms around the world aim to enhance the process of statistical inquiry across the curriculum from a very early age and to make young students statistically literate. Taking advantage of students’ interests outside the classroom to engage them in data gathering about themselves and bringing their data back to the classroom is an alternative that Statistics South Africa initiated with the SOCCER4Stats program described in this paper. We discuss how this program can be used to include more statistics in the Commom Core Standards of the K-12 curriculum. The paper assesses the incidence of soccer interest among youth in the United States.

KICKING AND SCREAMING ABOUT STATISTICS: HOW SOCCER DATA CAN POTENTIALLY ALLEVIATE STATISTICAL ANXIETY

Tue, 26 Mar 2013 00:00:00 +0000

GAISE and many school curriculum reforms around the world aim to enhance the process of statistical inquiry across the curriculum from a very early age and to make young students statistically literate. To improve understanding of the data gathering process, its purposes and benefits to society, taking advantage of students’ interests outside the classroom to engage them in data gathering about themselves and bringing their data back to the classroom is an alternative that teachers could explore further. In this paper, we explore how the SOCCER4Stats innovative activities of Statistics South Africa could be integrated into our school’s path towards statistical literacy. The paper describes the SOCCER4Stats activities for youth and prior use of them in the International Statistical Literacy Project. The paper also assesses the incidence of interest of soccer among youth in the U.S. Discussion of the use of these activities to implement the Common Core Standards in a consistent...

The Rescorla-Wagner Algorithm and Maximum Likelihood Estimation of Causal Parameters

Thu, 17 Nov 2011 00:00:00 +0000

The Rescorla-Wagner Algorithm and Maximum Likelihood Estimation of Causal Parameters

Modeling Causal Learning Using Bayesian Generic Priors on Generative and Preventive Powers

Thu, 17 Nov 2011 00:00:00 +0000

Modeling Causal Learning Using Bayesian Generic Priors on Generative and Preventive Powers

Motion Estimation by Swendsen-Wang Cuts

Thu, 17 Nov 2011 00:00:00 +0000

Motion Estimation by Swendsen-Wang Cuts

Object Perception as Bayesian Inference

Thu, 17 Nov 2011 00:00:00 +0000

Object Perception as Bayesian Inference

The Convergence of Contrastive Divergences

Thu, 17 Nov 2011 00:00:00 +0000

The Convergence of Contrastive Divergences

Efficient Coding of Visual Scenes by Grouping and Segmentation: Theoretical Predictions and Biological Evidence

Thu, 17 Nov 2011 00:00:00 +0000

Efficient Coding of Visual Scenes by Grouping and Segmentation: Theoretical Predictions and Biological Evidence

A Hierarchical Compositional System for Rapid Object Detection

Thu, 17 Nov 2011 00:00:00 +0000

A Hierarchical Compositional System for Rapid Object Detection

The Perceived Motion of a Sterokinetic Stimulus