Abstract: Stata 16 added some new features that could affect how users think of working with Stata. Two of these features are frames and dynamic document extensions. I will show the basics of using frames and explain how they can be exploited for both space and speed. I'll also introduce the new dynamic document features together with some example documents.

Abstract: I present a model and a new Stata routine for estimating a latent (for example, non-observable) network among N units (for example, individuals, companies, countries, etc.) using a set of units' characteristics and without knowing any prior linkage among them. In this approach, the units are represented via a set of indicators measuring a specific concept, such as riskiness, knowledge, etc. A standard regression would be unsuited for estimating the linkages because in this case the number of observations (the characteristics vector) is much smaller than the number of variables (the units). The lasso regression allows one to address high-dimensional settings like this one by allowing for an estimation of a generally sparse matrix of linkages (the network). I will provide a Stata simulation and possibly an application to real data.

Abstract: We introduce the new stpreg command to fit flexible parametric models for the event-probability function, a measure of occurrence of an event of interest over time. The event-probability function is defined as the instantaneous probability of an event at a given time point conditional on having survived until that point. Unlike the hazard function, the event-probability function defines the instantaneous probability of the event. This presentation describes its properties and interpretation along with convenient methods for modeling the possible effect of covariates on it, including flexible proportional-odds models and flexible power-probability models, which allow for censored and truncated observations. We compare these with other popular methods and discuss the theoretical and computational aspects of parameter estimation through a real data example.

Abstract: The original Stata command, xtarsim, simulates dynamic panel-data models with exogenous regressors and i.i.d. errors. I have now extended xtarsim in order to simulate models with various types of endogenous or predetermined regressors. This new version of xtarsim also allows MA(1) errors when regressors are exogenous.

Abstract: Dynamic stochastic general equilibrium (DSGE) models are used in macroeconomics for policy analysis and forecasting. A DSGE model consists of a system of equations (usually a nonlinear system of equations) that is derived from economic theory. This presentation illustrates how to easily solve, fit, and analyze nonlinear DSGE models. I will explore how to obtain policy matrices, transition matrices, and impulse–response functions for nonlinear models.

Abstract: In this presentation, we describe a new Stata command, zonotope, that, by resorting to a geometry-based approach, enables one to provide a measure of productivity that fully accounts for the existing heterogeneity across firms within the same industry. Further, the method that we propose also enables one to assess the extent of multidimensional heterogeneity with applications to production analysis and productivity measurement. Finally, we detail the functioning of Stata to perform the related empirical analysis, and we discuss the main computational issues encountered in its development.

Abstract: The python package facilitates integrating Python with Stata 16 by allowing automatic interprocess communication between the two software packages. Here I present a statistical application implemented in Python and called in Stata for discerning and quantifying power law behavior in empirical data.

Abstract: During the last two decades, a growing interest in understanding what determines the redistributive role of tax-benefit systems has been recorded worldwide. For the case of Italy, the previous analyses were mainly focused on quantifying the contribution of marginal tax rates, deductions, and tax credits to the redistributive capacity of PIT, neglecting the effect on income redistribution of proportional taxes and income sources exempt from taxation such as tax-free cash benefits. The following presentation aims to fill this gap by applying two alternative Gini-based decomposition methodologies (Onrubia et al. 2014; Urban 2014) to the Italian tax-benefit system's redistributive power over the period 2005–2018. The contribution of each tax-benefit instrument is quantified for several baseline policy scenarios that diverge from each other for being representative of different degrees of extension of the tax-benefit system under study.

Abstract: Older people are often affected by several comorbid conditions and by an increasing risk of death that rises with aging. Previous studies examining the association of cancer with dementia in older adults have usually used standard approaches without accounting for the competing risk of mortality. However, ignoring mortality may not provide valid estimates of risk of dementia, because cancer is strongly associated with the competing risk of death. This study considers people over 72 years old from two Swedish population-based longitudinal studies: The Kungsholmen Project (KP) and the Swedish National Study on Aging and Care project conducted in the Kungsholmen district of the city of Stockholm (SNAC-K project). The aim of the study is to analyze the association between cancer and the onset of dementia in the considered older population. The competing-risk methodology is used to illustrate the appropriate statistical methods for competing risks, their correct application, and interpretation of the results, having death as the competing event.

Abstract: In this presentation, I will attempt to demystify the field of machine learning and compare it with traditional statistical approaches in economics and social sciences. I discuss relative strengths and weaknesses and how machine learning can facilitate causal inference. This presentation serves as a preamble to the one-day workshop that will happen the following day.

Abstract: Stata developers present will carefully and cautiously consider wishes and grumbles from Stata users in the audience. Questions, and possibly answers, may concern reports of present bugs and limitations or requests for new features in future releases of the software.