Session: New estimators | |
9:10–9:25 | Jackknife methods for improved cluster–robust inference
Abstract:
Inferential problems have long been known to exist in finite
samples when using the conventional cluster–robust variance
estimator for ordinary least squares.
Many improvements to inference have been suggested, including
bootstrap and jackknife methods, in addition to alternative
standard errors and degrees of freedom. This presentation will
discuss how to use jackknife methods in Stata for improved
inference. We detail the new Stata ado-command,
summclust, which offers both improved inferences and
diagnostic tools for assessing when conventional errors can be
problematic. We also discuss jackknife methods for two different
situations: linear models with multiway clustering and nonlinear
models with one-way clustering. These alternative methods
considerably improve upon the finite-sample overrejection
problems.
Additional information:
Matthew Webb
Carleton University
|
9:25–9:45 | Identify latent group structures in panel data: The classifylasso command
Abstract:
This presentation introduces a new command,
classifylasso, that implements the classifier-lasso
method to simultaneously identify and estimate unobserved
parameter heterogeneity in panel-data models using penalized
techniques.
I document the functionality of this command, including
penalized least-squares estimation of group-specific
coefficients and classification of unknown group membership
under a certain number of groups; two lasso-type estimators with
robust standard errors, namely classifier-lasso and postlasso;
and determination of the number of groups based on a BIC-type
information criterion. I further introduce postestimation
commands to display and visualize the estimation results.
Reference: Su L., Z. Shi, and P. C. B. Phillips. 2016. Identifying latent structures in panel data. Econometrica 84: 2215–2264.
Additional information:
Yiru Wang
University of Pittsburgh
|
9:45–10:05 | Difference in differences with unpoolable data
Abstract:
In this presentation, we describe a new Stata package called
unpooled-DID.
This procedure is useful when data from different jurisdictions
cannot be combined for analysis because of legal restrictions or
confidentiality laws. Through Monte Carlo simulation studies,
this procedure has been shown to be equivalent to a variation of
the conventional DID model when data are poolable. The canonical
DID implicitly assumes that the data for the treated group and
the control group can be combined. The combined dataset is used
to generate a post and treat dummy variables, which are then
interacted to estimate the ATT. We also require “poolable”
data to verify parallel trends, a key assumption of DID.
As a result, conducting DID analysis is nearly impossible using traditional methods when datasets are not combinable. The problem is pronounced for health economists, for whom legal restrictions in sharing administrative data can constrain DID analysis to learn of health systems. This package will make it easier for researchers who work with “unpoolable” data to conduct DID analysis. Furthermore, the package will also provide researchers with a plausibility check for pretreatment trends.
Contributor:
Matthew Webb
Carleton University
Additional information:
Sunny Karim
Carleton University
|
Session: StataCorp presentation | |
10:45–11:45 | Fitting interval-censored Cox model with time-varying covariates in Stata
Abstract:
In survival analysis, interval-censored event-time data occur
when the event of interest is not always observed exactly but is
known to lie within some time interval.
These types of data arise in many areas, including medical,
epidemiological, economic, financial, and sociological studies.
Ignoring interval-censoring will often lead to biased estimates.
A semiparametric Cox proportional hazards regression model is used routinely to analyze uncensored and right-censored event-time data. It is also appealing for interval-censored data because it does not require any parametric assumptions about the baseline hazard function. Also, under the proportional-hazards assumption, the hazard ratios are constant over time. Semiparametric estimation of interval-censored event-time data is challenging because none of the event times are observed exactly. Thus, “semiparametric” modeling of these data often resorted to using spline methods or piecewise-exponential models for the baseline hazard function. Genuine semiparametric modeling of interval-censored event-time data was not available until recent methodological advances, which are implemented in the stintcox command. In this presentation, I will describe two basic formats for interval-censored data and will demonstrate how to fit the Cox model to these data using Stata's stintcox command. I will then demonstrate how to create time-varying covariates (TVCs) automatically using the stintcox command and how to use TVCs to test the proportional-hazards assumption. Last but not least, I will show how to incorporate TVCs in your predictions and plots of survivor and other functions.
Additional information:
Xiao Yang
StataCorp
|
Session: StataCorp presentation | |
1:15–2:15 | New meta-analysis (MA) features in Stata 18: MA for prevalence and multilevel MA
Abstract:
Meta-analysis is a statistical technique for combining the
results from several similar studies.
Stata’s meta command offers full support for
meta-analysis—from computing various effect sizes and
producing a basic meta-analytic summary to performing tests for
small-study effects. Stata 18 introduced support for
meta-analysis of one proportion, meaning you can now use
standard meta-analysis features such as forest plots and funnel
plots with one-sample binary data. Stata 18 also introduced two
new commands, meta meregress and meta multilevel,
for performing multilevel meta-analysis. These commands allow
you to analyze results from multiple studies in which the
reported effect sizes are nested within higher-level groupings
such as regions or schools. By properly accounting for the
dependence among the effect sizes, we can produce more accurate
inference.
In this presentation, I will demonstrate how to perform meta-analysis of proportions and multilevel meta-analysis in Stata 18. I will provide a brief introduction to meta-analysis and discuss effect sizes and confidence intervals relevant to prevalence data. For multilevel data, we’ll see how to include random intercepts and coefficients at different levels of hierarchy, perform sensitivity analysis, and assess the variability among the effect sizes at different levels of the hierarchy.
Additional information:
Gabriela Ortiz
StataCorp
|
Session: Applications | |
2:30–2:50 | The effects of women's bargaining power on contraceptive use: Evidence from Zambia
Abstract:
This presentation aims to examine the relationship between
women's household bargaining power and their adoption of modern
contraception in Zambia, using the 2018 DHS survey data.
Relying on direct measures of women's bargaining power (as
indicated by the preexisting literature), which include a
woman's ability to make decisions about her own healthcare,
large household purchases, small household purchases, visits to
her family and friends, and contraceptive use, as well as
measures of her autonomous financial capability. This measure of
financial capability is then interacted with a woman's ability
to make healthcare decisions solely or jointly with her husband
to shed additional light on the influence that bargaining power
has on the uptake of modern contraceptive methods. Having both
financial capability and the sole ability to make healthcare
decisions for herself increases a woman's probability of
adopting modern contraceptive methods by 87%, and having sole
responsibility over contraceptive decisions increases it by
approximately 56%.
Using lasso as a robustness check, it is determined that the model is relatively well specified and has quite a large amount of explanatory power. Finally, the presentation uses a comparative analysis of spousal discord to demonstrate how spouses' often conflicting reports of intrahousehold decision making can impact key outcomes for women and finds that both spousal accord and the scenario in which the woman takes power are most effective for the adoption of modern contraception (leading to a 16.7% and 14.6% increase in the probability of using modern contraception, respectively). Overall, the study finds that several aspects of a woman's household decision making and financial freedom, as well as the degree and directionality of spousal discord within her household impact her probability of adopting modern contraceptive methods.
Additional information:
Tamara Pressman
McGill University
|
3:10–3:30 | Behavioral drivers of intentions to use alternatives to cash: An African survey
Abstract:
Seeking to identify frictions to the possible implementation of
CBDCs, I explore potential behavioral drivers for people to use
cash or alternative payment methods in retail transactions.
I conducted an online survey targeting adults in sub-Saharan
Africa, a continent characterized by lower levels of banking
penetration, intensive use of cash, and popularity of mobile
money accounts to overcome financial exclusion. I obtained
robust evidence that the affect heuristic is the only relevant
behavioral trait against the use of cash and of credit cards.
This adds to criticisms of behavioral finance for frequently
neglecting emotional drivers. Cognitive traits, such as mental
accounting, fungibility bias, and habit do not mediate in the
overall preference but in which contexts people prefer to use
one payment method or another.
I find no behavioral drivers against the use of electronic payments but robust evidence that higher per capita income reduces their preference. All results are robust to alternative econometric specifications: multinomial logistic, ordered logistic, and logit regressions. My research provides a clear message for policy making: authorities might better favor ensuring that a wide variety of payment alternatives are available for people to use, including cash, and let them choose.
Additional information:
David Peón
Universidade da Coruña
|
3:30–3:50 | The market for Stata users: Evidence from online job postings
Abstract:
Using a sample of 110,284 unique online job postings during the
hiring period 2010–2022 that mentioned Stata as a requisite or
recommended skill, the market for Stata users is examined.
Primary focus is given to what other job skills are necessary
for Stata users to become hired, be they software skills, soft
skills, or general skills. Analyses of these jobs’ wages,
required education levels, requisite job experience, titles and
industries, and geography are also presented, as are trends in
all of these findings. A separate sample of 164,973 worker
profiles that mention Stata as a skill is then used to compare
the demand and supply sides of this labor market. Results are
meant to inform Stata users as to what they can expect on the
job market, and perhaps most importantly, what additional skills
they should gain to maximize their labor market outcomes or
stand out among others competing for the same jobs.
Additional information:
Wes Routon
Georgia Gwinnett College
|
3:50–4:20 |
Open panel discussion with Stata developers
Contribute to the Stata community by sharing your feedback with StataCorp's developers. From feature improvements to bug fixes and new ways to analyze data, we want to hear how Stata can be made better for our users.
|
6:00 | Optional dinner at Leña restaurant |
Xiao Yang is a Principal Statistician and Software Developer at StataCorp LLC. Xiao has been developing Stata since 2012. Her interests include survival analysis, longitudinal analysis, Bayesian analysis, and multilevel mixed-effects models. She has a bachelor's degree in computer science from the University of Electronic Science and Technology of China, a master's degree in mathematics from Southeast Missouri State University, and a master's degree in statistics from the University of Iowa.
Gabriela Ortiz is a Senior Applied Econometrician at StataCorp. She holds a bachelor's degree in psychology from the University of California, Davis, and a master's degree in economics from California State University, Long Beach. Gabriela is a primary author of Stata's reporting manual and has contributed to the development of each of the reporting features. She also developed and regularly teaches Stata's introductory webinars.
Open to users of all disciplines and experience levels, Stata Conferences bring together a unique mix of experts and professionals. Develop a well-established network within the Stata Community.
Hear from Stata experts in the top of their fields, as well as from Stata's own researchers and developers. Gain valuable insights, discover new commands, learn best practices, and improve your knowledge of Stata.
Presentation topics have included new community-contributed commands, methods and resources for teaching with Stata, new approaches for using Stata together with other software, and much more.
The scientific committee organizes the conference program. They encourage submissions from both new and experienced Stata users from a variety of backgrounds to develop an exciting, diverse, and informative program.
Anson Ho is an assistant professor in the Real Estate Management Department at Toronto Metropolitan University. His primary research interests include consumer finance, housing, and macroeconomics. Prior to joining TMU in 2020, Anson was a senior economist in the Financial Stability Department at the Bank of Canada (2016–2020) and an assistant professor at Kansas State University (2011–2016). Anson received his PhD. in economics from the University of Iowa in 2011.
Dr. Malhotra heads the data analysis team at the Birthplace Lab at the faculty of medicine, University of British Columbia, where her recent research projects focus on inequities in maternity care in the United States and Canada. Dr. Malhotra is an interdisciplinary researcher focusing on global health, gender, and development. Dr. Malhotra earned her doctorate at the University of Maryland, College Park.
Murtaza Haider is a professor of Data Science and Real Estate Management at Toronto Metropolitan University. He also serves as the research director of the Urban Analytics Institute. Professor Haider holds an adjunct professorship of engineering at McGill University. In addition, he is a director of Regionomics Inc., a boutique consulting firm specializing in the economics of cities and regions, and holds a master's in transport engineering and a PhD in civil engineering from the University of Toronto.