Data Science - Publications - Faculty & Research

04 Feb 2013
Research & Ideas

Are the Big Four Audit Firms Too Big to Fail?

standards by two experienced accounting professionals who were blind to the study's objectives. Overall, the results fail to support the proposition that the biggest auditors increasingly consider themselves too big to fail. Rather, the View Details

Keywords: by Martha Lagace; Accounting

01 Feb 2002
News

It's academic. (Not!)

business administration (DBA) in accounting and control, marketing, policy and management, or technology and operations management. Another option is a joint program with Harvard University's Graduate School of Arts and Sciences that... View Details

Keywords: Colleges, Universities, and Professional Schools; Educational Services

06 Mar 2012
First Look

First Look: March 6

benefits from racial diversity but that diversity is a liability when society's negative stereotypes about racial minorities' competence inhibit such interactions. We analyze two years of data from 496 retail bank branches to investigate... View Details

Keywords: Sean Silverthorne

Web

2024 Reunion Presentations - Alumni

28, 2024 10:00-11:15 a.m. EDT Right Kind of Wrong: The Science of Failing Well Professor Amy Edmondson (PHDOB 1996) + More Info - Video Recording – Less Info - Video Recording As the push to innovate intensifies in many industries, the... View Details

21 Apr 2015
First Look

First Look: April 21

society as a whole. Publisher's link: http://www.wiley.com/WileyCDA/WileyTitle/productCd-1118646983.html April 2015 Management Science Private Equity and Industry Performance By: Bernstein, Shai, Josh Lerner, Morten Sorensen, and Per... View Details

Keywords: Carmen Nobel & Sean Silverthorne

Research Summary

Overview

The overarching goal of my research is to produce works that are influential and informative to both academics and practitioners in the field of operations management. To accomplish this, I collaborate with industry partners who provide knowledge about their field,... View Details

01 Mar 2018
News

Realizing The Potential Of One Harvard

Administration at HBS. “This program will help established leaders work more effectively with data science teams and understand how to use new data capabilities to drive... View Details

25 Aug 2022
News

Harnessing the Tools of the Digital Age

digitalization and data science and artificial intelligence are deployed as management and business tools,” Lakhani explains. And that means HBS needs to think differently, too. Enter the Digital, Data, and... View Details

Keywords: April White

01 Dec 2018
News

Adapting to Meet Changing Needs

Sciences (SEAS), and the Faculty of Arts and Sciences debuted the Harvard Business Analytics Program (HBAP), an online certificate offering for executives focused on quantitative analysis and View Details

July 2024
Technical Note

Introduction to SQL in Python

By: Michael Parzen and Jo Ellery

This note walks through the basics of SQL and how to use this language in Python via the SQLite package. View Details

Keywords: Analytics and Data Science

Citation

Educators

Purchase

09 Sep 2013
Lessons from the Classroom

Teaching Climate Change to Skeptics

A few years ago, Joseph B. Lassiter traveled to San Francisco, Houston, and New York to hold discussions with Harvard alumni on the topic of business and the environment. Each time, he surveyed the audience about the touchy subject of climate change and how society... View Details

Keywords: by Carmen Nobel

2020
Working Paper

A General Theory of Identification

By: Iavor Bojinov and Guillaume Basse

What does it mean to say that a quantity is identifiable from the data? Statisticians seem to agree on a definition in the context of parametric statistical models — roughly, a parameter θ in a model P = {Pθ : θ ∈ Θ} is identifiable if the mapping θ 7→ Pθ is injective.... View Details

Keywords: Identification; Econometric Models; Analytics and Data Science; Theory

Citation

Read Now

Web

Workshops & Technical Talks - Research Computing Services

Introduction to Data Visualization with ggplot2 Cleaning Data in R Python Python workshop materials (e.g., Python Introduction; Python Web Scraping) from Harvard's Institute for Quantitative Social View Details

May 2020
Article

Scalable Holistic Linear Regression

By: Dimitris Bertsimas and Michael Lingzhi Li

We propose a new scalable algorithm for holistic linear regression building on Bertsimas & King (2016). Specifically, we develop new theory to model significance and multicollinearity as lazy constraints rather than checking the conditions iteratively. The resulting... View Details

Keywords: Mathematical Methods; Analytics and Data Science

Citation

Read Now

November 1996
Article

Localized Autocorrelation Diagnostic Statistic for Sociological Models: Times-series, Network, and Spatial Datasets

By: C. I. Nass and Y. Moon

Keywords: Society; Analytics and Data Science; Information

Citation

Find at Harvard

Web

Flatiron School: Reflections from Summer 2020 - Recruiting

practical skills, statistics fundamentals, and real-life data science project experience. This full-time, intensive eight-week remote learning program was designed for students with basic technical... View Details

January–February 2025
Article

The Double-Edged Sword of Exemplar Similarity

By: Majid Majzoubi, Eric Zhao, Tiona Zuzul and Greg Fisher

We investigate how a firm’s positioning relative to category exemplars shapes security analysts’ evaluations. Using a two-stage model of evaluation (initial screening and subsequent assessment), we propose that exemplar similarity enhances a firm’s recognizability and... View Details

Keywords: Natural Language Processing; Analytics and Data Science; Performance Evaluation

2023
Article

On Minimizing the Impact of Dataset Shifts on Actionable Explanations

By: Anna P. Meyer, Dan Ley, Suraj Srinivas and Himabindu Lakkaraju

The Right to Explanation is an important regulatory principle that allows individuals to request actionable explanations for algorithmic decisions. However, several technical challenges arise when providing such actionable explanations in practice. For instance, models... View Details

Keywords: Mathematical Methods; Analytics and Data Science

Citation

Read Now

23 Jul 2001
Research & Ideas

How Relationships are Building Biotech

context in which to study the missing link. Product development cycles are long, usually between seven and ten years. Millions of dollars are spent before a product ever gets to market. Uncertainty about the viability of a company's View Details

Keywords: by Martha Lagace & Mallory Stark