Philip B Stark
Biographic Data
| ID | 6891626 |
|---|---|
| NAME | Philip B Stark |
| GIVEN NAMES | Philip B |
| FAMILY NAME | Stark |
| SIGNATURE | STARK P B |
| AFFILIATIONS | University of California, Berkeley |
| ORCID | 0000-0002-3771-9604 |
| VERIFIED | Yes |
| TOTAL WORKS | 5 |
| TOTAL CITATIONS | 14 |
| AUTHOR COUNT | 4 |
| EDITOR COUNT | 1 |
| FIRST PUBLICATION YEAR | 1994 |
| LATEST PUBLICATION YEAR | 2020 |
| H-INDEX | 1 |
Five ways to ensure that models serve society: A manifesto
Student evaluations of teaching (mostly) do not measure teaching effectiveness
Student evaluations of teaching (SET) are widely used in academic personnel decisions as a measure of teaching effectiveness. We show: SET are biased against female instructors by an amount that is large and statistically significant. The bias affects how students rate even putatively objective aspects of teaching, such as how promptly assignments are graded. The bias varies by discipline and by student gender, among other things. It is not possi…
Sharper p-Values for Stratified Election Audits
Vote-tabulation audits can be used to collect evidence that the set of winners of an election (the outcome) according to the machine count is correct — that it agrees with the outcome that a full hand count of the audit trail would show. The strength of evidence is measured by the p-value of the hypothesis that the machine outcome is wrong. Smaller p-values are stronger evidence that the outcome is correct
Statistical Models and Causal Inference: A Dialogue with the Social Sciences
David A. Freedman presents here a definitive synthesis of his approach to causal inference in the social sciences. He explores the foundations and limitations of statistical modeling, illustrating basic arguments with examples from political science, public policy, law, and epidemiology. Freedman maintains that many new technical approaches to statistical modeling constitute not progress, but regress. Instead, he advocates a 'shoe leather' method…
Patterns of consultation among adolescent minors obtaining an abortion
Interviews with 184 adolescents revealed that all had consulted at least one individual before obtaining an abortion, although one-quarter, primarily the older adolescents, did not consult an adult prior to pregnancy counseling. At both the time of the abortion and one year later, the adolescents perceived their mother and their male partner as the two most important and helpful people in reaching a decision
Statistical Models and Causal Inference: A Dialogue with the Social Sciences
David A. Freedman presents here a definitive synthesis of his approach to causal inference in the social sciences. He explores the foundations and limitations of statistical modeling, illustrating basic arguments with examples from political science, public policy, law, and epidemiology. Freedman maintains that many new technical approaches to statistical modeling constitute not progress, but regress. Instead, he advocates a 'shoe leather' method…
Sharper p-Values for Stratified Election Audits
Vote-tabulation audits can be used to collect evidence that the set of winners of an election (the outcome) according to the machine count is correct — that it agrees with the outcome that a full hand count of the audit trail would show. The strength of evidence is measured by the p-value of the hypothesis that the machine outcome is wrong. Smaller p-values are stronger evidence that the outcome is correct
Patterns of consultation among adolescent minors obtaining an abortion
Interviews with 184 adolescents revealed that all had consulted at least one individual before obtaining an abortion, although one-quarter, primarily the older adolescents, did not consult an adult prior to pregnancy counseling. At both the time of the abortion and one year later, the adolescents perceived their mother and their male partner as the two most important and helpful people in reaching a decision
Statistical Models and Causal Inference: A Dialogue with the Social Sciences
David A. Freedman presents here a definitive synthesis of his approach to causal inference in the social sciences. He explores the foundations and limitations of statistical modeling, illustrating basic arguments with examples from political science, public policy, law, and epidemiology. Freedman maintains that many new technical approaches to statistical modeling constitute not progress, but regress. Instead, he advocates a 'shoe leather' method…
Sharper p-Values for Stratified Election Audits
Vote-tabulation audits can be used to collect evidence that the set of winners of an election (the outcome) according to the machine count is correct — that it agrees with the outcome that a full hand count of the audit trail would show. The strength of evidence is measured by the p-value of the hypothesis that the machine outcome is wrong. Smaller p-values are stronger evidence that the outcome is correct
Student evaluations of teaching (mostly) do not measure teaching effectiveness
Student evaluations of teaching (SET) are widely used in academic personnel decisions as a measure of teaching effectiveness. We show: SET are biased against female instructors by an amount that is large and statistically significant. The bias affects how students rate even putatively objective aspects of teaching, such as how promptly assignments are graded. The bias varies by discipline and by student gender, among other things. It is not possi…
Five ways to ensure that models serve society: A manifesto
Psychology (4 works) · Computer Science (3 works) · Mathematics (3 works) · Medicine (3 works) · Statistics (3 works) · Econometrics (2 works) · Economics (2 works) · Engineering (2 works) · Law (2 works) · Political science (2 works)