Cited by 4,316Statistical Methods and Bayesian InferenceStatistical Methods in EpidemiologySurvey Sampling and Estimation Techniques

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Logistic Regression in Rare Events Data

Open access

King, Gary, Zeng, Langche·2001·Political Analysis

DOI 10.1093/oxfordjournals.pan.a004868

Open this paper in CoChat — free account Open PDF

Abstract

We study rare events data, binary dependent variables with dozens to thousands of times fewer ones (events, such as wars, vetoes, cases of political activism, or epidemiological infections) than zeros (“nonevents”). In many literatures, these variables have proven difficult to explain and predict, a problem that seems to have at least two sources. First, popular statistical procedures, such as logistic regression, can sharply underestimate the probability of rare events. We recommend corrections that outperform existing methods and change the estimates of absolute and relative risks by as much as some estimated effects reported in the literature. Second, commonly used data collection strategies are grossly inefficient for rare events data. The fear of collecting data with too few events has led to data collections with huge numbers of observations but relatively few, and poorly measured, explanatory variables, such as in international conflict data with more than a quarter-million dyads, only a few of which are at war. As it turns out, more efficient sampling designs exist for making valid inferences, such as sampling all available events (e.g., wars) and a tiny fraction of nonevents (peace). This enables scholars to save as much as 99% of their (nonfixed) data collection costs or to collect much more meaningful explanatory variables. We provide methods that link these two results, enabling both types of corrections to work simultaneously, and software that implements the methods developed.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

Integrity signals

Registry

Crossref · 10.1093/oxfordjournals.pan.a004868

Cites

0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Designing Social Inquiry: Scientific Inference in Qualitative Research
King, G., Keohane, R. O., & Verba, S. (1994) · Princeton University Press · doi:10.1515/9781400821211 · Cited by 7,225
Self-citation

Show all 0 references

Research works printed but not linked: 47

Verba, 1995, Voice and Equality: Civic Voluntarism in American Politics, 10.2307/j.ctv1pnc1k7 · DOI
10.1007/978-1-4612-4024-2 · DOI
Smith, 1998, Bayesian Statistics
10.1111/0020-8833.00113 · DOI
10.2307/2585396 · DOI
Scott, 1986, Fitting Logistic Models Under Case-Control or Choice Based Sampling, Journal of the Royal Statistical Society, B, 48, 170, 10.1111/j.2517-6161.1986.tb01400.x · DOI
10.1017/CBO9780511812651 · DOI
10.1093/biomet/66.3.403 · DOI
10.1002/sim.4780140806 · DOI
10.2307/2938740 · DOI
Manski, 1981, Structural Analysis of Discrete Data with Econometric Applications
10.2307/1914121 · DOI · Paper page
Manski, 1999, Nonlinear Statistical Inference: Essays in Honor of Takeshi Amemiya
10.1016/0304-4076(94)01698-4 · DOI
10.1007/978-1-4899-3242-6 · DOI · Paper page
10.2307/2669316 · DOI · Paper page
King Gary , and Zeng Langche . 2000b. “Explaining Rare Events in International Relations.” International Organization (in press).
King Gary , and Zeng Langche . 2000a. “Inference in Case-Control Studies with Limited Auxilliary Information” (in press). (Preprint at http://Gking.harvard.edu.)
10.2307/2951544 · DOI
10.1080/01621459.1985.10478165 · DOI
10.1017/CBO9780511521713 · DOI
10.1007/978-1-4899-4467-2 · DOI
10.1093/biomet/80.1.27 · DOI · Paper page
10.2307/1912755 · DOI
Bueno de Mesquita, 1992, War and Reason: Domestic and International Imperatives, 10.2307/j.ctt1bh4dhm · DOI
Bueno de Mesquita, 1981, The War Trap
10.1080/01621459.1996.10476660 · DOI
10.2307/1913609 · DOI
10.1214/ss/1177011454 · DOI
Breslow, 1980, Statistical Methods in Cancer Research
10.1002/sim.4780020108 · DOI
Rothman, 1998, Modern Epidemiology
Cosslett, 1981b, Structural Analysis of Discrete Data with Econometric Applications
Rosenau, 1976, In Search of Global Patterns
10.1017/CBO9780511583483 · DOI
Levy, 1989, Behavior, Society, and Nuclear War, 1, 2120
McCullagh, 1987, Tensor Methods in Statistics
Mehta, 1997, Exact Inference for Categorical Data
10.1177/0049124189017003003 · DOI
10.2307/1957394 · DOI
10.1017/S0003055400220078 · DOI
Greene, 1993, Econometric Analysis
10.1016/0378-3758(93)E0091-T · DOI
10.1177/0193841X8801200301 · DOI
Lancaster, 1996b, Efficient Estimation and Stratified Sampling, Journal of Econometrics, 74, 289, 10.1016/0304-4076(95)01756-9 · DOI
10.1002/(SICI)1097-0258(19970315)16:5<545::AID-SIM421>3.0.CO;2-3 · DOI
Cordeiro, 1991, Bias Correction in Generalized Linear Models, Journal of the Royal Statistical Society, B, 53, 629, 10.1111/j.2517-6161.1991.tb01852.x · DOI

Sorted by citations

Items 401–500 of 1,016

Bank Deregulation and Stock Price Crash RiskPreprint
Dang, V., Lee, E., Liu, Y., & Zeng, C. (2020) · Social Science Research Network · doi:10.2139/ssrn.3537382 · Cited by 49
Coercive Control and Physical Violence in Older Adults
Policastro, C., & Finn, M. (2017) · Journal of Interpersonal Violence · doi:10.1177/0886260515585545 · Cited by 49
“To address this issue, we ran supplementary analyses utilizing a rare events logit model (King & Zeng, 2001).”
Method
Union Density and Political Strikes
Lindvall, J. (2013) · World Politics · doi:10.1017/s0043887113000142 · Cited by 57
“…strikes are most frequent in countries with intermediate levels of union density, since trade unions in these countries are strong enough to organize effective protests but not strong enough to ensure that governments will 36 Tomz, King, and Zeng 1999; King and Zeng 1999; King and Zeng 2001.”
Background
Issue linkage and international cooperation: An empirical investigation
Poast, P. (2013) · Conflict Management and Peace Science · doi:10.1177/0738894213484030 · Cited by 72
“This dataset should be estimated using a rare events logit model, which, by and large, is a logit model that applies a post-estimation correction to the constant term (King and Zeng, 2001).”
Method
Testing of Deep Reinforcement Learning Agents with Surrogate Models
Biagiola, M., & Tonella, P. (2023) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3631970 · Cited by 45
“Such formula, gives a higher weight to the underrepresented classes [32].”
Background
At odds with Europe: explaining populist radical right voting in Central and Eastern Europe
Santana, A., Zagórski, P., & Rama, J. (2020) · East European Politics · doi:10.1080/21599165.2020.1737523 · Cited by 60
“It is well known that estimations with few events are unreliable (Williams 2019; Leitgöb 2013; King and Zeng 2001; Firth 1993).”
Background
Network Effects in Blau Space: Imputing Social Context from Survey Data
McPherson, M., & Smith, J. A. (2019) · Socius Sociological Research for a Dynamic World · doi:10.1177/2378023119868591 · Cited by 71
“Cases that possess the given condition are combined with cases collected independently that do not possess the condition, and logistic regression analysis proceeds as though the entire data set were sampled under the same regime (Allison 1999; King and Zeng 2001).”
Background
Predictive modeling in urgent care: a comparative study of machine learning approaches
Tang, F., Xiao, C., Wang, F., & Zhou, J. (2018) · JAMIA Open · doi:10.1093/jamiaopen/ooy011 · Cited by 53
Reversal of Glaucoma Hemifield Test Results and Visual Field Features in Glaucoma
Wang, M.-Y., Pasquale, L., Shen, L. Q., Boland, M. V., Wellik, S. R., Moraes, C. G. D., Myers, J., Wang, H., Baniasadi, N., Li, D., et al. (2017) · Ophthalmology (Rochester, Minn.) · doi:10.1016/j.ophtha.2017.09.021 · Cited by 48
Exit, Tweets, and LoyaltyPreprint
Gans, J., Goldfarb, A., & Lederman, M. (2017) · American Economic Journal: Microeconomics · doi:10.2139/ssrn.2889388 · Cited by 48
The impact of pre-selected variance inflation factor thresholds on the stability and predictive power of logistic regression models in credit scoring
de Jongh, P. D., de Jongh, E. D., Pienaar, M., Gordon-Grant, H., Oberholzer, M., & Santana, L. (2015) · doi:10.5784/31-1-162 · Cited by 48
“For more discussion on this and related topics see King & Zeng [12].”
Background
Factors associated with Spanish older people’s membership in political organizations: the role of active aging activities
Serrat, R., Villar, F., & Celdrán, M. (2015) · European Journal of Ageing · doi:10.1007/s10433-015-0341-4 · Cited by 48
“…organization could be considered a rare event (with a rate as low as 7 % in our sample), we tested the robustness of the findings by following the suggestions described in King and Zeng (2001) and using King’s software for treating rare events in logistic regression, implemented in Stata 12.”
Method
Does cybersecurity risk stifle corporate innovation activities?
Wang, J., Ho, C. Y., & Shan, Y. G. (2023) · International Review of Financial Analysis · doi:10.1016/j.irfa.2023.103028 · Cited by 47
The importance of rare events and other outliers in global strategy research
Beamish, P., & Hasse, V. C. (2022) · Global Strategy Journal · doi:10.1002/gsj.1437 · Cited by 47
Obscuring Equity in Dual Language Bilingual Education: A Longitudinal Study of Emergent Bilingual Achievement, Course Placements, and Grades
Morita‐Mullaney, T., Renn, J., & Chiu, M. M. (2020) · TESOL Quarterly · doi:10.1002/tesq.592 · Cited by 49
Deviations from aspirational target levels and environmental and safety performance: Implications for operations managers acting irresponsibly
Wiengarten, F., Fan, D., Pagell, M. D., & Lo, C. K. Y. (2019) · Journal of Operations Management · doi:10.1002/joom.1032 · Cited by 52
Credible Commitments? Explaining IGO Suspensions to Sanction Political Backsliding
von Borzyskowski, I., & Vabulas, F. (2019) · International Studies Quarterly · doi:10.1093/isq/sqy051 · Cited by 47
Threatened grassland butterflies as indicators of microclimatic niches along an elevational gradient – Implications for conservation in times of climate change
Stuhldreher, G., & Fartmann, T. (2018) · Ecological Indicators · doi:10.1016/j.ecolind.2018.06.043 · Cited by 47
Factors related to Chinese older adults’ suicidal thoughts and attempts
Hong, L., Xu, L., & Chi, I. (2015) · Aging & Mental Health · doi:10.1080/13607863.2015.1037242 · Cited by 48
“We used a logistic regression model based on Firth’s penalized likelihood estimation to minimize the impact of low-frequency events on parameter estimates (King & Zeng, 2001).”
BackgroundMethodResultInfluential
The Tenuous Connections Involving Mass Shootings, Mental Illness, and Gun Laws
Fox, J. A., & Fridel, E. E. (2016) · doi:10.1089/vio.2015.0054 · Cited by 47
“…of 72 public mass shootings, with 4 Although there are sampling strategies and statistical models that can resolve some of the limitations inherent in researching rare outcomes (see King and Zeng, 2001), these do not necessarily lend themselves to early detection within the general population.”
Director Histories and the Pattern of AcquisitionsPreprint
Rousseau, P. L., & Stroup, C. (2015) · SSRN Electronic Journal · doi:10.2139/ssrn.1918454 · Cited by 47
“16These estimates understate the e¤ects of historical interlocks because binary choice models such as the logit are downward-biased in rare-events contexts such as the present application (see, for example, King and Zeng, (2001)).”
Background
Why do households invest in sanitation in rural Benin: Health, wealth, or prestige?
Gross, E., & Günther, I. (2014) · Water Resources Research · doi:10.1002/2014wr015899 · Cited by 47
“As the occurrence of zeros for the latrine ownership variable is very high (90% open defecators, 10% latrine users), it is also possible to estimate a rare-events model [King and Zeng, 1999].”
Background
The profile of gender equality issue attention in Western Europe
Annesley, C., Engeli, I., & Gains, F. (2015) · European Journal of Political Research · doi:10.1111/1475-6765.12095 · Cited by 47
Analysis of contributory factors of fatal pedestrian crashes by mixed logit model and association rules
Riccardi, M. R., Mauriello, F., Scarano, A., & Montella, A. (2022) · International Journal of Injury Control and Safety Promotion · doi:10.1080/17457300.2022.2116647 · Cited by 46
“The model was developed using the weighted maximum likelihood (Field & Smith, 1994; King & Zeng, 2001), which weights the data to balance the response variable.”
Method
Large-Scale Landslide Susceptibility Mapping Using an Integrated Machine Learning Model: A Case Study in the Lvliang Mountains of China
Xing, Y., Yue, J., Guo, Z., Chen, Y., Hu, J., & Travé, A. (2021) · Frontiers in Earth Science · doi:10.3389/feart.2021.722491 · Cited by 46
“Studies have shown that, in susceptibility assessment, the nonevent (nonlandslide points) sample size can be 2 – 10 times greater than the events (landslide points) (King and Zeng, 2001; Nam and Wang, 2019).”
Background
An Apocalypse Foretold: Climate Shocks and Sovereign Defaults
Cevik, S., & Jalles, J. (2020) · Open Economies Review · doi:10.1007/s11079-021-09624-8 · Cited by 46
“Alternatively, we use the bias correction method—the relogit estimator—proposed by King and Zeng (2001).(12) The relogit estimator for dichotomous dependent variables provides a lower mean square error in the presence of rare events and can be defined as follows:”
Influential
Safety effectiveness and performance of lane support systems for driving assistance and automation - Experimental test and logistic regression for rare events.
Cafiso, S., & Pappalardo, G. (2020) · Accident Analysis and Prevention · doi:10.1016/j.aap.2020.105791 · Cited by 46
Public safety assessment
DeMichele, M. T., Baumgartner, P., Wenger, M., Barrick, K., & Comfort, M. L. (2020) · Criminology & Public Policy · doi:10.1111/1745-9133.12481 · Cited by 44
A time-dependent model of generator failures and recoveries captures correlated events and quantifies temperature dependence
Murphy, S., Sowell, F., & Apt, J. (2019) · Applied Energy · doi:10.1016/j.apenergy.2019.113513 · Cited by 46
“Unbalanced data makes accurately estimating transition probabilities more difficult [34].”
Background
Informally Governing Information: How Criminal Rivalry Leads to Violence against the Press in Mexico
Holland, B., & Ríos, V. (2017) · Journal of Conflict Resolution · doi:10.1177/0022002715600756 · Cited by 46
How project description length and expected duration affect bidding and project success in crowdsourcing software development
Gefen, D., Gefen, G., & Carmel, E. (2016) · Journal of Systems and Software · doi:10.1016/j.jss.2015.03.039 · Cited by 46
A Review on Logistic Regression in Medical Research
Panda, N. (2022) · National Journal of Community Medicine · doi:10.55489/njcm.134202222 · Cited by 45
“=e ) .............................(5) Now solving equation (5) we can find out our required equation i.”
Background
Bank efficiency and failure prediction: a nonparametric and dynamic model based on data envelopment analysis
Li, Z., Feng, C., & Tang, Y. (2022) · Annals of Operations Research · doi:10.1007/s10479-022-04597-4 · Cited by 52
“We use both logistic regression and rare event logistic regression to determine the inputs/outputs, the latter of these models having been widely used in failure event studies (Eling & Jia, 2018; King & Zeng, 2001).”
Method
Effective network intrusion detection by addressing class imbalance with deep neural networks multimedia tools and applications
Rani, M., & Gagandeep, G. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11747-6 · Cited by 56
“In this work, weights are assigned to the classes using heuristic measures [36], which is proven to be helpful in solving many classification problems effectively in recent times [41], [58], [47].”
Method
Unimodal regularisation based on beta distribution for deep ordinal regression
Vargas, V. M., Gutiérrez, P. A., & Hervás‐Martínez, C. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108310 · Cited by 44
“Since datasets are imbalanced, the loss function is weighted based on the a priori probabilities of the classes (considering the number of instances of each class in the training set) following the method described in [38] .”
Method
Penerapan Metode Machine Learning dalam Klasifikasi Risiko Kejadian Berat Badan Lahir Rendah di Indonesia
Sihombing, P., & Yuliati, I. F. (2021) · Matrik · doi:10.30812/matrik.v20i2.1174 · Cited by 45
“Referensi [6] menyatakan bahwa ketika metode klasifikasi digunakan pada kasus imbalanced data, maka pengklasifikasian cenderung menihilkan peluang dari kelas minoritas karena nilai prediksi akan cenderung pada kategori yang mayoritas, sehingga tingkat ketepatan klasifikasi yang dihasilkan menjadi kurang baik.”
Background
Active backers, product commercialisation and product quality after a crowdfunding campaign: A comparison between first-time and repeated entrepreneurs
Butticè, V., & Noonan, D. S. (2019) · International Small Business Journal · doi:10.1177/0266242619883984 · Cited by 45
“Finally, to consider a possible bias due to the use of the delta method to approximate the probability distribution for a function of an asymptotically normal statistic to compute confidence intervals (King and Zeng, 2001), we follow the simulation-based procedure”
Method
Success in books: predicting book sales before publication
Wang, X.-D., Yucesoy, B., Varol, O., Eliassi-Rad, T., & Barabási, A. (2019) · EPJ Data Science · doi:10.1140/epjds/s13688-019-0208-6 · Cited by 45
Portable Innovation, Policy Wormholes, and Innovation Diffusion
Yi, H., & Chen, W. (2019) · Public Administration Review · doi:10.1111/puar.13090 · Cited by 51
Using a machine learning approach to determine the space group of a structure from the atomic pair distribution function
Liu, C.-H., Tao, Y., Hsu, D., Du, Q., & Billinge, S. J. L. (2019) · Acta Crystallographica Section A Foundations and Advances · doi:10.1107/s2053273319005606 · Cited by 81
“To mitigate the effect of the unbalanced data set, loss from each training sample is multiplied by a class weight (King & Zeng, 2001) which is the inverse of the ratio between the number of data entries from the same spacegroup label in the training sample and the size of the entire training set.”
Method
The Public Safety Assessment: A Re-Validation and Assessment of Predictive Utility and Differential Prediction by Race and Gender in KentuckyPreprint
DeMichele, M. T., Baumgartner, P., Wenger, M., Barrick, K., Comfort, M. L., & Misra, S. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3168452 · Cited by 46
“King and Zeng (2001) provide a critique of estimating logistic regression models with rare events and suggest that, despite large sample sizes, when event occurrence is lower than 5 percent there could be instability in the models. compared to white defendants in Kentucky.”
Background
The Negotiation Calculus: Why Parties to Civil Conflict Refuse to Talk
Kaplow, J. M. (2015) · International Studies Quarterly · doi:10.1093/isq/sqv005 · Cited by 46
Not all dictators are equal
von Soest, C., & Wahman, M. (2014) · Journal of Peace Research · doi:10.1177/0022343314551081 · Cited by 85
“Due to the relative rarity of democratic sanction onset we have also run rare-event logistic models as robustness check (King & Zeng, 2001).”
Sensitivity Analyses for Sparse-Data Problems—Using Weakly Informative Bayesian Priors
Hamra, G., Maclehose, R., & Cole, S. (2013) · Epidemiology · doi:10.1097/ede.0b013e318280db1d · Cited by 45
Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications
Kwon, Y. D., Chauhan, J., Kumar, A., Hui, P., & Mascolo, C. (2021) · IFIP International Information Security Conference · doi:10.1145/3453142.3491285 · Cited by 44
“As in [21], we applied a weighted loss to all evaluated methods by estimating the inverse class distribution which gives more importance to the loss of a class with fewer samples.”
Method
“I'll try the veggie burger”: Increasing purchases of sustainable foods with information about sustainability and taste
Piester, H. E., DeRieux, C. M., Tucker, J., Buttrick, N. R., Galloway, J. N., & Wilson, T. D. (2020) · Appetite · doi:10.1016/j.appet.2020.104842 · Cited by 54
RT-BENE: A Dataset and Baselines for Real-Time Blink Estimation in Natural Environments
Cortacero, K., Fischer, T., & Demiris, Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00147 · Cited by 44
“Therefore, we make use of oversampling [24, 27], where the weights of open eye samples is N total / (2 N open ) and accordingly for blink samples N total / (2 N closed ) .”
Method
Beyond coups: terrorism and military involvement in politics
Bove, V., Rivera, M., & Ruffa, C. (2019) · European Journal of International Relations · doi:10.1177/1354066119866499 · Cited by 44
Fertile Ground for Conflict
Berman, N., Couttenier, M., & Soubeyran, R. (2017) · Journal of the European Economic Association · doi:10.1093/jeea/jvz068 · Cited by 44
Political militaries in popular uprisings: A comparative perspective on the Arab Spring
Koehler, K. (2017) · International Political Science Review · doi:10.1177/0192512116639746 · Cited by 44
“Since military insubordination is a relatively rare occurrence, I estimate rare events logit models (King and Zeng, 2001) to test various aspects of my theory.”
Background
The last shall be the first: Competencies, equity and the power of resilience in the Italian school system
Alivernini, F., Manganelli, S., & Lucidi, F. (2016) · Learning and Individual Differences · doi:10.1016/j.lindif.2016.08.010 · Cited by 44
Temporal Displacement of Environmental Crime : Evidence from Marine Oil Pollution
Vollaard, B. (2015) · doi:10.2139/ssrn.2633964 · Cited by 44
“Lagring et al. (2012) correlate time-series data on possible oil spills from the Belgian Coast Guard with regulatory changes, and their findings suggest a positive impact, but the influence of other factors cannot be excluded.”
Climate shocks, dynastic cycles and nomadic conquests: evidence from historical China
Chen, Q. (2014) · Oxford Economic Papers · doi:10.1093/oep/gpu032 · Cited by 53
“2 The importance of the steppe frontier in Chinese history has been examined by Lattimore (1940 [1989]), Barfield (1989), Cosmo (2002), and Turchin (2009).”
A comparative analysis of the UK and Italian small businesses using Generalised Extreme Value models
Andreeva, G., Calabrese, R., & Osmetti, S. (2014) · European Journal of Operational Research · doi:10.1016/j.ejor.2015.07.062 · Cited by 44
“Moreover, the bias of maximum likelihood parameter estimators for logistic regression is ampliﬁed when the number of defaults is low [27].”
Central Banks at War
Poast, P. (2014) · International Organization · doi:10.1017/s0020818314000265 · Cited by 54
Facilitation and Teacher Behaviors
Arya, P., Christ, T., & Chiu, M. M. (2013) · Journal of Teacher Education · doi:10.1177/0022487113511644 · Cited by 59
“For infrequent outcomes, we estimate the Logit bias and remove it (King & Zeng, 2001).”
BackgroundMethod
Strategic Momentum
Turner, S. F., Mitchell, W., & Bettis, R. A. (2012) · Journal of Management · doi:10.1177/0149206312458704 · Cited by 59
“(7) As a sensitivity check for Hypothesis 1, we reran Model 3 using a standard rare events logit (King & Zeng, 2001); the results were similar.”
Method
Breast Cancer Risk Factors in a Defined Population: Weighted Logistic Regression Approach for Rare Events
Zare, N., Haem, E., Lankarani, K., Heydari, S., & Barooti, E. (2013) · Journal of Breast Cancer · doi:10.4048/jbc.2013.16.2.214 · Cited by 44
“King and Zeng [10] conducted a two-state simulation study on rare events data using the usual logistic regression and weighted logistic regression, and then the results were compared.”
BackgroundMethodInfluential
Technical assessment of the neonatal early-onset sepsis risk calculator.
Benitz, W., & Achten, N. (2020) · Lancet. Infectious Diseases (Print) · doi:10.1016/s1473-3099(20)30490-4 · Cited by 43
Acquirers’ Reception of Signals in M&A Markets: Effects of Acquirer Experiences on Target Selection
Wu, C.-W., & Reuer, J. (2020) · Journal of Management Studies · doi:10.1111/joms.12637 · Cited by 43
Path-dependent Routines in the Evaluation of Novelty: The Effects of Innovators’ New Knowledge Use on Brokerage Firms’ Coverage
Theeke, M., Polidoro, F., & Fredrickson, J. W. (2017) · Administrative Science Quarterly · doi:10.1177/0001839217747269 · Cited by 52
“Because this zero-inflation issue can bias estimates (King and Zeng, 2001), we limited the set of brokerage firms at hazard of covering a company to the group of brokerage firms that were currently covering at least one medical device company.”
Background
A joint framework for static and real-time crash risk analysis
Yasmin, S., Eluru, N., Wang, L., & Abdel-Aty, M. (2018) · Analytic Methods in Accident Research · doi:10.1016/j.amar.2018.04.001 · Cited by 43
Dodging the bullet: how crises trigger technocrat‐led governments
Wratil, C., & Pastorella, G. (2017) · doi:10.1111/1475-6765.12234 · Cited by 43
Human Rights, Geostrategy, and EU Foreign Policy, 1989–2008
Kreutz, J. (2014) · International Organization · doi:10.1017/s0020818314000368 · Cited by 43
Drivers of firm formalization in Vietnam: an attention theory explanation
Nguyen, T., Verreynne, M., & Steen, J. (2014) · Entrepreneurship and Regional Development · doi:10.1080/08985626.2014.959069 · Cited by 43
“…formalization is a binary variable and the total proportion of transitioned firms was only around 10%, rare-event logistic regression models (King and Zeng 2001) are used to test the relationship between formalization and government estimates and, although these results mirrored logistic…”
Result
What Drives the Partnership Decision? Examining Structural Factors Influencing Public-Private Partnerships for Municipal Wireless Broadband
Girth, A. M. (2014) · doi:10.1080/10967494.2014.935240 · Cited by 43
“King and Zeng (2001b; 2002) developed rare events logit to approximate unbiased and lower-variance coefficients while accounting for rare events and choice-based sampling.”
Background
Understanding random resampling techniques for class imbalance correction and their consequences on calibration and discrimination of clinical risk prediction models
Piccininni, M., Wechsung, M., van Calster, B., Rohmann, J., Konigorski, S., & van Smeden, M. (2024) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2024.104666 · Cited by 42
Issuer Motivations for Corporate Green Bond Offerings
Dutordoir, M., Li, S., & Neto, J. Q. F. (2023) · British Journal of Management · doi:10.1111/1467-8551.12747 · Cited by 58
Adverse experiences resulting in emergency medical treatment seeking following the use of lysergic acid diethylamide (LSD)
Kopra, E. I., Ferris, J., Rucker, J., McClure, B., Young, A. H., Copeland, C. S., & WINSTOCK, A. R. (2022) · Journal of Psychopharmacology · doi:10.1177/02698811221099650 · Cited by 47
Improving logistic regression on the imbalanced data by a novel penalized log-likelihood function
Zhang, L.-L., Geisler, T., Ray, H., & Xie, Y. (2021) · Journal of Applied Statistics · doi:10.1080/02664763.2021.1939662 · Cited by 42
“To apply logistic regression in the imbalanced data (i.e. rare event data), King and Zeng penalized misclassification costs of events and non-events differently by penalty weights W 1 and W 0 in the log-likelihood function [26], as shown in Equation (12).”
Method
Deep Learning–Driven Automated Detection of COVID-19 from Radiography Images: a Comparative Analysis
Rahman, S., Sarker, S. C., Miraj, M. A. A., Nihal, R. A., Haque, A. K. M. N., & Noman, A. A. (2021) · Cognitive Computation · doi:10.1007/s12559-020-09779-5 · Cited by 50
Modelling post-fire tree mortality: Can random forest improve discrimination of imbalanced data?
Shearman, T., Varner, J. M., Hood, S., Cansler, C., & Hiers, J. (2019) · Ecological Modelling · doi:10.1016/j.ecolmodel.2019.108855 · Cited by 42
“King and Zeng (2001) proposed that the class imbalance problem can be mitigated during the data collection stage of a study.”
BackgroundInfluential
Cross‐country evidence on the determinants of inclusive growth episodes
Jalles, J., & Mello, L. (2019) · Review of Development Economics · doi:10.1111/rode.12605 · Cited by 42
“However, as pointed out by King and Zeng (1999a, 1999b, 2001), the estimates of and 1 among observations that 18 For this reason, we also include in the baseline regressions (and robustness that follow) episodes of inclusive growth of one year in duration to minimize this rare-events…”
Serial electrocardiography to detect newly emerging or aggravating cardiac pathology: a deep-learning approach
Sbrollini, A., de Jongh, M. C., ter Haar, C. T., Treskes, R., Man, S., Burattini, L., & Swenne, C. (2019) · BioMedical Engineering OnLine · doi:10.1186/s12938-019-0630-9 · Cited by 42
Predictive models for bariatric surgery risks with imbalanced medical datasets
Razzaghi, T., Safro, I., Ewing, J., Sadrfaridpour, E., & Scott, J. (2019) · Annals of Operations Research · doi:10.1007/s10479-019-03156-8 · Cited by 42
Multi-Directional Dynamic Model for Traumatic Brain Injury Detection
Laksari, K., Fanton, M., Wu, L. C., Nguyen, T. H., Kurt, M., Giordano, C., Kelly, E., O'Keeffe, E., Wallace, E., Doherty, C., et al. (2018) · Journal of Neurotrauma · doi:10.1089/neu.2018.6340 · Cited by 42
Handling imbalance in an extended PLAID
Baets, L. D., Develder, C., Dhaene, T., Deschrijver, D., Gao, J.-K., & Berges, M. (2017) · Sustainable Internet and ICT for Sustainability · doi:10.23919/sustainit.2017.8379795 · Cited by 42
“This definition is standard in the Python’s sklearn library and is based on [18].”
Method
Logistic models as a forecasting tool for snow avalanches in a cold maritime climate: northern Gaspésie, Québec, Canada
Gauthier, F., Germain, D., & Hétu, B. (2017) · Natural Hazards · doi:10.1007/s11069-017-2959-3 · Cited by 42
Birds of a feather or celebrating differences? The formation and impacts of venture capital syndication
Du, Q.-Q. (2016) · doi:10.1016/j.jempfin.2016.09.001 · Cited by 42
You Can't Always Get What You Want: Why Foreign-Imposed Regime Change Seldom Improves Interstate Relations
Downes, A. B., & O’Rourke, L. A. (2016) · International Security · doi:10.1162/isec_a_00256 · Cited by 118
Research Note—IT Outsourcing and the Impact of Advisors on Clients and Vendors
Bapna, R., Gupta, A., Ray, G., & Singh, S. (2016) · Information Systems Research · doi:10.1287/isre.2016.0645 · Cited by 36
An asymmetric logistic regression model for ecological data
Komori, O., Eguchi, S., Ikeda, S., Okamura, H., Ichinokawa, M., & Nakayama, S. (2015) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.12473 · Cited by 45
Old friends and new acquaintances: Tie formation mechanisms in an interorganizational network generated by employee mobility
Collet, F., & Hedström, P. (2013) · Soc. Networks · doi:10.1016/j.socnet.2013.02.005 · Cited by 42
“As will be seen below, only about 15 out of 100,000 potential dyads are actually realized, and this means that if we were to draw a random sample of the dyads, we would not fully utilize the available information (Cosslett, 1981; Imbens, 1992; King and Zeng, 2001).”
Method
Environmental Social and Governance Controversies: A Bibliometric Review and Research Agenda
Shakil, M. H. (2024) · Finance Research Letters · doi:10.1016/j.frl.2024.106325 · Cited by 41
Remotely Incorrect? Accounting for Nonclassical Measurement Error in Satellite Data on Deforestation
Alix-Garcia, J., & Millimet, D. L. (2022) · Journal of the Association of Environmental and Resource Economists · doi:10.1086/723723 · Cited by 41
Weighting Methods for Rare Event Identification From Imbalanced Datasets
He, J., & Cheng, M. X. (2021) · Frontiers in Big Data · doi:10.3389/fdata.2021.715320 · Cited by 41
“In some applications, population information may be straightforward to know, such as in political activities (King and Zeng, 2001).”
BackgroundMethodInfluential
Fitness, strength and severity of COVID-19: a prospective register study of 1 559 187 Swedish conscripts
af Geijerstam, A., Mehlig, K., Börjesson, M., Robertson, J., Nyberg, J., Adiels, M., Rosengren, A., Åberg, M., & Lissner, L. (2021) · BMJ Open · doi:10.1136/bmjopen-2021-051316 · Cited by 50
Negative Spillovers Across Partnerships for Responsible Innovation: Evidence from the 2014 Ebola Outbreak
Arslan, B., & Tarakci, M. (2020) · Journal of Management Studies · doi:10.1111/joms.12607 · Cited by 41
“The two-year window was chosen since a larger window would have cast the number of realized partnerships as such a tiny fraction of all possible partnerships as to trigger a rareevent bias (King & Zeng, 2001).”
Background
Quantification of liver extracellular volume using dual-energy CT: utility for prediction of liver-related events in cirrhosis
Bak, S., Kim, J. E., Bae, K., Cho, J., Choi, H., Park, M., Choi, H. Y., Shin, H. S., Lee, S.-M., & Kim, H. O. (2020) · European Radiology · doi:10.1007/s00330-020-06876-9 · Cited by 41
Who Are the Bitcoin Investors? Evidence from Indirect Cryptocurrency InvestmentsPreprint
Lammer, D., Hackethal, A., & Hanspal, T. (2019) · Social Science Research Network · doi:10.2139/ssrn.3501549 · Cited by 41
“As in Table 4, logistic regression analysis might not be ideal to explain variables in rare events data (King and Zeng, 2001) due to a potential small-sample bias in the maximum likelihood estimation of the logistic model.”
Background
Democracy and Financial Crisis
Lipscy, P. Y. (2017) · International Organization · doi:10.1017/s0020818318000279 · Cited by 44
Identifying and modeling meteorological risk factors associated with pre-harvest contamination of Listeria species in a mixed produce and dairy farm.
Pang, H., McEgan, R., Mishra, A., Micallef, S., & Pradhan, A. (2017) · Food Research International · doi:10.1016/j.foodres.2017.09.029 · Cited by 41
Machine Learning Based Building Damage Mapping from the ALOS-2/PALSAR-2 SAR Imagery: Case Study of 2016 Kumamoto Earthquake
Bai, Y., Adriano, B., Mas, E., & Koshimura, S. (2017) · doi:10.20965/jdr.2017.p0646 · Cited by 41
Comprehensive Analysis of Wrong-Way Driving Crashes on Alabama Interstates
Pour-Rouholamin, M., Zhou, H., Zhang, B., & Turochy, R. (2016) · Transportation Research Record Journal of the Transportation Research Board · doi:10.3141/2601-07 · Cited by 41
How Does Customary International Law Change? The Case of State Immunity
Verdier, P., & Voeten, E. (2015) · doi:10.1111/isqu.12155 · Cited by 41
When terrorists go bad: : Analyzing terrorist organizations’ involvement in drug smuggling
Asal, V., Milward, H. B., & Schoon, E. W. (2015) · doi:10.1111/isqu.12162 · Cited by 41
Foreign Targets and Diversionary Conflict
Jung, S. C. (2013) · International Studies Quarterly · doi:10.1111/isqu.12087 · Cited by 35
Spatial vulnerability assessment of silver fir and Norway spruce dieback driven by climate warming
Piedallu, C., Dallery, D., Bresson, C., Legay, M., Gégout, J., & Pierrat, R. (2022) · Landscape Ecology · doi:10.1007/s10980-022-01570-1 · Cited by 45
“This method yielded correct regression coefficients, but it increased the intercept value, so that the probability of dieback in the model outputs was overestimated (King and Zeng 2001).”
Method
Parametric and Non-Parametric Analyses for Pedestrian Crash Severity Prediction in Great Britain
Riccardi, M. R., Mauriello, F., Sarkar, S., Galante, F., Scarano, A., & Montella, A. (2022) · Sustainability · doi:10.3390/su14063188 · Cited by 47
Has previous loan rejection scarred firms from applying for loans during Covid-19?
Cowling, M., Liu, W.-X., & Calabrese, R. (2021) · Small Business Economics · doi:10.1007/s11187-021-00586-2 · Cited by 40
“2), the legitimacy of conventional binary (probit or logit) regressions may be compromised by the ‘rare-event’ problem first noted by King and Zeng (2001).”
Background

Authors: King, G., & Zeng, L.
Affiliations: Harvard University (US)
George Washington University (US)
ORCID: King, Gary
Venue: Political Analysis
Publisher: Cambridge University Press (CUP)
Published: 2001
Volume: 9
Issue: 2
Pages: 137-163
ISSN: 1047-1987 (ISSN-L)
1476-4989
DOI: 10.1093/oxfordjournals.pan.a004868
OpenAlex: W2163848058
Cited by: 4,316
References: 0
Citations by year: 2026: 273 · 2025: 223 · 2024: 261 · 2023: 235 · 2022: 277 · 2021: 362 · 2020: 316 · 2019: 307 · 2018: 236 · 2017: 176 · 2016: 205 · 2015: 189 · 2014: 238 · 2013: 185 · 2012: 142
FWCI: 61.75
Type: journal article
Language: en
Open access: bronze
doi.org
Licence: www.cambridge.org/core/terms (unspecified, 5847 d)
Locations: Political Analysis (publishedVersion)
Digital Access to Scholarship at Harvard (DASH) (Harvard University) (submittedVersion, cc-by)
RePEc: Research Papers in Economics (submittedVersion)
Funders: National Science Foundation (9729884, 9753126)
University of Cambridge
Topics: Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
Physical Sciences › Mathematics › Statistics and Probability › Survey Sampling and Estimation Techniques
Keywords: rare events, logistic regression, binary dependent variables, sampling design, event sampling, war, risk estimation, data collection efficiency

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Logistic Regression in Rare Events Data

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Self-check

Citations

Cites

Cited by

Metadata

Record

About these checks