Limitations of the Application of Fourfold Table Analysis to Hospital Data
The DOI matches its Crossref record.
Abstract
In the biologic laboratory we have a method of procedure for determining the effect of an agent or process that may be considered typical. It consists in dividing a group of animals into two cohorts, one considered the “experimental group,” the other the “control.” On the experimental group some variable is brought to play; the control is left alone. The results are set up as in table 1-a. If the results show that the ratio a:a þb is different from the ratio c:c þd, it is considered demonstrated that the process brought to bear on the experimental group has had a significant effect. A similar method is prevalent in statistical practice, which I venture to think has come into authority because of its apparent equivalence to the experimental procedure. In Biometrika it is referred to as the fourfold table and it is used as a paradigm of statistical analysis. The usual arrangement is that given in table 1-b. The entries, a, b, c and d are manipulated arithmetically to determine whether there is any correlation between A and B. A considerable number of indices have been elaborated to measure this correlation. Pearson has given the formula for calculating the product-moment correlation coefficient from a fourfold table on the assumption that the distribution of both variates is normal; Yule has an index of association for the fourfold table; there are the chi-square test and others. In essence, however, all these indices measure in different ways whether and how much, in comparison with the variation of random sampling, the ratio a:a þb differs from the ratio c:c þd. If the difference departs significantly from zero, there is said to be correlation, and the correlation is the greater the greater the difference. Now there is a distinction between the method as used in the laboratory and as applied in practical statistics. In the experimental situation, the groups, B and not B, are selected before the subgroupings, A and not A, are effected; that is, we start with a total group of unaffected animals. In the statistical application, the groupings, B and not B, are made after the subgroupings, A and not A, are already determined; that is, all the effects are already produced before the investigation starts. In the end, the tables of the results which are drawn up look alike for the two cases, but they have been arrived at differently. Correlative to this difference, a different interpretation may apply to the results, and this paper deals with a specific case of a kind that arises frequently in a medical clinic or a hospital. I take an example.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“It is well known that outright selection on the outcome, as well as conditioning on a variable affected by the outcome, can lead to bias”
From Endogenous Selection Bias: The Problem of Conditioning on a Collider Variable (2014) · cites this paper as Berkson 1946
In the citing paper
“Selection bias is symptomatic of a general phenomenon associated with conditioning on collider nodes (Z in our example). The phenomenon involves spurious associations induced between two causes upon observing their common effect, since any information refuting one cause should make the other more probable.”
From Linear Models: A Useful "Microscope" for Causal Analysis (2013) · cites this paper as [16]
In the citing paper
“This special handling of collision nodes (or colliders, e.g., Z → X←U X ) reflects a general phenomenon known as Berkson's paradox (Berkson, 1946), whereby observations on a common consequence of two independent causes render those causes dependent.”
From An Introduction to Causal Inference (2010) · cites this paper as Berkson, 1946
In the citing paper
“However, clinical samples have the disadvantage of initial referral biases that limit inference about adult outcomes(7-10).”
From Is adult ADHD a childhood-onset neurodevelopmental disorder? Evidence from a four-decade longitudinal cohort study (2015) · cites this paper as [7]
Citations
Cited by
Items 501–600 of 1,012
Characteristics of police referrals to a psychiatric emergency unit in Australia
(1995) · Psychiatric Services · doi:10.1176/ps.46.6.620 · Cited by 82
Determinants of Duration of Untreated Psychosis and the Pathway to Care in Singapore
Chong, S., Mythily, Lum, A., Chan, Y. H., & McGorry, P. D. (2005) · International Journal of Social Psychiatry · doi:10.1177/0020764005053278 · Cited by 82
“McGorry and colleagues (Lincolin & McGorry, 1999) found that the treatment lag time for those with affective psychosis was shorter – possibly the more obvious mood symptoms incorporating an effect similar to Berkson’s bias (Berkson, 1946).”
BackgroundGrant, B. F., Hasin, D. S., & Dawson, D. A. (1996) · Journal of Affective Disorders · doi:10.1016/0165-0327(96)00002-x · Cited by 82
A prospective study of cognitive function in the elderly
KORTEN, A. E., HENDERSON, A. S., CHRISTENSEN, H., JORM, A. F., RODGERS, B., JACOMB, P., & MACKINNON, A. J. (1997) · Psychological Medicine · doi:10.1017/s0033291797005217 · Cited by 82
“…of a person’s cognitive impairment, thereby reducing the likelihood of information bias ; and the observations on both the cognitive change and the putative risk factors are independent of whether the person has reached treatment, thereby reducing the likelihood of Berkson’s bias (Berkson, 1946).”
BackgroundSpecific and nonspecific comorbidity in anorexia nervosa
Jordan, J., Joyce, P. R., Carter, F. A., Horn, J., McIntosh, V. V. W., Luty, S. E., McKenzie, J. M., Frampton, C. M. A., Mulder, R. T., & Bulik, C. M. (2008) · International Journal of Eating Disorders · doi:10.1002/eat.20463 · Cited by 81
Associations between dietary factors and pancreatitis in dogs
Lem, K. Y., Fosgate, G. T., Norby, B., & Steiner, J. M. (2008) · Journal of the American Veterinary Medical Association · doi:10.2460/javma.233.9.1425 · Cited by 99
Mega‐analysis methods in ENIGMA : The experience of the generalized anxiety disorder working group
Zugman, A., Harrewijn, A., Cardinale, E. M., Zwiebel, H., Freitag, G. F., Werwath, K. E., Bas‐Hoogendam, J. M., Groenewold, N. A., Aghajani, M., Hilbert, K., et al. (2022) · Human Brain Mapping · doi:10.1002/hbm.25096 · Cited by 80
“…data across participants and in the variation of the independent variable (i.e., it is a collider), adjustment for the undesired effect induces a false association (Berkson, 1946; Luque-Fernandez et al., 2019; Pearl, 2009, chapter 6), which can happen in either direction (positive or negative).”
BackgroundMaternal Rejection of the Young Child: Present Status of the Clinical Syndrome
Brockington, I. (2011) · Psychopathology · doi:10.1159/000325058 · Cited by 80
Vaden-Kiernan, N., Ialongo, N. S., Pearson, J. L., & Kellam, S. G. (1995) · Research on Child and Adolescent Psychopathology · doi:10.1007/bf01447661 · Cited by 101
Akhtar, N., & Bradley, E. J. (1991) · Clinical Psychology Review · doi:10.1016/0272-7358(91)90007-h · Cited by 80
The risk of affective disorders in patients with adrenocortical insufficiency
Thomsen, A. F., Kvist, T. K., Andersen, P. K., & Kessing, L. V. (2006) · Psychoneuroendocrinology · doi:10.1016/j.psyneuen.2006.01.003 · Cited by 79
Kendler, K. S. (1995) · Psychological Medicine · doi:10.1017/s0033291700035054 · Cited by 79
Main Causes of Death in Cirrhosis
Schlichting, P., Christensen, E., Fauerholdt, L., Poulsen, H. E., Juhl, E., Tygstrup, N., & CSL (1983) · Scandinavian Journal of Gastroenterology · doi:10.3109/00365528309182110 · Cited by 80
Low, N. C. P., & Merikangas, K. R. (2003) · CNS Spectrums · doi:10.1017/s1092852900018745 · Cited by 79
Major life event stress and dyspepsia of unknown cause: a case control study.
Talley, N. J., & Piper, D. W. (1986) · Gut · doi:10.1136/gut.27.2.127 · Cited by 79
An analysis of Berkson's bias in case-control studies
Feinstein, A. R., Walter, S. D., & Horwitz, R. I. (1986) · Journal of Chronic Diseases · doi:10.1016/0021-9681(86)90194-3 · Cited by 90
Heun, R., Schoepf, D., Potluri, R., & Natalwala, A. (2013) · European Psychiatry · doi:10.1016/j.eurpsy.2011.06.001 · Cited by 78
Graphical Models for Inference Under Outcome-Dependent Sampling
Didelez, V., Kreiner, S., & Keiding, N. (2010) · Statistical Science · doi:10.1214/10-sts340 · Cited by 60
“…for 1The two criteria, d-separation and moralization, are entirely equivalent and readers more familiar with the former can verify all conditional independencies in the following with d-separation. a different disease for which A is a risk factor and which is associated with B (cf. Berkson, 1946).”
BackgroundMortality study of 18 000 patients treated with omeprazole
Bateman, D. N., Colin-Jones, D., Hartz, S., Langman, M., Logan, R. F., Mant, J., Murphy, M., Paterson, K. R., Rowsell, R., Thomas, S., et al. (2003) · Gut · doi:10.1136/gut.52.7.942 · Cited by 78
Identifying anxiety disorders in adolescents hospitalized for alcohol abuse or dependence
(1995) · Psychiatric Services · doi:10.1176/ps.46.6.618 · Cited by 78
The Epidemiologic Association of Fuchs' Heterochromie Iridocyclitis and Ocular Toxoplasmosis
Schwab, I. R. (1991) · American Journal of Ophthalmology · doi:10.1016/s0002-9394(14)72322-0 · Cited by 78
Torvik, F. A., Ystrom, E., Gustavson, K., Rosenström, T. H., Bramness, J. G., Gillespie, N., Aggen, S. H., Kendler, K. S., & Reichborn‐Kjennerud, T. (2018) · Acta Psychiatrica Scandinavica · doi:10.1111/acps.12829 · Cited by 76
“Elevated comorbidity resulting from the higher probability of being in treatment among individuals with two compared to one disorder is known as Berkson’s bias (33, 34).”
BackgroundAlsheridah, N., & Akhtar, S. (2018) · BMC Cancer · doi:10.1186/s12885-018-5132-9 · Cited by 84
“This bias tends to make risk factors’ distributions similar in case and control groups, thus attenuating the strength of associations of interest between the outcome (case-control status) and studied risk factors [63].”
BackgroundHall, W., Degenhardt, L. J., & Teesson, M. (2009) · Addictive Behaviors · doi:10.1016/j.addbeh.2009.03.010 · Cited by 80
“Studies of specialist treatment samples in either type of specialist setting do not provide an accurate picture of comorbidity in the population because persons with comorbid disorders are more likely to seek and be treated by such services (Berkson, 1946; Galbaud du Fort, Newman & Bland, 1993).”
BackgroundComprehensive study of cardiovascular morbidity in hospitalized inflammatory bowel disease patients
Sridhar, A. R. M., Parasa, S., Navaneethan, U., Crowell, M. D., & Olden, K. W. (2011) · Journal of Crohn s and Colitis · doi:10.1016/j.crohns.2011.01.011 · Cited by 77
Bias in binge eating disorder: How representative are recruited clinic samples?
Wilfley, D. E., Pike, K. M., Dohm, F.-A., Striegel-Moore, R. H., & Fairburn, C. G. (2001) · Journal of Consulting and Clinical Psychology · doi:10.1037//0022-006x.69.3.383 · Cited by 77
A Prospective Longitudinal Study of Gilles de la Tourette's Syndrome
Carter, A. S., Pauls, D. L., Leckman, J. F., & Cohen, D. J. (1994) · Journal of the American Academy of Child & Adolescent Psychiatry · doi:10.1097/00004583-199403000-00012 · Cited by 77
Increased Mortality Among Elderly Patients Undergoing Cataract Extraction
Hirsch, R. P., & Schwartz, B. (1983) · Archives of Ophthalmology · doi:10.1001/archopht.1983.01040020036004 · Cited by 77
Herrman, H. E., Baldwin, J. A., & Christie, D. (1983) · Psychological Medicine · doi:10.1017/s0033291700048005 · Cited by 77
A Unification of Mediator, Confounder, and Collider Effects
MacKinnon, D. P., & Lamp, S. J. (2021) · Prevention Science · doi:10.1007/s11121-021-01268-x · Cited by 84
“Collider bias is also known as Berkson’s bias or Berkson’s fallacy because Berkson (1946) demonstrated the effect in research on risk factors for disease.”
BackgroundMedical Comorbidities in Bipolar Disorder
Sinha, A., Shariq, A., Said, K., Sharma, A., Newport, D. J., & Salloum, I. M. (2018) · Current Psychiatry Reports · doi:10.1007/s11920-018-0897-8 · Cited by 76
The prevalence of substance-induced psychotic disorder in methamphetamine misusers: A meta-analysis
Lecomte, T., Dumais, A., Dugré, J. R., & Potvin, S. (2018) · Psychiatry Research · doi:10.1016/j.psychres.2018.05.033 · Cited by 75
“This means that our results can partially be explained by Berkson's bias, which refers to the higher prevalence rates of disorders that are typically found in clinical relative to community sample (Berkson, 1946).”
ResultMalignant Diseases and Mortality Rate
Nielsen, O. H., Jacobsen, O., Pedersen, E. R., et al. (1985) · Scandinavian Journal of Gastroenterology · doi:10.3109/00365528509089626 · Cited by 75
Lim, S. I., Radicchi, F., van den Heuvel, M. P., & Sporns, O. (2019) · Scientific Reports · doi:10.1038/s41598-019-39243-w · Cited by 80
Nodler, J. L., Moolamalla, S. R., Ledger, E. M., Nuwayhid, B. S., & Mulla, Z. D. (2009) · BMC Pregnancy and Childbirth · doi:10.1186/1471-2393-9-11 · Cited by 72
“Berkson was a physician at the Mayo Clinic who reported the following phenomenon in 1946: Two diseases may appear to be correlated with one another in a hospitalbased case-control study when in fact they are not simply because individuals with two or more conditions are more likely to be hospitalized than patients wit…”
BackgroundTension-type headache and psychiatric comorbidity
Heckman, B. D., & Holroyd, K. A. (2006) · Current Pain and Headache Reports · doi:10.1007/s11916-006-0075-2 · Cited by 77
Treated and treatment-naive alcoholics come from different populations
Fein, G., & Landman, B. A. (2005) · Alcohol · doi:10.1016/j.alcohol.2004.10.007 · Cited by 73
“A classic example of Berkson’s fallacy occurred when Pearl (1929) found a negative association between the presence of cancer and tuberculosis in autopsy cases.”
BackgroundInfluentialDual Diagnosis: Alcoholism and Co‐Morbid Psychiatric Disorders
Kranzler, H. R., & Rosenthal, R. N. (2003) · The American Journal on Addictions · doi:10.1111/j.1521-0391.2003.tb00494.x · Cited by 73
Striegel‐Moore, R. H., Seeley, J. R., & Lewinsohn, P. M. (2003) · Journal of the American Academy of Child & Adolescent Psychiatry · doi:10.1097/01.chi.0000046838.90931.44 · Cited by 86
“We examined this question in a community sample in order to avoid the biases inherent in studies of patients (Berkson, 1946; Kessler et al., 1999; Wilfley et al., 2001) and with a comprehensive set of measures to capture a broad range of indicators of psychosocial adjustment.”
BackgroundVaricella Coinfection in Patients with Active Monkeypox in the Democratic Republic of the Congo
Hoff, N. A., Morier, D., Kisalu, N. K., et al. (2017) · EcoHealth · doi:10.1007/s10393-017-1266-5 · Cited by 71
“However, it has been demonstrated that two diseases can occur concurrently despite independent infection in a healthcare setting (Berkson 1946).”
BackgroundInfluentialGoldstein, B. I., & Levitt, A. J. (2008) · Bipolar Disorders · doi:10.1111/j.1399-5618.2008.00461.x · Cited by 71
Geller, D., Biederman, J., Faraone, S. V., Frazier, J., Coffey, B. J., Kim, G., & Bellordre, C. A. (2000) · Depression and Anxiety · doi:10.1002/1520-6394(2000)11:4<163::aid-da3>3.0.co;2-3 · Cited by 71
Standardization and Control for Confounding in Observational Studies: A Historical Perspective
Keiding, N., & Clayton, D. G. (2014) · Statistical Science · doi:10.1214/13-sts453 · Cited by 77
“A closely related issue is the phenomenon of selection bias, famously discussed by Berkson (1946) in relation to hospital-based studies.”
BackgroundFamilial factors in vulnerability to substance abuse.
Merikangas, K. R., Rounsaville, B. J., & Prusoff, B. A. (1992) · American Psychological Association eBooks · doi:10.1037/10107-003 · Cited by 71
Adolescent Substance Abuse and Internalizing Disorders
Clark, D. B., & Neighbors, B. (1996) · Child and Adolescent Psychiatric Clinics of North America · doi:10.1016/s1056-4993(18)30384-5 · Cited by 71
Recent research of relationships among eating disorders and personality disorders
Grilo, C. M. (2002) · Current Psychiatry Reports · doi:10.1007/s11920-002-0007-8 · Cited by 96
Epidemiological Methods and Inferences in Studies of Noninfectious Diseases: PHR Review
Lilienfeld, A. M. (1957) · Public Health Reports (1896-1970) · doi:10.2307/4589685 · Cited by 70
Thomsen, A. F., Kvist, T. K., Andersen, P. K., & Kessing, L. V. (2005) · Thyroid · doi:10.1089/thy.2005.15.700 · Cited by 69
“We preferred to use patients who had passed the thresholds for hospitalization as control persons, in order to reduce the effect of Berksons bias (18).”
Traumatic events and obsessive compulsive disorder in children and adolescents: is there a link?
Lafleur, D. L., Petty, C., Mancuso, E., McCarthy, K., Biederman, J., Faro, A., Levy, H. C., & Geller, D. A. (2011) · Journal of Anxiety Disorders · doi:10.1016/j.janxdis.2010.12.005 · Cited by 68
“, non-clinically referred subjects that avoids Berkson’s bias) (Berkson, 1946) although the extant literature may be limited by the changing nosology of the DSM and the stringency or sensitivity of evolving PTSD diagnostic criteria.”
BackgroundMcEwan, B. L. (2020) · Annals of the International Communication Association · doi:10.1080/23808985.2020.1792793 · Cited by 109
Geeraerts, S. B., Deutz, M. H. F., Deković, M., Bunte, T. L., Schoemaker, K., Espy, K. A., Prinzie, P., van Baar, A. L., & Matthys, W. (2015) · Journal of the American Academy of Child & Adolescent Psychiatry · doi:10.1016/j.jaac.2015.04.012 · Cited by 78
“35 In addition, Berkson bias 36 is a relevant concern when examining the associations between syndromes within clinically referred samples.”
Kochhar, P., Batty, M. J., Liddle, E. B., Groom, M. J., Scerif, G., Liddle, P. F., & Hollis, C. P. (2011) · Child: Care, Health and Development · doi:10.1111/j.1365-2214.2010.01123.x · Cited by 68
Association Between Hepatitis C Virus and Head and Neck Cancers
Mahale, P. S., Sturgis, E. M., Tweardy, D. J., Ariza‐Heredia, E., & Torres, H. A. (2016) · JNCI Journal of the National Cancer Institute · doi:10.1093/jnci/djw035 · Cited by 75
Chase, H. S., Mitrani, L. R., Lu, G. G., & Fulgieri, D. J. (2017) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-017-0418-4 · Cited by 68
“…of the Random sample set enabled us to obtain a more accurate measurement of sensitivity and specificity of classification of patients known to have MS as well as the true prevalence of MS in our adult population which would allow calculation of positive and negative predictive values [37, 38].”
BackgroundFuller, B. E., Chermack, S. T., Cruise, K. A., Kirsch, E., Fitzgerald, H. E., & Zucker, R. A. (2003) · Journal of Studies on Alcohol · doi:10.15288/jsa.2003.64.472 · Cited by 68
The construct validity of depressive personality disorder.
McDermut, W., Zimmerman, M., & Chelminski, I. (2003) · Journal of Abnormal Psychology · doi:10.1037//0021-843x.112.1.49 · Cited by 70
Cancer and diabetes mellitus a review of the literature
Kessler, I. I. (1971) · Journal of Chronic Diseases · doi:10.1016/0021-9681(71)90133-0 · Cited by 68
Blow, F. C., Cook, C. A. L., Booth, B. M., Falcon, S. P., & Friedman, M. J. (1992) · Psychiatric Services · doi:10.1176/ps.43.10.990 · Cited by 94
Grilo, C. M., McGlashan, T. H., & Skodol, A. E. (2000) · Psychiatric Quarterly · doi:10.1023/a:1004680122613 · Cited by 67
Barrett, E. L., Mills, K. L., & Teesson, M. (2013) · Australian & New Zealand Journal of Psychiatry · doi:10.1177/0004867413476752 · Cited by 67
Lesko, C. R., Jacobson, L. P., Althoff, K. N., Abraham, A. G., Gange, S. J., Moore, R. D., Modur, S. P., & Lau, B. M. (2018) · International Journal of Epidemiology · doi:10.1093/ije/dyx283 · Cited by 71
“Depending on how cases and controls are ascertained, case–control studies may come from a less clearly defined target population, which could be a source of bias, particularly if cases come from a tertiary care setting.(45,46) However, for rare outcomes or exposures that are expensive or invasive to collect, case–cont…”
BackgroundDegenhardt, L. J., & Hall, W. (2002) · Current Psychiatry Reports · doi:10.1007/s11920-002-0026-5 · Cited by 82
Kendler, K. S. (2004) · Focus · doi:10.1176/foc.2.3.416 · Cited by 67
Respiratory symptoms in patients with treated hypothyroidism and inflammatory bowel disease
Birring, S. S. (2003) · Thorax · doi:10.1136/thorax.58.6.533 · Cited by 67
Bouter, K. P., Diepersloot, R. J. A., van Romunde, L. K. J., Uitslager, R., Masurel, N., Hoekstra, J. B. L., & Erkelens, D. W. (1991) · Diabetes Research and Clinical Practice · doi:10.1016/0168-8227(91)90131-v · Cited by 67
Anxiety and the Development of Alcoholism: Clinical and Scientific Issues
Clark, D. B., & Sayette, M. A. (1993) · American Journal on Addictions · doi:10.3109/10550499309115943 · Cited by 67
ANALYSIS OF CASE-CONTROL DATA DERIVED IN PART FROM PROXY RESPONDENTS
Walker, A. M., Velema, J. P., & Robins, J. M. (1988) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a114893 · Cited by 67
“The proxy stratum in this case is directly analogous to the set of hospitalized patients that Berkson (22) considered in his discussion of bias in hospital-based case-control studies.”
ResultSidawy, A. N., Schweitzer, E. J., Neville, R. F., Alexander, E. P., Temeck, B. K., & Curry, K. M. (1990) · Journal of Vascular Surgery · doi:10.1016/0741-5214(90)90299-p · Cited by 66
Leo, R. J., & Singh, J. (2016) · Scandinavian Journal of Pain · doi:10.1016/j.sjpain.2015.12.002 · Cited by 70
Introduction to Probabilistic Graphical Models
Pernkopf, F., Peharz, R., & Tschiatschek, S. (2014) · Academic press library in signal processing · doi:10.1016/b978-0-12-396502-8.00018-8 · Cited by 77
“This is known as the Berkson’s paradox [Berkson, 1946] or the explaining away phenomenon.”
BackgroundZimmerman, M., McGlinchey, J. B., Chelminski, I., & Young, D. (2008) · Psychological Medicine · doi:10.1017/s0033291707001717 · Cited by 65
“It has been known for a long time that co-morbidity is associated with seeking treatment (Berkson, 1946).”
BackgroundDramatic-Erratic Personality Disorder Symptoms: I. Continuity from Early Adolescence into Adulthood
Crawford, T. N., Cohen, P., & Brook, J. S. (2001) · Journal of Personality Disorders · doi:10.1521/pedi.15.4.319.19182 · Cited by 65
“Such samples tend to include a misleadingly high proportion of participants with comorbid disorders because the probability of clinic referrals increases with the occurrence of each separate condition (Berkson, 1946).”
BackgroundComorbidity burden and its impact on psychosocial morbidity in depressed outpatients
McDermut, W., Mattia, J. I., & Zimmerman, M. A. (2001) · Journal of Affective Disorders · doi:10.1016/s0165-0327(00)00220-2 · Cited by 72
Agoraphobia without panic: clinical reappraisal of an epidemiologic finding
(1993) · American Journal of Psychiatry · doi:10.1176/ajp.150.10.1496 · Cited by 66
Causes of Death in Duodenal and Gastric Ulcer
Bonnevie, O. (1977) · Gastroenterology · doi:10.1016/s0016-5085(19)31847-5 · Cited by 66
How to remove or control confounds in predictive models, with applications to brain biomarkers
Chyzhyk, D., Varoquaux, G., Milham, M., & Thirion, B. (2022) · GigaScience · doi:10.1093/gigascience/giac014 · Cited by 65
“Conditioning on the third variable z can then reverse the correlation between 2 variables X and y , a phenomenon known as the Berkson or Simpson statistical paradox [66,67].”
Direct effect on validity of response run-in selection in clinical trials
Berger, V. W., Rezvani, A., & Makarewicz, V. A. (2003) · Controlled Clinical Trials · doi:10.1016/s0197-2456(02)00316-1 · Cited by 66
“But it has been known at least since 1946 [40] that the association between two variables may vary with the population, so it is a nontrivial step to infer that the apparent superiority is, in fact, due to true superiority of E to C.”
BackgroundQuantifying psychiatric comorbidity: Lessions from chronic disease epidemiology
Batstra, L., Bos, E. H., & Neeleman, J. (2002) · Social Psychiatry and Psychiatric Epidemiology · doi:10.1007/s001270200001 · Cited by 68
Épidémiologie de l’anorexie mentale : revue de la littérature
Roux, H., Chapelon, E., & Godart, N. T. (2012) · L Encéphale · doi:10.1016/j.encep.2012.06.001 · Cited by 85
Sensory Over-Responsivity in a Sample of Children Seeking Treatment for Anxiety
Conelea, C. A., Carter, A. S., & Freeman, J. B. (2014) · Journal of Developmental & Behavioral Pediatrics · doi:10.1097/dbp.0000000000000092 · Cited by 76
Covariance of personality, neurocognition, and schizophrenia spectrum traits in the community
Tien, A. Y., Costa, P. T., & Eaton, W. W. (1992) · Schizophrenia Research · doi:10.1016/0920-9964(92)90045-7 · Cited by 78
“due to Berkson’s bias (Berkson, 1946).”
Rodriguez, B. F., Weisberg, R. B., Pagano, M. E., Machan, J. T., Culpepper, L., & Keller, M. B. (2004) · Comprehensive Psychiatry · doi:10.1016/j.comppsych.2003.09.005 · Cited by 64
Nicenboim, B., Logačev, P., Gattei, C., & Vasishth, S. (2016) · Frontiers in Psychology · doi:10.3389/fpsyg.2016.00280 · Cited by 79
“The lack of correlation may be due to the so-called Berkson’s paradox (Berkson, 1946), which arises when a specific part of the population is absent (in this case we can assume that people with not enough reading fluency or WMC would not attend college).”
BackgroundTowards a definition of comorbidity in the light of clinical complexity
Bonavita, V., & Simone, R. D. (2008) · Neurological Sciences · doi:10.1007/s10072-008-0898-1 · Cited by 64
“Probably the most striking example of Berkson’s bias comes from the comparison between the rates of psychiatric comorbidity shown by migraine and tensiontype patients in clinical vs. population or community comorbidity studies.”
BackgroundInfluentialIncreased risk of multiple sclerosis among women with migraine in the Nurses’ Health Study II
Kister, I., Munger, K. L., Herbert, J., & Ascherio, A. (2011) · Multiple Sclerosis Journal · doi:10.1177/1352458511416487 · Cited by 67
“The studies of migraine in MS suffer from two main limitations: they are cross-sectional surveys and thus do not yield information regarding the temporal relationship between migraine and MS; all but one of these studies(9) were tertiary clinic-based and are therefore subject to selection and Berkman’s biases.(11) A m…”
BackgroundGoldstein, R. B., Grant, B. F., Ruan, W. J., Smith, S. M., & Saha, T. D. (2006) · Journal of Nervous & Mental Disease · doi:10.1097/01.nmd.0000235762.82264.a1 · Cited by 64
“This approach eliminates selection biases that could result from recruitment of respondents in clinical and correctional settings, where prevalence and severity of disorders and patterns of comorbidity may differ substantially from those observed in the general population (Berkson, 1946).”
BackgroundRisk of gastric cancer after Billroth II resection for duodenal ulcer
Fischer, A., Græm, N., & Jensen, O. M. (1983) · British journal of surgery · doi:10.1002/bjs.1800700915 · Cited by 64
Biases in Electronic Health Records Data for Generating Real-World Evidence: An Overview
Al‐Sahab, B., Leviton, A., Loddenkemper, T., Paneth, N., & Zhang, B. (2023) · Journal of Healthcare Informatics Research · doi:10.1007/s41666-023-00153-2 · Cited by 88
Kuss, D. J., & Griffiths, M. D. (2012) · IGI Global eBooks · doi:10.4018/978-1-4666-0315-8.ch062 · Cited by 65
Sensitivity and Specificity of Visual Acuity Screening for Refractive Errors in School Children
Tong, L. H. T., Saw, S., Tan, D. T. H., et al. (2002) · Optometry and Vision Science · doi:10.1002/j.1538-9235.2002.tb01552.x · Cited by 62
Redefining Abdominal Syndromes Results of a Population-Based Study
Kay, L., & Jørgensen, T. (1996) · Scandinavian Journal of Gastroenterology · doi:10.3109/00365529609006767 · Cited by 62
Guo, S.-W. (2005) · Molecular Human Reproduction · doi:10.1093/molehr/gah206 · Cited by 62
“This phenomenon, known as Berkson’s fallacy, could also happen when using hospital–based controls for association studies (Berkson, 1946).”
BackgroundThe Enduring Evolution of the P Value
Kyriacou, D. N. (2016) · JAMA · doi:10.1001/jama.2016.2152 · Cited by 62
Statistical Methods for Testing Genetic Pleiotropy
Schaid, D. J., Tong, X., Larrabee, B. R., Kennedy, R. B., Poland, G. A., & Sinnwell, J. P. (2016) · Genetics · doi:10.1534/genetics.116.189308 · Cited by 68
“One cause of spurious association is when subjects with more than onedisease symptomaremore likely ascertained for a study than if they had only one symptom—called Berkson’s bias (Berkson 1946).”
BackgroundFeinstein, A. R. (1981) · JAMA · doi:10.1001/jama.246.9.957 · Cited by 86
Isomura, K., Boman, M., Rück, C., Serlachius, E., Larsson, H., Lichtenstein, P., & Mataix-Cols, D. (2015) · Psychological Medicine · doi:10.1017/s0033291714002116 · Cited by 61
“These possible biases can optimally be addressed by examining the familial structure of SAD at the population level (Berkson, 1946), recruiting patients from non-specialist clinics and randomly selecting control families from the general population.”
BackgroundIn-depth study of personality disorders in first-admission patients with substance use disorders
Langås, A.-M., Malt, U. F., & Opjordsmoen, S. (2012) · BMC Psychiatry · doi:10.1186/1471-244x-12-180 · Cited by 76
“This is often referred to as Berkson’s fallacy [39].”
BackgroundLord’s Paradox Revisited – (Oh Lord! Kumbaya!)
Pearl, J. (2016) · Journal of Causal Inference · doi:10.1515/jci-2016-0021 · Cited by 73
“…and asks for the effect of smoking on mortality, discounting its effect on birth 4Other names for this effect are “Berkson paradox,” or “Berkson fallacy” (Berkson, 1946), which characterizes the general phenomenon whereby two independent causes become dependent upon observing their common effect.”
BackgroundWhat Is Schizophrenic in Acute and Transient Psychotic Disorder?
Marneros, A., Pillmann, F., Haring, A., Baizuweit, S., & Bloink, R. (2003) · Schizophrenia Bulletin · doi:10.1093/oxfordjournals.schbul.a007007 · Cited by 61
“This procedure might result in an overrepresentation of patients with multiple episodes by a mechanism analogous to Berkson's bias (Berkson 1946).”
BackgroundStrongyloidiasis in US Veterans of the Vietnam and Other Wars
Genta, R. M. (1987) · JAMA · doi:10.1001/jama.1987.03400010053026 · Cited by 61
Metadata
- Authors
- Berkson, J.
- Corresponding author
- Berkson, Joseph
- Venue
- Biometrics Bulletin
- Publisher
- JSTOR
- Published
- 1946-06
- Volume
- 2
- Issue
- 3
- Pages
- 47
- ISSN
- 0099-4987 (ISSN-L)
- OpenAlex
- W2400892929
- Semantic Scholar
- 6791402d01b453848c7dfda90eb4523674a23e93
- Cited by
- 1,810
- References
- 0
- Citations by year
- 2026: 29 · 2025: 32 · 2024: 36 · 2023: 36 · 2022: 39 · 2021: 48 · 2020: 45 · 2019: 57 · 2018: 30 · 2017: 36 · 2016: 45 · 2015: 45 · 2014: 73 · 2013: 58 · 2012: 47
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Biometrics Bulletin (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
- Physical Sciences › Mathematics › Statistics and Probability › Probabilistic Statistics in Medicine
- Physical Sciences › Mathematics › Statistics and Probability › Probability and Statistical Research
- Keywords
- hospital data, confounding, chi-square test, product moment correlation
- MeSH terms
- Hospital Records, Medical Records
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.