Monday, December 18, 2023

Does Artificial Intelligence Become More Intelligent Over Time?




In 2023, I asked ChatGPT a number of questions about suicide in order to test how knowledgeable it was about suicide. One question I asked concerned the motives for Jocasta’s suicide (Lester, 2023).

David Lester


In the play Oedipus Rex, written by Sophocles, why did Jocasta die by suicide?




In the play "Oedipus Rex" written by Sophocles, Jocasta, the wife of Oedipus and mother of his children, kills herself out of shock and despair upon realizing that Oedipus is her son and that she had unknowingly married and had children with her own son. The revelation is so devastating to her that she chooses to end her life rather than continue living with the knowledge and shame of her actions.

          I noted that it is clear from the play that Jocasta knew that she had married her son. Jocasta was prepared to live a life married to her son as long as this information was kept secret. Once the fact was likely to be known, she died by suicide, primarily out of shame.

          Has ChatGPT improved over the next six months? I asked it once more why Jocasta died by suicide.


David Lester


Why did Jocasta die by suicide?




In Greek mythology, Jocasta is a character best known for her role in the tragic story of Oedipus. The details of Jocasta's death vary in different versions of the myth, and it's important to note that the story itself is a work of fiction.


The most well-known version of the story is found in Sophocles' play "Oedipus Rex." In this version, Oedipus discovers that he has unwittingly fulfilled a prophecy that foretold he would kill his father and marry his mother. When Oedipus realizes the truth, he blinds himself, and Jocasta, horrified by the revelation and the tragic fate of her family, hangs herself.


The reasons for Jocasta's suicide are complex and involve a combination of shame, guilt, and horror at the fulfillment of the prophecy. The Oedipus myth explores themes of fate, free will, and the consequences of trying to avoid destiny, making it a powerful and enduring tragedy in Greek literature.


          This is impressive. Perhaps it read my article in Suicide Studies? ChatGPT now brings shame and guilt into the motivating forces for Jocasta’s suicide.



Lester, D. (2023). What does artificial intelligence know about suicide? Suicide Studies, 4(3), 25-28.

Thursday, March 02, 2023

What have we learned about suicide? A harsh critique of theory and research




David Lester

Stockton University




          The purpose of this essay is to review the field of what is known as suicidology in order to explore what we have learned about why people die by suicide. This review is going to be harsh, not in terms of criticizing what researchers and theorists have written, but rather by omitting citations to those who have become well-known in the field, past and present.


          I reviewed the research and theory on suicidal behavior from 1897 to 1997 in four books which I titled Why People Kill Themselves. Those books did not, however, critique the papers cited. The aim was to provide for those in the field a convenient reference to what had been published in those years. I did choose the outstanding contributors in the 3rd and 4th editions of the book, but many of those chosen there are not cited here. They did publish a large number of articles on one issue in the field, thereby stimulating others, but their contributions do not necessarily assist our understanding of suicidal behavior.


          This review will also focus on why people die by suicide and not people who attempt suicide but survive.


The Societal Suicide Rate


          The major questions about the societal suicide rate is what determines the variation over time within a region (time-series theories) and what determines the suicide rate from region to region (ecological theories). In fact, the explanations are typically given for both of these variations.


          There have scorers of correlational studies on both of these variations, but the results are typically uninteresting theoretically. For example, suicide rates (over time and region) are positively associated with divorce rates and unemployment rates. This is hardly surprising. Have there been any correlates of societal suicide rates that surprise us? No. What is of use for understanding suicide?


Insight #1: Henry and Short


          One of the theories that has been neglected is that provided by Henry and Short (1954). Henry and Short proposed that, when people in a society are miserable or unhappy, if they have an external cause to blame for their misery, then they will be angry, and homicide rates will increase. If, however, there is no external cause to blame for their misery, then they will blame themselves, become depressed and more likely to kill themselves.


          This theory explains, for example, why the oppressed in a society have higher homicide rates while the oppressors have higher suicide rates. In line with this, African Americans in the United States have higher homicide rates while whites have higher suicide rates.


          Interestingly, Henry and Short also extended their theory and applied it at the individual level and, in addition, proposed child-rearing techniques of punishment that would lead to individual differences in suicidal-homicidal tendencies. They proposed that love-oriented punishment techniques would lead children to suppress their anger and become depressed and suicidal in the long term, while physical punishment would allow anger to be experienced.


Insight #2: Uematsue and the Cohort Effect


          Uematsue (1961) in an obscure journal proposed that the number of potential suicides in a cohort is fixed. If that cohort has a high suicide rate at an early age, it will have a low suicide rate later in life, and vice versa. Lester (1984) tested this hypothesis and partially confirmed it. With data available for cohorts only for a maximum of 35 years (rather than lifetime), Lester confirmed Uematsue’s hypotheses for female suicide rates in the United States but not male suicide rates.


          This raises the possibility that suicide is, at least in part, genetically determined. Such a hypothesis could, of course, be tested using methodologically sound twin studies, that is, comparing identical with non-identical twin pairs. However, the childhood and subsequent experiences of identical and non-identical twins are not similar.


Insight #3: The Natural Suicide Rate


Maris (1981) speculated that the suicide rate could never be zero no matter how ideal the social-economic conditions were. Coming from a economic perspective, Yang and Lester (2004) speculated that, just as the unemployment rate can never be zero, perhaps the suicide rate of a society can never be zero. They tested this by devising regression equations for several countries using divorce and unemployment rates to predict the suicide rate over regions of each country. Setting the divorce and unemployment rates to zero still predicted positive and non-zero suicide rates for each country. For a review of recent research on this issue see Yang and Lester (2021).


Insight #4: Taylor and Moksony and a Broad Social Variable


          Both Taylor (1990) and Moksony (1990) argued that social indicators such as divorce rates do not directly affect the suicide rate. Rather, such social indicators are measures of broader social qualities which affect the suicide rate. Evidence for this comes from a study by Lester (1995) who found that the divorce rate of the states of the United States was associated with the suicide rate of divorced people and also the suicide rates of single, married, and widowed people, indicating that the divorce rate was an indicator of general social malaise.


          Lester (1994) correlated many variables over the states and found that one set of variables were highly inter-correlated and the factor score (using a factor analysis) was associated with the suicide rate of the states. The set included the crime rate, the divorce rate, inter-state migration, the percent divorced, And alcohol consumptions positively loaded on the factor and the percent born in state and church attendance loaded negatively on the factor. Again, this suggests the presence of a broader social variable such as social malaise or social disintegration.


Insight #5: The Suicide Rate as a Random Walk


The random walk was a concept proposed by Pearson (1905) and refers to a mathematical description of a path that consists of a succession of random steps. It describes such diverse phenomena as the path traced by a molecule as it travels in a liquid or a gas and the price of a fluctuating stock or stock index (Malkiel, 1973). If a stochastic process follows a random walk, then any disturbance to the process will persist over time. If the time series suicide rate was a random walk, then the changes from day to day would be random and yet subject to shocks, that is, societal crises. The randomness might explain, in part, why suicide prevention efforts have failed in the last ten years.

Yang (1994) explored whether the suicide rate in the USA from 1933 to 1987 followed a random walk. (The USA started producing mortality statistics for the whole USA only in 1933.) Using econometric techniques of analysis, she found that the time-series suicide rate fits a random walk process overall, for six age groups and for four sex-by-race groups.


Insight #6: Suggestion


One societal happening that might affect deviations from a random walk is the media coverage of a celebrity suicide. Phillips (1974) and Stack (1987) have documented that celebrity suicides result in an increase in suicides in the society after media coverage of the suicide.


Insight #7: Access to Methods for Suicide


          There is more to the suicidal act than the outcome. There is also the staging of the act (Lester & Stack, 2015) which involves choosing the method for suicide, the location, whether to write a suicide note, etc. Access to methods for suicide plays a large role. For example, in the UK, when home gas for heating and cooking was coal gas, coal gas was a popular method for suicide. When the UK switched to natural gas, which is less toxic and so more difficult to use for death, the suicide rate declined. In less industrialized and more rural countries, pesticides are used extensively, as is their use for suicide.




          There have been other interesting theories of the suicide rate in societies or in subgroups of the society which have received only partial support (that is, support in some studies and a failure to support the theory in other studies).


          For example, the social deviancy theory of suicide argues that suicide rates will be higher in groups in a society which are deviant in age, sexual orientation, ethnicity, etc. For example, Lester (1987) found that the fewer non-whites in a state, the higher their suicide rate.  


          Subcultural theories focus on characteristics of the society or part of the society. For example, states with a southern subculture have higher rates of gun ownership and higher rates of suicide using firearms (Lester, 1986-1987).


The Individual Suicide


Insight #8: Psychiatric Disturbance


          It is obvious that an understanding of suicide necessitates taking into account psychiatric disturbance. There are, however, grave problems with psychiatry as a science and, therefore, with psychiatric diagnosis.


To introduce you to my major objection, let us assume you have a headache and a fever. You go to your family physician, and he tells you that you have a disease called headache-fever, or HF for short. What would you do? You’d run as fast as you could out of his or her office and look for a good doctor. Medical illnesses are based on causes. What is causing your fever? What is causing your headache? Is it caused by a virus or bacteria? If so, which ones? Lyme’s disease or swine flu? Is it because of a brain tumor and, if so, is it malignant or benign?


Psychiatric disorders or mental illnesses are not defined by causes. They are defined by clusters of symptoms. Let us say you are depressed. Maybe it is because you do not have enough serotonin in certain regions of the brain. Maybe you have suppressed and repressed anger felt toward significant others in your life so that you are no longer conscious of the anger (a Freudian, psychoanalytic view). Maybe it is because you have learned from your life’s experiences that you cannot get out of the traps in which you find yourself (learned helplessness). Maybe it is because that are not enough rewards (positive reinforcers) in your life, either because you are in unrewarding relationships and employment or because you lack the skills to obtain rewards from others (a learning theory perspective). Maybe it is simply the melancholia that is part of all of our lives (Wilson, 2008)?


Don’t be fooled by new revisions of the Diagnostic and Statistical Manual (DSM). he criteria for this disease, disorders, or illness (call it what you will) still do not involve causes! Part of the motivation for revising the DSM is that psychiatrists cannot agree on which “illness” patients have. Using an older version of the DSM, Beck, et al. (1962) found that four psychiatrists, individually interviewing the same psychiatric patients, agreed only 54% of the time for the specific diagnosis and only 70% for the major category (schizophrenia, affective disorder, anxiety disorder, personality disorder, etcetera). In another study of the older version of the DSM, Sandifer, et al. (1968) had psychiatrists in three cities view tape-recorded interviews of psychiatric patients. In North Carolina, the patients were more often labeled as having neurotic disorders, In Glasgow, Scotland, the same patients were more often labeled as having personality disorders, and in London (England) the patients were more often labeled as having bipolar affective disorder (manic-depressive disorder)!


There have been three modern critiques of the current psychiatric system. Robert Whitaker’s Anatomy of an epidemic: Magic bullets, psychiatric drugs, and the astonishing rise of mental illness in America, Irving Kirsch’s The Emperor’s new drugs: Exploding the antidepressant myth, and Daniel Carlat’s Unhinged: The trouble with psychiatry. These books were favorably reviewed by Marcia Angell, a former editor of The New England Journal of Medicine, a prestigious scholarly medical journal, in The New York Review of Books (June 23 and July 14, 2012). Loren Mosher, a prominent psychiatrist, resigned from the American Psychiatric Association back in 1998, accusing the association of selling out to the pharmaceutical industry that markets psychiatric medications.[1]


          Even allowing for these problems with the psychiatric diagnostic system, I have never come across a methodologically sound study of psychiatric diagnosis of suicides. A sound study must have a control or comparison group, AND the diagnosis must be carried blind as to the presence of suicide or not. In all published studies, the diagnoses have been made by psychiatrists knowing that the person was a suicide. This knowledge accounts for some psychiatrists deciding that ALL suicides are psychiatrically disturbed.


Insight #9: Typologies of Suicides


          There have been many typologies of suicides proposed, but no one typology seems to be ideal. Van Hoesel (1983) chose typologies proposed by ten scholars and had judges classify 404 suicides from the files of the medical examiners in Baltimore and Maryland into the categories listed in the ten typologies. There were 69 subtypes in these ten typologies. Correlations between the 69 subtypes revealed five clusters of subtypes.


Escape (90 suicides)

Confusion (52 suicides)

Aggression (77 suicides)

Alienation (23 suicides

Depression/Low Self-Esteem (112 suicides)


          It is almost certain that no single theory of suicide can explain all suicides, and so a meaningful typology of suicides must be devised. Van Hoesel’s appears to be the best currently available. Next, it may be possible to find the causes for suicide that are specific for each type.


Insight #10: The Moods of Suicides


In his book Turning Points De Leo (2010) presented moving accounts from nine people who attempted to kill themselves, but who survived. Eight of the nine were happy to have survived. These accounts illustrate several features well-known to suicidologists, such as escape from mental and physical pain (Sergio and Maria), anger (Sandro), hopelessness and a feeling of being a burden (Anna), and suicide soon after discharge from a psychiatric hospital (Fabrizio). It is noteworthy that anxiety is noted by some. Alessa, Lucia and Maria all talk of suffocating and not being able to breathe anymore, and two of them (Lucia and Maria) indicate that the anxiety was long-standing and not simply a result of the decision to kill themselves. In fact, Maria tried to die to get away from the anxiety.


          Most commonly, depression and, in particular, the cognitive component of depression now labelled as hopelessness are proposed as present in suicides (Beck, et al. 1974). To this we might now add anxiety. Menninger (1938) classified the motives for suicide as to kill, to be killed and to die. The emotions accompanying these motives are anger, guilt and depression. Lester (1997) suggested that shame (as distinct from guilt) also plays a role in some suicides.


          This suggests that a typology based on the emotions experienced by suicides could be of value.


Insight #11: A Two-Self Theory of Suicide


          Lester (2022) proposed a two-self theory of suicide which he formally presented as a series of postulates and corollaries. Lester defined a subself is defined as a coherent system of thoughts, desires and emotions, organized by a system principle. For this theory of suicide, it is assumed that there are two subselves, a suicidal subself and a non-suicidal subself.


Postulate 1: Not every individual has both a suicidal subself and a nonsuicidal subself.

Postulate 2: At any point in time, one subself is in control of the mind. It may be said to have executive power.

Corollary 2a: When one subself has executive power, the other subself is said to be suspended.

Corollary 2b: A subself may appear in many situations, or only on rare special occasions. One subself may be domineering while the others is submissive.

Corollary 2c: A subself may have executive power for anywhere from seconds to hours or even longer periods of time.

Corollary 2d: Selfhood is whichever subself has executive power at the time.

Corollary 2e: The existence of two subselves accounts for the inconsistency in the behavior of individuals.

Postulate 3: Individuals can seek to create new subselves for the future.

Postulate 4: The individual can try to integrate the subselves.

Postulate 5: The suicidal subself may be a regressive subself developed early in life, formed by the introjection of the desires and thoughts of powerful others (in particular, parental figures) and imitation of their personality and behavioral styles.

Postulate 6: The suicidal subself may be formed as a result of early experiences.

Postulate 7: The possibility of attributing negatively valued aspects (thoughts, desires, emotions, or behaviors) of oneself to the suicidal subself may enable the individual to maintain high self-esteem since the negative aspects of the suicidal subself do not color the nonsuicidal subself.

Postulate 8: The two subselves may become enmeshed, and the psychotherapist must help the client create sufficiently impermeable boundaries so that the nonsuicidal subself can withstand pressure from the suicidal subself to take over executive power and resist intrusions from the suicidal subself into the nonsuicidal subself when the nonsuicidal subself has executive power.

Postulate 9: It is possible to create new subselves such as mediators and recording secretaries.




          Many theories of individual suicide are not theories that are applicable to all suicides, but merely provide one type of suicide and, therefore, should be included in typologies of suicide. For example, Joiner (2005) proposed that suicides have perceived burdensomeness, thwarted belonging, and the acquired capacity to inflict self-harm. However, Lester and Gunn (2022) found that this theory applied to only 3% of a sample of suicides that they studied. Perceived burdensomeness alone was found in only 15% of the sample.


          Another example comes from Transactional Analysis which proposes that suicidal individuals were exposed to desires of their parents that they not exist (Stewart & Joines, 1987). Perhaps the infant is handled with disgust or perhaps the mother wishes that the baby had never been born, a wish that may be expressed directly or consciously transmitted to the baby.


          A learning (or social learning) theory of suicide proposes that the individual learned suicide from others. A famous example is that both Ernest Hemingway and his brother Leicester Hemingway died by suicide, following in the footsteps of their father’s choice to die by suicide.




Insight #12: The Method of Substitute Subjects and Suicidal Intent


          The method of substitute subjects is the study of attempted suicides in order to learn about suicides. Suicides are deceased and cannot interviewed (of course), while attempted suicides can be interviewed and given psychological inventories. Also, of course, attempted suicides are of interest in their own right.


          But, as Lester, et al. (1975) noted, to learn about suicides from a study of attempted suicides, the attempters must be classified in terms of suicidal intent (or the lethality of their attempt). For example, a sample of attempted suicides can be divided into three groups, minimal suicidal intent, moderate suicidal intent and high suicidal intent. Then, if some variable increases (or decreases) in a linear fashion over these three groups, then extrapolation can be made to those who died by suicide. (Correlational studies using a suicidal intent score can also be used.)


Insight #13: Comparison Subjects


          This Insight is different because no research study has ever appeared on this idea. Palmer (1960) conducted a study of murderers by comparing them with their same sex siblings. Palmer also interviewed the parents of the men – murderer and brother. The use of same sex siblings, controlling for birth order of course, is that the subjects are matched on many variables, such as family dynamics (especially between the parents) and social and economic factors. Palmer was interested primarily in the physical and psychological frustrations that the men had experienced in the childhoods and adolescence, and he found that the murderers had experienced significantly more frustrations and had developed much less effective coping mechanisms. A study of suicides and their same-sex siblings would be extremely valuable!




          As mentioned in the beginning of this review of what we know about suicide, the harshness is not in the comments about those cited, but in the omission of scholars whom others may think have contributed greatly to suicidology. What is apparent, however, is how little we know about why people die by suicide.


          For example, given an adequate typology of suicides, have we a theory of causation of any type? One might argue that we can list some risk factors. But risk factors and not necessarily causes. For example, a risk factor for coming down with influenza is mingling socially with others during a flue epidemic without taking precautions such as wearing a mask or having a flu shot. But those are not the causes of influenza – a virus is the cause.





Angell, M. (2012a). The epidemic of mental illness: Why?

Angell, M. (2012b). The illusions of psychiatry.

Beck, A. T., Ward, C H., Mendelson, M., Mock, J. E., & Erbaugh, J. K. (1962). Reliability of psychiatric diagnoses. American Journal of Psychiatry, 119, 351-357.

Beck, A. T., Weissman, A., Lester, D., & Trexler, L. (1974). The measurement of pessimism: the hopelessness scale. Journal of Consulting & Clinical Psychology, 42, 861-865.

Carlat, D. (2010). Unhinged. New York: Free Press.

De Leo, D. (2010). Turning points. Bowen Hills, Australia: Australian Academic Press.

Henry, A. F., & Short, J., F, (1954). Suicide and homicide. Glencoe, IL: Free Press.

Joiner, T. E. (2005). Why people die by suicide. Harvard University Press.

Kirsch, I. (2010). The Emperor’s new drugs. New York: Basic Books.

Lester, D. (1972, 1983, 1992, 2000). Why people kill themselves. Springfield, IL Charles Thomas.

Lester, D. (1984). Suicide risk by birth cohort. Suicide & Life-Threatening Behavior, 14, 132-136.

Lester, D. (12986-1987). Southern subculture, personal violence (suicide and homicide) and firearms. Omega, 17, 183-186.

Lester, D. (1987). Social deviancy and suicide. Journal of Social Psychology, 127, 339-340.

Lester D. (1994). Patterns of suicide and homicide in America. Commack, NY: Nova Science.

Lester, D. (1995). Is divorce an indicator of general or specific malaise? Journal of Divorce & Remarriage, 23, 203-205.

Lester, D. (1997). The role of shame in suicide. Suicide & Life-Threatening Behavior, 27, 352-361.

Lester, D., Beck, A. T. & Trexler, L. (1975). Extrapolation from attempted suicides to completed suicides. Journal of Abnormal Psychology, 84, 563-566.

Lester, D., & Gunn, J. F. (2022).  Is perceived burdensomeness present in the lives of famous suicides? Death Studies, 46, 1801-1806.

Lester, D., & Stack, S. (2015). Suicide as a dramatic performance. New Brunswick, NJ: Transaction.

Malkiel, B. G. (1973) A random walk down Wall Street. New York: Norton.

Maris, R. W. (1981). Pathways to suicide. Baltimore: Johns Hopkins University Press.

Menninger, K. A. (1938). Man against himself. New York: Harcourt, Brace.

Moksony, F. (1990). Ecological analysis of suicide. In D. Lester (Ed.) Current concepts of suicide, pp. 121-138. Philadelphia, PA: Charles Press.

Palmer, S. (1960). A study of murder. New York: Thomas Crowell.

Pearson, K. (1905) The problem of the random walk. Nature. 72, 294.

Phillips, D. P. (1974). The influence of suggestion on suicide. American Sociological Review, 39, 340-354.

Sandifer, M., Horden, A., Timbury, G., & Green, L. (1968). Psychiatric diagnosis. British Journal of Psychiatry, 114, 1-9.

Stack, S. (1987). Celebrities and suicide. American Sociological Review, 52, 401-412.

Stewart, I., & Joines, V. (1987). TA today. Chapel Hill, NC: Lifespace.

Taylor, S. (1990). Suicide, Durkheim, and sociology. In D. Lester (Ed.) Current concepts of suicide, pp. 225-236. Philadelphia, PA: Charles Press.

Uematsue, M. A statistical approach to the host factor of suicide in adolescence. Acta Medica et Biologica, 8, 279-286.

Van Hoesel, F. M. T. (1983). An empirical typology of suicide. Master’s thesis, American University. Ann Arbor, MI: Proquest Dissertations Publishing.

Whitaker, R. (2010). Anatomy of an epidemic. New York: Crown.

Wilson, E. G. (2008). Against happiness: In praise of melancholy. New York: Farrar, Straus & Giroux.

Yang, B. (1994) A random-walk hypothesis for the suicide rate and its implications for Durkheim’s theory of suicide. In D. Lester (Ed.) Emile Durkheim: Le Suicide 100 years later, pp. 319-324. Philadelphia, PA: Charles Press.

Yang, B., & Lester, D. (2004). Natural suicide rates in nations of the world. Crisis, 25, 187-188.

Yang, B., & Lester, D. (2021). Is there a natural suicide rate? An update and review. Suicide Studies, 2(4), 5-12.


Monday, December 05, 2022

A review of citations to "Recalculating the economic cost of suicide" by Yang and Lester





David Lester & Bijou Yang


          Abstract: An analysis of 91 citations for an article by Yang and Lester (2007), which argued that suicides result in savings to the society, showed that only 9 reported Yang and Lester’s thesis correctly, and only one article conducted a serious discussion of the issues raised by Yang and Lester.




          Viscusi (1984) argued that the financial savings from the premature deaths of those who smoke cigarettes (as a results of reduced nursing home care costs and pension and social security payouts) were greater than the costs of medical care and life insurance. Viscusi calculated that each pack of cigarettes sold saves the society $0.72.


          Yang and Lester (2007) applied Viscusi’s arguments to those who die by suicide. Suicides results in savings from healthcare and nursing home costs later in life, as well as pension and social security payouts. When estimating the loss from future earnings by suicides, researchers typically forget that suicides may not be the most productive members of society. Many psychiatric researchers (e.g., Robins, 1981) argue that almost all suicides merit a psychiatric diagnosis, often a severe and disabling psychiatric disorder, and so their future earnings may be far lower than those of average citizens. Their psychiatric disorder may also incur large economic costs for psychiatric treatment had they lived.


Yang and Lester estimated the cost of suicides in 2005 in the USA to be $16.83 billion, the savings from not having to treat the psychiatric disorders of the suicides had they continued to live to be $8. 11 billion, the savings from pensions and nursing home care to be $12.99 billion, and the savings from assisted suicide to be $0.80 billion, giving a net savings from the suicides to be $5.07 billion in 2005 dollars.


          As of the time of writing this article, Yang and Lester (2007) had 91 citations noted in Google Scholar. That seems to be impressive. The present review examined these 91 citations to see how they cited Yang and Lester.


Reviewing the Citations


Google Scholar examines a variety of writings for citations, including, of course, articles in scholarly journals and books, but also dissertations, blogs and unpublished papers uploaded to websites such as ResearchGate. This is an impressive achievement, but Google Scholar citations are, therefore, not restricted to scholarly publications.


Thirteen of the citations were not in English and so not examined for this review. Five authors simply included a reference to Yang and Lester is a list of references without mentioning the article in the text, and two “citations” did not contain any reference to Yang and Lester.


          On six occasions, the same article was included twice, for example, as a pre-print on a university website and as the published article.


          Seven articles misquoted Yang and Lester. For example, Savage (2018) said that Yang and Lester discussed the rationality of suicide. This was not the focus of Yang and Lester. Other misquotes were made by Fredette (2014), Li and Zhang, (2010), Ring, et al. (2015), Rivera, et al. (2017), Saleh (2016), while others simply included a non-specific citation to Yang and Lester in a series of cites, such as 1-21 (Poduri, 2016).


Yang and Lester reviewed briefly research on the estimated costs to the society of attempted suicide, although Yang and Lester did not present new calculations, and 20 articles quoted Yang and Lester for the estimated costs of attempted suicide (Barrigan, et al., 2022; Bolton, et al., 2015; Brann, et al., 2021; Francisco, et al., 2020; Ghahramanlou-Holloway, et al., 2012; Gysin-Maillart, et al., 2016;  Keefner & Stenvig, 2021; Kim, et al., 2022; Kochanski, 2012; Lee, 2016; Lynch, 2014; Mickle, 2011; Milner & De Leo, 2010; Murrell, et al., 2014; Myrick, et al., 2017; Polits, 2016; Rothes, 2014; Sheftall, et al., 2013; Shepard, et al., 2016; Woodland, 2014).


Twenty authors cited Yang and Lester for saying completed suicide incurs costs for the society, which is the opposite of what Yang and Lester argued (Bermeo, 2019; Bolton, et al., 2015[1]: Brann, et al., 2021; Dunn, 2013; Johnston, 2013; Kim, et al., 2022; Kirigia, et al., 2020; Layden, 2017; Lynch, 2014; Moutier, 2014; Murphy, et al., 2021; O’Brien, 2010; Onoya, et al., 2021; Rothes, 2014; Sand, 2012; Sels, et al., 2021; Sheehan, et al., 2019; Singer, et al., 2022; Tondo, et al., 2008; Vannoy[2], et al., 2010). These 20 authors do not appear to have understood Yang and Lester’s thesis.


Kinchin and Doran (2017, 2018) looked at the cost of suicide in Australia. As well as calculating the cost of the legal and medical procedures following a suicide (direct costs), they also estimated the loss of economic productivity resulting from the lost years of life, but they admit that they ignored the savings discussed by Yang and Lester. A similar tactic of ignoring the essence of Yang and Lester’s analysis was made by Shepard, et al. (2016)[3] and Alfonso-Sánchez, et al. (2020). Others simply ignored Yang and Lester without mentioning that they were ignoring their argument (Lyszczarz, 2021).


Seven authors cited Yang and Lester correctly, admitting that suicides can result in an economic benefit for the society (Gunn, 2019; Ohayi, 2019; Snow, et al., 2016; Sueki, 2016; Torp, 2014; Ying & Chang, 2009; Zak, 2015). Luckily, two self-citations also correctly reported the results of Yang and Lester. Two more researchers cited the thesis of Yang and Lester correctly and did additional calculations (see the next section).


Research on the Economic Cost of Suicide


Sarma (2018) estimated the economic cost of suicides in India is 2015 and did consider both economic losses and gains resulting from those suicides, but he calculated that the losses far exceeded the gains.


The most complete discussion of Yang and Lester’s article was made by Stack (2007). Stack drew attention to three issues. First, although it is true that suicides, by dying at a younger age than those dying from other causes, save on the direct costs of healthcare (medical and psychiatric), the longer people survive, the more healthcare jobs created. In this regard, suicides incur a cost to the society.


Second, the costs incurred by those grieving for those who died by suicide may differ from the costs incurred by those grieving for those dying of other causes. Stack noted that suicides are typically sudden deaths, a factor which may affect grieving. On the other hand, suicides typically have smaller social networks than those dying from other causes, and so there are fewer people grieving.


Third, Stack argued that Yang and Lester overestimated the costs of healthcare for suicides. In his discussion, Stack focused on what percentage of suicides sought mental health treatment in the last year of their life. However, Stack also noted that the average age at death was 45 for suicides, and so they avoid roughly 30 years of life. It is during these 30 years that healthcare costs may be large.




          The present analysis of citations to our article indicates that citations may not be a valid measure of the significance of an article. Only nine researchers cited Yang and Lester’s article correctly, and only one (Stack, 2007) conducted a serious discussion of the issues raised by Yang and Lester. In the years since 2007, the thesis of Yang and Lester’s article has died a natural death.




Alfonso-Sánchez, L., Martin-Moreno, J. M., Martinez, R. M., & Martinez, A. A. (2020). Epidemiological study and cost analysis of suicide in Spain. Archives of Suicide Research, 24, S356-S369.

Barrigan, M. L., Porras-Segovia, A., Courtet, P., et al. (2022). Smartphone-based ecological momentary intervention for secondary prevention of suicidal thoughts and behavior. BMJ Open, 12, e051807.

Bermeo, M. I. T. (2019). Understanding self-harm behaviour in older adults. PhD dissertation, Keele University, UK.

Bolton, J. M., Walld, R., Chateau, D., Finlayson, G., & Sareen, J. (2015). Risk of suicide and suicide attempts associated with physical disorders. Psychological Medicine, 45, 495-504.

Brann, K. L., Baker, D., Smith-Millman, M. K., Watt, S. J., & DiOrio, C. (2021). A meta-analysis of suicide prevention programs for school-aged youth. Children & Youth Services Review, 121, #105826.

Dunn, E. (2013). The influence of belief in a positive afterlife on youth suicide in a Northwestern Ontario First Nation. PhD dissertation. Walden University.

Francisco, A. P., Motta, G. L. C. L., Zortea, F., et al. (2020). Lower estimated intelligence quotient is associated with suicide attempts in pediatric bipolar disorder. Journal of Affective Disorders, 261, 103-109.

Fredette, G. J. (2014). Tribulations and tears. MA thesis. University of Manitoba, Canada.

Ghahramanlou-Holloway, M., Cox, D. W., & Greene, F. M. (2012). Post-admission cognitive therapy. Cognitive & Behavioral Practice, 19, 233-244.

Gunn, J. F. III (2019). Suicide in younger and older adults.  PhD dissertation, Montclair University.

Gysin-Maillart, A., Schwab, S., Soravia, L., Megert, M., & Michel, K. (2016). A novel brief therapy for those who attempt suicide. PLOS Medicine, 13(3), e1001968.

Johnston, A. K. (2013). Suicidality in Australia. PhD dissertation, University of New South Wales, Australia.

Keefner, T. P., & Stenvig, T. (2021). Suicidality. Issues in Mental Health Nursing, 42, 227-238.

Kim, M. J, Lee, H., Shin, D., Hong, M., Rhee, S. J., Park, J. I., & Ahn, Y. M. (2022). Effect of attitude toward suicide on suicidal behavior. Psychiatry Investigations, 19, 427-434.

Kim, S., Jeon, H., & Park, J. (2022). The association of physical and mental illness and self-harm resulting in hospitalization. International Journal of Environmental Research & Public Health, 19, #8303.

Kim, Y. J. (2009). Influential factors on adolescent’s suicidal behavior. MSci thesis, University of Texas at Arlington.

Kinchin, I., & Doran, C. M. (2017). The economic cost of suicide and non-fatal suicide behavior in the Australian workforce and the potential impact of a workplace suicide prevention strategy. International Journal of Environmental Research & Public Health, 14, #347.

Kinchin, I., & Doran, C. M. (2018). The cost of youth suicide in Australia. International Journal of Environmental Research & Public Health, 15, #672.

Kirigia, J. M., Muthuri, R. D. K., & Muthuri, N. G. (2020). The monetary value of human lives lost to suicide in the African continent. Healthcare, 8, #84.

Kochanski, K. (2012). Characteristics of living and deceased suicidal military personnel based on single versus multiple suicide attempt status. MSci thesis, Uniformed Services University.

Layden, B. K. (2017). Structured professional assessment and management of self-directed violence (SDV). PhD dissertation. Simon Fraser University, Canada.

Lee, B. X. (2016). Causes and cures IX. Aggression & Violent Behavior, 30, 110-114.

Li., N., & Zhang, J. (2010). Influencing factors for depression among Chinese suicide survivors. Psychiatry Research, 178, 97-100.

Lynch, F. L. (2014). Population health outcome models in suicide prevention policy. American Journal of Preventive Medicine, 47, S137-S143.

Lyszczarz, B. (2021). Production losses attributable to suicide deaths in the European Union. BMJ Public Health, 21, #950.

Michel, K., Valach, L., & Gysin-Maillart, A. (2017). A novel therapy for people who attempt suicide and why we need new models of suicide. International Journal of Environmental Research & Public Health, 14, #243.

Mickle, T. A. (2011). LGB youth suicide risk. MA thesis, St Mary’s College of California.

Milner, A., & De Leo, D. (2010). Who seeks treatment where? Journal of Nervous & Mental Disease, 198, 412-419.

Moutier, C. (2014). Tactics of the war on suicide. Depression & Anxiety, 31, 961-963.

Murphy. L., Lyons, S., O’Sullivan, M., & Lynn, E. (2021). Risk factors for suicide among people who use drugs. HRB Open Research, 3, #45.

Murrell, A. R., Al-Jabari, R., Moyer, D., Novamo, E., & Connally, M. (2014). An acceptance and commitment therapy approach to adolescent suicide. International Journal of Behavioral Consultation & Therapy, 9(3), 41-46.

Myrick, A. C., Webermann, A. R., Langeland, W., Putnam, F. W., & Brand, B. L. (2017). Treatment of dissociative disorders and reported changes in inpatient and outpatient cost estimates. European Journal of Psychotraumatology, 8(1), #1375829.

O’Brien, R. M. (2010). Offender trajectories, crime trends, and costs. Criminology & Public Policy, 9, 313-319.

Ohayi, S. R. (2019). “Doctor, please don’t say he died of suicide.” Egyptian Journal of Forensic Sciences, 9, #48.

Onoya, E. D., Makwakwa, N. L., & Motioba, D. P. (2012). Temporal variation in suicide in peri-urban Pretoria. South African Family Practice, 63(1), e5260.

Poduri, G. S. Short-term cost of suicides in India. Indian Journal of Psychological Medicine, 38, 524-528.

Polits, M. (2016). Factors that affect recidivism for psychiatric patients in the emergency department. PsyD thesis, George Fox University.  

Ring, M., Walther, S., & Gysin-Maillart, A. (2019). The association between therapeutic alliance and individuals’ wish to die or live. Psychology, 10, 1711-1725.

Rivera, B., Casal, B., & Currais, L. (2017). Crisis, suicide and labour productivity losses in Spain. European Journal of Health Economics, 18, 83-96.

Robins, E. (1981). The final months. New York: Oxford University Press.

Rothes, I. M. S. A. 2014). Suicidal behaviours: explanations, current practices and difficulties of health professionals and the impact of a patient suicide. PsyD dissertation, University of Porto, Portugal.

Saleh, S. N. M. (2016). A novel dynamic feature selection and prediction algorithm for clinical decisions involving high-dimensional and varied patient data. PhD dissertation, Aston University, UK.

Sand, E. C. (2012). An examination of the effect of nostalgia on risk factors for suicide. MSc thesis, North Dakota State University.

Sarma, P. G. (2018) Financial aspect of Indian suicides in 2015. Indian Journal of Psychological Medicine, 40, 201-204.

Savage, D. A. (2018). A rational choice to die. University of Newcastle, Australia.

Sels, L., Homan, S., Ries, A., Santhanam, P., et al. (9021). SIMON: A digital protocol to monitor and predict suicidal ideation. Frontiers in Psychiatry, 12, #554811.

Sheehan, C. M., Rogers, R. g., & Boardman, J. D. (2015). Postmortem presence of drugs and method of violent suicide. Journal of Drug Issues, 45, 249-262.

Sheftall, A. H., Mathias, C. W., Furr, R. M., & Dougherty, D. M. (2013). Adolescent attachment security, family functioning, and suicide attempts. Attachment & Human Development, 15, 368-383.

Shepard, D. S., Gurewich, D., Lwin, A. K., Reed, G. A., & Silverman, M. M. (2016). Suicide and suicidal attempts in the United States. Suicide & Life-Threatening Behavior, 46, 352-362.

Singer, S., Sievers, L., Scholz, I., Taylor, K., Blanck, J., & Maier, L. (2022). Suicidal ideation and attempts in adults seeking outpatient psychodynamic psychotherapy. Clinical Psychology & Psychotherapy, in press.

Snow, C. E., & Abrams, R. C. (2016). The indirect costs of late-life depression in the United States. Geriatrics, 1, #30.

Stack, S. (2007). Societal and economic costs and benefits from death. Death Studies, 31, 363-372.

Sueki, H. (2016). Willingness to pay for suicide prevention in Japan. Death Studies, 40, 283-289.

Tondo, L., Lepri, B., & Baldressarini, R. J. (2008). Suicidal status during antidepressant treatment in 789 Sardinian patients with major affective disorder. Acta Psychiatrica Scandinavica, 118, 106-115.

Torp, E. (2014). Development of YLL due to suicide in young people in Norway. Master’s thesis. University of Oslo, Norway.

Vannoy, S., Whiteside, U., & Unützer, J. (2010). Current practices of suicide risk management protocols in research. Crisis, 31, 7-11.

Viscusi, W. K. (1984). Cigarette taxation and the consequences of smoking. Cambridge, MA: NBER.

Woodland, J. M. (2014). Native American youth and suicide. PhD dissertation, Widener University.

Wortzel, H. S., Gutierrez, P. M., et al. (2010). Surrogate endpoints in suicide research. Suicide &Life-Threatening Behavior, 40, 500-505.

Yang, B., &Lester, D. (2007). Recalculating the economic cost of suicide. Death Studies, 31, 351–361.

Ying, Y. H., & Chang, K. (2009). A study of suicide and socioeconomic factors. Suicide & Life-Threatening Behavior, 39, 214-226.

Zak, D. (2015). Mental Health—An Issue Neglected by European Public Health Systems? In D. Claborn (Ed.) Topics in public health.


[1] Already cited above.

[2] Vannoy, et al. (2010) and Kim (209) had the authors’ names incorrect.

[3] Already listed above.