A Statistical Analysis of the ICTY's bias. | 220 comments (213 topical, 7 editorial, 0 hidden)

Re: A Statistical Analysis of the ICTY's bias. (4.00 / 2)

What you've done is shown that Serbs are convicted more often than you'd expect in random experiments.

No he hasn't. That's a statistical mirage, because he arbitrarily classifies 7 of the Serbian suspects as being related to Kosova (rather than, say, split them evenly among the three wars, or split them among the three wars in proportion to the number of civilian casualties, both of which would have been more appropriate).

To understand why this is misleading, consider the outcome if I placed those seven indictees in Bosnia instead of Kosova: Then the vanilla average (which remains an inappropriate measure), goes from 3 per mille to 2.4 per mille. Purely from arbitrarily designating the 7 Serbian indictees for which there is too little information in the indictments to tell which wars they were indicted over.

And then he proceeds to happily make a vanilla average out of ratios that are up to a full order of magnitude different in both numerator and denominator. You're not allowed to do that. When you divide a very small number by another very small number, you get a higher uncertainty on your ratio than when you divide a very big number by another very big number. One or two wrongfully indicted Serbs from the Croatian war - or one or two hundred civilians miscounted - would count far more towards the ratio than a similar number for Bosnia.

So the three ratios cannot be given equal weight. You avoid all these problems by using a weighted average. But of course, the "signal" goes away when you do that...

- Jake

Friends come and go. Enemies accumulate.

by JakeS (JangoSierra 'at' gmail 'dot' com) on Mon Mar 16th, 2009 at 05:37:29 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 1)

JakeS:

he arbitrarily classifies 7 of the Serbian suspects as being related to Kosova

The classification needn't be arbitrary. In wikipedia's List of indictees of the International Criminal Tribunal for the former Yugoslavia each indictee is assigned an ethnic group and an incident.

One thing that Vladimir does wrong is compare Indictees to Convictions, implying that those not convicted have been acquitted. This is not the case. The proper comparison would be the ratio of convictions to acquittals/case-dismissals as there are a number of cases which are ongoing, have been transferred to national jurisdiction, were never concluded because the indictee died, or in which the indictee is at large. Vladimir posted the full stats
here (these do not distinguish between the different wars or regions, only ethnic groups):

Stats from ICTY (none / 0) Here they are

Most economists teach a theoretical framework that has been shown to be fundamentally useless. -- James K. Galbraith

by Carrie (migeru at eurotrib dot com) on Mon Mar 16th, 2009 at 05:50:00 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 1)

The 7 didn't have a classification... it would have required hours of sifting through documents to find them.

by vladimir on Mon Mar 16th, 2009 at 05:55:26 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 1)

Then you can't ascribe them to Kosova, especially given that Kosova is the conflict with the smallest number of indictees and arbitrarily assigning 7 Serbs to it biases the data more than, say, assigning the 7 to Krajina or Republika Srpska.

Most economists teach a theoretical framework that has been shown to be fundamentally useless. -- James K. Galbraith

by Carrie (migeru at eurotrib dot com) on Mon Mar 16th, 2009 at 05:58:04 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 1)

Another usegul comparison would be between indictees and population. Serbs were the largest ethnic group in the former Yugoslavia by a factor of nearly 2. See the table on Ethnic composition of Yugoslavia in 1981 in Wikipedia's Demographics of SFR Yugoslavia. A log-log regression of indictees vs. population might be appropriate in this case, too.

Most economists teach a theoretical framework that has been shown to be fundamentally useless. -- James K. Galbraith

by Carrie (migeru at eurotrib dot com) on Mon Mar 16th, 2009 at 05:56:38 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 0)

I've delved into their documents. I agree, it's an unorganized mess. A horror-show for scholars.

"It Can't Be Just About Us"
--Frank Schnittger, ETian Extraordinaire

by papicek (papi_cek_at_hotmail_dot_com) on Mon Mar 16th, 2009 at 05:59:33 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 1)

OK, then that's kosher.

The vanilla averages instead of weighted averages is still nonsense, though.

- Jake

Friends come and go. Enemies accumulate.

by JakeS (JangoSierra 'at' gmail 'dot' com) on Mon Mar 16th, 2009 at 05:58:38 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 1)

European Tribune - A Statistical Analysis of the ICTY's bias.

For 7 Serbs (like Slobodan Milosevic) and others (mostly members of the FRY government or army and navy) who were not accused of a specific war crime in Bosnia or Croatia, I associated their indictment with events in Kosovo.

Who are the 7?

Milosevic is mentioned as part of a "Joint Criminal Enterprise" with Seselj, who was indicted for events in Croatia. You can't just throw Milosevic into the Kosovo pot to inflate the ratio of Serbs to Albanians indicted for Kosovo.

Most economists teach a theoretical framework that has been shown to be fundamentally useless. -- James K. Galbraith

by Carrie (migeru at eurotrib dot com) on Mon Mar 16th, 2009 at 06:46:12 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 1)

Dragoljub Ojdanic
Charges of war crimes, deportation and forcible transfer, murder and persecution

Nebojša Pavkovic
Charges of war crimes, deportation and forcible transfer, murder and persecution.

Nikola Šainovic
Charges of war crimes, deportation and forcible transfer, murder and persecution.

Sreten Lukic
Command authority for crimes against humanity in Kosovo

Vladimir Lazarevic
Charges of war crimes, deportation and forcible transfer, murder and persecution.

Milan Simic
No information

by vladimir on Mon Mar 16th, 2009 at 06:52:03 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 1)

Google is your friend.

BBC News | EUROPE | Profile: Dragoljub Ojdanic

During 1999, when the Yugoslav army and police committed atrocities against Kosovo Albanians, Colonel General Dragoljub Ojdanic held the position of the Yugoslav Army's chief of staff.

Nebojša Pavković - Wikipedia, the free encyclopedia

Nebojša Pavković (Serbian Cyrillic: Небојша Павковић; born in the village of Senjski Rudnik near Ćuprija on April 10, 1946) was former Chief of the General Staff of FRY. In 2009, he was convicted by the International Criminal Tribunal for the former Yugoslavia (ICTY) of committing crimes against humanity and war crimes in the Kosovo War.

BBC News | EUROPE | Profile: Nikola Sainovic

In May 1999, the UN War Crimes Tribunal in the Hague indicted Nikola Sainovic for war crimes committed in Kosovo in 1998 and 1999.

Trial Watch : Sreten Lukic

The original indictment alleges that Sreten Lukic as well as Vladimir Lazarevic, Vlastimir Djordjevic and Nebojsa Pavkovic (see "related cases"), planned, instigated, ordered, committed or otherwise aided and abetted in preparing certain crimes. According to the indictment Lukic was part of a joint criminal enterprise which had the aim, in addition to other objectives, to expel a major part of the Kosovo Albanian civilians from the province in which they were living in order to maintain this province under Serb control. This joint criminal enterprise reportedly came into being, at the latest, in October 1998 and continued until 20 June 1999.

Trial Watch : Vladimir Lazarevic

The original indictment alleges that Vladimir Lazarevic as well as Vlastimir Djordjevic Nebojsa Pavkovic and Sreten Lukic (see "Related Cases"), planned, instigated, ordered, committed or otherwise aided and abetted in preparing certain crimes. According to the indictment Lazarevic was part of a joint criminal enterprise which had the aim, in addition to other objectives, to expel a major part of the Kosovo Albanian civilians from the province in which they were living in order to maintain this province under Serb control. This joint criminal enterprise reportedly came into being, at the latest, in October 1998 and continued until 20 June 1999.

Sentencing Judgement in the case "The Prosecutor v. Milan Simic"Accused Convicted to 5 years Imprisonment

The accused, Milan Simic, a 42 year-old Bosnian Serb, was first indicted by the Prosecutor of the Tribunal together with Blagoje Simic, Simo Zaric, Miroslav Tadic, Stevan Todorovic and Slobodan Miljkovic for crimes alleged to have occurred in the area of Bosanski Samac in north-western Bosnia and Herzegovina in 1992.

Most economists teach a theoretical framework that has been shown to be fundamentally useless. -- James K. Galbraith

by Carrie (migeru at eurotrib dot com) on Mon Mar 16th, 2009 at 07:08:11 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 0)

Thank you.
So I was right for 6 out of 7 of them.

by vladimir on Mon Mar 16th, 2009 at 07:18:08 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 0)

But you were wrong that that

it would have required hours of sifting through documents to find them

Most economists teach a theoretical framework that has been shown to be fundamentally useless. -- James K. Galbraith

by Carrie (migeru at eurotrib dot com) on Mon Mar 16th, 2009 at 08:06:37 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 0)

Well, as I read it it would have required hours of sifting through documents to find them for vladimir which he is uniqely positioned to judge.

So, one out of seven was misplaced. Does it change anything.

Sweden's finest (and perhaps only) collaborative, leftist e-newspaper Synapze.se

by A swedish kind of death on Mon Mar 16th, 2009 at 08:12:03 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 0)

Changes nothing.

by vladimir on Mon Mar 16th, 2009 at 08:22:55 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 0)

Actually, for some unknown reason, Google stopped working on my machine. Each request takes 15-30 seconds to display, so I have no choice but to use Yahoo search which is not nearly as good.

by vladimir on Mon Mar 16th, 2009 at 08:15:12 AM EST
[ Parent ]

Cuil search (none / 0)

Try Cuil

You can't be me, I'm taken

by Sven Triloqvist on Mon Mar 16th, 2009 at 08:22:52 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (none / 1)

So Jake, the 6 of the 7 were classified correctly. It's not a mirage.

by vladimir on Tue Mar 17th, 2009 at 04:00:58 AM EST
[ Parent ]

Re: A Statistical Analysis of the ICTY's bias. (4.00 / 2)

Read the entire comment that you reply to. Specifically:

And then he proceeds to happily make a vanilla average out of ratios that are up to a full order of magnitude different in both numerator and denominator. You're not allowed to do that. When you divide a very small number by another very small number, you get a higher uncertainty on your ratio than when you divide a very big number by another very big number. One or two wrongfully indicted Serbs from the Croatian war - or one or two hundred civilians miscounted - would count far more towards the ratio than a similar number for Bosnia.
So the three ratios cannot be given equal weight. You avoid all these problems by using a weighted average. But of course, the "signal" goes away when you do that...

- Jake

Friends come and go. Enemies accumulate.

by JakeS (JangoSierra 'at' gmail 'dot' com) on Tue Mar 17th, 2009 at 04:58:29 AM EST
[ Parent ]

A Statistical Analysis of the ICTY's bias. | 220 comments (213 topical, 7 editorial, 0 hidden)

Top Diaries

Ireland 2023 Rugby World Cup Squad selected

Integrating Ukraine Into NATO Family

Leinster's demise and Munster's hope

Southern Irish disinterest in Northern Ireland affairs

The end is Nigh?

Joe Biden. America's Interventionist Hero

The law of conservation of transness

Recent Diaries

June 2023

Ireland 2023 Rugby World Cup Squad selected

Integrating Ukraine Into NATO Family

Southern Irish disinterest in Northern Ireland affairs

Incident Ukrainian War Display Gets Int'l Attention

German Climate Activists Group Outlawed

Leinster's demise and Munster's hope

Joe Biden. America's Interventionist Hero

Targeted Assassinations: a Bankrupt Strategy

The end is Nigh?

Hijacking Peace by Zelensky for War Escalation

UA Drone Attack On Moscow

Rightwing Operation New EU 'Enlightenment’

May 2023

The law of conservation of transness

US Provoked Conflict In Europe

U.S. Will Be Ousted From Middle-East

Settler Extremism Blessed by Jerusalem Leaders

Occasional Series