Tuesday, April 14, 2009

Interrogating the Data

My good friend and colleague, Valentin Mikhailov, has reminded me that the main issue with election fraud is not its presence, but rather its scale. Systematic error - of origins both sinister and benign - is a common component of elections. While several political scientists have weighed in on methods to identify fraud, notably Walter Mebane, Misha Myagkov, and Peter Ordeshook, at best researchers can uncover data anomalies that are most plausibly explained by vote manipulation. As Mark Nigrini noted, forensic accountants tend to rely on a series of "data interrogation tests" to uncover improprieties. Even then, the existence of an anomaly does not reveal its cause.

When I evaluate precinct-level election data, I pay close attention to the performance of pro-regime parties, turnout, invalid ballots, and if available, other features like mobile ballot box use. In addition, I compare the distribution of digits to a Benford-type distribution. Several decades ago, Frank Benford re-discovered an interesting property of digits in naturally occurring datasets: ones are the most common first digit, with the probability of a digit being first declining logarithmically. His work has informed the accounting literature, as well as political science. Unfortunately, some properties of election data undermine the application of Benford's Law, such as the presence of zeros (Benford does not account for a zero as the first and only digit), and precinct size (precinct size varies, and it determines the "available" digits). Despite these complications, I have compared data from other post-Soviet states to the Benford distribution and found interesting results, especially in Ukraine.

While I have not performed a full and systematic analysis of the data (having only acquired it last night), the initial scan of data suggests that there is no "smoking gun." The first and second digit Benford test on the results for the PCRM reveals no major issues. While the number of ones is low (significantly lower than anticipated by Benford), the distribution of PCRM first and second digits is not statistically different from the Benford-type distribution. The PCRM performs exceptionally well in several precincts: it received above 90% in eleven precincts. But, no precincts report 100% for the PCRM (in many questionable elections, I have found precincts with regime support at 100%). Some precincts report extremely high turnout, based largely on voters added through a supplemental list (some of these are polling places outside of the country in embassies or consulates). In these precincts, the average vote for the PCRM was 35% - below what it received nationally. The rate of invalid ballots is not high (the mean is just above 1%). The highest invalidation rate was 9%; the PCRM received 43% of the vote in that precinct.

Tomorrow's recount will be an interesting, and unprecedented, exercise in the post-Soviet world. The opposition has decided to boycott the recount, instead hoping to have voter lists re-evaluated. The opposition claims that "dead souls" and other illegitimate persons were on the voter lists, allowing the PCRM to inflate its results. Based on the precinct-level data that has been released, evidence of large-scale ballot box stuffing is not strong.

Monday, April 13, 2009

Countdown to the Recount

Moldova's Constitutional Court authorized a recount of the parliamentary election, which is now scheduled to take place on Wednesday. On a related note, the CEC has made precinct-level data available, and I plan to acquire and take a look at the information soon.

Saturday, April 11, 2009

Repression in Moldova

Several unpublished imedia reports note that the political opposition is being quietly repressed. While it can be difficult to separate rumor from fact, news agencies (imedia cites Unimedia) and NGOs (Amnesty International) have reported arrests of young people, or threats of harassment. Stories broadcasting evidence of abuse and the allegations of victims are on YouTube.

In addition, the use of Twitter and other methods to mobilize protesters has been undermined by spamming and contradictory messages. Further complicating matters, imedia also indicates that reporters from several international media agencies such as the BBC, Associated Press, and Reuters, as well as Romanian news outlets, have been denied entry into Moldova. Some reporters in Moldova have been detained.

Nicu Popescu's blog provides ongoing discussion of events.

[Thanks to imedia for several reports on events in Moldova.]

Friday, April 10, 2009

Chisinau and Tbilisi

In response to protest activities, President Voronin has called for a recount of Sunday's parliamentary vote. This decision would be rendered more transparent by public release of precinct-level data. It is interesting to note that links to turnout and voting data are no longer active on the CEC website. While protests have been scheduled for today in Chisinau, early activity is light, with no protesters assembled by mid-morning. Looking to the south, the opposition has increased its activities in Georgia, staging a large protest to call for an early presidential election (also see Eurasianet's story).

Tuesday, April 7, 2009

Protests Escalate in Moldova

In a scene reminiscent of Georgian protesters' occupation of parliament in 2003 and Kyrgyz protesters' takeover of the presidential administration building in 2005, Moldovan protesters attacked parliament to express their deep dissatisfaction with Sunday's election. An unpublished imedia report suggests that the opposition has not planned major protests, but may "organize 'mass protests' soon," perhaps spurred on by the demonstrations on Monday and Tuesday. Several sources, including imedia, suggest that mobilization has been decentralized, with young people organizing activities online and by using sms. Protest is difficult to organize and maintain, however. Facing an overwhelming gap between the PCRM and opposition parties' tallies at the polls, lacking clear evidence of widespread falsification and condemnation from international observers, and absent plans to stage long-term protests, the odds are stacked heavily against the opposition.

Monday, April 6, 2009

Post-Election Protest

Several thousand Moldovans protested the PCRM's victory in yesterday's election, alleging that vote fraud was a major factor in the PCRM's success (the OSCE's preliminary post-election report was generally positive, although some problems were noted). Reports indicate that largely young people were mobilized. Estimates of protest size range from 2,500 to 20,000; photographs certainly suggest that the number of participants exceeds the lowest estimates. More protests are scheduled for Tuesday.

The Results are In

With just under 2% left to count (98.08% reporting), the Party of Communists (PCRM) has 49.96% of the vote, with the PL (12.78%), PLDM (12.26%), and ALM (9.81%) trailing far behind. With roughly 15% of the vote wasted on parties failing to pass the 6% barrier, the PCRM will secure a majority in parliament. While the exit polls indicated a lower tally for the PCRM, it is likely within the margin of error (which was not reported). Hopefully, the CEC will release data aggregated at a lower level to facilitate more extensive analysis of the results.

[The graphic is posted on the CEC site.]

Sunday, April 5, 2009

Preliminary Results in Moldova

At the time of this post, it is a bit past 3 am in Chisinau, Moldova. The CEC is reporting results with 31.45% of the vote counted, and the Party of Communists leads with 53.87% of the recorded votes. While the CEC has posted information about polling stations, the current reports about voting are aggregated at the national level only. It is difficult to assess how the vote count is likely to evolve without a sense of what precincts have reported. With the previously mentioned BBC report on exit polls as a guide, we should expect the Communist tally to taper off as more results come in.

Turnout in Moldova

The CEC is reporting regional turnout data (but no precinct-level results seem to be available). As of 6:45 p.m., national turnout was 52.4%, ranging from a high of 73.28% in Basarabeasca to a low of 43.09% in Balti. Lenta.ru notes that the election officially passed the minimum turnout threshold of 50%. The CEC will also post preliminary results, but it is too early for information to be available.

UPDATE (4/5/09, 2:45 pm Central Time (US)): The CEC server seems to be down. A BBC report on exit polls indicates that the Party of Communists should enjoy a substantial win (46%).

UPDATE (4/5/09, 7:00 pm Central Time (US)): The CEC server is up and is reporting some preliminary results as well as updated turnout data.

Friday, April 3, 2009

Under the Radar

Moldova's parliamentary election is only two days away, but it continues to fly under the radar of Western news organizations (even those covering the post-Soviet region). The CEC has published documents related to the election (pdf in Russian), but its website provides limited information. Moldova Azi reports on CEC preparations and concerns about potential problems on Sunday. The OSCE has posted several preliminary reports. I will post additional information in the coming days, but I am currently attending a conference (limiting my ability to be attentive to the final hours of the campaign).