The Moorish Wanderer

Elections – Dewey Defeats Truman. (And a Mea Culpa)

Posted in Flash News, Intikhabates-Elections, Morocco by Zouhair ABH on December 26, 2012

I should first start by apologising for some shortcomings in my earlier predictions about results in the couple of by-elections that took place last week, as well as those scheduled in the near future. I have realised I was manipulating the wrong codes to generate my results, and so results from the two latest posts on predictions about electoral outcomes may have been false. It is even more of an unforgivable error that I got mixed up in computations; Mea Culpa, as they say.

How clumsy it was too. the line codes I was using read:

# Sample Size
# Data generation on the basis of moments (Median + Standard Deviation)
RNIND<-rlnorm(n, meanlog =7.69802917027281 , sdlog =1.04882476079341)
# This generates a distribution for RNI historical voting performance per district
# Computes the probability of performing a particular score (a margina)
plnorm(8569,meanlog = mean(RNIND), sdlog = sd(RNIND, lower.tail = FALSE, log.p = FALSE)

whereas it should read:

# Sample Size
# Data generation on the basis of moments (Median + Standard Deviation)
RNIND<-rlnorm(n, meanlog =7.69802917027281 , sdlog =1.04882476079341)
# This generates a distribution for RNI historical voting performance per district
# Computes the probability of performing a particular score (a margina)
plnorm(8569,meanlog = log(mean(RNIND)), sdlog = log(sd(RNIND)), lower.tail = FALSE, log.p = FALSE)
# Probabilities are computed on the basis of logged, not level moments.
# Dummkopf.

So this is the brand new method with which I crunch the numbers is simpler and hopefully, more understandable. I should say it has done a good job in “explaining” PJD’s victory in Inzegane (an obvious result as a matter of fact) and why the same party may have lost to RNI in Chichaoua. Since elections in Azilal, Moulay Yacoub, Settat, Sidi Kacem and Youssoufia have not taken place, I would like to redeem myself by offering a more thorough assessment of electoral probabilities in shifting away, or holding in contested seats.

Enrolled voters:                                 197,679
Votes cast:                                       71,608  36.2
Invalid votes:                                    13,580  19.0
Valid votes:                                      58,028  81.0
Party                                         Votes       %        Seats
Popular Movement (MP)                                230  00.4       -
Party of Authenticity and Modernity (PAM)          2,411  04.2       -
Independence Party (PI, Istiqlal)                  4,958  08.5       -
Party of Justice and Development (PJD)            29,541  50.9       2
Party of Progress and Socialism (PPS)              1,545  02.7       -
National Rally of Independents (RNI)               5,257  09.1       -
Constitutional Union (UC)                            135  00.2       -
Socialist Union of Popular Forces (USFP)           7,807  13.5       1
Others                                             6,144  10.6       -
Total                                             58,028             3

In essence, I try to provide a probability for a party to win a seat in a particular district, given its past electoral history there, conditioned also on the fact they may or may not have a seat there already. Inzegane was as expected an easy win for PJD because not only they got 2 seats there, but also because they had in 2011 a 21,000 lead over they nearest USFP competitor, whose seat was up for election last week. It would have been enough for the PJD candidate to turn out a fraction of their electoral to carry the seat, most likely with the same votes they got last year. According to the party’s own communiqué, they managed to carry 15,000 votes, which was an overkill, to say the least. It matters little they managed to mobilise only half of their 2011 turnout, it was more than enough to complete its control of all three seats at Inzegane.

Moreover, The probability for PJD of getting at least as many votes as USFP in 2011 was the highest among all competing parties: there was a 46.82% chance of getting at least 7,800 votes, and anything between 7,800 and 21,000 was likely to happen at 44.07%. These results show a very strong lead for PJD compared to other parties: RNI had virtually no chance of getting more than the required 7,800 votes – because its own national and local made it so: the probability of improving its 2011 electoral performance.

And so were USFP’s chances, especially so when its marginal seat in Inzegane ranked in the top 1% districts for the 2011 elections. Istiqlal was the only real contender whose electoral performance allowed it some significant chance to improve its score to 7,807 votes – a probability of 9.4%. In absolute terms, the likelihood of getting more than their 2011 votes was 13.54%, the closest to PJD in this district.

I have some results on Chichaoua as well, which I will be posting later on, with predictions for the remaining seats following shortly.


PJD’s “Pocket Landslide”

Posted in Flash News, Intikhabates-Elections, Morocco, Read & Heard, Tiny bit of Politics by Zouhair ABH on December 8, 2012

A little over one year after PJD‘s victory, it would be interesting to look at what is already their electoral legacy, or indeed the lack of real appreciation of how important it is. Not matter how past electoral results come under criticism, they have been de facto the law of the land – whatever the real results following the 2002 elections, all parties agreed to the official results, and these have been validated as such. And it would be better, I think, if this criticism was laid aside, especially since the 2002 election did give PJD a clear win, were it not for the diluting proportional ballot.

Majorities are 'easier' to form when the ballot system weighs in pluralities in districts

Majorities are ‘easier’ to form when the ballot system weighs in pluralities in districts

In general terms, I describe a method that points to majority-based ballot system as a good indicator of how political parties can improve their probabilities of forming a government by themselves, thus delivering stable governments and even more stable parliamentary majorities.

PJD’s victory in 2011 was a pocket landslide because the party was 65 seats short of an absolute majority – even if it was well ahead of its nearest competitor. A majority-based ballot system could have delivered the absolute majority they needed. Their feat was only matched by the joint USFP-PI 1993 campaign. Unfortunately for PJD, they are in a coalition with parties directly (and adversely) affected by any re-districting, or majority-based ballot system. (read here the theoretical argument against coordinated effort among political parties)

This is how I compute these majorities: for a particular district, all of the seats are allocated to the party with a plurality of votes. The simplest, crudest rule of politics – and poker: winner takes all. On the basis of this principle, the electoral map since 1963 is radically changed. I further consolidated party performances by aggregating split-offs – which leads to 13 big ‘partisan conglomerates’ – and these results tell a story: a consolidated political competition over parliamentary control allows for larger probabilities of reaching an absolute majority (in the cases of seats open for local ballot) and these contradict the final outcomes observed over the past couple of elections; for one, the 1997 Alternance would have been led by Istiqlal instead of USFP, and 2002, not 2011 would have been PJD’s coronation. But then again, efficiency is not Morocco’s forte.

These results can then be compared against the probabilities of each party to get a majority of the votes. These probabilities are computed on the basis of past electoral results – with increasing weightings for more recent electoral campaigns. And I am pleased that up to 92% of the historical results are explained by the following, rather simple linear model: V(\max_{i,j})=\sum\limits_{p_{k,i,j}}^n\alpha_k \mathbb{E} \left[V(P_{k,i,j})\right]+\epsilon_{k,i,j}

where \alpha_k the estimated probability for a party k to get the plurality in a district i. These parameters need not sum over 1, because there are a lot of cross-party historical votes. This confirm my earlier claim about PJD’s robust position on its 2016 prospects, as well as the need to go for a majority-based system – some parties have clearly more chances to get the majority, while others do not (those have been taken out of the fitting because of the statistical insignificant results)

      Source |       SS       df       MS              Number of obs =     153
-------------+------------------------------           F(  6,   147) =  292.75
       Model |  5.1894e+10     6  8.6491e+09           Prob > F      =  0.0000
    Residual |  4.3430e+09   147  29544400.6           R-squared     =  0.9228
-------------+------------------------------           Adj R-squared =  0.9196
       Total |  5.6237e+10   153   367564886           Root MSE      =  5435.5
         max |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
     pnd_pam |   .2806256   .0863479     3.25   0.001      .109982    .4512693
     rni_ind |   .4540341   .1007729     4.51   0.000     .2548834    .6531848
    mpdc_pjd |   .5029201   .0445715    11.28   0.000     .4148364    .5910038
          pi |   .3938989   .0974869     4.04   0.000      .201242    .5865558
     fdic_mp |   .2368222   .0761314     3.11   0.002     .0863687    .3872757
   unfp_usfp |   .3958337   .0742675     5.33   0.000     .2490639    .5426035

As one can see, the next elections tend to favour PJD (with an estimated 50.2% chance of getting a vote majority on all seats – quite different from getting a majority of seats) although there are a couple of contenders, and an even stiffer competition between say RNI vs USFP, RNI vs PI, and finally, USFP vs PI. As for PAM, my estimate is they are not likely to get anywhere close to a serious contender for governing party.

In essence, PJD’s electoral legacy would be that of ‘breaking the mould’ of opposition parties: strong enough to have a large caucus, but too weak to force censure motions, and definitely unable to form a government on their own right. It would be a breakthrough legacy if PJD could force through an electoral reform that seeks to improve the chances of a one-party government. True, this would mean PJD is most likely to stay in office for the next decade, but this is about representative democracy.

Data description: seats are allocated to each district per each electoral districting. All of the seats are allocated to the party with a plurality of votes. Parties are merged afterwards when applicable.


Predictions for the 2016 Elections, Part.2

So a uniform swing across all 84 marginal constituencies does not change the picture that much: of the 305 seats, the ranking of the 8 largest parties that concentrate 94% of parliamentary, local ballot selected seats did not change but for two: Because it exhibits a larger than usual number of marginal seats, Istiqlal is bound to lose a net 6 seats, thus leaving RNI as second-in-command. PJD on the other hand, can expect to win a net additional 3 seats, still 65 seats shy of an absolute majority.

2011 and 2002 exhibit similar and almost coinciding density curves.

But this is a highly unlikely outcome, precisely because these swings are assumed to be uniformed: indeed, the discrepancies in voting results do point to heterogeneous outcomes, essentially due to the discrepancies in carried votes between the incumbent marginal and the potential challenger. Let me use an example to illustrate my point: the Speaker of the First Chamber, Karim Ghellab, represents a marginal – voted in with 4,789 votes, a long way behind PJD and UC, respectively 14,853 and 8,925 votes. The immediate competitor to Mr Ghellab is the MP list, with 2,735 votes. What is the probability, ceteris paribus, Mr Ghellab would lose his seat to the MP challenger in 2016?

Consider the party’s past electoral performance. Amazingly enough, Istiqlal’s vote distribution did not vary much if not at all between 2002 and 2011 (the density curves for 2002 and 2007 shows it on the graph). Therefore, it makes sense to assume Mr Ghellab’s margin can be computed in terms of probabilities. And this shows us he would keep his seat with a probability of 46.7%, with a vote tally fluctuating most likely between 3,976 and 5,841 votes, regardless of Mr Ghellab’s or the nationwide electoral performance, he needs to ensure a a marginal majority of 813 votes.

(incidentally, voter distribution per party or per seat exhibits very common forms, as various papers from academia[pdf] testify to that)

How about PJD’s six marginal constituencies? According to the averaged PJD past electoral performances since 2002, three of these are more likely to go over the edge to PJD’s local challenger, and one is a pure, statistical toss-up. This is moderate good news for PJD, because they are assured to keep a comfortable margin, provided 2016 Elections come with no exceptional events (the “Black Swan”) In fact, all three marginals have strictly positive likelihoods to swing against PJD incumbents, but three only of these lean toward PJD’s local challengers, and Laayun remains in a tie (a feat for maverick PJD considering the voting pattern down South)

Of the 6 marginals, PJD has a significant chance to lose three, and a fourth is nearly a toss-up

On the other hand, one could also look at the Head of Government’s own seat in Salé, and while it is by no means a marginal (M. Benkirane got 27,000 votes to a second with a little over 8,000) yet there is a positive (very low) likelihood of losing his seat: less than 3% – precisely because it would entail a huge swing, with a third of Salé voters going over to any challenger.

The Istiqlal party is a peculiar contender: though it ranks a distant second in electoral results, it has maintained its initial strength even as the party led a relatively unpopular government, and has been associated with all government coalitions at least since 1997. It is undoubtedly an establishment party. Yet for its formidable 60-members strong caucus, many of those have been elected on razor-thin margins in very competitive districts, and the Istiqlali challengers have not been numerous enough to make up for the endangered seats. All in all, Istiqlal could well expect a net loss of 6 seats.

The party with the most interesting marginal record is undoubtedly Istiqlal, first, because they have the largest number of marginals, and second, because their electoral performance per district did not change over the years (a remarkable stability given its Establishment status) the odds for and against voter swing in PI-held seats is the perfect case study for the proposed method. As one can see, the initial assumption of a uniform swing across all marginals was unrealistic. By that account, Istiqlal was to expect to net a loss of 6 seats. But now, and according to the computed probabilities, Istiqlal can expect – again, ceteris paribus, to lose only 4 seats, with one is a small district where lopsided swings are expected and observed, and four others with moderate loss expectations. Assouerd is a peculiar seat, because a 200 voter switch is a dead heat, 600 is a landslide (respectively 4.3% and 13% swing)

Aousserd is very competitive, the high likelihood of part swing is due to the small constituency to start with.

Can this set-up deliver reliable results for marginals as well as ‘safe’ districts? The Tangier by-election provides good case study (given the fact polls do not curry favour with our esteemed representatives[pdf]) the model tells PJD was strongly favoured to retain all its Tangier seats, since the probability of losing its majority is so small it is not even statistically significant (larger than 99%) but on the other hand, the model predicts it may lose 12,500 votes (but this is probably due to the fact that Tangier district is a PJD stronghold, and their maximum voter reserve has been reached) so even if it retains its majority almost certainly (and it did) it was expected to lose some votes. The actual results show PJD lost 16,200 votes – a figure statistically close (well within the margin of error) to the projected 12,500 synthetic potential loss.

Howe about the other competitors for the Tangier district representatives? According to their respective results, PAM was the marginal representative, with a potential risk of losing it to UC, with a probability of 17%. So actually, PAM’s marginal Tangier seat was relatively safe, with expected losses of no more than 1,730 votes – it turns out PAM lost only 300-odd votes. The actual loser in this Tangier recall election was RNI, even though it was not a marginal (yet exhibited a loss probability of 9.7%) yet it failed to carry any vote. The model predicted PAM could lose to UC, but since RNI did not get any votes, UC candidate list simply filled in.