Hele nummeret kan downloades som pdf her.
pkk
Viser opslag med etiketten Republikanerne. Vis alle opslag
Viser opslag med etiketten Republikanerne. Vis alle opslag
1.11.19
Temanummer af "Samfundsøkonomen" om amerikansk politik under Trump
Jeg har redigeret et temanummer af Samfundsøkonomen om "Trumps Amerika" med bidrag fra bl.a. Mirco Reimer-Elster (Firenze), Christian Bjørnskov (Aarhus), Otto Brøns-Petersen (CEPOS), samt Frederik G. Hjorth, Birthe Hansen og jeg selv (København).
Hele nummeret kan downloades som pdf her.
Hele nummeret kan downloades som pdf her.
6.11.16
Too close to call (again): A "fundamentals" look at the US presidential election
Here a few days before the 2016 US presidential election I have updated my own little model (which I call "Bread & The Cost of Ruling") with the most recent data. My model--which I have developed over the last four elections and which is inspired by somewhat different, but also slightly similar, models by Douglas Hibbs, Michael Lewis-Beck, Ray Fair and Alan Abramowitz--relies on three elements for the explanation of the two-party vote share of the incumbent party's presidential candidate:
The explanatory power of the three variables together is quite strong, explaining 87% of the variation in the two-party vote 1952-2012.
In particular, there is the familiar picture of economic conditions playing a large role--here the correlation between economic growth and incumbent party's share of two-party vote when controlling for other factors:
Plugging in the relevant data for 2016 (3.3 pct. average quarterly growth up to and including 2Q of 2016, given that we do not yet know 3Q; 51.3% approval rating for Obama, using RealClearPolitics.com's averages), we get that the Democratic candidate for president (Hillary Clinton) should get ... (drum roll) ... 49.99% of the two-party vote.
Essentially this is as close to a coin toss as possible--although it should be noted that such a use for "prediction" comes with a caveat: In this case the standard error of the estimate (when applied to the 1948-2012 elections) is at 2.28%.
What this means is that the election--in the eyes of the model--should look so extremely close at the national level (disregarding the issue of the Electoral College votes) that we really cannot say who is going to win. In fact, we should not be surprised by a relatively narrow win in the national vote (with, say, a 2 pct.point margin) for either of the candidates.
This is not really what the opinion polls, the forecasting models and prediction markets suggest and have suggested all year (namely a relatively clear Clinton victory). However, it does match the tendency in the last weeks of the presidential campaign for the national polls to tighten rather visibly.
If there was a modern presidential campaign where "the ground game" ("get out the vote"-operations) and voter enthusiasm/lack thereof might play a role, this could very well be it.
If on Tuesday Clinton ends up winning more like the opinion polls suggest than what econometric models such as the present one tends to forecast, then the "credit" might very well go to the Republicans and their candidate.
- Economic growth: Developments in real disposable income since the previous midterm election (presumed to be positive for the candidate);
- "The cost of ruling": A composite measure balancing a) the number of terms a party has held the presidency (presumed to be negative), but also considering b) whether the candidate is an incumbent (presumed to be positive);
- Presidential approval: The incumbent president's positive approval ratings (presumed to be positive).
- Constant: 40.22
- Economic Growth: 1.95
- Cost of Ruling: -1.52
- Presidential approval: 0.12
The explanatory power of the three variables together is quite strong, explaining 87% of the variation in the two-party vote 1952-2012.
In particular, there is the familiar picture of economic conditions playing a large role--here the correlation between economic growth and incumbent party's share of two-party vote when controlling for other factors:
Plugging in the relevant data for 2016 (3.3 pct. average quarterly growth up to and including 2Q of 2016, given that we do not yet know 3Q; 51.3% approval rating for Obama, using RealClearPolitics.com's averages), we get that the Democratic candidate for president (Hillary Clinton) should get ... (drum roll) ... 49.99% of the two-party vote.
Essentially this is as close to a coin toss as possible--although it should be noted that such a use for "prediction" comes with a caveat: In this case the standard error of the estimate (when applied to the 1948-2012 elections) is at 2.28%.
What this means is that the election--in the eyes of the model--should look so extremely close at the national level (disregarding the issue of the Electoral College votes) that we really cannot say who is going to win. In fact, we should not be surprised by a relatively narrow win in the national vote (with, say, a 2 pct.point margin) for either of the candidates.
This is not really what the opinion polls, the forecasting models and prediction markets suggest and have suggested all year (namely a relatively clear Clinton victory). However, it does match the tendency in the last weeks of the presidential campaign for the national polls to tighten rather visibly.
If there was a modern presidential campaign where "the ground game" ("get out the vote"-operations) and voter enthusiasm/lack thereof might play a role, this could very well be it.
If on Tuesday Clinton ends up winning more like the opinion polls suggest than what econometric models such as the present one tends to forecast, then the "credit" might very well go to the Republicans and their candidate.
5.2.16
Social choice and the 2016 US presidential election
 |
| Marquis de Condorcet |
On the day of the Iowa Caucus I wrote a hasty little research note on the topic, which you can download here.
But here is the gist of it, where > means "beats":
- Clinton > Trump
- Clinton > Sanders
- Cruz > Clinton
- Rubio > Clinton
- Rubio > Sanders
- Sanders > Cruz
- Sanders > Trump
- Trump > Cruz
- Trump > Rubio
If that is correct (and we are disregarding the question of the confidence intervals of the polls), then we would seem to have three possible "cyclical majorities" (of a sort) involving all five leading contenders for the nomination of the two parties:
- Sanders > Trump > Rubio > Sanders
- Rubio > Clinton > Trump > Rubio
- Cruz > Clinton > Sanders > Cruz
 |
| Not Marquis de Condorcet |
6.11.12
Amerikansk præsidentvalg 2012: Vægtet, dagligt gennemsnit af "tracking polls" af "sandsynlige vælgere"
Tidligere datoer§:
- 3.11.: Obama: 49,00%; Romney: 48,42%% (-0,6%) [N = 3.569. Kilder: ABC News/Washington Post; Rasmussen]
- 2.11.: Obama: 48,50%; Romney: 48,50%% (+0,0%) [N = 2.985. Kilder: ABC News/Washington Post; Rasmussen]
- 1.11.: Obama: 48,00%; Romney: 48,51% (+0,5%) [N = 3.035. Kilder: ABC News/Washington Post; Rasmussen]
- 31.10.: Obama: 47,93%; Romney: 48,54% (+0,6%) [N = 2.793. Kilder: ABC News/Washington Post; Rasmussen]
- 30.10.: Obama: 47,92%; Romney: 49,00% (+1,1%) [N = 2.788. Kilder: ABC News/Washington Post; Rasmussen]
- 29.10.: Obama: 47,46%; Romney: 49,00% (+1,5%) [N = 2.771. Kilder: ABC News/Washington Post; Rasmussen]
- 28.10.: Obama: 46,97%; Romney: 49,99% (+3,0%) [N = 5.459. Kilder: ABC News/Washington Post; Gallup; Rasmussen]
5.11.12
Too close to call: Growth and the cost of ruling in US presidential elections, with an application to the 2012 election
I have finally written-up a small research note trying to collect together the little model for the explanation of outcomes of US presidential elections that I have played around with for years. What could be more relevant than do so on the eve of the 2012 election? At this risk of being proven totally wrong, here is the title and abstract and link to files for download:
Too close to call: Growth and the cost of ruling in US presidential elections, with an application to the 2012 election
The note briefly outlines a new model for the explanation of US presidential elections, founded on (a) recent economic growth and (b) a measure of what may be called “’the cost of ruling”. The former is based in changes in real disposable income for the period following a mid-term election, while the latter combines factors of incumbency and terms-in-office. The model is applied to data from the US presidential elections 1932-2008 and has considerable explanatory power for the variation in the incumbent party’s candidate’s share of the two-party vote (R2=0.74). The model is controlled against a number of other frequent explanations and is found to be quite robust. When augmented with approval ratings for incumbent presidents, the explanatory power increases to 83 pct. and only incorrectly calls one of the last 15 US presidential elections. Applied to the 2012 election as a forecasting model the prediction is that President Obama will win 49,6 pct. of
4.10.12
Amerikansk valgsæson
På det seneste har jeg blogget
- om nomineringen af Paul Ryan som Republikansk vicepræsidentkandidat
- om hvorvidt denne nominering har betydet noget for Romneys meningsmålinger
- om dårlig dansk research af en dansk TV-station
- Første debat
4.1.12
2012: There you go again ...
10.12.10
Midtvejsvalget 2010: Post mortem med en vis blæreret
Finally, the votes are in ... Først nu, mere end en måned efter USA’s jordskreds-midtvejsvalg, er det sidste mandat blevet afgjort, og dermed foreligger det “endelige”, fulde valgresultat. Dermed er der nu også muligheden for at sige noget om, hvilke ”pundits” og meningsmålere, der ramte tættest eller fjernest, eller midt imellem, i deres forsøg på at forudsige valgresultatet. I nedenstående tabel kommer tre af de centrale forhold: Stemmeandelene, ”the popular vote” (som vanligvis og aldeles konventionelt opgøres som stemmeandelene ved valget til Repræsentanternes Hus); antal mandater i Repræsentanternes Hus; antal mandater i Senatet. (Det henholdsvis fjerde og femte relevante element ville være at se på fordelingen af guvernørposter og kontrollen med delstaternes lovgivende forsamlinger, men det lader vi ligge her.)
På hver af de tre områder er nedenfor angivet de faktiske tal med fed skrift, ligesom der er angivet de ”prognoser”, som enten meningsmålingsfirmaer eller ”eksperter” fremkom med inden valget. Jeg har taget stort set revl og krat med. Dertil har jeg så angivet ”brutto-fejlene” ved hvert estimat (d.v.s. forskelle i.f.t. de faktiske tal for Demokraterne og Republikanerne, lagt sammen). (Feinschmeckere vil sikkert spørge, hvorfor jeg angiver brutto-fejl snarere end netto-fejl? Og dén kan man så tygge lidt på …)
På hver af de tre områder er nedenfor angivet de faktiske tal med fed skrift, ligesom der er angivet de ”prognoser”, som enten meningsmålingsfirmaer eller ”eksperter” fremkom med inden valget. Jeg har taget stort set revl og krat med. Dertil har jeg så angivet ”brutto-fejlene” ved hvert estimat (d.v.s. forskelle i.f.t. de faktiske tal for Demokraterne og Republikanerne, lagt sammen). (Feinschmeckere vil sikkert spørge, hvorfor jeg angiver brutto-fejl snarere end netto-fejl? Og dén kan man så tygge lidt på …)
| Demokrater (forskel i.f.t. faktisk resultat) | Republikanere (forskel i.f.t. faktisk resultat) | Brutto-fejl i.f.t. de to store partiers faktiske resultater | |
| ”Popular vote” (baseret på House-stemmeandele, jf. Wikipedia) | 44,8 | 52,1 | -- |
| Meningsmålingsgennemsnit: | |||
| Mark Blumenthal, Pollster.com/ Huffington Post, vægtet gennemsnit (2.XI.2010) | 42,9 (-1,9) | 50,6 (-1,5) | 3,4 |
| Peter Kurrild-Klitgaard på Punditokraterne, vægtet gennemsnit (2.XI.2010) (afrundet) | 42 (-2,8) | 51 (-1,1) | 3,9 |
| RealClearPolitics.com, uvægtet gennemsnit (2.XI.2010) | 41,3 (-3,5) | 50,7 (-1,4) | 4,9 |
Diverse meningsmålinger: | |||
| YouGov/Polimetrix (1.XI.2010) | 45 (+0,2) | 52 (-0,1) | 0,3 |
| Zogby (1.XI.2010) | 45 (+0,2) | 50 (-2,1) | 2,3 |
| Ipsos (31.X.2010) | 44 (-0,8) | 50 (-2,1) | 2,9 |
| Opinion Research (30.X.2010) | 42 (-2,8) | 52 (-0,1) | 2,9 |
| Hart McInturf (30.X.2010) | 43 (-1,8) | 49 (-3,1) | 4,9 |
| Rasmussen (31.X.2010) | 39 (-5,8) | 51 (-1,1) | 6,9 |
| Pew (30.X.2010) | 42 (-2,8) | 48 (+4,1) | 6,9 |
| Gallup (31.X.2010) | 40 (-4,8) | 55 (+2,9) | 7,7 |
| Opinion Dynamics (28.X.2010) | 37 (-7,8) | 50 (-2,1) | 9,9 |
Repræsentanternes Hus | 193 | 242 | -- |
| Steve Lombardo/Lombardo Consulting, Huffington Post (2.XI.2010) | 191 (middel af estimat) (-2) | 244 (middel af estimat) (+2) | 4 |
| Peter Kurrild-Klitgaard på Punditokraterne (2.XI.2010) | 190 (-3) | 245 (+3) | 6 |
| Stuart Rothenberg, Rothenberg Report (2.XI.2010) | 196 (middel af estimat) (+3) | 239 (middel af estimat) (-3) | 6 |
| Larry Sabato, Sabato’s Crystal Ball (2.XI.2010) | 201 (+8) | 234 (-8) | 16 |
| Charlie Cook, Cook Report (2.XI.2010) | 201 (+8) | 234 (-8) | 16 |
| Jay Cost, Weekly Standard (2.XI.2010) | 181 (-12) | 254 (+12) | 24 |
| Nate Silver, FiveThirtyEight.com/NYT (2.XI.2010) (afrundet) | 203 (+10) | 232 (-10) | 20 |
Abonner på:
Opslag (Atom)
Abonner på
Opslag
Alle kommentarer