Let’s take a look at what went right and what went wrong for statistics in Hollywood. First, we’ll turn our attention to the closest races which Ben’s Oscar Forecast picked correctly.

Best Director: Ang Lee – Life of Pi. This was a very controversial category. Many “experts,” including some people endeavoring to use statistics, picked Steven Spielberg for Lincoln. Mathematically speaking, though, my model found it wasn’t that close. When I crunched the numbers, Spielberg was down at 10%, even behind David O. Russell for Silver Linings Playbook and Benh Zeitlin for Beasts of the Southern Wild. Why? There are a few reasons, but the biggest is that Mr. Spielberg did not receive a BAFTA nomination, which hurts him severely in a model using data from the past 15 years.

Best Picture: Argo. Many correctly called this award, while a few picked Lincoln as the favorite. While it is true that Argo was not nominated for Best Director, that is not nearly as important as the plethora of predictors Argo had going for it. For that reason, my model put Lincoln way down at 9%, with Argo up at 60%.

Best Writing – Adapted Screenplay: Argo. Others had Silver Linings Playbook, but anyone who put enough weight on the Writers’ Guild for this category got this one correct.

Best Animated Feature: Brave. The other popular pick was Wreck-It Ralph. This shows why it’s a dangerous pitfall to put too much weight on the Annies and the Producers Guild. The other factors, the BAFTAs and the VES awards, made Brave was the clear frontrunner.

There were also plenty of categories that most other statistical prognosticators did not attempt. My model correctly predicted Life of Pi for Best Original Score and Best Visual Effects, Argo for Best Film Editing, Anna Karenina for Best Costume Design, and Les Miserables for Best Makeup/Hairstyling and Best Sound Mixing. It also called Skyfall for Best Sound Editing, which split the award with Zero Dark Thirty, the first tie in 18 years.

Almost every predictor, including my model, picked Daniel Day-Lewis in Lincoln for Best Actor, Jennifer Lawrence in Silver Linings Playbook for Best Actress, Anne Hathaway in Les Miserables for Best Supporting Actress, Amour for Best Foreign Film, Searching for Sugar Man for Best Documentary – Feature, and “Skyfall” for Best Original Song.

In 4 of the 21 categories, the mathematical frontrunner which I calculated and the winner did not correspond. Three of them were simply extremely tight races. Christoph Waltz, who won Best Supporting Actor for his role in Django Unchained, was only 9% behind leader Tommy Lee Jones. Lincoln took Best Production Design despite falling 8% below Anna Karenina. Best Cinematography went to Life of Pi, though the math put it 3% behind Skyfall. From a mathematical perspective, these results are all entirely reasonable and expected, since the differences were so slight.

The only category with a larger difference was Best Writing – Original Screenplay, where second-place Django Unchained beat first-place Zero Dark Thirty. The mathematical suggestion partially rested on Zero Dark Thirty’s win at the Writer’s Guild, but Quentin Tarantino was ineligible for a Writer’s Guild award for his Django Unchained script under the WGA’s restrictive rules.

The overall lesson: math is an extremely powerful tool for prediction, working at an 81% clip on this occasion. But absolute perfection is unlikely to be found on a calculator; I’d prefer to look for it in a great movie.

-Odds that Best Picture and Best Director go to the same movie: 8%
-Odds that Argo becomes the fourth film ever to win Best Picture and nothing else: 7%
-Odds that Silver Linings Playbook becomes the fourth film ever to sweep the “Big Five”: 0.02%

How about the acting awards? Most critics, as well as my numbers, agree that Daniel Day-Lewis and Jennifer Lawrence are the favorites, but let’s dig deeper to learn some more interesting facts:

-Odds that Lincoln becomes the third film ever to win three acting awards: 5%
-Odds that Silver Linings Playbook becomes the first movie to win all four acting awards: 0.04%

So a clean sweep isn’t too likely for David O. Russell’s love story. But some other categories that typically go together have a bit more of a chance at honoring the same movie:

-Odds that either Life of Pi or Skyfall wins Best Original Score and Best Original Song: 8%
-Odds that Argo, Life of Pi, or Skyfall wins Best Sounds Editing and Best Sound Mixing: 10%
-Odds that Anna Karenina, Lincoln, or Life of Pi wins Best Production Design and Best Cinematography: 16%
-Odds that Life of Pi sweeps the six technical categories: 0.009%

If you’re into more dispiriting predictions, we can calculate facts about losses, not just wins:

-Odds that Lincoln breaks the all-time record for Oscar losses, going 0/12: 3%
-Odds that Django Unchained goes 0/5: 44%

Ouch. It seems that Quentin Tarantino has nearly a 50/50 shot of going home without any trophies. Anyway, here are a few more miscellaneous ones, because this is too much fun to stop:

-Odds that either Moonrise Kingdom or Flight wins Best Adapted Screenplay, even without a Best Picture nomination: 7%
-Odds that a European country wins Best Foreign Film: 89%
-Odds that Anna Karenina wins all four of its nominations: 0.1%

Do you have any similar questions that you’d like me to calculate? Just leave a comment below and I’ll respond with the percent chance of your scenario coming true.

I have created a statistical model to predict the Oscars, using numerical data from critic scores, other awards shows, and guild awards over the past 15 years. This method is entirely mathematical: no personal hunches are taken into account. Last year, my model correctly predicted all eight of the major categories.

This year’s final tallies show that six movies will take home multiple awards this Sunday. On the flip side, no movie will win more than three for the first time since 2005. The “big winner,” if any movie even deserves that title, will most likely be Argo, claiming Best Picture, Best Adapted Screenplay, and Best Film Editing.

In a very tight Best Director race, Ang Lee (Life of Pi) is the slight favorite. However, Life of Pi is only expected to win two other awards – Best Original Score and Best Visual Effects – despite its 11 nominations.

The acting awards are not as close, mathematically speaking. Check off Daniel Day-Lewis (Lincoln), Jennifer Lawrence (Silver Linings Playbook), Tommy Lee Jones (Lincoln), and Anne Hathaway (Les Miserables) on your Oscar ballots without too much worry.

The biggest lock goes to an often overlooked category. Searching for Sugar Man is expected to win Best Documentary with 80%, the best odds for any nominee this year.

Other races will be a lot closer. Skyfall, at 30%, leads Best Cinematography over Lincoln (29%) and Life of Pi (27%) by the slimmest of margins. Don’t get up for more popcorn during that award. And Anna Karenina, expected to win for Best Production Design and Best Costume Design, is similarly unsafe in both of those categories.

For the full list of predictions, please see www.oscarforecast.wordpress.com/predictions.

Where exactly do these numbers come from? I explain the methodology at www.oscarforecast.wordpress.com/about.

For more trivia, follow me on Twitter at www.twitter.com/BensOscarMath, or go to www.oscarforecast.wordpress.com/trivia.

The Academy Award acceptance speech. While others have done analyses of individual years of Oscars, this is a bit more comprehensive, including every word uttered during the last 20 years of acceptance speeches. In total, there have been over 73,000 spoken, including 7,000 unique words, throughout the 468 speeches available on the Academy’s website. Here are the top 100 words, with the size proportional to the number of uses:

The top ten words are unsurprising: and (spoken 3,679 times over the last 20 years), to (2,923), the (2,502), you (2,807), thank (2,044), I (1,904), my (1,525), of (1,343), for (1,220), a (1,200).

As expected, the top portion of the list is filled with pronouns, prepositions, articles, forms of “to be,” and similar small words. Ignoring those, the top ten are: thank (2,044), like (491), much (473), very (411), want (398), Academy (313), film (307), love (265), people (246), great (246). Clearly, it’s very popular to “like” to “thank” the “Academy,” though only 26 people have used the specific phrase “I’d like to thank the Academy.” Visual effects editor Ken Ralston is the only one in this time period to use the famous phrase twice, after wins for Death Becomes Her (1992) and Forrest Gump (1994). Seven others have used the more formal “I would like to thank the Academy.”

As you can see, film made the cut, easily beating out the alternative movie (161). It was much tighter between films (44) and movies (43). Other close races include:

-producers (74), director (74), producer (73)
-parents (48), kids (47), children (45)
-pictures (38), nominees (38), picture (35)
-inspired (33), inspiration (32)
-supporting (19), supported (19)
-translator (1), translation (1), translating (1), translate (1)

With so many people being honored, there are plenty of adjectives to go around, most of them very positive. The top ten are: great (246), wonderful (158), amazing (108), good (96), beautiful (89), incredible (88), best (58), brilliant (47), fantastic (46), special (45). The only measure in which negativity won the day? No (71) destroyed yes (18).

Among those being thanked, there are some times it is better to be a woman. Wife (158) sped past husband (32), mom (63) slipped past dad (61), mother (53) beat father (40), and women (31) edged out men (27). In other areas of vocabulary, the men won out: man (74) over woman (22), son (32) against daughter (25), brother (26) versus sister (20), and king (22) ruled queen (7).

The most-mentioned countries list has a surprising winner: New Zealand (19), followed by America (10), England (7), Italy (6), Australia (5), Canada (5), China (5), Hong Kong (5), Mexico (4), India (4), and USA (4). If you’re still stuck on that nation in first place, remember that it also goes by the name “Middle Earth” in a highly awarded trilogy.

What do people actually call that thing they just won? Some of the common words include honor (116), award (98), and Oscar (50). Statuette (5) and statue (3) do not fare as well.

Many winners invoke religion, explaining the prevalence of God (91) and bless (27).

Some common words failed to merit more than one mention, including:

-built (James Cameron, Titanic, 1997)
-fiction (Martin Strange-Hansen, The Charming Man, 2002)
-fit (Mira Sorvino, Mighty Aphrodite, 1995)
-happiness (Michel Hazanavicius, The Artist, 2011)
-tall (Eric Roth, Forrest Gump, 1994)
-Sunday (J. Roy Helland, The Iron Lady, 2011)

Many people begin their speech with “first” (appropriately, 111), but in the heat of the moment few remember to reach second (21), third (9), or fourth (1). In terms of cardinal numbers, here’s how they stack up:

What’s one common word that was uttered zero times in all of these speeches? Fittingly, the answer is ‘zero.’

But does any of this actually correspond with the facts? The answer, perhaps surprisingly, is no. Despite the beliefs that veteran actors win more awards for their talent or their career achievements, veterans actually win 17% less often than relative newcomers.

Here, we will define an Oscar veteran as an actor who has received more than five nominations either in the lead or supporting category. There are currently 33 members of this exclusive club, with the newest – Denzel Washington – just added this year thanks to his sixth acting nomination for his role in Flight.

In the 84 years of Oscars (excluding this year), there have been, coincidentally, 84 acting nominations for those I have defined as Oscar veterans, counting only nominations after their first five. In these nominations, only 14 times has a veteran emerged victorious, for a rate of 16.7%. The overall average for acting nominees is 20%, since one out of five wins each category. Technically, before 1936 the number of acting nominations varied each year, but the first Oscar veteran was Norma Shearer, who did not receive her sixth nomination until 1938 for Marie Antoinette.

This graph shows the success of Oscar veterans at each nomination number. For instance, the first column shows that 32 people have received a sixth nomination, and five have won on that nomination.

Impressively, the last five columns represent only Meryl Streep, the one actress who has received more than 12 nominations.

Percentage-wise, the most successful Oscar veterans are Jessica Lange and Kate Winslet, who each won upon her only nomination as a veteran, for Blue Sky (1994) and The Reader (2008), respectively. Katherine Hepburn has won the most awards as a veteran – three between her sixth and her twelfth nomination. Jack Nicholson is the only other multiple-Oscar winning veteran; he claimed two prizes after entering this prestigious group. The worst records belong to Bette Davis and Laurence Olivier, who each went 0-for-5 as veterans.

Even among the nine actors who went 0-for-5 among their first five nominations on their paths to becoming Oscar veterans, the record is still only 4-for-19, or 21.1% – just a hair above 20%. So, if luckless veterans receive a boost out of sympathy or career recognition, it’s very slight. Paul Newman, Al Pacino, Geraldine Page, and Kate Winslet are the winners in this category, and none of them has won twice. Five Oscar veterans have never won a competitive award: Peter O’Toole (8 total nominations), Richard Burton (7), Glenn Close (6), Deborah Kerr (6), and Thelma Ritter (6).

Interestingly, the numbers do not paint the same picture for Best Director. If we define Oscar veteran in a similar manner – being nominated for Best Director more than five times – then Oscar veteran directors actually fare better than average, winning at a 25% rate. Only eight people belong to this group, representing five wins in 20 nominations. William Wyler won twice as a veteran, and Billy Wilder, Fred Zinneman, and Martin Scorsese each won once. The four members of the club who did not win after their sixth nomination are Woody Allen, Frank Capra, David Lean, and Steven Spielberg, who will have a chance to change that this year.

This means it’s possible that the Academy does award established directors more often than others for the reasons we discussed earlier – talent or overall career achievement – but the numbers do not say the same thing about acting recognition. There has never been a year in which a veteran director and a veteran actor, or two different veteran actors, both won an award.

The first veteran director to win was William Wyler for directing The Best Years of Our Lives (1946). The first veteran actress to win was Katherine Hepburn for her role in Guess Who’s Coming to Dinner (1967). Five years later, Marlon Brando became the first veteran actor to win for The Godfather (1972).

What does this mean for this year’s nominees? Two veteran actors are nominated: Robert De Niro for Silver Linings Playbook and Denzel Washington for Flight. One veteran director is nominated: Steven Spielberg for Lincoln. While the sample size is quite small for directing, the math would indicate that we should not expect De Niro and Washington, despite their long and nomination-filled careers, to have any special advantage during the biggest night in Hollywood.

This is the eighth time that this occurred, along with 1984, 2004-2008, and 2011. But it hasn’t always been this way: The Academy’s and the box office’s top choices used to match up quite frequently. In 1949, 1950, 1953, and 1962, all Best Picture nominees made the top ten. The most top-ten grossing movies to receive a Best Picture nomination in one year was seven in 1934.

The Best Picture winner made the top ten money-making list 14 years in a row between 1934 and 1947, the longest streak in history. There are even two pairs of back-to-back Best Picture winners which were also the highest-grossing film of the year: You Can’t Take It with You (1938) and Gone with the Wind (1939), along with My Fair Lady (1964) and The Sound of Music (1965).

But there has been a significant decline in money-makers being nominated for and winning the Academy’s top prize. Of the 18 movies that have won Best Picture and have also been the highest-grossing film of the year, the most recent was Lord of the Rings: Return of the King in 2003. However, 16 of those 18 were before 1980, with Titanic (1997) the only other post-1980 film to receive both distinctions.

Similarly, 59 of the 84 Best Picture winners made the top ten, though none since Lord of the Rings. Since 2004, only four top-ten grossing hits have been nominated: Avatar (2009), Up (2009), Inception (2010), and Toy Story 3 (2010).

The following graph has one data point for every year of the Oscars, with the height representing the number of Best Picture-nominated top-ten films.

The line of best fit trends downward with a slope of -0.04. Put another way, for every 25 years, the expected number of overlaps between the top-ten list and the Best Picture nominee list falls by one. Of course, that trend can’t go on much longer, since the expected value is already below one, compared to its initial position just above four in the late 1920s.

What is the explanation for this change? One possibility is that, in the 21^st century, franchises and sequels tend to do very well at the box office but not nearly as well with Academy voters. The main exception is Lord of the Rings, which saw all three of its films receive Oscar recognition.

All entries in the list of 2012 top-ten grossers are part of a franchise, which was also true in 2011. Compare this to 1934, the only year that all of the top five grossing movies were nominated for Best Picture. Only one of those five, The Thin Man, spawned sequels. It’s a similar story in 1938 and 1970, the only other two years when all of the top four hits received nominations.

Another possibility is that the Academy just doesn’t go for high-budget action movies with the same frequency as epic historical dramas, while the average viewer’s preferences in recent decades are precisely the opposite. While others might argue that so-called “popcorn viewers” nowadays will watch anything, or on the flip side, that Oscar voters are becoming too snobby and out-of-touch, either of these assertions would be very difficult to prove mathematically.

Some more trivia: The Best Picture winner has appeared in every position of the top ten grossers. As a matter of fact, that was already accomplished by 1950, when All About Eve finished seventh, the final unfilled spot. Gentleman’s Agreement (1947) happens to be the only Best Picture to finish in eighth, while all other positions in the top ten have been occupied by at least three Best Pictures.

Interestingly, part of the reason that the Academy expanded the Best Picture nominations in 2009 was to try to include more popular films among the artsy critical darlings. It’s too early in this experiment to see if it will work in the long run, but perhaps that best fit curve will start sloping upward again in the near future.

But does receiving the most nominations really mean that a movie is most likely to win Best Picture? The short answer is yes – 2/3 of the time. But for movie buffs and math nerds, here is the longer answer.

Over the 84 years of Oscars, the movie that received the most nominations (including ties for first place) among the Best Picture nominees went on to take the top prize in 56 years, exactly 2/3 of the time.

The higher a movie ranks in nominations among its Best Picture competitors, the more likely it is to win: 85% of winners came in the top two in nominations, and 93% of the winners at least made bronze. So should you go ahead and fill out your Oscar ballot with Lincoln or Life of Pi, this year’s runner-up with 11 nominations?

Not so fast. For 68 of the Oscars’ 84 years, there were only five nominees. In the inaugural event in 1928, there were only three. Making top three was an easier feat in many years than in 2012, a year with nine nominees for Best Picture.

Plus, some underdogs have pulled off big upsets over the years. Grand Hotel (1932) is the only movie to win Best Picture on its only nomination, meaning it was actually tied for fifth place among the eight Best Picture nominees that year (Arrowsmith and The Champ received four nods, while Bad Girl and Shanghai Express had three). In the five-nominee era (1929-1931, 1944-2008), three movies have tied for last and won: In the Heat of the Night (1967) with seven nominations, Annie Hall (1977) with five, and Ordinary People (1980) with six.

Let’s break this down a bit further. The graph below shows that movies with at least seven nominations tend to win Best Picture much more often than those with six or fewer – specifically, 73 to 11.

This next graph shows how many Best Picture nominees received a given number of Oscar nominations:

As you can see, 17 movies have been nominated for Best Picture but nothing else, most recently The Ox-Bow Incident (1943).

The longest streak of years in which the nominations leader won Best Picture is nine, in both 1982-1990 and 1992-2000. The movie that broke what could have been a 19-year streak was Silence of the Lambs (1991), which defeated nominations leader Bugsy. The most consecutive years in which the nominations leader did not win Best Picture is just three. This happened in 1928-1930 and 2004-2006. As a matter of fact, 2005 was the only year in which the leader was not nominated for Best Picture at all, when eight-time nominee Dreamgirls missed the cut.

Let’s get back to the original question: What does the number of nominations indicate about the probability of winning Best Picture? Using a statistical model known as logistic regression, the graph looks like this:

Note that the calculations used to make the above graph include all 84 years, regardless of the number of nominees or categories in each year, so these numbers are not perfect predictors for 2012. If we use linear regression instead, each additional nomination adds a 5.4% chance of winning Best Picture.

While none of this is enough to predict Lincoln or Life of Pi with much confidence – I’ll need to see some of the other awards season results before I can make that call on this website on February 19 – there are some things we can learn.

The record for coming from behind was set in 1977. Five-time nominee Annie Hall overcame a six-nomination deficit to beat out The Turning Point and Julia, which each had 11. That means that this year, Amour, Beasts of the Southern Wild, Django Unchained, or Zero Dark Thirty would need to pull off a never-before-accomplished feat in order to stage an upset. But there’s a reason we all still watch the Academy Awards with rapt attention – regardless of all the numbers, anything can happen when the final envelope is opened.