The return of quota sampling

Everyone knows about the famous Dewey Defeats Truman headline fiasco, and that the Chicago Daily Tribune was inspired to its premature announcement by erroneous pre-election polls. But why were the polls so wrong?

The Social Science Research Council set up a committee to investigate the polling failure. Their report, published in 1949, listed a number of faults, including disparaging the very notion of trying to predict the outcome of a close election. But one important methodological criticism — and the one that significantly influenced the later development of political polling, and became the primary lesson in statistics textbooks — was the critique of quota sampling. (An accessible summary of lessons from the 1948 polling fiasco by the renowned psychologist Rensis Likert was published just a month after the election in Scientific American.)

Serious polling at the time was divided between two general methodologies: random sampling and quota sampling. Random sampling, as the name implies, works by attempting to select from the population of potential voters entirely at random, with each voter equally likely to be selected. This was still considered too theoretically novel to be widely used, whereas quota sampling had been established by Gallup since the mid-1930s. In quota sampling the voting population is modelled by demographic characteristics, based on census data, and each interviewer is assigned a quota to fill of respondents in each category: 51 women and 49 men, say, a certain number in the age range 21-34, or specific numbers in each “economic class” — of which Roper, for example, had five, one of which in the 1940s was “Negro”. The interviewers were allowed great latitude in filling their quotas, finding people at home or on the street.

In a sense, we have returned to quota sampling, in the more sophisticated version of “weighted probability sampling”. Since hardly anyone responds to a survey — response rates are typically no more than about 5% — there’s no way the people who do respond can be representative of the whole population. So pollsters model the population — or the supposed voting population — and reweight the responses they do get proportionately, according to demographic characteristics. If Black women over age 50 are thought to be equally common in the voting population as white men under age 30, but we have twice as many of the former as the latter, we count the responses of the latter twice as much as the former in the final estimates. It’s just a way of making a quota sample after the fact, without the stress of specifically looking for representatives of particular demographic groups.

Consequently, it has most of the deficiencies of a quota sample. The difficulty of modelling the electorate is one that has gotten quite a bit of attention in the modern context: We know fairly precisely how demographic groups are distributed in the population, but we can only theorise about how they will be distributed among voters at the next election. At the same time, it is straightforward to construct these theories, to describe them, and to test them after the fact. The more serious problem — and the one that was emphasised in the commission report in 1948, but has been less emphasised recently — is in the nature of how the quotas are filled. The reason for probability sampling is that taking whichever respondents are easiest to get — a “sample of convenience” — is sure to give you a biased sample. If you sample people from telephone directories in 1936 then it’s easy to see how they end up biased against the favoured candidate of the poor. If you take a sample of convenience within a small demographic group, such as middle-income people, then it won’t be easy to recognise how the sample is biased, but it may still be biased.

For whatever reason, in the 1930s and 1940s, within each demographic group the Republicans were easier for the interviewers to contact than the Democrats. Maybe they were just culturally more like the interviewers, so easier for them to walk up to on the street. And it may very well be that within each demographic group today Democrats are more likely to respond to a poll than Republicans. And if there is such an effect, it’s hard to correct for it, except by simply discounting Democrats by a certain factor based on past experience. (In fact, these effects can be measured in polling fluctuations, where events in the news lead one side or the other to feel discouraged, and to be less likely to respond to the polls. Studies have suggested that this effect explains much of the short-term fluctuation in election polls during a campaign.)

Interestingly, one of the problems that the commission found with the 1948 polling with relevance for the Trump era was the failure to consider education as a significant demographic variable.

All of the major polling organizations interviewed more people with college education than the actual proportion in the adult population over 21 and too few people with grade school education only.

When did the sixties end?

The Guardian’s obituary for Baba Ram Dass comments about his most famous book

He wrote about his conversion in Be Here Now, which became popular in the 1960s and provided a road map for the burgeoning New Age movement of spirituality.

Now, this should have given the writer pause, given that a prior paragraph dated his travel to India and religious conversion to late 1967. Indeed, Be Here Now was published in 1971, making its popularity in the 1960s of a particularly esoteric sort.

I suppose they’re not talking about the literal 1960s — as in, the span of ten years beginning from 1 January, 1960 AD — but rather, about the cultural 1960s, that began between the Chatterley case and the Beatles’ first LP, continued, as Hunter Thompson put it, only in San Francisco,

in the middle sixties… a very special time and place to be a part of. Maybe it meant something. Maybe not, in the long run … but no explanation, no mix of words or music or memories can touch that sense of knowing that you were there and alive in that corner of time and the world.

and concluded

now, less than five years later, you can go up on a steep hill in Las Vegas and look West, and with the right kind of eyes you can almost see the high-water mark—that place where the wave finally broke and rolled back.

Or maybe it never ended. Donald Trump is in many ways the apotheosis of the 1960s. The reduction of politics and traditional institutions to pure id and appetite. The unmasking of the White House mystique as just a cranky old antisemite with a fourth-grade vocabulary and a jones for Big Macs. He’s not what Abbie Hoffman thought he was fighting for, but in retrospect it turns out that’s what he was fighting for.

“Spirit of innovation”

I’m fascinated by the way ideologies get hardwired into language, so that the ideology becomes unchallengeable and yet invisible. And sometimes you only notice it when you observe how words have changed their meanings or their valence over time.

Thus I was brought up short by this remark of George Washington (quoted in Michael Klarman’s wonderful new account of the origins of the US Constitution The Framers’ Coup: The Making of the United States Constitution) expressing his concerns that the first Congress, considering the clamour for a Bill of Rights and other immediate amendments would produce such

amendments as might be really proper and generally satisfactory without producing or at least fostering such a spirit of innovation as will overturn the whole system.

I’ve never seen the word innovation used to express something to be avoided, rather than something to be promoted and praised. (The one exception is in time-series analysis, where the “innovation” has a purely neutral technical sense.) There is a whole world-view wrapped up in our modern veneration of “innovation”.

The meaning of “is”

One of Bill Clinton’s most famous contributions to the political lexicon is

It depends upon what the meaning of the word “is” is.

This was his defense from the accusation of having lied when he explicitly said, of his relationship with Monica Lewinsky,

There is not a sexual relationship, an improper sexual relationship, or any other kind of improper relationship.

It was immediately obvious that there was something strange about his somewhat tortured insistence on the present tense, where what he was asked to deny was in the past. Of course, we know that he was trying to be extremely clever in making a statement that was literally true, while seeming to deny an accusation that he knew to be correct.

Now Speaker of the House Paul Ryan has spoken out, not in his own defense, but in defense of the president:

“In all of this, in any of this, there’s been no evidence that there’s any collusion between the Trump campaign and the President and Russia,” he said. “Let’s just make that clear — there is no collusion.”

Is he being ironic?

The dead end of 70s childrearing

People often raise their children with ideals that they don’t really hold themselves, either because they on some level think they would be better people if they shared these ideals and hope their children will be better (tolerance, patience), or because they think these ideals are particularly appropriate to this stage of life (sharing, studiousness, Santa Claus). But I’ve been realising that some of what I learned as I child — at home, at school, and from the general culture

I genuinely found it weird that Barack Obama was attacked for harboring a secret “anti-colonialist” agenda (inherited from his father’s experience fighting the British for Kenyan independence. If I’d had to say what the core historical experience was that Americans harked back to, that defined our national identity, that we could agree upon, it was the history as colonials fighting for independence. The people opposing Obama dressed up in colonial-era costumes, harked back to the Boston Tea Party, striking a blow against the imperial power. Continue reading “The dead end of 70s childrearing”

Jared Kushner thinks ahead on prison reform

One of the oddest trends of the latter half of the odd 1970s in the US was the transformation of law-and-order conservatives like Charles Colson and even G. Gordon Liddy into prison-reform advocates, after they had spent some time themselves in federal prison for their role in the Watergate scandal. The President’s son in law isn’t waiting. Congress is considering a package of reform measures to improve federal prison training programmes, and increase the possibilities for early release for good behaviour. Reports are that Kushner has taken time out of his busy schedule making peace in the Middle East and solving the opioid crisis to lobby for the bill. JK is, of course, famously well behaved. What good is advocating prison reform if it comes too late for you to take advantage of it?

Horse thieves and inverse probabilities

Reading Ron Chernow’s magisterial new biography of Ulysses Grant, I came across this very correct statistical inverse reasoning from the celebrated journalist Horace Greeley (whose role in the high school history curriculum has been reduced to the phrase, “Go West, young man” — that he denied having invented):

All Democrats are not horse thieves, but all horse thieves are Democrats.

This seems like an ironic bon mot, but after he became the Democratic candidate for president against Grant in 1872 he tried to use a milder version unironically as a defence of his new party colleagues:

I never said all Democrats were saloon keepers. What I said was all saloon keepers are Democrats.

Presumably he meant to add that if we knew the base rate of saloonkeeping (or horse thievery) in the population at large, we could calculate from the Democratic vote share the exact fraction of Democrats (and of Republicans) who are saloonkeepers (or horse thieves).

Very fine people of 1863

I’ve just been reading Ron Chernow’s new biography of U.S. Grant, struck by some of the parallels to current events. As interim Secretary of War Grant was at the center of the struggle over the Tenure of Office Act that served as the pretext for Johnson’s impeachment. Johnson’s supporters charged Grant with lying and drunkenness. The New York Tribune retorted

In a question of veracity between U.S. Grant and Andrew Johnson, between a soldier whose honor is as untarnished as the sun, and a President who has betrayed every friend, and broken every promise, the country will not hesitate.

And Grant’s opponent in the 1868 presidential election, New York governor Horatio Seymour, had

Denounced the Emancipation Proclamation as “a proposal for the butchery of women and children, for scenes … of arson and murder.” During the 1863 draft riots in New York, Seymour had praised the responsible hooligans as “my friends”.

Shades of Charlottesville.

On the one hand, it might be comforting to know that the US has come through worse. On the other hand, to say that current affairs have their parallels in the extreme crisis of civil war, and in a state of division that could only be “resolved” by policies that imposed essentially a century of apartheid in the southern states, is hardly comforting.

The compromise candidate

Several years ago I wrote a post about the strikingly different place of the US Civil War and the English Civil War in the collective memories of their respective countries. The other day I alluded in a post title to William Faulkner’s famous dictum “The past is never dead. It’s not even past.” This things come together in the way the news from Washington was dominated for a few days by an argument over the causes of the Civil War. Donald Trump’s Chief of Staff decided to take up the white supremacist’s burden by claiming that the war was an unfortunate consequence of well-intentioned men on both sides being unwilling to compromise. (Rather in the same way that Polish intransigence over the border issue started the Second World War. Not to mention the SS guards’ well-documented failure to maintain proper air-quality standards in Auschwitz…) Continue reading “The compromise candidate”

The mystic electric cords of memory

I’ve just been reading Eric Foner’s masterful treatise The Fiery Trial, on the evolution of Abraham Lincoln’s views on slavery and race. I was struck by this passage from Lincoln’s speech in Chicago, during the 1858 senate election campaign. Referring to the suggestion that citizenship was inherited by blood from the patriots of the Revolutionary era he said that half the current population had no blood tie to those English, but

when they look through that old Declaration of Independence they find that those old men say that “We hold these truths to be self-evident, that all men are created equal,” and then they feel that that moral sentiment taught in that day evidences their relation to those men, that it is the father of all moral principle in them, and that they have a right to claim it as though they were blood of the blood, and flesh of the flesh of the men who wrote that Declaration, (loud and long continued applause) and so they are. That is the electric cord in that Declaration that links the hearts of patriotic and liberty-loving men together, that will link those patriotic hearts as long as the love of freedom exists in the minds of men throughout the world.

So I wondered, why is he referring to an “electric cord”? This is long before any household electricity. I’m guessing he is thinking of a telegraph wire. I find it surprising that he could expect his audience to have a meaningful association with this specific element of what was then a brand new technology, and I wonder what feelings went with it.

(In case you don’t know the reference in the title, it’s in the last paragraph.)