Wednesday, December 29, 2010

Prediction is difficult, especially when it involves the future

In late 1949, a Gallup Poll asked people about their predictions for the next 50 years.


Do you think there will be another world war during the next 50 years, or not?
Yes—81%, no—11%, don't know—7%

Do you think a cure for cancer will be found?
Yes—89%, no—7%, don't know—4%

Do you think trains and airplanes will be run with atomic power?
Yes—64%, no—21%, don't know—15%

Do you think men in rockets will be able to reach the moon or the planet Mars?
Yes—16%, no—69%, don't know—14%

Do you think people in this country will go to church more often or less often than they do now?
More—40%, less—31%, same—22%, don't know—7%

Do you think labor unions in this country will become stronger or weaker than they are now?
Stronger—45%, weaker—33%, same—15%, don't know—8%

Another Gallup Poll conducted at the same time asked about some other possibilities:

Do you think the number of working hours per week for the average person will be cut down to about 30 hours—or do you think that the number of hours will stay about where it is today?
Cut—47%, same—39%, don't know—14%

During the next 50 years, do you think that most of the nations of the world will have a democratic government like the U. S., a Communistic government like Russia, or a socialistic government like England?
Democratic—54%, communistic—7%, socialistic—11%, other—3%, “no code or no data”--24%

Do you think a woman will be elected President of the United States at any time during the next 50 years?
Yes—31%, No—59%, Don't know—9%

During the next 50 years, do you think that the government in Washington will own and run  …. the railroads in the U. S.?
Yes—37%, No—43%, Don't know—20%

...the banks.
Yes—28%, No—53%, Don't know—18%

….the big industries, like auto, steel, etc.
Yes—24%, No—57%, Don't know—18%

By my count, that means the majority was right on six and wrong on six, which doesn't seem too bad. 

PS:  The "reach the moon or the planet Mars" is a classic example of poor question design.  I'm surprised they didn't notice that.    On the prevailing form of government, they didn't show a "don't know" category.  I'd guess that "no code or no data" is mostly people who said they didn't know. 

Sunday, December 26, 2010

America and Britain

In 1973, the United States Information Agency sponsored a survey of British elites concerning their views of the United States and Britain. It included seven types of elites: government, arts, academics, media, student organizations, business, and labor. I thought that there might be large differences among the groups—for example, business would be more favorable to the United States, arts or academics would be more critical. But although there were some differences, they weren't very striking. The comparison of general views of the nations was more interesting. The survey asked how successful each nation was in providing different things, on a scale ranging from 1 (“very successful” to “not successful at all”). The differences between the average ratings, with positive numbers meaning that Britain was seen as doing better than the United States:

1.51 'taking care of its sick people'
1.24 'rights of its minorities'
1.06 'minimizing drug addiction'
1.03 'peaceful means for changing social conditions'
1.02 'taking care of its poor people'
1.22 'maintaining law and order' 
  .50 'taking care of its old people'
  .35 'good quality education' 
  .35 'minimizing environmental pollution'
  .24 'jobs for everyone who wants to work'
  .18 'full educational opportunities for most people'
  .02 'adequate standard of living for most people'
  .01 'encouraging full development of the arts'

-.32 'stable economy'
-.66 'opportunites for personal career advancement'

It also asked how well certain pairs of terms described British and American societies:
for example, “class conscious” versus “classless,” with the scale ranging from 1 to 7.
The ratings:

2.81 'non-violent'
2.48 'stable'
2.44 'cooperative'
2.22 'law-abiding'
1.86 'disciplined'
1.72 'tolerant'
1.43 'non-materialistic'
.66 'permissive'

   .00 'non-conformist'
-0.10 'innovative (vs. imitative)'
-0.18 'ideological (vs. pragmatic)'
-1.42 'classless'
-2.52 'dynamic'

For example, British elites saw the term “non-violent” as more descriptive of Britain than the United States, and “dynamic” as less descriptive of Britain than the United States. The words in parentheses are the opposing term when it isn't obvious.

Monday, December 13, 2010

Christmas shopping guide (slightly outdated)

In December 1958, a Gallup Poll asked "If you could have your choice, what one present would you most like to have for Christmas?"  About 14% didn't know, said that there was nothing, or didn't answer.  About 7% named some kind of general improvement in their living standards ("lots of money," "a job"), and about 6% said a new house or apartment. Other popular choices: 

New car                                       14%
Clothing                                      11%
Large appliances (e. g., a stove)              8%
Electronics                                    7%
Furniture, home furnishings                    6%
Sporting/Hobby equipment                       4%
Jewelery                                       2%
Small appliances (e. g., sewing machine)       2%
Vacation, trip                                 2%

What struck me was how practical most people were.  Even most of the things I've counted as sporting/hobby equipment might have some practical value--the group includes 27 people who said "tools," compared to two who said golf clubs.  "Jewelery" includes 24 who wanted a watch, compared to only two who wanted a bracelet, and one who wanted pearls.  Of course, there were a few dreamers:  one person want an airplane. 

People were also remarkably centered on their homes.  No one mentioned anything related to dining out or entertainment, except for five who said "a good meal."

This question, or similar ones, have been asked a few times since then, but I haven't looked at them in enough detail to compare them. 

Saturday, December 4, 2010

Of a certain age

A 1958 Gallup poll asked  "at what age . . . a woman reaches the peak of her beauty."  Answers ranged from 15 to 75, with an average of 29.9.  Yes, but there was a big difference between the opinions of men and women, right?  Not really--women gave an average answer of 30.1 and men gave an average of 29.6.  The difference is not statistically significant. 

It also asked "at what age does a person reach the peak of his mental ability"?  Answers ranged from one to 83, with a mean of 39.4.  Here, there was a difference between men and women--women gave an average of 37.8, and men an average of 41.1. When I was younger I might have been able to think of a plausible explanation for this difference, but now I'm coming up blank.

There were a few other questions about ages:  when middle age begins (average of 43.9 years), when old age begins (65.3), when an unmarried man should be described as a bachelor (33.8), and when an unmarried woman should be described as a spinster (32.4).  For all of them, women chose a slightly (but significantly) higher average. 

Tuesday, November 23, 2010

They do things differently there

From a 1959 French survey:

"When you were, let's say between 8 and 12 years of age what did you usually drink at meals?"
Only water            22%
wine with water added 44%
a little wine, pure    4%
cider                 15%
beer                  10%
other                  4%

There was a series of questions about the first time you had "the impression that you had drank a little too much."  One of them asked "Was it at a particular occasion and which one?"

15% Ceremonies of a family character very often religious followed by celebrations 
 8% Gatherings [at a] family meal 
11% Gathering [of] friends
 7% Popular celebrations
 8% Usual drinking excess marking the beginning of adult life
 3% During work
 2% At the army
 4% Curiosity or childhood feat unknown to the adults
 4% Accidentally, exceptionally, taken surprise by circumstances
 2% Other answers
36% Don't know or don't remember

"How did your parents react when they observed that you had effectively drunk a little too much for the first time?  Were they..."

amused                        11%
kind                          16%
did they think it was normal   4%
judged you severely            4%
they didn't know about it     20%
No answer                     40%

The question about the occasion on which you first drank a little too much was open-ended:  people gave whatever answer they wanted and later someone classified it into the categories.  The report gave some examples of people's answers:

"It's sad to say but it was my first communion"
"pig fair"
"when I buried my life as a boy"
"I was an apprentice for an old gardener who made me drink"
"after school, to celebrate his little brother's birth, a friend took me to a cafe"
"I had gone to be paid by a wine-grower and they made me taste their wine"
"to be a braggart"
"I was coming back from a long stay in England where I had drunk only water"
"it was at boarding school, we were well taken care of"

Monday, November 15, 2010

Will this reading be on the test?

My friend and colleague Brad Wright has included several plugs for this blog on his own blog.  Brad is interested in religion, so here's a finding for him, from a 1965 Gallup Poll.  The survey asked people whether they'd done various things--there was no particular logic to the list, which included flying in a plane, eating caviar, and betting money at a race track (more common than I would have guessed).  One of the items was "read the Bible through--every word."  20% of the respondents said they had.  The straightforward interpretation is that 20% of Americans had read the Bible all the way through, but I find that hard to believe.  The Bible is a long book, and as a college professor I have a good sense of the chance that people will read long books all the way through.

Another possibility is "social desirability bias"--people are giving the answer that they think they "ought" to give, rather than telling the truth.  If the question involved general frequency of reading the Bible or attending religious services, social desirability might be an important factor.  But I don't think many people imagine that the world will think worse of them if they skipped a few of the minor prophets.  Also, the way that the question was asked cut down on the risk--it gave them a list and asked them to read off the letters designating the things they had done.  So you didn't have to explicitly say "no"--you just had to leave the letter "p" off of your list. 

A third  possibility, which I find the most plausible, is that most of these people thought they had read the Bible all the way through, even though they probably hadn't actually done so.  How would this be possible?  My guess is that many people who attended church frequently, or had done so at some point in their lives, figured that given the Bible reading involved they must have covered it all over the course of time, even if not in consecutive order. 

Another question in the list asked if you'd read a book all the way through since leaving school.  Of the people who said they hadn't, 12% said they'd read every word of the Bible.  People who'd gone to college were most likely to say that they'd read the entire Bible (26%), but people who'd just reached grades 8-11 were almost as likely (22%).  Among high school graduates who hadn't attended college, it was only 15%.

Wednesday, November 10, 2010

Are we downhearted?

A CNN/Opinion Research Corporation poll question:  "As you may know, the United States went through a depression in the 1930s in which roughly one out of four workers were unemployed, banks failed across the country, and millions of ordinary Americans were temporarily homeless or unable to feed their families. Do you think it is very likely, somewhat likely, not very likely, or not likely at all that another depression like that will occur in the US within the next 12 months?"

                       Oct 2008  Oct 2008   Dec 2008   Mar 2009  July 2009  Dec 2009
Very            21%      12%     10%     12%      12%     17%
Somewhat        38%      29%     28%     33%      29%     26%
Not very        29%      35%     41%     36%      36%     39%
Not likely      13%      24%     20%     18%      22%     19%

There was a substantial change between the first two surveys, which were only two weeks apart (Oct 3-5 and 17-19), but very little change since then.  I'm not even sure if the differences among the last five surveys are statistically significant.  (If you want to calculate it yourself, the sample sizes are about 1,000 for each survey).  After a year when the worst didn't happen, it would be reasonable to think that it wasn't going to happen in the next year.  But that wasn't how people reacted.  

The improvement over a two-week period in October 2008 is also interesting.  The TARP bill was signed into law on Oct 3.  Maybe the process leading up to that contributed to a sense of panic, and people just bounced back after a few weeks.  Or maybe something positive happened between early and mid-October that affected people's outlook, although I don't remember the history well enough to think of what that might be.

Sunday, November 7, 2010

Elitism, part 2

As I said in my last post, very few surveys have asked about elites or elitism.  But back in 1996, a Gallup/CNN/USA Today poll asked whether the description "The Party of the Elite class in this country" applied more to the Democrats or the Republicans.  The results:  65% Republican, 19% Democrats, 4% both, 4% neither, 8% don't know.  Opinions differed by political views, but even among extreme conservatives, more people said Republicans than Democrats (32% to 30%). 

But political commentators seem to have a very different impression--many of them are convinced that the Democrats are really the party of the elites.  For example, in the New York Times Book Review a few weeks ago, Christopher Caldwell (a conservative) says that 19 out of the 20 richest Zip codes "gave the bulk of their money to the Democrats in the last election", while Jonathan Alter (a liberal) says it's only 8 out of 10.

Of course, 1996 was a while ago, and maybe popular opinion changed since then.  But the gap between public opinion and what might be called elite opinion on the subject is still impressive. 

Sunday, October 31, 2010

Elitism, part 1

Elitism is in the news these days (there's a story in today's New York Times called "Elitism: The Charge Obama Can’t Shake", and it has 316 reader comments as I write this). A few years ago, I looked for survey questions on the topic, and to my surprise, found very few.  There was one interesting survey, and I'm going to do a post on it in a few days, but in checking for more recent questions I found one that deserves an entry by itself.

This was in June 2004--a Pew survey asked:  "Does the phrase...'he is a wealthy elitist' better describe John Kerry, George W. Bush or don't you think it describes either of them"  20% said Kerry, 27% said Bush, 25% said neither, 14% volunteered that it described both of them, and 15% weren't sure.  Almost everyone who commented on the 2004 election said that one of Kerry's biggest problem was that he came across as aloof and elitist,  while Bush somehow managed to seem like a regular guy despite his wealth and background.  But it seems like more ordinary voters actually saw Bush as the elitist.  True, this survey was taken early in the campaign, and maybe more people came to see Kerry as a wealthy elitist as the campaign went on.   But people knew Bush well by this time, so why didn't he do better?

Sunday, October 24, 2010

There ain't half been some clever bastards

In 1952, a Gallup Poll asked people if they could identify some famous people (the questions were introduced as things that "might be on a radio quiz program").  Answers that said what a person did were counted as correct, and those that just gave his nationality were counted as "approximately correct."  In 1975, a Gallup poll asked respondents to identify the same people.  This time, the answers were just counted as correct or incorrect, and they didn't explain what it took to be correct.  So I give two figures for 1952--the first just counts correct and the second includes approximately correct.  The results:
              1952    1975
Beethoven    62 63    84
Raphael      30 30    35
Tolstoy      17 23    29
Freud        16 21    47
Aristotle    25 33    44
Rubens       15 15    24
Shakespeare  78 80    89
Gutenberg    17 24    24
Karl Marx    26 32    41
Napoleon     57 66    58
Columbus     88 89    92

Regardless of how you count the "approximate" answers, there were gains from 1952 to 1975, and in some cases big gains (e. g., Freud).  In a way, that's not surprising, since levels of formal education increased over that time.  But levels of political knowledge (things like ability to name public officials or knowing which party controlled Congress) haven't changed much since about 1950.  So the good news is that people were learning something during the 1960s and 1970s.  

As is often the case, the question hasn't been asked recently.  There are a lot more surveys than there used to be, but they tend to focus more heavily on politics.  I'd gladly sacrifice a few more questions on whether you approve of the job Congress is doing for a repeat of this one. 

Thursday, October 21, 2010

Post-racial society, 1949

A Gallup Poll in 1949 contained the question "Scientists are reported to be working on a drug that may be able to turn colored skins white. If such a drug were developed, people with colored skins who wanted to could turn (bleach) their skins white. Do you think this would be a good thing or a bad thing?" I don't know whether there really was talk of something like this at the time or whether it was just something they made up. In any case, 11% said it would be a good thing, 77% a bad thing, and the rest weren't sure.
  • Who was in favor? The survey asked about vote in the 1948 Presidential election. The two major party candidates, Truman (D) and Dewey (R), were both pretty progressive on civil rights by the standards of the time. There were also two minor-party candidates. On the left, there was Henry Wallace, who was a strong supporter of civil rights. On the right there was Strom Thurmond, the Governor of South Carolina, running under the States' Rights (Dixiecrat) party, which was about preserving segregation (this was the same Strom Thurmond who later was elected to the Senate, switched to the Republicans and served in the Senate until 2003).

  • 11% of Truman's voters thought the drug would be a good idea. Opinions among Dewey's supporters were just about the same, also at 11%. But 28% of Wallace's supporters thought it would be a good idea, compared to 0% of Thurmond's. None of Thurmond's supporters were undecided, either: 100% thought it would be a bad idea. There were only 40 Thurmond voters in the data set, but it's still pretty unusual to get unanimity in a group of that size. White southerners as a whole were strongly opposed, with 4% saying it would be a good idea and 6% unsure.

  • So basically, it seems like people with progressive views were more favorable. (That's also true if you compare using some other variables related to political outlook). Blacks, however, were not favorable--only 10% thought it would be a good idea, with 7% not sure.

Thursday, October 14, 2010

This is the saddest story I have ever heard

Well, not really, but maybe the saddest story involving survey research. A few years ago I was looking at the questionnaires from Gallup Polls of the early 1950s, and saw one with a question that went something like "Suppose that all laws were repealed for one day--what would you do?" The sad part--the words "not punched" were written across the question. That means the answers weren't recorded in the data set (which at that time involved punching holes in cards), and are lost forever.

Why didn't they record them? One possibility is that it would have been extra work. The interviewer wrote down the answers that people gave to questions like this. Someone had to read those answers and classify them into a number of categories. Maybe they punched the answers to the multiple-choice questions first, then turned the questionnaires over to the people who classified the answers, and didn't bother to send it back to punch that question. Or maybe the answers were so shocking that they decided that decency and good taste demanded be suppressed. On the other hand, maybe the answers were so dull that they decided it was wasn't worth bothering. We'll never know.

Monday, October 11, 2010

Confidence in higher education

In the last few years, I've heard a lot about how people are losing confidence in higher education because of rising costs, concerns that our graduates aren't ready for the globalized and diverse workplace, ... You can fill in the rest. I was skeptical of this, but I hadn't seen any data. I looked and found that the Harris Poll has asked this question pretty much annually since the 1970s: "As far as people in charge of running...major educational institutions, such as colleges and universities are concerned, would you say you have a great deal of confidence, only some confidence, or hardly any confidence at all in them?"

That's not ideal, since it asks about the "people in charge of running" them rather than the institutions rather than the institutions as a whole, and "major educational institutions" could go beyond colleges and universities. Still, it's what we have, so here's a figure of the percent who said "a great deal" of confidence. The line is broken because in the 1970s, they used different question wordings, so it's not clear if the results are comparable. Still, it is clear that confidence dropped from the mid-1980s to the early 1990s, and then recovered. I don't think that confidence in other institutions followed a pattern like this, so it must have been something specific to higher education. I recall that there were a lot of books about the failings of higher education then (Alan Bloom's The Closing of the American Mind was the best known). Maybe their message got through to the general public. Or maybe they reflected the spirit of the times?

Thursday, October 7, 2010

Men are such fools

A Gallup Poll from 1946: “Generally speaking, which do you think are more intelligent, men or women?”
40% said men, 21% women, 36% said no difference, and 4% had no opinion.

A Pew Research Center survey from 2008: “Now I would like to ask about some specific characteristics of men and women. For each one that I read, please tell me whether you think it is generally more true of men or more true of women..... intelligent?”
14% said men, 38% women, 45% said equal or it depends, 3% don't know

A big change there. A few other surveys since the 1990s have asked similar questions, with about the same results as the Pew question.

Opinions about racial differences in intelligence have also changed, but in a different way. In 1939 a Fortune surveys asked “Do you think Negroes now generally have higher intelligence than white people, lower, or about the same?
Only 1% said higher, 71% said lower, 22% about the same, and 6% don't know

In 1999 a Newsweek/PSRA poll asked “In general, do you think black people are more intelligent than whites, less intelligent than whites, or about the same?”
3% said more, 1% less, 92% about the same, and 4% don't know

To put it another way, the percent of people who say that there are race differences in intelligence has dropped from over 70% to less than 5%; the percent who say that there are sex differences in intelligence has declined only slightly (61% to 52%), but opinions on which sex is more intelligent have reversed.

Sunday, October 3, 2010

Lower cost, same result

It's been over a week since my last post. This blogging thing isn't as easy as it looks. Maybe if I click on that "Monetize" tab I can figure out how to quit my job and...

The Tea Party movement has reminded me of the anti-tax movement of the late 1970s. A Roper survey from July 1978 asked about measures to limit property taxes (which were popular), and then had some interesting follow-up questions. One asked “if the property tax were cut to 1% of market value . . . Do you think tax increases or service cuts would be necessary, or that needed services could be maintained without resorting to service cuts or tax increases?”

A majority (53%) said that tax increases or service cuts would NOT be needed. Those people were asked “Do you think that the government would find the needed money somewhere else, or that they would cut costs by eliminating waste, inefficiency, and needless programs?” 28% said they'd find the money somewhere else, 59% that they'd eliminate waste—the rest said some of both or weren't sure.

26% said that service cuts or tax increases would be necessary. They were asked which they thought the government would do—18% said raise taxes, 60% said cut services, and the rest weren't sure or said that they'd do some of both.

So for a lot of people, it seems that tax cuts were not a way to stop the welfare state, but a way to get it more cheaply. I haven't seen any similar questions asked recently.

The 20% who were not sure on the first question weren't asked any follow-up.

Thursday, September 23, 2010

More boredom, more excitement

Since the 1940s, surveys have been asking questions about overall happiness--"In general, how happy would you say you are--very happy, fairly happy, or not very happy?" Of course, there are are all sorts of things that could make people happy or unhappy, so I've kept an eye out data on more specific feelings. There isn't much, but a few surveys have included a series of questions: "During the past few weeks did you ever feel....
1. Particularly excited or interested in something
2. So restless that you couldn't sit long in a chair
3. Proud because someone complimented you on something you had done
4. Very lonely or remote from other people
5. Pleased about having accomplished something
6. Bored
7. On top of the world
8. Depressed or very unhappy
9. That things were going your way
10. Upset because someone criticized you?"

Notice that the odd numbered ones are generally regarded as good feelings, and the even numbered ones as bad. You can make a total score by adding the percents for the five good feelings and subtracting the percents for the five bad ones. For example, in 1963 it's:
The numbers mean 52% said they'd been particularly excited or interested, 45% said they'd been restless, and so on. Here's how the total scores have changed over the years:

Nov 1963   +98
July 1965 +152
April 1981 +203
June 1990 +222
Sept 2001 +180
Jan 2002   +211

So it looks like people have been feeling better according to these questions. That's interesting, because happiness as measured by the general question hasn't really changed since the 1950s.

I also looked at trends for the individual question. Excited, proud, pleased, going my way, and bored have become more common. Restless and unhappy have become less common. There's no clear change in lonely, on top of the world, and upset. So four out of the five positive feelings have become more common, but so did boredom. Why? I don't know. That's the advantage of a blog over a research paper--you can just say "I don't know" and leave it at that.

Technical PS: Notice the dates--the first survey was taken just after the assassination of JFK, and the one in September 2001 just after the 9/11 attacks. It seems reasonable that both of those events produced some negative feelings. If you adjust for that, the upward trend in the total scores gets even more clear. In a linear regression including a time trend just a time trend, the t-ratio is 2.26; add a dummy for the Nov 1963 and Sept 2001 surveys, and the t-ratio for the trend rises to 4.41.

Monday, September 20, 2010

The progress of humankind

In 1995, a Harris Poll asked: "Would you say you are a better than average driver, an average driver or worse than average?"
54% said better, 40% average, and only 1% worse (most of the remaining 5% didn't drive)

People have a pretty high estimate of their abilities in most areas, so the general pattern isn't surprising. But a 1965 Gallup Poll makes an interesting comparison:

"In general, how do you rate yourself as a driver--better than average, average, or not up to average?"
36% said better, 62% average, and 2% not up to average (non-drivers were not asked)

The question wordings weren't identical, but I don't see any reason that they should produce different responses, so it looks like Americans' estimate of their own driving ability became substantially more favorable over the thirty years.

Wednesday, September 15, 2010

What about a Blue Dog?

A CBS News Poll in 2008 asked the following question:

"Which would you prefer to be stranded on a deserted island with—another human being or a dog?"

74% chose a human, 22% a dog, 1% said neither, and 3% didn't know. It was only 1%, but the people who said "neither" worry me.

Back in 1958, the Gallup Poll had a different desert island question:

"Of course it would depend on the person, but other things being equal, would you rather be cast up on an island alone with a Democrat or a Republican?"

27% chose a Democrat, 14% a Republican, 34% neither, and 34% no opinion.

I assume that "neither" here means they'd prefer someone who wasn't a member of either party, not that they'd rather be alone.

The obvious explanation for the Democratic edge is that some people would rather have someone who shared their political views, and that there were more Democrats than Republicans at the time.  That's certainly part of it, but it doesn't seem to explain the magnitude of the Democratic edge. In the same survey, 50% said that they were Democrats and 31% said Republicans. That's a considerable lead for the Democrats, but less than the almost 2:1 edge in preference for a companion on the island.

By the way, I found these questions in the iPOLL database maintained by the Roper Center for Public Opinion Research at the University of Connecticut. It's an essential resource for research on public opinion, and unless otherwise indicated, is the source of all survey data mentioned in this blog.

Thursday, September 9, 2010

Back to school

In 1950, the Gallup Poll asked the following question:
WANT HIM TO GO?" (no, it didn't have a question about daughters).  About 8% said they didn't know, 4 percent gave the reasonable answer that it would be up to the hypothetical son, and a handful (less than 1%) said they wouldn't send him to college, leaving about 1300 who named a college.  The top choice was Harvard, but then things get more interesting.  Second place wasn't Yale, Princeton, Stanford, or one of the service academies, but Notre Dame.  Presumably a lot of Catholic parents wanted their son to go to a Catholic college, and Notre Dame was the best. 

The list of colleges picked by more than 10 people:

1.  Harvard       122
2.  Notre Dame    104
3.  Yale           78
4.  MIT            41
5.  West Point     40

6.  Michigan       34
7.  Columbia       31
8.  Berkeley       28
9.  Illinois       27
10. Chicago        25

11. Princeton      22
12. Cornell        22 
13. Minnesota      21 
14. Ohio State     21
15. Wisconsin      19

16. Stanford       17
17. Penn           16
18. Texas A & M    16
19. Purdue         14
20. Naval Academy  14

21. Northwestern   13
22. Dartmouth      13
23. NYU            13
24. USC            13
25. Penn State     12

26. UCLA           11
27. Kansas         11
28. Johns Hopkins  11
29. Michigan State 10

Some other patterns:  Midwesterners were loyal to their regional schools--the top 15 includes five Big Ten schools, plus the University of Chicago (and Notre Dame, although its appeal was probably to Catholics across the country).  Californians also were pretty loyal:  Berkeley, Stanford, UCLA, and USC appear on the list.  Southerners were not:  the only college in the South on the list is Texas A & M.  Distinguished schools like North Carolina, Virginia, Duke, Texas, Vanderbilt don't appear on the list, and most of them weren't even close. Finally, the choices were scattered among a lot of schools--about 40 percent of parents chose one other than those listed (including 2 for UConn, which unforunately was not enough to make us #1 among public universities in New England).

Unfortunately, no one seems to have asked this question since 1950.  I'd guess that the concentration on the Ivy League and similar places would have increased.

Advertisement to the reader.

In the course of my work as a sociologist, I often run across bits of information that I think are worth preserving.  That's the purpose of this blog.  As the blog title suggests, the goal is to just report the facts, although probably some interpretation and opinion will wander in from time to time.   Most of the facts will be from surveys, since that's what I use for my research.