Tuesday, September 19, 2017

They did it their way

Since my last post was long and complicated, I thought I should follow with something short and simple.  In 1987, the Roper Organization asked "Thinking about the way your own life has turned out so far, would you say it has been primarily a matter of luck or fate, or has it been more a matter of factors which are within your control?"  The same question was asked in CBS News polls in 1996 and 2016.  The results

                  Luck   Your Control   Both    DK
1986           22%        66%             9%       3%
1996           18%        72%             6%       4%
2016           27%        60%             9%       4%

The differences in the relative frequencies of luck and own control are statistically significant.  It seems possible that opinions on this are affected by economic conditions--when people experience bad things like unemployment or reduced income, they are likely to say it's luck.  However, as I recall economic conditions in 1986 and 1996 were roughly like they were in 2016--pretty good but not outstanding.

[Data from the Roper Center for Public Opinion Research]

Sunday, September 17, 2017

More old news

About six months ago, I saw several stories saying that "Having just one black teacher can keep black kids in school," to quote NPR's summary.  They all noted the magnitude of the effect:  almost 40% reduction in dropout rates for low-income black boys.  I located the paper on which the stories were based and thought about posting on it, but it was a long paper by the time I got around to reading it, the attention seemed to have passed.  However, last week's NY Times magazine had a list of statistics on education, and one of them was "exposure to at least one black teacher in Grades 3 to 5 reduced the probability of low-income black male students dropping out of school by almost 40%."  So that led me back to the paper.

The thing that originally attracted my attention was not the general idea that having a black teacher would help to keep black children in school, which seemed plausible, but that it could reduce dropouts by 40% for any group.  There is a lot of data on basic educational outcomes like finishing school, and by the standards of social science it's high quality data.  Moreover, there are a lot of people who have studied the issue, so it seems that any simple and straightforward way to dramatically reduce dropout rates would have been discovered long ago.

The paper reports that the estimated effect on dropout rates is -.04 for all black students, -.06 for persistently low-income black students, and -.12 for persistently low income black male students.  Since about half of students are boys, that suggests that the estimated effect on persistently low income black female students would be about zero, and indeed they report an estimate of 0.00 for that group.  So the issue was treating only the big estimate as worthy of interest.  If you believe that there are differences in the effects on boys and girls (and the difference appears to be statistically significant), both of the estimates are equally important; if you don't, you should just report the estimate for boys and girls combined.  The differences between persistently low income students and other students don't appear to be statistically significant (it's hard to tell from the tables), so maybe you should just report the estimate for all students.

There's also a more complex issue which relates to the way that they got the estimate.  The simple approach would be to do a regression with dropping out as the dependent variable, and having a black teacher plus some other variables as independent variables.    But the authors say that those estimates "are likely biased by unobserved student characteristics that jointly predict classroom assignments and long-run outcomes, even after conditioning on the basic socio-demographic controls in X and school FE (Rothstein 2010). For example, students with lower achievement (Clotfelter, Ladd & Vigdor, 2006) and greater exposure to school discipline (Lindsay & Hart, 2017) are more likely to be matched to black teachers, and these factors likely affect long-run outcomes as well."  That is, black teachers tend to be given the kind of students who are at higher risk of dropping out.  The authors had an idea on how to eliminate this potential bias.  They had multiple students from each school, which means that they could include a dummy variable for each school.  That's a reasonable thing to do, since it's generally agreed that some schools are more effective than others.  They also had five different classes of students:  those who started third grade in 2000, 2001, 2002, 2003, and 2004.  Because of new hires, departures, and leaves, the percent of the teaching staff that was black could change from year to year.  Those personnel changes would depend on idiosyncratic individual factors--getting pregnant, reaching retirement age, having a spouse get a job offer in another state--so they would be random from the point of view of the students.  So you can use within-school variation in the racial composition of the teaching staff over time as a substitute ("instrument") for the original variable (having a black teacher or not) and get unbiased estimates.

This approach strikes me as clever but not very convincing.  Teachers' decisions to stay or go will depend partly on how rewarding it is to work in a school.  That could depend on student performance (teachers like it when their students do well) or on things that might affect student performance, like discipline problems, or how well teachers get along with the administration.  Things get more complicated because what matters is differential effects on black and white teachers, but I can think of possibilities here too:  for example, black teachers may be particularly interested in how the black students are doing.  I think I might trust the simple results more than the results from their method--at any rate, I'd like to see them, but they aren't reported in the paper.

This isn't a straightforward mistake, but the sort of difference of judgment that often comes up with research, and the authors could probably say more in defense of their approach.  But I will stick with my original feeling that a 40% reduction in dropout rates for anyone is too big to be believed.

Saturday, September 9, 2017

Alternate history

This came up several weeks ago, but I hadn't gotten around to posting on it.  On July 26, Elizabeth Hinton (a professor of History and African-American Studies at Harvard) reviewed three books on race and policing in the New York Times.  She said that one of the books (Chokehold, by Paul Butler), "demonstrates that when citizenship rights are extended to African-Americans, policy makers and officials at all levels of government historically used law and incarceration as proxy to exert social control in black communities. Black Codes, convict leasing and Jim Crow segregation followed Emancipation; overpolicing and mass incarceration followed the civil rights movement."  This reminded me of the figures on crime and prison that I showed in a previous post.  I concentrated on crime rates there, so here is more detail about imprisonment.  First, the figure for 1929-86, which was the period covered in the data source (it kept going up after 1986):

 
The next one focuses on the period during and after the civil rights movement:


The rate of imprisonment didn't start rising until 1973, when the movement had either faded away or become mainstream (that is, not really a "movement").  During the period of peak activity of the civil rights movement, the rate of people in prison declined or stayed about the same, although crime was increasing.  In a literal sense, the rise in imprisonment did follow the civil rights movement, but the suggestion of cause and effect is not very credible.




Saturday, September 2, 2017

Respect

The Pew survey I mentioned in my previous post had a series of questions about "how much respect do you think Donald Trump has" for various groups "a great deal, a fair amount, some, or none at all."  Then the same questions were asked about how much respect Hillary Clinton had for the groups.  The averages, ranked from greatest to least average respect for the group:

                               Trump       Clinton
White people                    3.23       3.03
Men                             3.21       2.77
Veterans                        2.84       2.73
Women                           2.19       3.16
Blue collar workers             2.64       2.66
Black people                    2.31       2.84
Evangelical Christians          2.66       2.42
Hispanic people                 2.16       2.85
Immigrants                      2.00       2.93
Muslims                         1.86       2.93
People who support [opponent]   1.91       1.91

The standard errors are about .03 or .04.  The ratings aren't surprising--Trump is seen as having substantially less respect for women, black and Hispanic people, immigrants, and Muslims, and somewhat more respect for white people, men, veterans, and evangelical Christians.  However, it's noteworthy that Trump and Clinton are rated almost exactly the same in respect for blue collar workers--this is one of many pieces of evidence that contradicts the popular story that working class voters turned to Trump because they thought that liberals were condescending to them.  It's also notable that Clinton was seen as having pretty high respect across the board--her perceived respect for Evangelicals, which was lower than her perceived respect for any group except Trump supporters, was higher than Trump's perceived respect for six of the groups.

What difference did these perceptions make?  I regressed intended vote on each candidate's perceived respect for the groups (one half of the sample was asked about women, men, whites, blacks, Hispanics, and veterans; the other about Muslims, evangelicals, immigrants, blue collar workers, and people who supported the other candidate).  The logistic regression coefficients, with positive values meaning that more perceived respect for the group goes with more support for the candidate (standard errors are typically about .2 or .3, and standard errors of the differences about .3):

                              Trump       Clinton
White people                   -0.31      -0.03
Men                             0.12      -0.09
Veterans                        0.66       1.14
Women                           1.13       0.32
Blue collar workers             1.10       1.19
Black people                    1.17       1.06
Evangelical Christians          0.34       0.91
Hispanic people                 0.74       0.62
Immigrants                      0.57       0.04
Muslims                         1.53       0.72
People who support [opponent]  -0.13       0.77

I don't think that perceptions of respect are necessarily causes of the way that people vote:  to some extent, probably a large extent, people are rationalizing the way they voted.  But the way that people rationalize their actions is still interesting.  

A large coefficient could mean that a group is held in high esteem (that people think it should be respected) or regarded as important in some sense.  But from that point of view, the coefficients for white people and men are puzzling.  Another factor could be whether respect from the candidate in question could be taken for granted.  For example, there wasn't much doubt that Hillary Clinton respected women, and it didn't make much difference in support for her; there was a lot of doubt about whether Trump did, and it made a lot of difference in support for him.  So the fact that perceived respect for men and white people didn't matter could be because most people thought they'd be all right regardless of which candidate won (this contradicts another popular story, about how Trump supporters were motivated by perceived threats against whiteness or masculinity).

The combination of these principles seems to make sense of the coefficients, with one exception:  the difference in the effect of Trump and Clinton's perceived respect for supporters of their opponent.  Clinton gained from being seen as respecting Trump voters; Trump didn't gain from being seen as respecting Clinton voters.  This pattern suggests there's a bit of truth in the "liberal condescension" story--that on the average, people cared more about whether Clinton respected them than whether Trump did.

[Data from the Roper Center for Public Opinion Research]