nm
“ProPublica found evidence of a disparity in the risks faced by young black and white men. This does not prove that police officers target any age or racial group – the data is far too limited to point to a cause for the disparity. We hoped that our analysis would spur further inquiry into why this disparity exists, which it has done, and we stand by it.”
Those studies have been done. At least twice that I know of and that police do not kill blacks more frequently than whites after taking variables into account.
See Roland Fryer.
Age was taken into account.
Once again, we are talking about 37 police killings out of 3000.
If pro-publica wanted to do an ACTUAL study, nothing is stopping them but the raw data on a data series that represents about 1& of the data set is meaningless and best (and a deliberate lie at worst).
Hah. You think I’m a liberal?
If that was what you got from reading " hundreds of other pages" of my posts, you clearly have been reading " hundreds of other pages" by the wrong poster. I am not a liberal.
Apparently I’m “the most dangerous poster on this board”. Awesome!
So jealous!
I think you are confusing emotions with data. There may even be information there but its not data.
Lets say that we wanted to determine whether Harvard is discriminating against Asians in the admissions process. Could we listen to the story of one Asian student that was denied by Harvard and call that data? Of course not. We would need a systematic attempt to collect relevant information that is collected in a way to weed out distortive factors and constructed to prove or disprove a hypothesis.
Some law professor talking about how lonely they felt as the only black male at Yale law school is not data. Its just a story, even though he gets to teach an entire law school lecture on those feelings, its still just a story.
I’m not sure how a robot would be any worse at confusing anecdote (essentially emotion) from logic and reason.
Emotion and anecdote is how you get Willie Horton, racism, lynching.
Just because they THINK they are being reasonable and logical doesn’t mean they are. Every scientific racist I have ever heard ignores the effects of racism and cherry-pick’s data. There are too many studies that document things like stereotype threat that you can’t simply say “hey look rich black kids do worse on IQ tests than poor white kids so it couldn’t be environmental and therefore its is a genetic difference in IQ, no need to look any further”
Are you even reading what you’re writing?
No, I’d call it a datum.
I’m not being insulting here, honestly, but are you a second-language English speaker?
“Logic and reason” is how you get gas chambers and Unit Unit 731.
Whee, this is fun. Ok, your turn for using argumentum ad passiones.
Yes, funny that. Almost ironic, really…
Yes. If we are doing an analysis of racism in the law and you tell me how you lonely you felt in law school. That is not data.
That is meaningless in this conversation. Data as we are discussing it is a pool of information that we can use to test a hypothesis. A single point of data is useless. An emotional rendition of that data through storytelling is more entertaining but just as useless.
Third but I speak and read at native levels. I think the confusion you are sensing is the result of thinking that all information is data. While the saying that “the plural of anecdote is not data” is too simplistic its not entirely inaccurate either. A couple of anecdotes is not really enough information to draw any conclusions or develop any sort of policy.
You started it. Logic and reason did not get us gas chambers. The desire to exterminate people did. Whether they used gas chambers or firing squads, it was the desire to exterminate that did it unless you think the extermination of jews was logical and rational.
Unit 731 was inhumane.
We are talking about CRT. Is CRT using loosey goosey emotional arguments to stop genocide or human medical experimentation? Of course not.
I can point to where they are not being logical. Can you point me to where I am not being logical?
The scientific racists are not being rebutted by arguments that logic and reason can be ignored. They are being rebutted by better logic and reason. You are rebutting logic and reason with anecdotes, feelings and emotions.
You have the scientific racists cherry-picking information, ignoring other variables, and using the raw unanalyzed data to reach their conclusions (sort of like how iiandyiiii is taking 37 deaths out of 3000 to imply that cops like killing young black males). Objective facts, logic and reason are almost always better for minorities and the politically weak than subjectivity. If subjectivity is working in your favor, you have to wonder how politically weak you are.
…apparently I’m such a danger to this board that you are forced to say incorrect things about me. Apologies for being so, so dangerous. I’d say you have nothing to fear, but like a poor friendly dog that got caught on the edge of nuclear fallout testing, I probably don’t fully understand the extent of the danger I present to others.
Of course your cartoon rendition of CRT is not the actual substance of it. And if the actual question is “Why are most judges white men”, how PoCs feel about law school is very much relevant data.
Nope.
Sure.
That’s … just not true.
A single datum can sometimes blow an entire thesis out of the water. If it’s the right datum.
Native American levels?
All information is data. It just wants the right processing.
It’s an idiotic homily people who have never done a day of research like to use to pat themselves on their (virtual) backs.
Good thing the narrative of racism isn’t just a “couple of anecdotes”, then…
Did I?
Oh, they very much did.
No, that gets people shot in the woods. It takes “logic and reason” to get to gaschambers.
The Nazis certainly thought it was. Their thinking is laid quite plain. “Problem”->“Solution (Final)” is the language of “reason”, not emotion.
And yet, to the people doing it, “logical and reasonable”
Were we? I thought we were talking about how I’m a liberal and andy is a most dangerous man…
“loosey goosey”? Is that your empirical analysis?
There was that time you called an established academic school a “cancer”… that didn’t seem very logical…
Where have I done that?
Many minorities don’t seem to agree with you…
We already know how the deck is stacked, thanks .
Ask and the Dope will provide.
There is nothing inherently bad about taking a small subset of say 40 samples out of a larger set of 1200, if that smaller subset is the data of interest. All that you have to do is to treat it as though it was a study of 40 samples rather than a study of 1200. I understand your concern about data mining. When looking at the data you do need to account for the number of different subsets you looked at.
Since I haven’t seen the data I can’t be certain how it was organized and what different analyses they considered before settling on this one. Age is an obvious divisor to look at and it is possible that the sole hypothesis going in was to look specifically at the shootings of black youth (14-19 years) since anecdotally this is the group that appears to get the worst rap in the media. If that is the case than there is no need for p-value adjustement.
Otherwise you would have to consider whether they analyzed a number of different subgroups and only focussed on this group when they found that the other groups weren’t significant. For example they could have fully data mined by looking at every possible lower cut-point and every possibly upper cut-point until they found the one that gave the best results. I doubt they did this for two reasons. First, subgroups a division into under 14 (pre-teen), 14-19 (teen) and, 19+ (adult) with possibly a few other older subgroups seems natural rather than data derived. Secondly if they did this I would expect them to report 19 and under, since the under 14 group also showed significant bias and including them would probably improve their statistics. What I actually think is probably most likely is that the data the got from the FBI was already divided into age groups that they analyzed directly. Worst case scenario you should multiply any p-value you come up with by the number of different groups they looked at (although you could then divided by 2 to create a false discover rate to account for the fact that both the under14 and 14-19 groups appeared significant.)
There could also be some concern about the independence of the shootings. Correlated data will act to increase the variance of any estimates although not change the point estimates directly, I suspect however that most of the shootings are independent, given the fact that I haven’t hear any reports along the lines of Police slay 3 black teenagers in mass shootout, which would make national headlines.
So following Damuri Ajash back of the envelope calculation with a black/white ratio of with a black vs white relative risk of 31.17/1.47=21.2. According to the article, if blacks and whites were killed at equal rates, than there would be 185 additional deaths implying that N21.2=N+185 so the number of white deaths was about 9. The ratio of blacks to whites aged 15-24 in the population is about 33.3/7.32 = 3.54, and so the number of black youths shot in the study was about 921.2/3.54 =54.
So the log odds ratio is equal to log(21.2)=3.05
The standard error of this is approximately sqrt(1/8+1/54) =.378
resulting in a 95% confidence interval of (2.31 - 3.79) corresponding to a relative risks of 10.1-44.3. (about the same as they report)
and a Z-score of 3.05/.378 = 8.07 and a (two sided) p-value of 7.1*10^-16
So while it is possible that the authors might of taken multiple looks at the data, I think it rather unlikely that that the number of looks were greater than the 7x10^13 that would be required to make their result insignificant due to multiple comparisons (or data drudging as you call it).
A better complaint is that they didn’t take into account other covariates (different poverty rates between whites and blacks is the most obvious), this plus the issue of correlated data (which is very hard to account for) might lead me to hold off on fully endorsing the final number, but I find it difficult to believe that any alternative analysis would fully eliminate such a massive effect.
- Buck Godot Statistics PhD.
Wow, what a wonderfully dangerous post! Kudos, Buck Godot!
The danger you present (IMO) is the same danger that all attractive packaging presents. It is easy to believe you. You’re seem like a nice person who cares about people and you certainly sound reasonable and I suspect you are genuinely a nice person, the sort of person I would leave my children to if my wife and I were killed in a car accident. However this makes people believe you just because you believe what you are saying. Even if its wrong.
You are very sincere and earnest but your fuzzy thinking and emotion laden arguments lead you to the conclusions you wanted to reach before you started your inquiry, almost without fail. I mean geez, I like you and if it wasn’t for the frustration I feel at someone being wrong on the internet, I’d probably just go along with you too and then we’d both be wrong.
“emotion laden arguments”? Arguing just to get to a desired conclusion? Being wrong on the internet?iiandyiiii?
I haven’t seen that much projection since I last visited the IMAX…
And my danger is so great that apparently I’ve sucked in a professional statistician, poster Buck Godot. Wow, how dangerous can one poster be?
I am anxiously awaiting any reply to the statistics PhD by Damuri Ajashi.
Nice job by the way, Buck Godot, even if I don’t understand a lot of it.
Here’s a dangerous statement: it doesn’t really matter what a random internet person thinks about the professional opinion of a statistician about a statistical question. So I’m not sure if you need to anxiously await it.
Sorry. I’ll limit my statements to those that are non-dangerous.
Hey, I like kittens!
It’s broken down granularly by exact age at death. We should get your hands on the raw numbers but based on a more granular analysis by realclearpolicy, it appears that there are statistics kept much more granularly than 14-19.
There were only 2 murders in the under 14 age group in those three years. One black kid and one hispanic kid. (according to the footnotes in the pro-publica article). The numbers in the article go back to 1980.
And what if there are actually 80 age groups from 0-80?
Would it be fair for me to point out that cops kill old white men age 74-79 INFINITELY more frequently than black men age 74-79? Cops killed 6 white men in that age group and no black men. What is the statistical significance of that?
Yeah, I don’t think that’s a concern unless there are gangland type shootouts.
Ah OK I missed the fact that the 185 deaths were ADDITIONAL deaths.
I’m not arguing the math. I’m arguing the logic of even applying the math.
There are only ~3000 deaths to cherry pick. Are you saying that I have to run 70,000,000,000,000 simulations to figure out how to come up with skewed numbers? I literally just looked at the numbers for about 10 seconds to come up with the fact that white men between 74-79 are murdered by police infinitely more frequently than black men 74-79.
Recent paper by Roland Fryer says almost exactly but with more variables.