Trump 2nd term prediction thread
So, looks like Trump not only smashed the electoral college, but is looking on track to win the popular vote, which seems to be an unexpected turn of events, but a clear sign of the current temperature in the country and perhaps the wider world.
Would be interested to hear views on how his 2nd term will pan out from both sides of the aisle - major happenings, what he's going to get done, what he's not going to get done, the impact of his election on the current conflicts in Ukraine and Gaza, whether his popularity will remain the same, wane, or increase, etc.
A bit of an anemic OP, I know, just interested to hear people's thoughts now that the election uncertainty is over.
Regardless of any of the above, you did (and still do) stubbornly refuse to either understand or acknowledge that the male-female split can't be taken to be constant across non-randomly selected subgroups. Maybe you found that to be an invalid claim, but if so, you didn't explain why, even after it
It is not "a necessary constant across non randomly selected groups" *BUT IT IS A PRIOR UNLESS PROVEN OTHERWISE*.
It is the best estimate available until proven otherwise.
There is no a priori reason it varies within the subpopulation.
It is still informative until proven otherwise.
It is not irrelevant.
It is not "a necessary constant across non randomly selected groups" *BUT IT IS A PRIOR UNLESS PROVEN OTHERWISE*.
It is the best estimate available until proven otherwise.
There is no a priori reason it varies within the subpopulation.
It is still informative until proven otherwise.
It is not irrelevant
Notwithstanding the fact that I don't think any of the above is correct from a statistics POV, it's a bit late. I'm saying you should have addressed it when it was raised (multiple times).
I even gave toy examples you could have objected to at the time. My toy examples already show why the reasoning above is suspect.
Notwithstanding that I don't think any of the above is correct, it's a bit late. I'm saying you should have addressed it when it was raised (multiple times).
Lol no i don't have to answer any bad faith attack on my claims ever in general or in the specific in this case.
Anyway I understand you guys are fixated with me but this is the "what happens now that trump is president" thread.
Lol no i don't have to answer any bad faith attack on my claims ever in general or in the specific in this case.
Anyway I understand you guys are fixated with me but this is the "what happens now that trump is president" thread.
Bad faith? I went back and forth on this with you in nothing but good faith for 2 days and was actually defending your claims if you recall. **** you, you ungrateful little prick.
I was able not only to understand, but to go way above what you were talking about, and you hadn't understood at all what other people were talking about and inserted yourself in the sole attempt to "make me look bad" which I mean, I get it,your tribe got annihilated in elections and you want "reven
This is all poorly written rambling. Nobody disputes people with STEM degrees vote more dem than the general population. The base of the republican party that culturally and intellectually agree with you are unsurprisingly white non college rural welfare types. It's probably true that people with STEM degrees vote more DEM than just 4 year degree holders, but we don't know. It's certainly true of advanced degree holders in STEM subjects.
It is not "a necessary constant across non randomly selected groups" *BUT IT IS A PRIOR UNLESS PROVEN OTHERWISE*.
It is the best estimate available until proven otherwise.
There is no a priori reason it varies within the subpopulation.
It is still informative until proven otherwise.
It is not irrelevant
It's been explained, but it's very bad math to use population data on such a small subset. Like 15% of men have a STEM degree. That trailer park non college types are overwhelmingly right doesn't tell you really anything about people with STEM degrees. That you can't understand this is fine/expected. But it's not trash talk if I point out the error.
Lol at ED still trying to argue that STEM doesn't skew right.
Skew right in relation to? The only hard claim I saw him make above is that STEM skews left from the general population. Are you disputing that?
I would be potentially disputing that. It would seem to make sense that if the general population is 50/50 and all degree holders are 55/45 Democrats, and if STEM is only like 15% of degrees then it would seem to make sense that they are further right than 50/50.
Perhaps if you adjust for age and race maybe not idk.
It is not "a necessary constant across non randomly selected groups" *BUT IT IS A PRIOR UNLESS PROVEN OTHERWISE*.
It is the best estimate available until proven otherwise.
There is no a priori reason it varies within the subpopulation.
It is still informative until proven otherwise.
It is not irrelevant
if all we know is there's a skew in the whole population then that's the default for any subgroup
but I think we think we do have more information about the subgroups.
if all we know is there's a skew in the whole population then that's the default for any subgroup
but I think we think we do have more information about the subgroups.
That's the point I've been trying to make. I doubt even Luciom is going to argue that the subgroup "students with blue hair and tongue piercings in Massachusetts" shares many properties with the subgroup "truck drivers having a tattoo : visible skin ratio exceeding 50% in Alabama".
I would be potentially disputing that. It would seem to make sense that if the general population is 50/50 and all degree holders are 55/45 Democrats, and if STEM is only like 15% of degrees then it would seem to make sense that they are further right than 50/50.
Perhaps if you adjust for age and ra
The lower % STEM represent of all degree holders, the less confident you can be about your conclusion. Case in point, if STEM are 100% of all degrees, then they are 55/45 with 100% certainty; conversely, if there is one STEM degree holder, then you have essentially zero information about how he or she voted.
The lower % STEM represent of all degree holders, the less confident you can be about your conclusion. Case in point, if STEM are 100% of all degrees, then they are 55/45 with 100% certainty; conversely,
BOLD IS FALSE.
if one one person has a STEM degree and you know a portion of non stem degree holders is crazy leftist (and you do for a fact) your expected value for the single STEM degree holders of baking more right-wing of 55-45 is higher than 50%, if you don't know anything else about him.
you don't know nothing (!!!!).
The lower % STEM represent of all degree holders, the less confident you can be about your conclusion. Case in point, if STEM are 100% of all degrees, then they are 55/45 with 100% certainty; conversely, if there is one STEM degree holder, then you have essentially zero information about how he or s
Right. If we didn’t know anything about advanced degree holders, the same logic would say “well men are over represented in hard science phds so thry probably lean right”. But we pretty much know that has to be wrong. And the reason is obvious; non random small enough samples don’t preserve population wide trends.
BOLD IS FALSE.
if one one person has a STEM degree and you know a portion of non stem degree holders is crazy leftist (and you do for a fact) your expected value for the single STEM degree holders of baking more right-wing of 55-45 is higher than 50%, if you don't know anything else about him.
you don
You are missing the point. Maybe re-read the post you replied to - it's about how confident you can be in that conclusion. If there are a million total degree holders and 1 of them has a STEM degree, the answer is essentially zero.
btw the "non random sampling" has to be treated as random unless you can define the structure (skew) of the non randomness.
it does decrease the quality of estimators drawn from the sample but it doesnt invalidate the estimate unless and until you can confidently claim the non-random sampling is skewed in a specific direction.
think of 200 red an black balls randomized inside a jar.
if you pick 10 of them "only from the bottom" that's non-random but it doesn't change anything...
that's statistics 102 maybe not 101 but still, if this isn't absolutely intuitively obvious for you, you aren't very knowledgeable of statistics.
You are missing the point. Maybe re-read the post you replied to - it's about how confident you can be in that conclusion. If there are a million total degree holders and 1 of them has a STEM degree, the answer is essentially zero.
15-20% of degree holders alive in the USA are STEM and they are overwhelmingly male
Are you able to keep track of the conversation? I was responding to Luckbox, when he said that the fact that STEM represents only 15% means that they are more likely to lean right. I was pointing out that the lower that percentage is, the less confident he can be. The actual percentage is completely irrelevant to that specific point.
As for being overwhelmingly male, I am beginning to suspect that you can't read or something. It's been explained 100 times now why this argument is fallacious, including in the last dozen or so posts. You might disagree with the objections, but just repeating yourself without actually addressing them is not a particularly persuasive form of argumentation.
You are missing the point. Maybe re-read the post you replied to - it's about how confident you can be in that conclusion. If there are a million total degree holders and 1 of them has a STEM degree, the answer is essentially zero.
Are you able to keep track of the conversation? I was responding to Luckbox, when he said that the fact that STEM represents only 15% means that they are more likely to lean right. I was pointing out that the lower that percentage is, the less confident he can be. The actual percentage is completely
15% is a huge amount that makes your comment about "one" irrelevant. actual percentage is relevant, if it was 0.03% the validity of my claim "they are mostly male" would be smaller. it would be easier for s tiny subdemographic to share anomalies.
15% and 75-80% male lol. you need some dramatic, exceptional, close to impossible idiosyncratic element to make them vote trump less than the other degree holders just because they are overwhelmingly male.
nothing you "explained" eliminates the fact that them being male primes them to be overwhelmingly more trump voters than other degree holders.
you need to show that possessing a degree eliminates what everywhere else in society is a huge predictor of voting propensities.
and btw we do know that men with a degree voted trump more than women with a degree, that's in exit polls as well.
there is no fallacy. being a man makes you more likely to vote for Trump. STEM degree holders are overwhelmingly male.
15% is a huge amount that makes your comment about "one" irrelevant. actual percentage is relevant, if it was 0.03% the validity of my claim "they are mostly male" would be smaller. it would be easier for s tiny subdemographic to share anomalies.
15% and 75-80% male lol. you need some dramatic, excep
Look, I can't be ****ed with this. Clearly you can't follow a logical discussion. You made a point about a toy example, that point was wrong, now you're arguing that the toy example doesn't apply in the real world. Clearly, no **** Sherlock, that's why it's a toy example and its intention was to illustrate a very specific point by using extreme values. And I really can't be ****ed expending any more effort unweave your chaotic ramblings since you clearly think you're god's gift to logical reasoning and when I do make that effort, you are completely unable to accept criticism or admit error.
DING
DONG
Look, I can't be ****ed with this. Clearly you can't follow a logical discussion. You made a point about a toy example, that point was wrong, now you're arguing that the toy example doesn't apply in the real world. Clearly, no **** Sherlock, that's why it's a toy example. And I really can't be ****e
the point was not wrong at all. the toy example I provided does apply to the real world.
btw the "non random sampling" has to be treated as random unless you can define the structure (skew) of the non randomness.
it does decrease the quality of estimators drawn from the sample but it doesnt invalidate the estimate unless and until you can confidently claim the non-random sampling is skew
lol guy who didn’t know what a Gaussian is makes something up and calls it stats 102. What you said is obviously wrong. No statistician in the world will say you you should just assume non random data converges to population means.
That’s the whole magic of random data. It’s really the only subset we can prove reliably converges to population means. Again, this is stats 101. There is 0 justification for using other samples as stand ins and the generally moronic objection of “how can 500 people possible tell us how 10s of millions will vote” actually applies to non random samples.
