Science does not rely on authority as an indicator of truth.

Ben Goldacre: Battling bad science


Go to transcript

It is worth reiterating that contrary to popular depictions of science, science does not rely on authority as an indicator of truth.

The video reminds me of an xkcd comic showing the problem with using statistical significance if the studies showing no effect are unreported.

Significant
In this analogy, the study showing a link between green jelly beans and acne has only a 5% probability (or less) of being a coincidence (p < 0.05). This would be convincing evidence that there is a link between green jelly beans and acne, except all the 19 studies showing no link between non-green jelly beans and acne were unreported and discarded. If all the study results were reported, then it would suggest that the result of the green-jelly-bean study is indeed a coincidence: 1/20 = 5%.

Scientific studies in real life can be even worse. Companies, and even university researchers, are not obligated to publish studies in which the results show no effect (studies with “null results”). This means that researchers can run the hypothetical green-jelly-bean study 20 times until they get the result that they want, by coincidence. What normally happens does not involve ill intent, but has the same effect. The hypothetical green-jelly-bean study is run independently by 20 different research teams (who can be separated by time), who are unaware of each other, because studies with negative results are not published. Only the group with the positive result publishes its results, but the result is actually a coincidence. See the concept of publication bias at Wikipedia.
Read the rest of this entry »

Advertisements

White Canadians earn more, because they have white privilege.

White Canadians earn more than non-white Canadians, even when comparing only the whites and non-whites with the same education and of the same age. Comparing only the foreign-born white Canadians with the foreign-born non-white Canadians, white people earn more. Comparing only the second-generation, Canadian-born white Canadians with the second-generation, Canadian-born non-white Canadians, white people still earn more.

In other words, even when controlling for age, education, and generation, white Canadians earn more than non-white Canadians. Racial appearance causes the difference in earnings.

Wellesley Institute’s study, Canada’s Colour Coded Labour Market, was released in March 2011 and draws on data from the last mandatory long-form Census (which has been cancelled recently by the politically-conservative Harper government):

THE LAST AVAILABLE CENSUS DATA before the federal government cancelled the country’s mandatory long form Census reveals a troubling trend in Canada.

Despite years of unprecedented economic growth and an increasingly diverse population, this report confirms what so many Canadians have experienced in real life: a colour code is still at work in Canada’s labour market.

Racialized Canadians encounter a persistent colour code that blocks them from the best paying jobs our country has to offer.

[…]

Default explanations like “it takes a while for immigrants to integrate” don’t bear out. Even when you control for age and education, the data show first generation racialized Canadian men earn only 68.7% of what non-racialized first-generation Canadian men earn, indicating a colour code is firmly at play in the labour market. Here, the gender gap — at play throughout the spectrum — becomes disturbingly large: Racialized women immigrants earn only 48.7 cents for every dollar non-racialized male immigrants earn.

The colour code persists for second generation Canadians with similar education and age. The gap narrows, with racialized women making 56.5 cents per dollar non-racialized men earn; while racialized men earn 75.6 cents for every dollar non-racialized men in this cohort earn.

Further Reading:


Related posts:

White Americans did NOT elect Obama.

This myth won’t die:

But not everyone buys that script. Mona Charen, a conservative columnist for the National Review, challenges that view with this question: If more white Americans feel like an embattled minority, why did they elect President Barack Obama?

“Did they become racist after electing the first black president?” she asks.

Charen says the United States today is “incredibly tolerant and open.”

White Americans did not elect Obama. Most White Americans (55%) voted for McCain. Obama was elected by most Americans of color and a minority (43%) of White Americans.

Yes, the numbers can and do work like that.

Map of Recent Immigrants in Toronto: 1981 versus 2006

For these maps, “recent immigrants” are those who arrived in Canada within the last five years of the Census date. You can click on the maps to see larger versions.

1981

Toronto CMA. Recent immigration population in 1981 Census by 2006 Census Tracts (CTs).

2006

Toronto CMA. Recent immigration population in 2006 Census by 2006 Census Tracts (CTs).

Via Recent immigrant population from 1981 to 2006 Census by 2006 Census Tracts (CTs) by Statistics Canada.


Related post:

Map of White Segregation/Enclaves in Toronto

Statistics Canada has a “thematic” map of the percentage of visible minorities in Toronto CMA (Census Metropolitan Area) in 2006. You can click on the map below to see a larger version. Generally, the lighter areas are where the whites live.

Toronto CMA. Percentage of Visible Minorities by 2006 Census Tracts (CTs). Map 2 of 2.

Toronto is a multi-racial city with a marshmallow centre (or two). The suburbs surrounding Toronto have a greater percentage of visible minorities, while large patches of Toronto’s core have been gentrified are inhabited by whites.

Note that some areas of Toronto are whiter than the national average, over 90% white.

Read the rest of this entry »

Statistics of Women of Colour Profiles at OkCupid

OkCupid statistically analyzed the profiles of their users and found the phrases that made each racial group distinct:

We selected 526,000 OkCupid users at random and divided them into groups by their (self-stated) race. We then took all these people’s profile essays (280 million words in total!) and isolated the words and phrases that made each racial group’s essays statistically distinct from the others’.

There is a lot of data at the link, but here are the phrases that make groups of women of colour—Asian women, Pacific Islander women, Indian women, Middle Eastern women, Black women, Latina women—distinct. (For some reason, all female groups except for White women and Indian women really like Alicia Keys.)

Asian women: coz

coz, chocolates, i'm a simple girl, a foodie, surfing the net, love story, alicia keys, serendipity, asian food, romantic comedy, different places, the xx, tuesday's with morrie, the time traveler's wife, bossa nova, sashimi, jolly, different cultures, china, music, jason mraz, noodle, food network, cheerful, good heart, trying out new things, petite, mom's, michael buble, my cellphone, r & b, my passport, malcolm gladwell, u are, norah jones, anthony bourdain, a walk to remember, gossip girl, pls, badminton, slumdog millionaire, pop rock, food, new recipes, asian, cooking and baking, sleepless in seattle, lip balm, pho, cookbooks
Read the rest of this entry »

Asians are not all rich.

There is a ridiculous post at 8asians titled Asian Men Have The Highest Salary that was linked from Racialicious for some reason. The author, Tim, writes:

If you were looking for another reason to date an Asian male, the U.S. Bureau of Labor Statistics just came up with one. In their latest report on earnings in the 2nd quarter of 2010, Asian men topped the charts again, making $901 in median weekly earnings. Asian women were second at $854, followed by white men at $838.

Let us ignore the often sexist stereotype that women are attracted to rich men for now and look at the issue of race and income. The data I have comes from Ontario, Canada, and the great thing about Canadian race statistics is that Asians are not all lumped together.

Average Employment Income By Racialized Group, Ontario, 2005

Men Women Total
Japanese 73079 40572 56170
Non-racialized 50255 31682 41335
Chinese 41283 30129 35717
Multiple Visible Minority 39940 29156 34613
South Asian 37198 24897 31711
Arab 36894 24258 31963
Southeast Asian 36506 24549 30619
Visibly Minority not included elsewhere 35943 26583 31201
Filipino 35323 28798 31472
Black 33497 27485 30337
Latin American 33218 22518 28145
Korean 32828 22326 27757
West Asian 30212 21660 26502

Read the rest of this entry »