Total Posts:2|Showing Posts:1-2
Jump to topic:

[PROPOSAL] DDO Statistics Summer Camp

Diqiucun_Cunmin
Posts: 2,710
Add as Friend
Challenge to a Debate
Send a Message
7/7/2016 4:27:41 PM
Posted: 5 months ago
DDO loves throwing around statistics and arguing over them. Conflicts can sometimes arise when members don't agree on how a particular stat is to be interpreted, how much it can be trusted, or what implications it has. In response to this, I suggest a DDO Statistics Camp.

Each week, we'll write up a short article on a particular aspect of statistics and how it can be applied to discussions and debates that DDO users are passionate about.

I suggest dividing this into several modules, roughly arranged as follows:
Module I: Probability
Week 1: Frequentist and Bayesian interpretations of probability, probability axioms, relationship between probability and statistics, odds and odds ratio, relative risk, the Gambler's fallacy.
Week 2: Conditional probability, independence, Bayes' theorem, the confusion of the inverse, the prosecutor's fallacy, the defence attorney's fallacy, sensitivity and specificity.
Module II: Variables
Week 3: Levels of measurement, the random variable, probability distributions, measures of central tendency, measures of dispersion, skewness and kurtosis, outliers, presentation of data
Week 4: Major probability distributions and densities: The Bernoulli, binomial, Poisson, hypergeometric, exponential and normal distributions
Module III: Inference
Week 5: Random sampling, sampling methods, non-probability sampling and its problems, sampling distributions: the chi-square, Student's t and F-distributions
Week 6: Point estimation: minimum-variance unbiased estimator, Cramer-Rao lower bound and Fisher information; interval estimation: confidence intervals based on the Z-, chi-square and Student's t-distributions
Week 7: The Neyman-Pearson paradigm of hypothesis testing: Null and alternative hypotheses, test statistic, rejection region, p-value, statistical significance vs. practical significance.
Module IV: Relationships
Week 8: One-sample and two-sample tests, randomisation methods, observational experiments, confounding variables.
Week 9: Pearson and Spearman correlation coefficients, simple linear regression, linear trend model, chi-square goodness-of-fit test, contingency tables, chi-square test for homogeneity, more on confounding variables: Simpson's paradox.

Although we will cover the mathematical concepts associated with statistics, we'll skip the gritty details for members who dislike maths. Notable omissions (that would normally be covered in a college introductory course in statistics) include:
-Mathematical details of pmfs, pdfs, cdfs and mgfs
-Functions of random variables
-Proofs
-Finding point estimators

If possible, we could licence the final product under a CC-BY-SA licence and publish it somewhere else, as well.

If you are interested in reading the articles or writing for the Camp, please leave a comment below. We'll need enough members who are willing to devote the time to write, as well as a strong enough demand. Other comments or suggestions are always appreciated as well. :)

Soo... anyone with me? :P
The thing is, I hate relativism. I hate relativism more than I hate everything else, excepting, maybe, fibreglass powerboats... What it overlooks, to put it briefly and crudely, is the fixed structure of human nature. - Jerry Fodor

Don't be a stat cynic:
http://www.debate.org...

Response to conservative views on deforestation:
http://www.debate.org...

Topics I'd like to debate (not debating ATM): http://tinyurl.com...
zmikecuber
Posts: 4,093
Add as Friend
Challenge to a Debate
Send a Message
7/8/2016 2:08:29 AM
Posted: 5 months ago
At 7/7/2016 4:27:41 PM, Diqiucun_Cunmin wrote:
DDO loves throwing around statistics and arguing over them. Conflicts can sometimes arise when members don't agree on how a particular stat is to be interpreted, how much it can be trusted, or what implications it has. In response to this, I suggest a DDO Statistics Camp.

Each week, we'll write up a short article on a particular aspect of statistics and how it can be applied to discussions and debates that DDO users are passionate about.

I suggest dividing this into several modules, roughly arranged as follows:
Module I: Probability
Week 1: Frequentist and Bayesian interpretations of probability, probability axioms, relationship between probability and statistics, odds and odds ratio, relative risk, the Gambler's fallacy.
Week 2: Conditional probability, independence, Bayes' theorem, the confusion of the inverse, the prosecutor's fallacy, the defence attorney's fallacy, sensitivity and specificity.
Module II: Variables
Week 3: Levels of measurement, the random variable, probability distributions, measures of central tendency, measures of dispersion, skewness and kurtosis, outliers, presentation of data
Week 4: Major probability distributions and densities: The Bernoulli, binomial, Poisson, hypergeometric, exponential and normal distributions
Module III: Inference
Week 5: Random sampling, sampling methods, non-probability sampling and its problems, sampling distributions: the chi-square, Student's t and F-distributions
Week 6: Point estimation: minimum-variance unbiased estimator, Cramer-Rao lower bound and Fisher information; interval estimation: confidence intervals based on the Z-, chi-square and Student's t-distributions
Week 7: The Neyman-Pearson paradigm of hypothesis testing: Null and alternative hypotheses, test statistic, rejection region, p-value, statistical significance vs. practical significance.
Module IV: Relationships
Week 8: One-sample and two-sample tests, randomisation methods, observational experiments, confounding variables.
Week 9: Pearson and Spearman correlation coefficients, simple linear regression, linear trend model, chi-square goodness-of-fit test, contingency tables, chi-square test for homogeneity, more on confounding variables: Simpson's paradox.

Although we will cover the mathematical concepts associated with statistics, we'll skip the gritty details for members who dislike maths. Notable omissions (that would normally be covered in a college introductory course in statistics) include:
-Mathematical details of pmfs, pdfs, cdfs and mgfs
-Functions of random variables
-Proofs
-Finding point estimators

If possible, we could licence the final product under a CC-BY-SA licence and publish it somewhere else, as well.

If you are interested in reading the articles or writing for the Camp, please leave a comment below. We'll need enough members who are willing to devote the time to write, as well as a strong enough demand. Other comments or suggestions are always appreciated as well. :)

Soo... anyone with me? :P

I will read them. Definitely. I dunno if I'm good enough at stats to write though.
"Delete your fvcking sig" -1hard

"primal man had the habit, when he came into contact with fire, of satisfying the infantile desire connected with it, by putting it out with a stream of his urine... Putting out the fire by micturating was therefore a kind of sexual act with a male, an enjoyment of sexual potency in a homosexual competition."