Desperate Housewives of the ASA
What Even Is Truth?
Hypothesis Testing My Patience
Frequently Wrong
San Francisco Bayes
100

The school of thought claiming that probability comes from forming a collection of similar events

What is frequentist statistics?

100

If the premises of the statement are true, the conclusion must be true. (If all trees are green, this tree is green)

What is deductive reasoning?

100

This is the method by which we come up with a hypothesis and look for evidence to prove it wrong

What is hypothesis testing?

100

This is what Fisher proposed you do when you find a p-value less than 0.05.

What is continue to do research?

100
Defining this value explicitly is one of the first steps of a Bayesian analysis and separates it from the Frequentist analysis.

What is a prior?

200

The school of thought claiming that probability comes from previous knowledge and current evidence

What is Bayesian statisitcs?

200
If the premises of the statement are true, the conclusion may or may not be true. (If all trees on campus, then all trees are green)
What is inductive reasoning?
200

The person who wrote about forming a collective of similar studies and testing how far the current data are away from that collective of studies?

Who is Fisher?

200

This is what you do when your p-value is less than the pre-defined threshold.

What is rejecting the null hypothesis?

200

This analysis mistake can break down the examination of many outcomes using freqentist methods, but Bayes statistics are unaffected.

What is multiple testing?

300

The school of thought claiming that probability comes from logical deductions of physical properties

What is logical statistics?

300

This is the type of reasoning that hypothesis testing primarily relies on.

What is inductive reasoning?

300

This is the probability of a positive result being a false positive.

What is type I error/alpha?

300

Frequentist statistics does use prior knowledge when doing this.

What is forming the collective?

300

This is the most likely value of the alternative hypothesis when performing an analysis with Bayesian statistics.

What is the observed value?

400

This is an infinite group of occurrences of a random event

What is a collective?

400

These are the attributes we look for when deciding what the "best explanation" is.

What is an explanation that is simple and parsimonious?

400

The ASA rejected the idea of making decisions solely based on this when working with p-values.

What is a threshold?

400

One problem with Frequentist probability is the invocation of this where a truth about the collective applies to the individual.

What is the ecological falacy?

400

Another name for a Bayes Factor, describing the relative probability of the data under two hypotheses.

What is a likelihood ratio?

500

This principle states that if you don't know how likely a number of events are, you can assume they're equally likely

What is the principle of indifference?

500

We make this assumption so that we can apply principles we have learned in the past to things in the present.

What is the uniformity of nature assumption?

500

The ASA made it clear that the p-value does not measure this.

What is the effect size?

500

Using a smaller collective that is more representative but contains fewer data points OR a large collective that is less representative but is more robust is an example of what?

What is the bias-variance tradeoff?

500

The results under the null hypothesis are half as likely as under the alternative hypothesis.

What is a Bayes Factor of 0.5?