Stratified vs Cluster Sampling
Stratified vs cluster sampling is a common confusion, so that's why I made sure to put them in the same video to confuse you further. Scratch that, I meant "clearly explain the difference". You knew what I meant.
Author Archives: hangtime
Sampling With or Without Replacement
If you're in the habit of deriving and proving statistical formulas in your spare time, then you're definitely going to want to watch someone else's replacement video, since I'm basically going the other direction with it. "With replacement" is the boilerplate of intro stats!
Convenience Sampling
This is one of those rare math terms where they tell you what it is just so they can tell you not to do it. What example did I pick to illustrate this point? A bunch of science projects from my kids' elementary school! Enjoy.
Simple Random Sampling
Different from plain-old-normal random sampling (in ways that don't really matter). This video puts the simple in simple random sampling.
Lots of sampling methods: simple random sampling, convenience sampling, sampling with and without replacement, stratified vs cluster sampling, and systematic sampling!
Double-Blind, Placebo-Controlled Study
This term mostly applies only to medical research trials, such as investigating new drugs and whatnot, but it's illustrative to show you just how awesomely statistical a study can be. No confounding variables here!
Prospective (Longitudinal or Cohort) vs Cross-Sectional vs Retrospective Studies
With these studies, it's mostly a matter of timing. Discuss.
Observational Study vs Designed Experiments
This video may be, at first glance, about observational and designed experiments. But really it's a how-to for your future career as a data-mastering statistics master who will not -- who dare not -- do experiments that suck (statistically speaking). God speed.
Observational study, designed experiment, prospective (longitudinal or cohort) vs cross-sectional vs retrospective studies, double-blind, placebo-controlled study.
Confounding & Lurking Variables
"Confounding" and "lurking" are the words statistics people use to say "oops". As in, "oops, I didn't account for that variable." Stay tuned for a couple examples and the one tried and tested way to avoid these "oops" in your own experiments. (You're doing experiments, right?)
Explanatory & Response Variables
Like x and y in algebra, explanatory and response variables are the yin and the yang of studies in statistics.
This chapter covers the main types of variables you'll see in stats: explanatory variables, response variables, lurking variables, and confounding variables.
Census vs Sample
To census or sample? That is the question. It's a subtle distinction, but like so many small things in stats, you may see it in a short answer question on a test.
Correlation vs Causation
This video introduces one of the biggest problem plaguing big, real-world problems: just because two things seem to go together, what if it's just a coincidence? Does carbon dioxide cause global warming, or is it just a coincidence that a historic rise in greenhouse gasses corresponds to a historic rise in global temperatures? That's correlation vs causation.
Statistical Significance & Confidence Intervals
The last 3/4 of your typical stats class -- or more -- is about determining whether a sample or test is statistically significant. In other words, does the data from your survey/study/experiment mean something, or was it just luck, kind of like flipping a coin and getting 5 heads in a row?
Variability & Dispersion
These are two names for the same thing: how spread out is the distribution. It's all subjective, though, with lots of ins and outs, so naturally we'll delve into examples involving small dogs to explain what's happening here.
Reliability vs Validity
Kind of like "accuracy vs precision", reliability and validity are the terms for whether a test is both repeatable and accurate.
Outliers
There are lots of ways to define what an outlier is, other than a "way out there" piece of data you want to just ignore to make your homework easier. This video explains what outliers are, and the most common way of defining them.
The Normal Distribution & z-score
You're going to be hearing the world "normal" every two minutes for the rest of the semester, in tons of depth, so this video isn't going to do anything but scratch the surface of this topic. But if you're wondering what the heck this normal thing is, and what z-scores have to with anything, this video introduces them both.
Continuous vs Discrete
Whether you're talking about variables or data, continuous and discrete describe the same situation: is the data something you count, or are decimals okay? And what about those tricky situations that my teacher seems to find so interesting, where something discrete is actually considered continuous?