How likely to get lots of cheese lovers?? Sampling Distribution for p-hat

Often you are asked the likelihood of getting some proportion of your sample to have some characteristic when you know the proportion of the population who have that characteristic.. here is a cheezy example.

[@wh33l6r]

OMG! Somebody who explains stats in human terms! I didn't think that was possible! And with enthusiasm yet! Yikes. Is this guy for real? One of the best instructors I've ever seen.

[@Fribee83]

Seriously! I've been staring at these formulas and text book explanations for the past hour while shouting "FUCK STATS, FUCK P-HATS, FUCK THIS CLASS! The fuck am I suppose to do!?". 90 seconds in and it's "Oh shit, that's what they want?! Why didn't they just say that!"

[@MrNystrom]

I'll generally do lots of problems just "eyeballing it" for students. I want them to feel the normal model first, using 68-95-99.7. (look at my videos for normal model). Once students "feel" the normal model, I have them use the calculator or table. (see my FLO CHART video). The "feel" is important because it spreads on to t models and null models for hypothesis testing... Thanks for watching... more videos to come!

[@ehsamproduction]

Hands down for the most awesome, passionate and 100% understandable lecturer ever. This channel is gold

[@eddiesushi]

Arda Turan sure knows his statistics! Great video

[@Mikej1592]

nice guess. Using the ti-89 I used normal-cdf with low=.85 high=infinity mean=.8 SD=.04 and I got .1056498 or 10.56498% I hope I am understanding the use of the normal-cdf function.

[@mystichobbies]

Making my semester easy! Thanks man!

[@taylordashawn]

Thank you so much. You explain things so well.... literally saving me from just about dropping my stats class.

[@MrNystrom]

.8 is the probability that a person likes cheese (80%) .2 are the rest of the people that don't like cheese (20%) p+q= 1 p is probability of success... q is probability of failure (which is always 1-p ).

[@nickmartinez4064]

Awesome stuff dude. Really reinforcing what I'm learning in my stats class.

[@heraldloomis]

Great presentation, thank you so much for your help.

[@TheMarkthetruth]

Dude! Hell yeah. this helped me so much! Thanks.

[@Mathbyfives]

Ti-82 is a classic!

[@timpinckney]

Area under a curve... CALCULUS! :)

[@MHSSRC]

the emotion and enthusiasm, haha, good stuff!

[@CartesianFirstPrinciples]

Much appreciated, excellent video.

[@daijahblackburn331]

Thanks a lot, this video is great!

[@chrisdaviddawson]

Thanks for the video. You are awesome :D

[@roneddie250]

Love it :) Better than my prof. :)

[@cto8003]

you are a god. thank you.

[@ProfBoggs]

The P(Z>+1.25) is 1-0.8944 = 0.1056, no? Pretty close to your 10% estimate. Do you ever show students how to use Z-tables? Or do you find that just confuses them even more?

[@waggles1989]

Hi MrN, quick question, where does the 0.2 (Q) come from for the Standard Deviation Formula used above? Fantastic effort with the videos, I came across them today and they have aided me tremendously. Best, from London - England, S

[@anthonyajlouni]

i dont understand how you used normal cdf. i wish you specified

[@joggypro4676]

+Anthony Ajlouni It's the formula for finding the z-score ([x - xbar] / standard deviation). So you would just plug in what you know.

[@davidazinger5639]

there is 100% probability more than 85% like cheese because everybody like cheese!!! Like 100% !!! Bad example.