Hypothesis test for difference of means | Probability and Statistics | Khan Academy

Hypothesis Test for Difference of Means

Missed the previous lesson?

Probability and statistics on Khan Academy: We dare you to go through a day in which you never consider or use probability. Did you check the weather forecast? Busted! Did you decide to go through the drive through lane vs walk in? Busted again! We are constantly creating hypotheses, making predictions, testing, and analyzing. Our lives are full of probabilities! Statistics is related to probability because much of the data we use when determining probable outcomes comes from our understanding of statistics. In these tutorials, we will cover a range of topics, some which include: independent events, dependent probability, combinatorics, hypothesis testing, descriptive statistics, random variables, probability distributions, regression, and inferential statistics. So buckle up and hop on for a wild ride. We bet you're going to be challenged AND love it!

About Khan Academy: Khan Academy offers practice exercises, instructional videos, and a personalized learning dashboard that empower learners to study at their own pace in and outside of the classroom. We tackle math, science, computer programming, history, art history, economics, and more. Our math missions guide learners from kindergarten to calculus using state-of-the-art, adaptive technology that identifies strengths and learning gaps. We've also partnered with institutions like NASA, The Museum of Modern Art, The California Academy of Sciences, and MIT to offer specialized content.

For free. For everyone. Forever. #YouCanLearnAnything

Subscribe to KhanAcademy’s Probability and Statistics channel:

[nesandtwos]

6:51 "now the variance of the first pftchsfgshtch.." 

[norwayte]

04:37: "...hardest thing in statistics is getting the wording right..." . And that's one reason :-) that there is an alternative - Bayes-Statistic.
Because every statistic is made for supporting decisions. Making decisions.

[miriam]

I am TAing a statistics course, and can't share this video because there are a few things that will confuse students. First of all, alpha usually equals the probabilities in the look-up table. So instead of alpha = 95%, I would write, alpha = 5% or .05. Also, if you want to make your alternative hypothesis directional, then the null needs to be directional as well. When you say alpha = 95%, I think you mean 1- alpha = 95%. This would refer to the rest of the probability distribution once you've decided what your type 1 error rate should be (i.e. alpha).

[deveshbhatt]

Note to self: Need to revise this lecture

[sid]

Thanks a lot! I was stuck so badly but now I guess I would move on!!

[shanebehemoth]

seriously dude I love you.. you saved me from failure

[awaishasmi]

Significance level denoted by Alfa " and is approximately 5 percent not 90 percent

[masshunter]

I think you had some mistakes in the video but you are great teacher.

[harryyuan]

alpha does not equal to 95%, that is simply saying if the P-value is larger than 5%, you would reject the null, which doesn't make sense. The alpha in your case is 5%, which you would reject the null if the P-value is smaller than 5%.

[haneulkim]

What if you have two groups with different population size and want to do hypothesis test for difference of means then do we need to sample same amount from each group? Can I use the whole population even though two groups are different sizes?

[ZahidIrfan]

Should not we be using t-distribution in this case?

[emilymiller]

I watch review videos to solidify what I already know before a test, but I feel like when I watch these videos I watch about 2 minutes, get super confused, and go find another video.

[ajstyleslegend]

better to take z = 1.64 for the area P(0.95) because P(0.9505) is not P(0.95) but(0.9495) it's approximately 0.95
= 1.64 it's the better choice

[mairatahir]

isn't this supposed to be a two tailed test? and if yes than why are you using 5% it should be 2.5% on each tail no? this confused me more than i was already confused!

[yadavche]

i actually found greek much easier than this.

[bettyboopbh]

hey darling they say that because they are taking the mean of all the scores

[labaom]

Can someone help me? What if it is the same population? I am doing a test between male vs female spending. I have two different means. 49 people are my sample. But 21 of them are male and 28 of them are female. Would my n1/n2 be both 49 or 21 and 28? They both stem from the same population of 49 so I am not sure what to do! 

[brianriley]

You shouldn't be referring to these 2 sample sets as 'sampling distribution'. they are 2 samples, therefore your characters for labeling these should be x-bar sub 1 and x-bar sub 2, not mu sub x-bar 1 and mu sub x-bar 2.

Also, your sigma/variance labels would change from omega's to s'.

According to your own videos (and all other documentation) the term 'sampling distribution' is strictly reserved for when you are summing multiple samples together to refinee a data set to ve representative of an immeasurable population.

[BarbaraGonzalez-lv]

Miller Thomas Lee Maria Robinson Kevin

[BarbaraGonzalez-lv]

Anderson Richard Taylor Lisa Miller Kimberly