Sample Size and Effective Sample Size, Clearly Explained!!!

The sample size for an experiment depends on what you want to say and what kind of replicates you have. This StatQuest shows examples of how biological and technical replicates are counted differently. It also shows what to do when your samples are correlated. Oh, and just in case you're interested, the twins are monozygotic.

For a complete index of all the StatQuest videos, check out:

If you'd like to support StatQuest, please consider...

Buying The StatQuest Illustrated Guide to Machine Learning!!!

...or...

...a cool StatQuest t-shirt or sweatshirt:

...buying one or two of my songs (or go large and get a whole album!)

...or just donating to StatQuest!

Lastly, if you want to keep up with me as I research and create new StatQuests, follow me on twitter:

#statquest #statistics

[pamaa]

Thank you so much for explaining a student who got low marks in Statistics I'm feeling happy that my concepts are clear now. Can't thank you enough.

[baharehbehrooziasl]

Thank you so much for another helpful video. When discussing "effect size" and "effective sample size, " we discuss two totally different concepts, right?

[mastermike]

Such a great series! Really helps make statistics approachable to us! I can't wait for a Central limit therm, delta method, strong law of large numbers or perhaps slutsky's theorem. Those are all topics which I found really challenging when I first started my studies.

[qwerty]

1:10 interesting, tree blood. This was a nice and sweet statquest.

[fatemehkarimi]

dear Josh, I will be thankful if you make a video about the effect size and cohen's d. these topics are intangible and I didn't find a good video for them on the net. thanks in advance.

[joshstat]

Clearly explained. I have something to request. Would you like to create a video about law of large numbers and order statistics?

[nanazeethiopia]

BAM!! I Really like your lectures . They are super professional. Can you do on LSTM, Long range dependence, and other types of distributions like Pareto Distributions ....??. Thanks.

[ehsansalehabadi]

Thanks for these awesome sets of lectures, sir.

I had a question. does the formula work only for positive correlations? I mean what if the correlation between twins is negative so that they zeroed the denominator, or for example, make the effective size negative?

[parklee]

Can you please make a video about effect size or randome effect model?

[pjgdba]

Cool, I have no reason to know this info, but it is really interesting.

[afzalsiddique]

If you're a mouse geneticist, you can think of blue dudes as a specific strain of mouse. DOUBLE BAMM!!!

[joshtwigg]

These videos are awesome! Is this the same concept as ICC for cluster-RCT analysis? Thanks :)

[karthica]

Amazing as always, but here when you mention correlation are you referring to pearson correlation coeff? Is it possible for them to be non-linearly correlated (I cannot think of a situation)?

[csmatyi]

how do we calculate correlation between let's say, 5 blue dudes?

[ciherrera]

I have a couple questions about this video. Is there an explanation for the effective sample size equation you show? Also, why would the effective sample size equation not be linear with correlation? If you have a sample size of 2, and a correlation of 0.5, why would the effective sample size be 1.33 and not 1.5?

[AmitKumar-ujed]

Well! Everything is clearly explained 😅

[PGDM_SHASHANKJAIN]

Hi, Here you calculated the effective sample size for persons belonging to the same set of population( blue ones), However there must be some correlation between the orange and blue ones or blue and green ones or orange and green ones or among all three of them .Aren't we supposed to calculate effective sample size for them too?

[ZiauddinAzimi]

Nice explanation. I have a question. I want to find the effects of Vitamin A on the methylation status of some specific genes in children. Now how to calculate the sample size?

[thegamingannex]

If you're a quality engineer, you can think of technical replicates as repeatability and reproducibility samples. TRIPLE BAMMM!

[kevindeng]

Could u please do one on latent variable?