The Difference Between Technical and Biological Replicates

You can't do statistics without replication and in the biological sciences, there are two main types of replication: technical and biological. This StatQuest explains the differences between these two types of replication and dive into some subtleties and grey areas, too.

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

[mToreno]

Every few years or so I stumble again on statquest while googling something, and remember your awesomeness! Thank you Josh for this amazing series <3

[zhoulingyu]

Extremely helpful! Thanks, dude! I was wondering about this in one of my experiment.

[adithyapbalakrishnan]

Thanks StatQuest. Love the way u explain concepts.

[鄭凱鴻-oe]

Thanks, dude! It's extremely clear for Taiwanese student like me!

[junhyunglee]

StatQuest is Best! Very, very practical!

[adrianguinrizzo]

Way easier than google's explanation.

[alakshendrasingh]

Your way of explaining is immaculate for neophyte learners...Thanks a lot

[WalyB]

There is a state quest for anything is there. Just great!

[yanxu]

Your videos are super awesome!!! I have learned a lot from them. Thanks

[alessandrobusetti]

Hi Josh, thanks for the video. How does one deal with standard deviation for multiple biological replicates each with multiple technical replicates?

[etesvgz]

Thank you very much for all your videos. I'm currently preparing to enter in an international enterprise thanks to your videos. I've already bought your book but I am going to also buy something else ! Your content is so precious that I have to give you my money for your help.
Just one question : In the case of a biological replicates, as we measure only one time for each people, measure wouldn't be accurate compared to technical replicates. Isn't it a problem ?

[manochehrteimory]

Great, if you get into different design of experiments and points, it would be better. I have the same difficulties with my students in our lab, as they do not know what to repeat and do not know the reason for their repetition in a set of experiments

[ryanzhou]

The replicates are like the GRR in the manufacturing industrial.

[eye_oph]

If I mixed both biological replicates and technical replicates in the experiments, how should the sample size be determined when comparing the differences between the experimental group and the control group? Should the number of biological replicates be used, or should it be multiplied by the number of technical replicates? Thank you.

[jyeo]

Hi Josh,
Quick Question:
For cell lines, if I were to use only one particular cell line and repeat it.
If I have done this experiment 3 times, as compared to having 3 different measurements in 1 experiment.
Would that be considered biological replicates for repeating the experiment 3 times?

[chw]

Thanks for the awesome video! I did have a question about technical replicate though. If at day 1, I run an experiment on a sample where I measure the absorbance (measure the absorbance 3 times), is this considered a technical replicate? Or would an example like at day 1, measure the absorbance of a sample 3 times, then day 2 and 3, do the same with the exact sample from day 1, is this considered technical triplicate? So essentially, would measuring the absorbance 3 times be considered technical triplicate in this case or would total of 9 measurements be technical

[johnbarryyallagher]

how do you combine technical and biological replicate variance if both are of the same if tech replicate variance is large and could affect the comparisons in the biloical replicates the object if the study

[fengtang]

Hi Josh. Thanks for your video. I am still confused about my case. Recently, I am collecting sample for RNAseq. My sample is pig oocyte. Each week, I can get 10 ovaries from 5 individual pigs (one pig contains two ovaries). Normally, one ovary contains 10-20 healthy oocytes so I can get ~150 oocytes I want each week. For establishing the RNA library, 30 oocytes is required. If I want to have 4 biological repeats (4 repeats need 120 oocytes), can I finish it within one week? Or I should collect 30 oocytes each week and finish sampling 4 weeks later?

[erick]

Hi StatQuest, thanks for the video. It confuses me a bit because in the examples you give of technical replication, seems like an example of pseudoreplication, due to the samples are not independent of each other. Am I right? if not, why? Thank you again.

[Shinle]

Anyone knows a book discussing about these statistics in biology? Thanks in advance