DEV Community

Cover image for "Day 40 of My Learning Journey: Setting Sail into Data Excellence! Today's Focus: Maths for Data Analysis (Stats Day -19)
Nitin-bhatt46
Nitin-bhatt46

Posted on

"Day 40 of My Learning Journey: Setting Sail into Data Excellence! Today's Focus: Maths for Data Analysis (Stats Day -19)

STATISTICS FOR DATA ANALYTICS - 19

T-test - numerical - 2

T - test : Unpaired Two sample Mean Test :-

Mostly data is unpaired :-
Eg :- testing a new drug over the existing one.

Two different sample ( comparison )

It is divided into 2 parts :-

Equal variance

Unequal variance

Step 1 :-

Null hypothesis => mean of sample A = mean of sample B.
Alternate hypothesis => mean of sample A is not equal to mean of sample B.

Step 2 :-

T- statistics

Step 3 :-

t - tabular(critical) > t- calculated { reject the null hypothesis )

T - test : Two sample Proportion Test :-

It cannot be used directly in excel so, we have to use the extension XLSTATS.
It is used when sample output is in Categorical form.

SAMPLE A 0 1
SAMPLE B 0 1

Like :- A person SHOWS SYMPTOMS OF DISEASE AFTER MEDICATION OR NOT..

ITS BEST APPLICATION :-

A/B testing
It is a direct industry application of the two sample proportion tests.

Z vs T test

If standard deviation is given, go for the Z-test or T- test.
If standard deviation is not given, go for the T- test
If sample size is above 30 go for Z-test
If sample size is less than 30 go for T-test

Feel free to share this post to enhance awareness and understanding of these fundamental concepts in statistical analysis!

🙏 Thank you all for your time and support! 🙏

Don't forget to catch me daily at 6:30 Pm (Monday to Friday)for the latest updates on my programming journey! Let's continue to learn, grow, and inspire together! 💻✨

Top comments (0)