t-test Mathematically
The task of the t-test is to determine whether the difference between the two samples' means is significant. What should we take into consideration to perform it?
- Obviously, we should consider the difference between the means itself;
![](https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/Testing2.0/BiggerDiff.png)
- As shown in the image below, the variance matters too;
![](https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/Testing2.0/BiggerVar.png)
- Also, the size of each sample should be taken into consideration.
![](https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/Testing2.0/BiggerSize.png)
To account for the difference between the means, we simply calculate that difference:
![](https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/Testing2.0/MeanDiff.png)
The situation becomes more complex when it comes to variance. The t-test assumes that the variance is equal for both samples. We will delve deeper into this in the t-test assumptions chapter. To estimate the variance from two samples, the pooled variance formula is applied:
![](https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/Testing2.0/SPooled.png)
And to account for the size, we need sample sizes:
![](https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/Testing2.0/Sizes.png)
Let's put it all together into t statistic.
![](https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/Testing2.0/Tstat.png)
You may have noticed that sample sizes are not used in the most intuitive manner. However, this approach ensures that t follows the t-distribution, as we'll explore in the next chapter.
What sample properties does the t-test take into account?
Selecciona unas respuestas correctas
¿Todo estuvo claro?
Contenido del Curso
Learning Statistics with Python
2. Mean, Median and Mode with Python
4. Covariance vs Correlation
Learning Statistics with Python
t-test Mathematically
The task of the t-test is to determine whether the difference between the two samples' means is significant. What should we take into consideration to perform it?
- Obviously, we should consider the difference between the means itself;
![](https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/Testing2.0/BiggerDiff.png)
- As shown in the image below, the variance matters too;
![](https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/Testing2.0/BiggerVar.png)
- Also, the size of each sample should be taken into consideration.
![](https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/Testing2.0/BiggerSize.png)
To account for the difference between the means, we simply calculate that difference:
![](https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/Testing2.0/MeanDiff.png)
The situation becomes more complex when it comes to variance. The t-test assumes that the variance is equal for both samples. We will delve deeper into this in the t-test assumptions chapter. To estimate the variance from two samples, the pooled variance formula is applied:
![](https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/Testing2.0/SPooled.png)
And to account for the size, we need sample sizes:
![](https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/Testing2.0/Sizes.png)
Let's put it all together into t statistic.
![](https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/Testing2.0/Tstat.png)
You may have noticed that sample sizes are not used in the most intuitive manner. However, this approach ensures that t follows the t-distribution, as we'll explore in the next chapter.
What sample properties does the t-test take into account?
Selecciona unas respuestas correctas
¿Todo estuvo claro?