data analyst面试统计知识总结~求大米

有用！谢谢楼主！

very useful information! thanks!

真是谢谢了，很有帮助

太感谢楼主了！

感谢楼主贡献！

小二来耕地 发表于 2019-1-28 12:38
ANOVA
Analyze differences among 3 or more group means in a sample
Categorical/qualitative predicto ...

Central Limit Theorem: If n is large, sampling distribution of y_bar is approximately normal,  regardless of the distribution of y

Your definition of P value is interesting.

补充内容 (2019-2-20 07:04):
I will put it as : The P value, is the probability of finding the observed, or more extreme, results assuming HO is true.

小二来耕地 发表于 2019-2-5 07:09
Linear Regression (STATS 500)
a linear approach to model the relationship between a dependent varia ...

Diagnosis of linear regression assumption is a common interview topic.

1. Linearity - Residual plot. ei vs X
2. Constant variance: e vs X, if funnel shape, reject constant variance assumption
3. Independence. residual vs time
4. Normality (of error distribution). qq plot or Residual vs Expected.

小二来耕地 发表于 2019-2-14 05:13
Logistic Regression
Binomial classification
Robust

One interview question I had before is:

What assumption do you need to check for Logistic Regression

非常有用感谢！