数据科学理学硕士

1.学生背景：不详 面试时间：2018年4月6号

【申请专业：数据科学 MSDS】Paul Intrevado

Linear Algebra:
1. how to determine linear dependent
2. relationship between eigenvalue and egienvetor
3. given A 4x4 matrix and eqaution Ax=B, tell you I can find two solution. can I say I can always find five solution?? 【5个解是什么鬼，不知道是lz听错还是太渣。。不会回答这题】

Stats:
1. what is the differnece between desciptive and inferential statistic？
2. what is the difference beween correlation and covariance ?
3. box plot

2.学生背景：不详 面试时间：2018年3月22号

【申请专业：数据科学 MSDS】David Uminsky

Stats: 

• 1.A, B independent events, what's the prob (A|B)
• 2.box and whisker plot
• 3.95% interval
• 4.A study shows that tutoring hours and grade are negatively correlated, can we say that tutoring harms students’ academic performance?

Linear Algebra:

• 1.Given 5 3-dimensional vectors, can you explain what does linear dependent mean?
• 2.Intuitively what can you tell by looking at the 5 vectors? (David: they are dependent because 3 dimension vectors have only 3 directions, 5 vectors must mean there are two redundant)
• 3.Given a matrix A, explain what is Eigenvector and Eigenvalue?
• 4.If A is invertible, what can we tell about eigenvalue? (David: eigenvalue is not zero)

Python: （share screen, read code what does the code return）

• 1.return average
• 2.return index of the maximum

3.学生背景：不详 面试时间：2018年3月7号

【申请专业：数据科学 MSDS】

Statistics:
1.条件概率
2.observational study和experimental study的区别
3.假设有人来本科班上调查大家课后补习的情况，在sample的获取没有bias也没有同学撒谎的情况下，发现补习和同学的成绩是有个negative relation的，问能否说补习多了成绩就不好，以及猜测为啥会出现这种情况。

Linear algebra:
1.什么是linear independence以及怎么判断
2.rank
3.投影矩阵

Python3道题
就是list dictionary tuple之类

4.学生背景：不详 面试时间：2018年1月4号

【申请专业：数据科学 MSDS】

1. Why USF MSDS
2. Linear Algebra part
a. definition of eigenvalue and eigenvector
b. how to calculate eigenvalue
c. what is the rank of a matrix
3. Stats part
a. What is the salary distribution of a city? show me the picture of its histogram (画了个图举到摄像头前面); which is larger, mean or median, and why
b. If we found the sales of ice cream and people died of drowning have a high correlation, should we outlaw the ice cream? what do you think cause these two things have a high correlation?
4. Python part
word上写的三个自定义函数，先问你这个函数做了什么，然后在函数里输入一个特定的数字/list，问你outcome是什么
这部分有code不知道怎么表达了，没有刁钻的函数，主要是考循环，不难，会给足你时间想，可以写草稿，实在不行就自己手动写一写总能知道在干什么的
5. Questions for the program