Interview Questions and Answers For Data Analysts
Interview Questions and Answers For Data Analysts
data, general knowledge ? how to build a portfolio, python skill for DA,
numpy, pandas? . phân tích các chỉ số kd? Ý nghĩa ? cách tìm insight
What is DA?
DA is a process of inspecting, collecting, cleaning, modeling data with the goal to
reveal trend and metrics that can be used to optimize process, improve
performance, making informed decision and drive strategic planning in business or
the other organization.
Data mining is a subset or small step in DA process, it is involved exploration and
analysis of the large data set to find important pattern behind the data
Step involved?
Define problem, collect data, cleaning data, explore data/analyzing data,
interpreting data/ story telling
What is outlier? How to detect them? It is the observation that lies far away from
the remaining values in data set? Using box plot
Hypothesis testing?
Is a form of statistical inference that uses data from a sample to draw conclusion
about a population parameter or population distribution.
Normal distribution?
Is a common type of probability distribution in statistic with the bell-shaped curve,
and it is characterized by some parameter like mean, variance, standard deviation,..
it performs exactly probability distribution of natural phenomena
2. Can you describe how you currently or have used SQL in the past?
Example Answer: I currently use it in my role to query tables and views to
analyze data. I also use it to create Stored Procedures to automatically send
my reports to clients. I work with our programming team to help optimize
scripts in SQL. Lastly, I use SQL to help with acquiring data, cleaning data,
and modeling it for use in our products.
3. Have you ever used a Cloud based platform? And if so, how have you used
it?
Example Answer: I currently use Azure, but I have use AWS in the past. I
use Azure DataLake to store large amounts of data. I also use Databricks to
automatically ingest flat files from clients.
Broad Questions
1. What was your most challenging data analyst project?
Example Answer: In March we were submitting data for MIPS for one of
our largest clients. We were on a very tight deadline and one of our contract
workers who worked in Canada was not answering emails or calls. We
needed him to help analyze a very large data set for several things and when
we couldn’t reach him we had to figure out a solution. We had a very narrow
deadline and I ended up working with our Director of Data Analytics in an
all night session to get the analytics to our client to prepare for the
submission of their MIPS data. We successfully handled the project and
submitted their data on time.
2. Describe a time when you had to work with a group on a Data Analyst
Project?
Example Answer: We were working with a client in North Carolina who
needed a Gap Analysis done of their current on-prem system compared to
their new Cloud based system. We had to work with a small team in North
Carolina as well as our team at our company to get access to their data from
both locations. The team lead on our side gave us our tasks and we worked
for several weeks to give them an in-depth analysis of their data.
4. Describe a time when you’ve made a mistake on a project and how you
handled it.
Example Answer: I was working with a client to get them an analysis of
some data they sent us. At the time we had 2 servers with almost the same
configurations. One was a historical server and the other an active server that
was getting a daily feed. I spent a few days on the analysis and sent it to the
client and they emailed back saying the numbers looked off. I quickly
realized that I had accidentally done my analysis on the historical server and
not the updated server. I quickly apologized to the client and said I would
get him an analysis with the correct data. Luckily, I had a good relationship
with the client and he said it was all good and to get him a new analysis of
the correct data as soon as I could. I sent that to him shortly after that and
was still able to meet the deadline that we had set.
SQL In-Person Interview Question
Easy
1. What is the difference between a table and a view?
Example Answer: A table is a preliminary storage for storing data in a
relational database management system. A view is a virtual table and is a
subset of a tables or tables and typically does not take up as much space as a
table.
2. How would you write a query that would only select unique records in a
column?
SELECT DISTINCT(Column)
FROM Table
4. What does GROUP BY (Statement) do in a Query? And why would you use
it?
Example Answer: The Group By statement groups rows that have the same
value into summary rows and are typically use with aggregate functions to
look at specific data in the dataset in a more organized manner.
5. I have a column called Drug_Name. I want to look at Drugs that start with
“Aspirin”. How would you only return drug names that start with Aspirin?
(Answer use the “Like” Operator”)
Answer:
SELECT Drug_Name
FROM table
WHERE Drug_Name LIKE ‘Aspirin%’
Intermediate
1. What is a subquery and can you describe how you would write that?
Example Answer: A Subquery is a query nested inside of a larger query.
I would write it like this:
SELECT *
FROM Table
WHERE UserID in
(SELECT userID
FROM Table2)
2. What is an join and what data would be returned if you use an inner join?
Example Answer:
A Join combines two tables into a single output. An Inner Join will return
data that is intersects (or is common) between both tables. For example: if
Table 1 has a,b, and c and Table 2 has b and c. Only b and c will be returned
because a is only in Table 1.
6. I have 2 tables. One table contains patient information and the other contains
Drug information. In the Patient table we have PatientID, First_Name,
Last_Name, and Disease. In the Drug table we have PatientID,
Dispensed_drug, Date_dispensed. Can you create a Query to return the
PatientID, Disease, and Dispensed_drug?
Answer:
SELECT PatientID, Disease, Dispensed_Drug
FROM Patient
JOIN Drug
ON Patient.PatientID = Drug.PatientID
Difficult
1. What are sys tables or System tables?
Example Answer: sys.tables is a system table and is used for maintaining
information on tables in a database. For every table added to the database, a
record is created in the sys.tables table. There is only one record for each
table and it contains information such as table name, object id of table,
created date, modified date, etc. Object ID is unique and we will use it to
join this table with other system tables (sys.columns) in order to fetch
column details.
Server Hay nói đơn giản thì máy chủ cũng là một máy tính, nhưng được thiết kế
với nhiều tính năng vượt trội hơn, năng lực lưu trữ và xử lý dữ liệu cũng lớn
hơn máy tính thông thường rất nhiều. Và nó được sử dụng cho nhu cầu lưu trữ và
xử lý dữ liệu trong một mạng máy tính hoặc trên môi trường Internet. Máy chủ
là nền tảng của mọi dịch vụ trên Internet, bất kỳ một dịch vụ nào trên Internet
như Website, ứng dụng, trò chơi,… muốn vận hành cũng đều phải thông qua một
máy chủ nào đó.
Outer join
PREPARE FOR INTERVIEW
I, Get acquaintance with small talk: how was your weekend, how you travel to the
office
II, tell me a bit about yourself: focus on education and experience
How you know about this position: the way you know about it and the insight that
you and company have in common
What attract you to our company: leader, environment, insight, spirit
What would you say is the greatest strength: ( settle(V): solve a problem, resolve, reach
an agreement, build a career,…), my work ethic wont let me settle less than my best.
( perseverance “pơ sơ via rằn” = persistence(N), persevere(v)). I can persevere go
through the adversity/ obstacle or challenge/ setback without falling into frustration or
anger. I’ve notice that this tends keep those around me always in the good spirit
Can y tell me the time when you suffer the setback and had to maintain your
enthusiasm: can be a hypothetical( 2 per THe đơ cồ)(aj) (giả định) situation
+ tell me about the time you have to deal with difficult coworker or client, when you
cope up with a crisis, disagreed with your manager about problem.
‘sure, one definitely comes to my mind, 2 years ago, when we were in the plan of
launching our new product, it was in its final stages, as we are looking at branding,
working up a final marketing campaign, our competitor launched an exact same product
that we were launching. As a leader of the project I acknowledge that it was a setback,
my reaction can set the tone of the team, and the foremost thing I have to do is
challenged the group to (find the solution/ think of this as a blessing in disguise). I asked
them to go out and by competitor’s product and make a list of what they wish the toy
could but it didn’t. it turn out the list pretty long, and as a result, after 6 months a
research showed that our product satisfied customer much more the competitors. In
many ways I can say, competitor product is the key to our product