Module 1: Organizing data to being analysis

Tutorial: Mastering the Analyze Phase of Data Analysis

Welcome, future data analysts! This tutorial takes you deep into the Analyze phase of the data analysis process, empowering you to transform raw data into insightful answers. Buckle up, we’re about to unlock the secrets of data manipulation and efficient exploration!

Step 1: Data Organization Essentials

• Spreadsheet Savvy: Master sorting, filtering, and pivot tables to categorize and summarize your data efficiently.
• SQL Power: Leverage SQL’s query language to extract specific data points and relationships from relational databases.
• Visualization Prep: Prepare your data for impactful visualizations by addressing missing values, outliers, and data types.

Step 2: Data Manipulation Techniques

• Descriptive Statistics: Calculate measures of central tendency (mean, median) and dispersion (standard deviation, variance) to understand your data’s distribution.
• Data Transformations: Scale, normalize, and transform your data to prepare it for powerful statistical analysis and algorithms.
• Data Aggregation: Group and summarize your data by relevant categories to identify trends and patterns.

Step 3: Efficiency Hacks for Data Analysis

• Automation is Key: Automate repetitive tasks like data cleaning and calculations using built-in spreadsheet formulas or Python libraries.
• Visualization Tools: Utilize interactive dashboards and data visualization platforms for quicker exploration and deeper insights.
• Version Control: Track changes and maintain data integrity with tools like Git to collaborate effectively and avoid overwriting work.

Step 4: Combating Bias in Data Analysis

• Identify Biases: Understand potential biases in your data sources, sampling methods, and analysis techniques.
• Control for Biases: Choose unbiased sampling methods, standardize data collection procedures, and avoid leading questions.
• Transparent Reporting: Acknowledge limitations and potential biases in your analysis to ensure ethical and trustworthy conclusions.

Bonus Round: Pro Tips for Mastering the Analyze Phase

• Ask the Right Questions: Define clear and focused research questions to guide your data analysis and avoid irrelevant exploration.
• Document Your Process: Create a detailed analysis log to track steps, decisions, and insights, facilitating reproducibility and collaboration.
• Think Outside the Box: Explore beyond basic calculations and try advanced techniques like hypothesis testing and statistical modeling to uncover hidden patterns.

Remember: Mastering the Analyze phase is about transforming data into meaningful insights. Practice these techniques, stay curious, and embrace the power of data!

Next Steps:

• Put your skills to the test! Work on real-world data analysis projects to solidify your understanding and build your portfolio.
• Stay updated on the latest data analysis tools and techniques through online resources and communities.
• Share your knowledge and contribute to the data analysis community by collaborating on projects and mentoring others.

By mastering the Analyze phase, you’ll unlock the true potential of data, transforming you into a skilled and insightful data analyst! Are you ready to make your mark on the world of data?

Hey there, future data analysts! You’ve made a lot
of progress so far. It’s not an easy journey, but you’re doing great. Before you started this program, something inside of you
convinced you to get your Google Data
Analytics Certificate. You had an idea, did some research, and made
the time to get started. Then you made the decision
to commit to your goal. Now look where you are! That is something to be proud of. Early on, we jumped right into the world of
data analytics and saw how data played a part
in your everyday life. You learned how to navigate
spreadsheets and why structured thinking was
key to solving problems. You also explored the best ways to collect and store your data. From there, you gained
an understanding of clean data and data integrity. You’ve identified how to ask the right questions and
learned to clean data. Now we’ll take your
skills to the next level. Next up, you’ll learn
how to come up with clear and objective answers to any data question you encounter. Earlier, we learned about
the data analysis process. As a quick reminder, the phases of that
process are Ask, Prepare, Process,
Analyze, Share, and Act. We’ll explore the
Analyze phase more here, focusing on how to organize
and format the data you have so that you can do
all sorts of calculations. Knowing how to analyze
the data you’ve collected and cleaned is essential to
your work as an analyst. Before we get started, I’d like to introduce myself. My name is Ayanna, and I’m excited to be your
instructor for this course. I’m a global insights
manager at Google, and I’ve also taught at the
Google Analytics Academy, which is a training resource
for Google analysts. In my job, I help
advertisers determine the value of investing
in Google products. When you search for
something online, you’ll often see
an ad on the page. That’s an investment an
advertiser has made. I use data analysis
to show advertisers the value they could gain
from investing in those ads. That’s what I love about
being a data analyst: figuring out how to create value anytime I enter a situation. The best way to know
if you’re creating value is if you have evidence. For me, that evidence is data. Now that you know a little
bit about my love for data, let’s talk about what
you’ll learn here. You’ll start by covering best practices for
organizing your data and the different ways
you can sort through that data using
spreadsheets and SQL. We’ll also spend time
learning three important ways to work with data that will
boost your analytical skills. Then we’ll talk
about saving time. You’ll discover tips and
tricks that can help you analyze data
more efficiently. Last but not least, we’ll work together to
identify techniques to help you be as fair and
unbiased as possible. Well, that’s all you
need to know for now. Coming up, we’ll break down the basics of data analysis and bring you one step closer
to a future in data.

The 4 Phases of Data Analysis: Unlocking Insights from Your Data

Data surrounds us! From online purchases to fitness trackers, we generate information constantly. But how do we turn this raw data into valuable insights? Enter data analysis, the magical process of transforming numbers into understanding.

This tutorial will guide you through the 4 key phases of data analysis:

Phase 1: Organize Your Data Jungle

Imagine exploring a rainforest blindfolded. Data without organization is like that – confusing and overwhelming. Your first task is to structure your data, making it accessible and ready for exploration. Here’s how:

• Identify your data sources: Where is your data lurking? Spreadsheets, websites, databases? Gather them all!
• Clean and tidy: Fix missing values, inconsistencies, and errors. Think of it as weeding out the tangled vines in your data jungle.
• Choose your tools: Excel, Google Sheets, or even specialized software – pick the weapon that fits your data battle.

Phase 2: Format for Clarity and Convenience

Raw data is like an uncooked meal – nutritious but not exactly appetizing. Formatting transforms it into a delicious dish, ready for analysis. Here’s the recipe:

• Descriptive names: Don’t leave columns as cryptic codes. Rename them something informative, like “Customer Age” or “Product Rating.”
• Categorize and sort: Group similar data points together (age ranges, product categories) and arrange them logically (ascending, descending).
• Visualization: Charts, graphs, and tables are your visual allies. They condense complex data into digestible pictures.

Phase 3: Gather Insights from Diverse Lenses

Data analysis isn’t a solo act. Consulting others adds valuable perspectives and strengthens your conclusions. Here’s how to bring in the team:

• Subject matter experts: If you’re analyzing sales data, talk to the sales team! Their experience can reveal hidden patterns or unexpected interpretations.
• Peers and colleagues: Fresh eyes are crucial. Share your findings and get feedback to avoid blind spots and biases.
• Public resources: Research papers, industry reports, and online forums offer existing analysis and insights relevant to your data.

Phase 4: Transform Data into Knowledge Nuggets

Now comes the alchemy! By combining organized, formatted data with diverse insights, you can start unearthing valuable knowledge. Here’s how to turn data into gold:

• Identify trends and patterns: Look for correlations, outliers, and unexpected relationships within your data.
• Ask “why” relentlessly: Don’t settle for surface-level observations. Dig deeper to understand the reasons behind the trends you’ve discovered.
• Draw conclusions and recommendations: Based on your analysis, what can you infer? What actions can you recommend based on your newfound knowledge?

Remember: Data analysis is an iterative process. Be prepared to revisit each phase as you learn more and refine your understanding.

Bonus Tip: Practice makes perfect! Start with small, manageable datasets and gradually work your way up.

By mastering these 4 phases, you’ll be well on your way to transforming data into powerful insights, unlocking the secrets hidden within your information jungle. So, grab your machete (analytical skills) and set off on your data analysis adventure!

Ready to explore further? Check out these resources:

• Online courses on data analysis platforms like Coursera and edX
• Books like “Naked Statistics” by Charles Wheelan or “Storytelling with Data” by Cole Nussbaumer Knaflic
• Interactive data visualization tools like Tableau and Power BI

Welcome back. It’s
great to see you again. So let’s talk about analysis. We’ve learned how to ask
the right questions, prepare data for exploration, and then process that data to make sure it’s squeaky clean. Now it’s time for the heart of the process: the actual analysis! Finally, right? But what is analysis? Basically, analysis is the process used to make sense of
the data collected. It means taking the
right steps to proceed and think about your
data in different ways. The goal of analysis
is to identify trends and relationships within the data so that you can accurately answer the
question you’re asking. To do this, you should stick to the 4 phases of analysis: organize data, format
and adjust data, get input from others, and transform data by
observing relationships between data points and
making calculations. Let’s apply the 4 phases of analysis to a
real-world scenario. Imagine you want
to buy a gift for your friend Zara’s wedding. The problem is you’re not
sure what to get her. Fortunately, you have a ton of data from her wedding website. But instead of reading all
the data on her website and scrolling through
a photo album of her and her partner, you go straight to
the online registry, a wish list of
gifts they’d enjoy. The registry is like
a dataset that you can analyze to make a decision. Now that you’re checking out organized data in the registry, you want to make sure that
the list of data, or gifts in this case, is formatted in a way that’s easy to reference. Formatting data streamlines
things and saves you time. Scrolling through hundreds of gifts can be time-consuming. Instead, you can adjust the
data in a way that makes it easy to digest by filtering
and sorting your data. You have a budget you
want to stick to, so you sort the gift
prices from low to high. You then filter prices to include gifts that are within
your budget of $60. You’re working with a newly
formatted list of data. At this point, it’s good to remember that input
from other people can also be really helpful when analyzing information
and making decisions. You can check the list of
gifts to figure out if anyone else has already
bought any of the items. You realize a few of the items in the list have been purchased, and this informs your decision. When analyzing data, gaining input from others is
important because it gives you a viewpoint
you might not understand or have access to. On top of gaining input
from other people, it’s also important to seek out others’ perspectives early. That way, if they predict any obstacles or challenges,
you’ll know beforehand. The people you’ll look
to for input don’t have to be experts to be helpful. Sometimes all you need
is for someone who’s familiar with a topic or
data you’re considering. In our example, that would be Zara’s wedding guests
who are purchasing gifts from the same
online registry. They probably aren’t
wedding gift experts, but their collaborative
effort to mark off the item they purchase can help you
figure out what not to buy, which will prevent Zara from
getting the same gift twice. In the end, getting input is
valuable to your analysis. This brings us to the last step of the analysis: transforming data. Transforming data means identifying relationships
and patterns between the data, and making calculations based on
the data you have. Going back to our example, you were able to find a gift that you knew Zara would like, and one that fits your budget. You were also able
to choose a gift that wasn’t already
purchased by someone else. By finding the
relationship between these data points, you chose, purchased, and sent
a gift that would answer the problem
you wanted to solve. The beauty of the analysis
process is that you probably already analyze situations
in your everyday life. Whether you’re analyzing data in your personal life
or in your career, these four tasks can help
you make better decisions. The more you do it, the more comfortable you’ll
feel with the process. I hope this gives you
a better understanding of the basics of analysis. As we move forward, we’ll check out how to
locate data for analysis, both in a spreadsheet
and using SQL. When you’re ready, you can
go ahead. See you soon!

[MUSIC] I think one of the coolest things
about working with data at Google is that we have one of the world’s,
most valuable datasets. People refer to Google data as
really a lens into human curiosity. We often look at Google as really a proxy
for what’s happening in the world. And so for many of our advertisers,
they really, really value the data and the insights that we’re able to give them
from Google because they believe it’s a proxy or a reflection of what’s
happening in their business or within their industry. And so I think the value of the data
that we’re able to work with at Google really keeps me interested and
excited about the work that I do. So I came to Google about three years ago
after spending a few years in consulting. And so I was really interested in
switching into a role that was really focused on sales and marketing. But at the same time, I still wanted to be
able to leverage the analytical skill set that I had gained prior. This role was a great complement to
the skillsets that I already had and the interest that I had in moving
into the sales and marketing function. I think one important thing for all students to realize is that no
one learns this material overnight. Many of your colleagues you may look at
as experts, but most likely they’ve been able to gain that level of expertise
through their years within the field. I think one of the biggest attributes
that students should keep in mind is that the most important thing that
they need to have throughout this learning journey is grit. Grit to understand that it may be
a struggle, it may be a challenge, but if you put in the work, you put in the time,
these concepts will eventually click, and you’ll be well on your way
to becoming a data analyst. Hi, my name is Ayanna and I’m a global
insights manager here at Google.

Hi again. Let’s jump back in. Right now we’re in the Analyze
phase of the data analysis process. And even though each phase is unique, data
analysts make decisions about organization throughout all of them. That’s what we’re talking about here: organization. It’s super important that
you keep your data organized throughout your analysis. How your data is classified and
structured will impact your findings, whether you’re working in a spreadsheet
or a database. And once you know how your data is
organized, you’ll be able to capture or collect the information you need. Most of the data you’ll use in your
analysis will be organized in tables. Tables help you organize similar
kinds of data into categories and subject areas that you can
focus on as you analyze. For example, this basic database
has tables for car dealerships, product details, and repair parts. Each table then has several fields
of data, like branch owner and the cost of repair parts. You can use these tables and fields to help you decide how to
move forward with your analysis. The structure of this database can
help you decide which data you need to pull to meet your objectives. For example, the total number of
a particular brand of car sold, or a repair part for a specific make
and model of a car at a certain branch. Tables allow you to make
decisions about data types. They help you to figure out
what variables you need and the data type those variables should have. So if you have a database where you need to
convert a data type during your analysis, you can do that by using
the CAST command in SQL or any other method that you learn on
the job or from your own research. Like this example where we converted
a purchase price column to be a FLOAT instead of a STRING so that it was in a numerical form
we could use for calculations. If you’re performing your
analysis in a spreadsheet, you want to make sure that the columns and
rows are effectively organized. You can even hide columns that
you won’t need for analysis or that show duplicate information. Once you have the data organized and
formatted, you’ll be ready to sort and filter it to find the data you need. We’ll cover sorting and filtering soon. But for now,
just know that both filters and sorts are affected by the type
of data we’re working with. The bottom line is that it’s important
to have your data in the right format. So always be prepared to adjust, no matter
how far into your analysis you are. That’s all for now. Coming up, we’ll show you what
filters are all about. Bye!