Google Data Analytics Certificate Study Guide

Vocabulary flashcards covering the core concepts, analytical skills, data life cycle phases, database structures, statistical rules, and visualization terms from the Google Data Analytics Certificate study guide.

Data analysis

The collection, transformation, and organization of data to draw conclusions, make predictions, and drive informed decision-making.

Data analytics

The science of data (the entire discipline), in contrast to data analysis, which is the specific act of examining data for conclusions.

Data-inspired decision-making

A decision-making approach that uses facts to guide strategy while also weighing experience and context.

Data ecosystem

The people, tools, and environments that produce, manage, and use data, including clouds, databases, and organizations.

Data life cycle

The six-stage existence of data over its entire lifetime: Plan, Capture, Manage, Analyze, Archive, and Destroy.

Big data

Large, complex datasets typically described by volume, variety, and velocity (the "3 Vs"), and sometimes veracity and value.

Technical mindset

The analytical skill of breaking big problems into smaller steps and working with them logically and in an orderly way.

Data design

The analytical skill of organizing information, such as choosing columns and tables, so that analysis is easy later.

Data strategy

The management of the people, processes, and tools used in data analysis to ensure the right data reaches the right people.

Structured thinking

The process of recognizing the current problem or situation, organizing available information, revealing gaps and opportunities, and identifying the options.

Scope of work (SOW)

A document that defines deliverables, milestones, timeline, reports, and boundaries of what is in or out of scope.

Gap analysis

An analytical method where you document the current state, define the target state, and list what must change to close the gap.

Root cause analysis

A structured problem-solving practice that uses the "five whys" to keep asking why until the underlying cause is reached rather than just the symptom.

Metric

A single, quantifiable data type used for measurement.

ROCCC

A credibility assessment framework that checks whether data is Reliable, Original, Comprehensive, Current, and Cited.

Discrete data

Quantitative data that is countable and consists of a limited number of values, such as the number of tickets sold.

Continuous data

Quantitative data that is measured and can take on any numerical value within a range, such as temperature or time.

Nominal data

Qualitative data categorized without any natural or meaningful order, such as eye color or country.

Ordinal data

Qualitative data divided into categories that follow a meaningful order, such as a satisfaction rating from 1 to 5.

Wide data

A data structure where each subject has one row with many columns (e.g., one column per year), making it easier to read in spreadsheets.

Long data

A data structure where each subject has several rows with one value per row, making it easier to analyze and plot in tools like R and Tableau.

Data anonymization

The privacy practice of permanently removing personally identifiable information (PII) such as names, addresses, and phone numbers.

Tokenization

A security technique that replaces sensitive data elements with non-sensitive tokens that map back to the original values.

Metadata

Data about data (such as title, creator, date, and format) that aids in consistency and discoverability.

Primary key

A relational database field that uniquely identifies each row in a table and cannot contain null values.

Foreign key

A field in a relational database table that points to the primary key in another table to establish a link between the two.

Data integrity

The accuracy, completeness, consistency, and trustworthiness of data across its entire life cycle.

Changelog

A file or document that records every change made to data (including date, change made, reason, and author) to maintain transparency and repeatability.

Margin of error

The maximum amount by which sample results are expected to differ from the true population value.

Statistical power

The probability that a test of significance will detect an effect that is truly present in the population.

COALESCE

An SQL function that returns the first non-null value from a specified list of arguments.

Common Table Expression (CTE)

A temporary named result set defined using a WITH clause that exists for the duration of a single SQL query.

Simpson's paradox

A statistical phenomenon in which a trend seen in separate groups reverses when the groups are combined together.

Pre-attentive attributes

Visual properties the human brain notices almost instantly without conscious effort, such as position, color, size, shape, length, and orientation.

Tableau Dimension

A qualitative field in Tableau (usually displayed in blue) used to categorize, slice, and reveal detail in data.

Tableau Measure

A quantitative field in Tableau (usually displayed in green) that can be aggregated into sums or averages and generates axes.

Tidy data

A standardized data structure where each variable forms a column, each observation forms a row, and each value forms a cell.

Pipe operator

An R operator (expressed as %>% or |>) that passes the output of one expression forward as the input to the next function.

Tibble

A modern data frame from R's tidyverse that provides friendlier printing and enhanced handling over basic data frames.

STAR method

A behavioral interview answering technique structured around four parts: Situation, Task, Action, and Result.