Certificate Exam Flashcards
A/B test
A test that allows you to conduct experiments
that compare multiple targeting groups
or campaigns by splitting audiences into
randomized and mutually exclusive groups.
Advanced matching
A Facebook pixel feature that allows websites
to pass additional site-visitor information (such
as email addresses or phone numbers).
Alternative
hypothesis
A hypothesis contrary to the null hypothesis, that
there’s a relationship between two measured
phenomena or an association among groups.
API (Application
programming
interface)
Defines how software components communicate.
Attribution
The practice of assigning value to various
marketing efforts.
Attribution model
Determines how credit is given to touchpoints
for a conversion. The logic that determines how
credit is given to touchpoints for a conversion.
The attribution model logic can be based on a
rule or set of rules, or a statistical model.
Attribution window
The finite period of time during which
conversions can be credited to a particular ad.
Auction
An ad buying methodology in which the ads run
based on the maximum bid and performance.
Ads compete against each other in this process
and the system determines the ones most likely
to be successful to be displayed.
Bid
The amount an advertiser is willing to pay to
achieve their desired outcome.
Bid cap
A bid strategy that enables advertisers to
set a maximum bid Facebook can use in each
auction.
Bid pacing
Adjusts a bid or which auctions to enter based
on how much budget and time are left for an
ad set.
Bid strategy
A setting in Ads Manager and Reporting that
helps Facebook determine how to spend a
budget to compete in a Facebook auction.
Brand lift
Measurement product that uses experimental
design (randomized control trials) to detect
brand impact that might be caused by ads run
on Facebook.
Budget allocation
The amount of marketing expenditure allotted
foreach marketing activity
Buying type
Options in Ads Manager that determine the
method by which you purchase ads on Facebook,
either through auction or reach and frequency.
CTR
The number of times an ad or a link to a web
page is clicked, compared with the number of
times it’s displayed.
CTR Acronym
Click-through rate
Control group
The group in an experiment or test for which
none of the factors in the test are variable. It’s
used as a benchmark to measure the effect of
the test.
Conversion efficiency
How effectively your ads drove the interactions
you’re measuring.
Conversion Lift
A Facebook product that uses randomized
control trials (RCTs) to measure the number
of incremental conversions that result from
Facebook ads.
Conversion lift
A marketing metric that quantifies the number
of additional conversions that result from
Facebook ads.
Conversion lift
percent
The percent difference in conversions between
the people who did and didn’t see your ads
during a test.
Conversion rate
The (estimated) number of times a link on a web
page is clicked, compared with the number of
times it’s displayed.
Conversion window
Period of time considered between seeing an ad
and acting upon it toward the ad’s main goal, be
it generating a lead or making a purchase.
Cost cap
A bid strategy that enables advertisers to set a
maximum average cost per optimization event for
an ad set. Facebook will keep the average cost
as far below that amount as possible, but keep
showing ads until it’s reached.
CPA Acronym
Cost per action
CPA
The cost to the advertiser each time an ad
prompts an action.
CPC Acronym
Cost per click
CPM Acronym
Cost per thousand
impressions
CPC
The cost to the advertiser each time an ad is
clicked.
CPM
Also known as “cost per mille,” it’s the
average cost for 1,000 impressions of an ad,
or the average revenue received for 1,000
impressions of an ad on apps or websites.
Cross-channel
measurement
Indicates outcomes related to advertising
across numerous online or offline channels,
such as Facebook and television.
Custom event
A logged action based on a specific action you
want audiences to take on your website, app or
offline.
CRM Acronym
Customer relationship
management
CRM
A tool that enables businesses to manage
customers’ contact information and interactions
through the customer life cycle.
Daily budget
The average amount you’re willing to spend on
an ad set or campaign every day.
Data analysis
A process of inspecting, cleansing,
transforming and modeling data with the goal
of discovering useful information, informing
conclusions and supporting decisionmaking.
Data analysis has multiple facets and
approaches, encompassing diverse techniques
under a variety of names, and is used in
different business, science and social-science
domains. In today’s business world, data
analysis helps businesses to operate more
effectively and make decisions more scientific.
Data source
A tool, connection, piece of code or other
object that collects information, such as
Facebook pixel, Facebook SDK or offline
conversions. The information can be used for
measurement and analysis.
Dependent variable
A variable whose value depends on that
of another.
Event
A logged action that people take on your
website, app or offline, usually used for capturing
and measuring ad performance.
Exact matching
In marketing research, an observational method
that examines a group of people exposed to an
ad campaign and tries to find a match for each
person in the non-exposed group.
Experimental method
In marketing research, a measurement method
that shows different types of ads to separate
groups of people in a controlled manner.
Facebook Attribution
A Facebook measurement product that
provides advertisers with cross-platform, crosschannel,
cross-device, multi-touch attribution
performance reports for ad campaigns.
Facebook’s data-driven
attribution
The process of determining credit for
touchpoints on a conversion path based
on their estimated incremental impact and
statistical modeling.
Facebook pixel
A piece of code installed on a website that
captures website events.
First-party data
Data a brand collects directly from its
customers (for example, website activity data,
sales data, and so on). Data a brand collects
directly from its customers (for example,
website activity data, sales data, and so on).
First-touch
attribution
A rule-based attribution model that gives 100%
of conversion credit to the first click or visit in a
conversion path. If there is no click or visit, then it
will credit the conversion to the first impression.
GRP Acronym
Gross rating point
Gross rating point
A unit of measurement of audience size
for TV advertisements. GRP is used to
measure exposure to one or more programs
or commercials, without regard to multiple
exposures of the same advertising to individuals.
Holdout test
Measures the total conversions caused by your
Facebook ads.
Hypothesis
A supposition or proposed explanation made on
the basis of limited evidence. Used as a starting
point for further investigation.
Impression
A single instance of an ad or piece of content
(such as a post) appearing on screen.
Independent variable
A variable whose variation does not depend on
that of another. It is the factor that is purposely
changed or controlled in order to see what
effect it has.
ITT Acronym
Intent to treat
ITT
A randomization method that includes all
randomized participants in a statistical
analysis and analyzes according to the group
they were originally assigned, regardless of
what treatment (if any) they received.
Inter-channel budget
The allocation of budgets across different
channels.
KPI Acronym
Key performance
indicator
KPI
A metric selected to evaluate the success of a
campaign or ad.
Last-touch attribution
A rule-based attribution model that gives 100%
of credit to the last ad a person interacted with
before a conversion, whether it’s an impression
or a click.
Lifetime budget
The amount you’re willing to spend over the
entire runtime of your ad set or campaign.
Lift solutions
A platform for running experiments on
Facebook ads and measuring the incremental
impact of ads on business outcomes.
Liquidity
In the context of machine learning, the concept
of allowing Facebook to determine the best
placement, ad set budget and bids for a
campaign.
Lowest-cost bid
strategy
The bid strategy that provides the highest
volume of conversions for the available budget.
Machine learning
A discipline that uses science, information and
computer code to automatically predict certain
outcomes based on discovered patterns that are
not explicitly programmed.
MMM Acronym
Marketing mix
modeling
MMM
A regression-based analysis that quantifies how
much sales and thus return on ad spend can be
correlated to each media channel in the mix, for
both offline and online channels.
Multi-cell test
A test that runs multiple experimental designs at
the same time. For example, in a two-cell multicell
test, cell A has two groups (test and control)
and cell B has two groups (test and control).
Multi-touch
attribution
The process of considering credit for each
touchpoint on a conversion path.
Natural experiment
An observational study in which subjects fall
into either the exposed or non-exposed groups
based on a naturally occurring event.
Nested test
An experimental method in which the
treatment group for one test is subdivided into
a control group and a secondary testing group.
Null hypothesis
A general statement or default position
in inferential statistics that there is no
relationship between two measured
phenomena or no association among groups.
Observational method
A way of collecting data through observing.
Offline conversions
Allow you to measure how much Facebook
ads lead to offline outcomes, such as in-store
purchases, phone orders, bookings and more.
Opportunity logging
In an ad’s test period, for the target audience
that has an opportunity to see the ad at
some specific stage along the delivery funnel
(meaning, for a user’s request, that the user has
an ad passed at some stage), Facebook logs the
opportunities (uniquely identified by tags like,
userId, studyId, dynamicHoldoutId and isContro)
to scribe tables.
Pacing system
A component of ad delivery whereby Facebook
measures and projects a campaign’s end date to
ensure a budget is spent as evenly as possible
over the lifetime of an ad set.
P-value
The probability of obtaining test results
at least as extreme as the results actually
observed during the test, assuming that the
null hypothesis is correct.
Parameter
Included alongside events to measure
additional information about the product or
service type people engage with on an app
or website.
Propensity score
matching
In marketing research, an observational method
that assigns everyone in the exposed and nonexposed
groups a probability of being exposed.
Then people from each group are matched
based on their similar probabilities.
R²
Also known as the coefficient of determination,
R2 is the proportion of the variance in the
dependent variable that is predictable from the
independent variable(s).
RCT Acronym
Randomized control
trial
RCT
RCTs test a hypothesis by introducing a
treatment, studying the effects and determining
the impact of your ad. Ultimately, an RCT can
help determine how much to spend on each
marketing channel in order to maximize results.
Reach
The number of people exposed to a medium at
least once during a given period.
Reach and frequency
A method of buying ads on Facebook that
allows advertisers to predict the audience size
reached and control the average frequency
that the audience is exposed to their ads.
Regression
adjustment
In marketing research, an observational
method whereby people build a model based
on the observed data and use the model to
predict the outcome of the campaign based on
a set of observed variables, including whether
or not people were exposed to the advertising
campaign.
ROAS Acronym
Return on ad spend
ROAS
An economic indicator used to evaluate the
effectiveness of ad spend. It is calculated as
the ratio of the amount gained or lost relative
to the amount invested.
ROI Acronym
Return on investment
ROI
An economic indicator used to evaluate the
efficacy of total media investment, including
trade. It is calculated as the ratio of the amount
gained or lost relative to the amount invested.
Rule-based
attribution model
Different attribution models distribute different
amounts of credit for conversions across ads.
They can be based on a rule or a set of rules,
or a statistical model. Rule-based models let
you select the rule that will determine how
conversions should be attributed to different
touchpoints. Single-touch models give credit
to only one touchpoint, while multi-touch
models give credit to multiple touchpoints in the
consumer’s conversion path.
Sales lift
The additional revenue caused by ads in a test,
when compared to the test and control groups.
SEM Acronym
Search engine
marketing
SEM
The practice of marketing a business using
paid advertisements that appear on search
engine results pages.
Single-cell test
A test with one test group, where group A is
shown the ad and group B is not.
SDK Acronym
Software
Development Kit
SDK
A piece of code installed on an app that
captures app events.
Statistical attribution
model
An attribution model that uses algorithms to
determine credit for each touchpoint.
TRP Acronym
Targeting rate point
TRP
The number of impressions bought per 100
people in an ad’s target audience.
Test duration
How long a test runs for, from beginning to end.
Third-party data
Data collected by a party that does not have a
direct relationship with the user (such as DMP).
Total value
calculation
Advertiser Bid x Estimated Action Rates + User
Value
User value
A prediction of how engaging or relevant a
user may find an ad based on available signals.
Variable
A quantity or other piece of data that can
assume different values.
Visit
In Facebook Attribution, the number of times a
person loaded your website from any channel
(including paid, direct, organic and untracked
channels), as recorded by the Facebook pixel
or SDK.
S M A R T Goals
specific, measurable,
achievable, relevant and time-bound,
A/B test
A test that allows you to conduct experiments that
compare multiple ad sets by splitting audiences into
randomized and mutually exclusive groups.
Testing multiple campaigns
against one another to see which
tactical approach produces the
best results based on your KPIs.
Limitations of A/B Tests
- Does not assess incremental impact.
- Reliable only if the confidence level is at least 75%.
- Some A/B tests do not include control groups, only randomized
test groups. In these cases, they do not measure causality
or the incremental value of a strategy, and therefore are
not recommended when strategy A has a different baseline
conversion rate than strategy B (such as audience). - Not all tests are appropriately powered with adequate
conversion numbers in each group.
Randomized control trial (RCT)
RCTs test a hypothesis by introducing a treatment,
studying the effects and determining the impact
of your ad. Ultimately, an RCT can help you decide
how much to spend on each marketing channel to
maximize your results. It can infer causality.
Limitations of RCT
Limitations
* Tests may not be set up with sufficient statistical power.
* The treatment variable may not always be isolated.
* Some tests will have effects beyond initial user interaction.
* They can’t account for the unknown (e.g., people use cash or
make other untraceable purchases).
* Test and control groups might have outliers.
* Outcomes might be difficult to replicate.
Observational method
A measurement method in marketing research
that observes the effect of ads on people without
changing who is exposed to the ads.
Limitations of Observational method
- Not experimental, so causal inferences cannot be made.
- Difficult to perform strategy comparisons in a controlled way.
- Might deliver biased outcomes.
- Does not take into consideration contextual variables that
may affect the final outcome.
Cross-channel reach reporting
Measures how channels work together
to generate business outcomes.
Channels include but are not limited
to email, TV, direct mail, Facebook and
paid search.
Limitation of Cross-channel reach reporting
- Metrics vary by channel.
- Cross-channel reach reporting can be challenging,
because not all channels share touchpoint/reach data. - Limitations vary by specific solution. In general,
limitations arise when metrics are not comparable or likefor-
like data is not available. - Reach does not always correlate with brand and
conversion business outcomes.
Attribution
The process of determining credit for
each touchpoint on a consumer’s path to
conversion.
Multi-touch attribution models, or MTAs,
allocate value to more than one touchpoint in
a consumer’s path to conversion. Data-driven
attribution is the process of determining
credit for touchpoints on a conversion path
often based on historical data and statistical
modeling.
Attribution Limitations
- Statistical attribution models can be costly to
access in some cases, while others are limited
to specific channels. - Cross-device limitations on cookie- or webbased
systems. - Many tools do not have access to the full path
to conversion (for example, in-app impression
data is often not shared across publishers.) - Often only includes digital channels.
Marketing mix modeling
A data-driven statistical analysis that
quantifies the incremental sales impact and
return on investment of marketing and nonmarketing
activities, measuring both offline
and online sales across channels.
Marketing mix modeling Limitations
- Can struggle to capture incremental sales
where an increase is minimal. - Requires collaboration between modelers and
an econometric model. - Doesn’t help with in-channel optimization.
- Does not infer causality, only correlation.
- Can be time-intensive to implement.
Lift test
Use a Lift test to measure incremental outcomes by comparing
the actions of people who have seen your ad with people who haven’t.
Lift tests with
statistically significant results can infer causality and accurately measure incrementality, unlike proxy
metrics, like clicks and likes, which are indirect approximate measurements that may not be correlated
with actual business value and can result in suboptimal business decisions.
Single-cell test Lift Test
This option is best used to get a baseline understanding of incremental
brand or conversion outcomes your campaign is currently driving.
Multi-cell test Lift Test
Compare two competing strategies to understand which leads to
greater incrementality.
Nested Lift Test
In this experimental method, the treatment group for one test is subdivided into a control
group and a secondary testing group. A nested test can help an advertiser to understand the
incremental impact a new strategy has on a strategy that’s already under way.
Facebook Attribution - Strengths
Measure the performance
of your ads across channels
(paid vs. organic), publishers
and devices.
Understand your consumer’s
journey to purchase.
Choose from two types of
models: rule-based and
statistical-based.
Can be a useful complement
to lift tests.
Facebook Attribution - Limitations
Since there are a variety of
attribution models, it will take
time and experimentation to
find the one that best fits your
business.
The length of the attribution
window may limit results.
Results may not reflect
performance from all
marketing efforts.
Facebook Attribution - Outputs
Metrics for variables
related to the media
channels used in marketing
(paid, organic, direct)
Metrics for variables
that relate to the desired
action (visits, conversions,
sources)
Return on ad spend (ROAS)
Brand Lift - Strengths
Measure the incremental
impact your ad has on
people’s perception of your
brand. Can be single-cell or
multi-cell.
See how your campaign
performs against norms for
campaigns in your industry
and your region.
See lift by demographic
breakdown (for example,
age, gender).
Can be performed with
third-party measurement
partners.
Brand Lift - Limitations
You need to get at least 250
responses to one poll question
in order for Facebook to show
results.
A holdout is required for
measurement.
Brand Lift - Outputs
Poll results
Brand lift percent for all
responses
Brand lift percent by
demographic
Cost per Brand Lift
Test details: a summary of
your test setup
Confidence levels
Conversion Lift - Strengths
Measure the incremental
impact your ad has on
people’s perception of your
brand.
Use intent to treat (ITT)
to manage the effect of
potential error in the test
results and more accurately
ensure comparable
audiences.
Can be performed with
third-party measurement
partners.
Conversion Lift - Limitations
A holdout is required for
measurement.
Must ensure that the test
has at least 80% statistical
power in order to allow
for statistically significant
outcomes.
Conversion Lift - Outputs
Conversion lift
Sales lift
Cost per conversion lift
ROAS lift
Conversion lift percent
Breakdowns by demographic
and attribution window
Confidence levels
Marketing Mix Models - Sttrengths
Quantify the impact of a
large set of variables on
sales.
Understand what influenced
past sales and predict what
may happen as a result of
future marketing.
Understand how your
marketing activity impacts
sales.
Marketing Mix Models - Limitations
Requires high-quality data.
Requires collaboration
between modelers and an
econometric model.
Doesn’t help with in-channel
optimization.
Does not infer causality, only
correlation.
Can take up to six months to
fully implement.
Marketing Mix Models - Outputs
Marginal return associated
with each marketing
channel
A report that details how
much influence each of
your marketing activities
had on sales
An overview of how your
spending in different
channels contributed to
success
A/B Test - Strengths
Assess the correlation
between different versions of
your ads. Create multiple ad
sets and test them against
each other to see which
tactical approach produces
the best results.
Understand which specific
images, videos, placement,
text and/or call to action
performs best.
Know which combination of
variables (creative, audience,
delivery optimization, product
sets or placement) performs
better at meeting your
business goal.
Understand the best
allocation between full
funnel stages.
Ideal time for an A/B Test
at least 3 days, but no longer
than 30 days.
Single-Touch Attribution Models
Single-touch attribution models give credit to only one touchpoint.
Multi-Touch Attribution Models
Multi-touch attribution models take into account more than one
interaction with a given media channel. They are inclusive of other
models, including even credit, positional and time decay.
Lift %
Indicates how much your ads increased
the rate at which people converted (as defined
by the conversion events you chose when
you created the test).
Confidence
percentage that represents how
confident Facebook is that your ads caused
conversion lift.
P-value
The probability of obtaining test
results at least as extreme as the results
actually observed during the test, assuming
that the null hypothesis is correct. The null
hypothesis is rejected when p < alpha and
not rejected when p > alpha where alpha is
determined by the analyst.
R2
Also known as the coefficient of
determination, R2 is the proportion of the
variance in the dependent variable that is
predictable from the independent variable(s).
This is typically used when evaluating the
goodness of fit of multiple models to determine
the most accurate model.
Total Value
Budget Pacing
The aspect of pacing where we may increase
budget if there’s an opportunity to get many
optimization events with costs aligned with your
bid strategy
Bid Pacing
The aspect of pacing where we adjust your bid
or which auctions we enter based on how much
budget and time are left for your ad set.
Auction Buying
Auction buying offers more choice, efficiency and flexibility, with less predictable results.
Ads can be placed across Facebook, Instagram, Messenger and Audience Network
Reach and Frequency Buying
Reach and frequency buying lets you plan and buy your campaigns in advance,
with predictable ad delivery and more control over your frequency settings.
Lowest Cost Bid
Select the lowest-cost bid strategy if you want
to spend as much of your budget as possible
without having to keep costs within a specific
amount. With the lowest-cost bidding strategy,
you don’t have a specific cost threshold; you
prioritize spending budget over cost control.
The lowest-cost bid strategy may lead to
more cost fluctuation. For example, if auction
competition decreases, costs may go down. If
auction competition increases, costs may go
up. We will work to get you the most results
available for your ad set.
Bid Cap
Use this strategy if you want to set a maximum
bid across auctions to limit the bid amount
in every auction and reach as many people
as possible at that bid. This bid strategy
maximizes volume at a specified maximum bid
cost and can increase competitiveness against
other advertisers who are targeting similar
audiences. If you want to control for the cost of
actual results, we recommend the cost-cap bid
strategy.
Target Cost
If you choose the target-cost bid strategy,
Facebook randomly enters you into auctions
using your full cost control. Some outcomes are
expensive, and some are cheaper. Cost stability
versus cost efficiency is the trade-off when you
use target-cost bidding.
Cost Cap
Using a cost control with the cost-cap bid
strategy lets Facebook deliver the maximum
number of conversions. The cost provided
is an average amount, which Facebook
tries to stay under by going after the lowest
cost events available. As you spend more
or increase your budget, your average cost
per optimization event might increase. Cost
controls apply to your average cost per
optimization event, so Facebook’s ad delivery
system can pursue opportunities across
auctions at a wider range of costs. Some
optimization events cost more than your cost
control. Over the lifetime of your ad set, your
average cost should be at or below your costcontrol
amount.
