Interview guides · Amplitude

Amplitude Data Scientist Interview Questions & Guide 2026

Practice explaining analysis before a Amplitude data scientist interview: the recommendation, the uncertainty, the follow-ups.

The 60-second brief

As a Data Scientist at Amplitude, you sit at the intersection of advanced statistical methodology and real-world product impact. Amplitude is the leading AI-powered analytics platform, and your work directly influences how thousands of customers—including global brands like Atlassian and Square—measure, test, and optimize their digital experiences. Whether you are working on the internal Experimentation team or serving as a Customer Data Scientist, you are responsible for defining the rigor that powers product-led growth.

Seniority shifts the scope more than the words in the title do. Earlier-career loops mostly check that you execute a well-posed analysis correctly; senior loops check that you can decide which question is worth answering and defend what you chose not to do.

Focus areas

Separate novelty effects from durable behaviour change
Size an experiment before anyone launches it
Pick a randomisation unit that respects interference

Overview

This role is highly strategic and technical. You will not just be running models; you will be acting as a trusted advisor on experimentation infrastructure and causal inference. You will collaborate closely with product managers, engineers, and sales teams to solve complex data challenges, from designing robust A/B test frameworks to diagnosing unexpected metric fluctuations. It is a role for those who enjoy translating complex statistical concepts into actionable product insights that drive actual business value.

The Amplitude interview process

Amplitude candidates report 5 rounds · ≈ 4-6 weeks. The stages below are what candidates describe, not a published process.

Recruiter Screen

A screening call is a matching exercise run by someone who will not evaluate your statistics. They are checking that the work described on your resume is work you personally did, and that its scope matches the level the role is written for. Logistics get settled in the same half hour so nobody spends an interviewer's afternoon on a mismatch. The answer that fails is the one narrated in the plural. If every sentence is 'we built' and 'the team decided', there is nothing specific to write down about you. Name the piece that was yours, the decision you made inside it, and what changed after.

What to demonstrate

Whether the ownership implied by your resume survives one round of follow-up about who actually did which part
Whether your described scope (data size, stakeholders, what shipped) matches the seniority the role is written at
Whether timeline, location and compensation expectations make the rest of the loop worth scheduling

How to prepare

Rewrite your top three resume bullets in the first person singular, each with the decision you made and what moved afterwards, then say them out loud once so the 'we' does not return under pressure
Attach one number to each project: the baseline, the change, and the window it was measured over. Where impact was never measured, say that plainly rather than inventing a figure
Settle your compensation range before the call and give it as a range with a reason behind it, such as current total comp or a competing timeline, instead of deflecting the question twice

Technical Screen

This round decides whether someone can hand you a schema and a question and trust the number that comes back. Correctness under a clock is the bar, not clever syntax. The habit that separates strong from weak answers is checking the grain: after every join, know how many rows you expect and whether the count moved. Most wrong answers in this format are not wrong logic, they are a fan-out from a key that turned out not to be unique, or a filter applied before an aggregate when it belonged after. Say what you expect before you run it.

What to demonstrate

Whether your row counts survive each join, and whether you notice on your own when they do not
Deliberate handling of rows that fail to match, including whether the question needs an inner join or a left join with the non-matches kept and counted
Whether NULLs are treated on purpose, given that a NULL compares equal to nothing and that COUNT of a column skips it
Reaching a defensible answer inside the window instead of a refined one after it

How to prepare

Take a two-table schema, write a join that fans out on purpose, then fix it by collapsing the many-side to one row per key before joining. Repeat until the fix is reflex rather than recall.
Write a funnel as one query and print the distinct user count at each stage, then confirm each stage is a subset of the one above it rather than assuming it
Do a few timed runs in a plain text box with no autocomplete and no formatter, since assessment editors often have neither

Case Study

A case has a fixed clock, and a good deal of what is being scored is how you spend it. Thirty to forty-five minutes buys one pass across the whole problem or a deep read of one part of it, and choosing between those is the work rather than a compromise forced on you. Announce the shape early: the structure you are using, the branch you think carries the decision, and what you are setting aside. An answer that is thorough for the first third and silent on the recommendation reads worse than one that is rougher throughout and lands.

What to demonstrate

Whether a visible structure appears in the opening minutes and survives the rest of the case
Whether the depth goes to the branch that carries the decision, rather than the branch you find most comfortable
Whether you say what you are leaving out and why, instead of quietly omitting it and hoping nobody asks

How to prepare

After each practice case, write down the branches you chose not to open and the reason for each, then check whether you said any of them out loud while the case was running. A branch you only cut privately reads to the interviewer as one you missed.
Redo a case you have already worked in half the time, deciding in advance which single branch you keep, then compare which version a listener would find more useful.
Write a two-sentence opening you can reuse, holding the restated question and your plan for the available time, and deliver it within the first ninety seconds of every practice run.

Behavioral Interview

Behavioural answers from data candidates get audited in a way that answers from other roles do not. When you say a model lifted retention, the next question is the denominator, the window, and how you knew the lift was not seasonal. So attach the measurement to each claim while you tell it: what the metric was before, over what period, and against what comparison. Numbers with no baseline read as rounded-up memory, and one unsupported figure tends to make the rest of the story sound rehearsed.

What to demonstrate

Whether each impact number arrives with a baseline, a window and a comparison, or as a bare percentage
Whether you can name the method that attributed the effect to your work (an experiment, a staged rollout, a seasonal control) or concede the link was correlational
Whether the magnitudes stay internally consistent when the interviewer multiplies them against the scale you described earlier

How to prepare

For each story, write the impact line as metric, value before, value after, window, and how attribution was established. Any line missing two of those five is a follow-up you will answer badly.
Re-derive one headline number from the source table rather than the deck that reported it. Resume numbers drift upward across retellings.
Decide in advance which figures you cannot share, and prepare the ratio or relative change you can give instead, so a confidentiality limit does not read as evasion.

Final Round

Where a loop includes a partner from outside the data team, that conversation usually carries the same weight as the technical ones and gets the least preparation. The person opposite you will not follow a derivation and does not need to. They are working out whether having you involved would make their decisions better or slower. The failure mode is not being too technical. It is answering a question about a decision with a description of your method, leaving the translation to them. What they carry into the debrief is the sentence you handed them, not the analysis underneath it.

What to demonstrate

Whether a statistical result arrives as something the partner could act on, with the one caveat that would change their decision kept and the rest left out
Whether you can state what you need from their side, in their terms: instrumentation that does not exist yet, a definition they own, or a holdout they have to agree to
Whether uncertainty is given as a range someone can plan against, rather than as hedging that invites them to ignore the result
Whether you ask what decision is actually on the table before explaining anything

How to prepare

Take a result you know well and write the version for someone who stops reading after one sentence, then the three-minute version, and check the short one is not the long one with the qualifications stripped out
For a past project, list everything you asked a non-technical partner for and how you phrased it, then rewrite each ask so it names what goes unmeasured without it
Practise saying where a result does not apply, out loud, in one sentence that a partner could repeat accurately to someone else

Where candidates lose points

Reading a pooled rate that moved because the mix moved, not because any behaviour changed

A pooled conversion rate is a weighted average, and a shift in the weights can move it in the opposite direction to every one of its parts. A paid campaign that brings low-converting traffic drops overall signup conversion even if desktop, mobile web and app conversion each rose that week, which is Simpson's paradox and it is the single most common cause of an inexplicable dashboard move. The discipline is to decompose before explaining: recompute the rate holding last period's segment weights fixed, and compare that counterfactual to the actual, so the mix effect and the rate effect are separated numerically rather than argued about. Segment on the dimensions that actually reweight, which in this domain are almost always device_type, referrer_channel, country and new versus returning.

Slicing a flat experiment until a segment reaches significance

Testing one metric across twenty segments at a nominal 5% level produces a significant result about two thirds of the time when nothing is happening anywhere, and the segment that surfaces is by construction the one with the most favourable noise. The reported effect in that slice is then badly overstated, because selection on significance conditions the estimate on being large. What makes it dangerous rather than merely wrong is that a post-hoc segment always has a plausible story attached, so it survives the meeting. The controls are declaring the small number of segments of interest before launch, correcting across the ones tested, and treating anything discovered afterwards as a hypothesis that needs its own adequately-powered test rather than a finding.

Averaging per-user rates to produce a population rate

Decide which quantity you want: the mean of per-user ratios and the ratio of summed numerator to summed denominator are different estimands, and heavy users dominate one but not the other. For a ratio metric, aggregate numerator and denominator separately and use the delta method for its variance.

Interpreting a change before checking data quality and logging

Spend the first pass on row volume by day, null rates, duplicate keys, and whether the step change lands on a release or tracking-migration date. A discontinuity that coincides with a deploy is an instrumentation hypothesis before it is a behavioural one.

Questions & practice

How would you approach causal effects modeling in the context of heterogeneous treatment effects?

Medium · machine learning and modelling

Approach

Say how the offline result would be validated online before it is trusted.
Pick an evaluation metric that matches the cost of each error type, not a default.
Set a baseline first, so any model has something honest to beat.

Follow-up

How would you choose the decision threshold, and who owns that choice?
What would you monitor after launch to know the model is still valid?

Cluster bootstrap for a per-session rate randomised on users

Hard · cluster bootstrap · randomisation unit · variance

An experiment randomised on user_id reports a per-session conversion rate, so sessions inside a user are correlated. Input: one row per session with user_id, variant in {control, treatment} and converted in {0,1}. Write a cluster bootstrap from scratch: resample users with replacement within each arm, keep every session of a drawn user, recompute each arm's ratio of converted sessions to sessions, and take the difference. Return the point estimate, a 95 percent percentile interval from at least 2,000 resamples, the naive session-level interval that ignores clustering, and the ratio of their widths.

Approach

Name the estimand precisely: it is a ratio of sums, sum(converted) over sum(sessions) within an arm, not the mean of per-user rates. Those differ whenever session counts vary across users, and the ratio is what the reported metric is.
Resample the cluster, not the row. Draw n_users user ids with replacement inside each arm and take every session belonging to each draw, including duplicate draws of the same user. Keeping the user count fixed per arm rather than the session count is what preserves the sampling design.
Precompute per-user (converted_sum, session_count) once, so each resample is two vector lookups and a division rather than a repeated filter over the session frame. That turns 2,000 resamples from minutes into under a second.
Take the 2.5th and 97.5th percentiles of the 2,000 differences for the interval, and report the point estimate from the full data rather than from the bootstrap mean, since the bootstrap mean carries the resampling bias.
Compute the naive interval from the session-level binomial standard error and compare widths. The expected inflation is roughly sqrt(1 + (m-1)*rho), with m the mean sessions per user and rho the intraclass correlation of converted within users, so a computed ratio far from that value points at a bug in one of the two intervals.

Worked solution (35 min)

per_user = df.groupby(['variant','user_id'])['converted'].agg(['sum','size']); split into two arrays per arm.
point = (t_sum.sum() / t_n.sum()) - (c_sum.sum() / c_n.sum()).
For b in range(B): idx = rng.integers(0, len(t_sum), len(t_sum)); ratio_t = t_sum[idx].sum() / t_n[idx].sum(); same for control; store the difference. Vectorise by drawing a (B, n) index matrix if memory allows.
ci = np.percentile(diffs, [2.5, 97.5]); naive_se = sqrt(p_t*(1-p_t)/n_sessions_t + p_c*(1-p_c)/n_sessions_c); naive_ci = point +/- 1.96*naive_se.
width_ratio = (ci[1]-ci[0]) / (naive_ci[1]-naive_ci[0]).

Expected result: A point estimate identical to the full-data ratio difference, a percentile interval containing that point estimate, and a width ratio greater than 1 whose value approximates sqrt(1 + (m-1)*rho) for the data's mean cluster size m and intraclass correlation rho. A ratio of approximately 1.0 means sessions were resampled instead of users.

Verify it yourself

Construct data where every user has exactly one session: the cluster and naive intervals then agree to within Monte Carlo error, since m = 1 makes the design effect 1.
Construct data where converted is constant within each user: rho is 1, and the width ratio should approach sqrt(m).
The bootstrap distribution's mean sits close to the point estimate; a large offset means the resampled arms have drifted in size.
Doubling B narrows the Monte Carlo noise in the percentile endpoints without shifting the interval's centre.

Follow-up

Users average 3.4 sessions and the intraclass correlation is 0.12. What width ratio do you predict before running it, and does your bootstrap land there?
Give the delta-method standard error for this ratio and say when you would prefer it to the bootstrap.
Half the users in the treatment arm have exactly one session. What does that do to the cluster bootstrap's coverage, and how would you check it?

Simulate the false positive cost of repeated peeking

Medium · simulation · peeking · type i error

Quantify the cost of peeking. Simulate a two-arm experiment with no true effect: each arm accumulates Bernoulli conversions at a base rate of 0.10 up to 40,000 units per arm. Run a two-sided two-proportion z-test at alpha 0.05 at ten equally spaced interim points, and record whether the test ever crossed. Report the false positive rate over at least 10,000 replications, alongside the rate for a single look at the final sample only. Use a fixed seed and report a Monte Carlo standard error on both figures.

Approach

Generate each replication as two cumulative sums of Bernoulli draws, then read the interim points off the cumulative arrays. Regenerating data at each look would make the looks independent, which destroys exactly the dependence the exercise is about: later looks share data with earlier ones.
Use the pooled-variance two-proportion z: p_pool = (x1+x2)/(n1+n2), z = (p1-p2) / sqrt(p_pool*(1-p_pool)*(1/n1 + 1/n2)), reject when |z| > 1.96. State that the normal approximation is fine here because the smallest look has roughly 400 expected conversions per arm.
Vectorise across replications rather than looping: draw a (reps, n) array of uniforms, threshold at 0.10, cumsum along axis 1 and slice the ten look indices. A per-replication loop at 10,000 by 40,000 is unnecessarily slow.
Record the any-cross indicator per replication, take the mean, and compute the Monte Carlo standard error as sqrt(p*(1-p)/reps) so the reported figure comes with its own precision.
Report the single-look rate in the same run as a control. If it does not land near 0.05, the bug is in the test statistic and not in the peeking argument.

Follow-up

Re-run with 40 looks instead of 10. Why does the curve flatten rather than continue rising linearly?
Among the replications that crossed, what is the mean observed lift, and why is it not zero?
What does an O'Brien-Fleming boundary or an always-valid confidence sequence change about this simulation, and what does each cost in power?

Write a query using SQL window functions to calculate the rolling 7-day average of user signups.

Medium · sql and data manipulation

Approach

Compute rates by summing numerator and denominator separately, never by averaging rates.
State the window function and its partition and ordering out loud before writing it.
Handle the rows that do not match: a LEFT JOIN with a NULL check is usually the question.

Follow-up

What breaks if events arrive late or out of order?
How does the query change if the join becomes one-to-many?

Given a table of event logs, how would you calculate the time-to-conversion for users who performed a specific sequence of actions?

Medium · sql and data manipulation

Approach

Compute rates by summing numerator and denominator separately, never by averaging rates.
Handle the rows that do not match: a LEFT JOIN with a NULL check is usually the question.
Check whether any join is one-to-many before aggregating, or the sums inflate.

Follow-up

How would you verify this result without re-running the same query?
What breaks if events arrive late or out of order?

Pair flow starts to completions within a thirty-minute bound

Medium · event-streams · conditional-aggregation · flow-funnel

fct_event holds event_id, flow_id, flow_instance_id, event_name, occurred_at_utc, surface, app_version. Using only rows where event_name is 'flow_started', 'flow_completed' or 'error_shown', compute the daily core-flow completion rate by surface and app_version. Numerator: distinct flow_instance_id whose flow_completed occurs within 30 minutes of its flow_started with no error_shown for the same instance in between. Denominator: distinct flow_instance_id with a flow_started that day. Report rows with a NULL flow_instance_id as a separate coverage count, not inside either side.

Approach

Collapse the stream to one row per flow_instance_id using conditional aggregation: MIN(occurred_at_utc) FILTER (WHERE event_name = 'flow_started') AS started, MIN(...) FILTER (WHERE event_name = 'flow_completed') AS completed, MIN(...) FILTER (WHERE event_name = 'error_shown') AS first_error. This makes the 'first' semantics explicit and avoids a self-join entirely.
Apply the predicates on that single row: completed IS NOT NULL AND completed <= started + interval '30 minutes' AND (first_error IS NULL OR first_error > completed). Note the last clause encodes 'in between' literally, so an error surfaced after a successful completion does not disqualify the attempt.
Bucket by started::date, surface and app_version. Splitting by app_version is not decoration: a completion-rate regression is nearly always confined to one client build, and a pooled daily rate hides it behind the installed base.
Count NULL flow_instance_id rows as a separate coverage figure. They cannot be attributed to an attempt at all, so they belong in neither numerator nor denominator, and their share tells you how much of the rate is unmeasurable.
For any roll-up to week or to all surfaces, re-sum the numerator and denominator rather than averaging the daily rates.

Worked solution (25 min)

Write the per-instance collapse CTE and confirm COUNT(*) equals COUNT(DISTINCT flow_instance_id).
Add the three predicates one at a time, recording how many instances each removes.
Aggregate by day, surface and app_version with FILTER on the clean-completion flag.
Compute the NULL-instance coverage count as a separate select and report it alongside.
Pick the worst day-surface-version cell and pull ten raw instances to confirm the disqualification reason.

Expected result: One row per (day, surface, app_version) with started, completed_clean and a rate bounded by 0 and 1, plus a scalar coverage count of events carrying a NULL flow_instance_id. Instances completing after 30 minutes appear in the denominator only.

Verify it yourself

No rate exceeds 1.
COUNT(*) equals COUNT(DISTINCT flow_instance_id) in the collapsed CTE.
Total started across cells equals the count of distinct flow_instance_id values carrying a flow_started event in the window.
Instances with an error strictly between start and completion are excluded from the numerator but present in the denominator.

Follow-up

occurred_at_utc is client-supplied. What do you do with an instance whose completion timestamp precedes its start?
flow_instance_id is missing on 4 percent of starts for one app_version. What can and cannot you conclude about that build?
An instance starts at 23:55 and completes at 00:04. Which day owns it, and what does the alternative do to the daily series?

If a user conversion rate increases but overall revenue decreases, how would you evaluate the success of the product change?

Medium · product sense and metrics

Approach

Fix the population and the time window before naming any metric.
Name one primary metric, then the guardrail that stops it being gamed.
Restate the decision this analysis has to support, and who acts on the answer.

Follow-up

How would you detect that the metric is being gamed rather than genuinely improving?
Which segment would you cut first, and what would that rule out?

How would you design a metric to measure the success of a new feature in a collaboration tool?

Medium · product sense and metrics

Approach

State what result would change your recommendation, so the answer is falsifiable.
Decompose the metric into the rates that drive it, and say which one you would check first.
Name one primary metric, then the guardrail that stops it being gamed.

Follow-up

What would you do if the primary metric and the guardrail moved in opposite directions?
How would you detect that the metric is being gamed rather than genuinely improving?

How do you prioritize your work when you have multiple competing requests from different customer teams?

Medium · product sense and metrics

Approach

Restate the decision this analysis has to support, and who acts on the answer.
Decompose the metric into the rates that drive it, and say which one you would check first.
State what result would change your recommendation, so the answer is falsifiable.

Follow-up

What would you do if the primary metric and the guardrail moved in opposite directions?
How would you detect that the metric is being gamed rather than genuinely improving?

How do you balance long-term user retention with short-term engagement metrics?

Medium · product sense and metrics

Approach

Name one primary metric, then the guardrail that stops it being gamed.
Restate the decision this analysis has to support, and who acts on the answer.
Decompose the metric into the rates that drive it, and say which one you would check first.

Follow-up

Which segment would you cut first, and what would that rule out?
What would you do if the primary metric and the guardrail moved in opposite directions?

What are the most common experimentation pitfalls you encounter when helping customers scale their testing programs?

Medium · a/b testing and experimentation

Approach

Say whether units interfere with each other, and switch design if they do.
Name the guardrails that would stop a launch even on a positive primary result.
Name the randomisation unit first; it decides the variance and what the test can detect.

Follow-up

What would you conclude if the result is positive but the test is underpowered?
What would you do if you could not randomise at all?

Explain the difference between frequentist and Bayesian approaches to statistical significance in an A/B test.

Medium · a/b testing and experimentation

Approach

Name the randomisation unit first; it decides the variance and what the test can detect.
State the primary metric and the minimum effect worth shipping, then size the test.
Say whether units interfere with each other, and switch design if they do.

Follow-up

What would you do if you could not randomise at all?
How would you handle interference between treated and control units?

Define success for a rebuilt first-run onboarding checklist

Easy · activation · metric tree · cohorts

A rebuilt first-run checklist ships to all new signups next month. You have dim_user (user_id, account_created_at_utc, signup_surface, is_internal) and fct_event (user_id, occurred_at_utc, is_core_action, event_name, surface). Propose a primary metric with an explicit numerator, denominator, window and publication lag, plus two guardrails and one diagnostic you would refuse to treat as success. The team wants a number it can read weekly, and the constraint is that everything must be computable from those two tables alone. Deliver the metric tree from the north star down to the metric you chose.

Approach

Fix the grain and the cohort key first: the checklist is seen by users, so count on user_id with account_created_at_utc as the cohort key, and say out loud that the north star is account-grained so the tree crosses grains here deliberately rather than by accident.
Take seven-day activation as the primary — core action on at least 2 distinct UTC dates inside [account_created_at_utc, +7 days) — because the two-distinct-days predicate cannot be satisfied by the single checklist-completion click the feature itself produces.
Demote checklist completion rate to a diagnostic and give the reason: it is an output of the feature, so it is near-perfectly correlated with having shipped the feature and cannot fall when the feature is bad.
Pick guardrails by the failure each one catches, not by what is easy to query: week-4 signup-cohort retention catches an activation gain that does not persist, and p50 minutes to first core action catches a checklist that adds steps to a path users already completed.
State the operational rules explicitly: is_internal = FALSE, an 8-day publication lag, and signup_surface values 'invite' and 'sso_provisioned' split out because those users arrive through an administrator rather than a self-serve signup and may not be shown the checklist at all.

Worked solution (20 min)

Write the primary in full: numerator = cohort users with is_core_action = TRUE events on at least 2 distinct UTC dates in [account_created_at_utc, +7 days); denominator = all dim_user rows in the cohort week with is_internal = FALSE.
Draw the tree downward: weekly active accounts completing a core action, then seven-day activation rate multiplied by weekly signups, then checklist step completion and time-to-first-core-action labelled as diagnostics.
Attach the timing rules: 8-day lag, and a cohort with fewer than seven full elapsed days published blank rather than partial.
Attach each guardrail to its named failure mode in one line each, so the guardrail list reads as a list of specific risks rather than a list of metrics.
Write the exclusion rule and the surface split, and state what you would do if 'invite' users turn out to be a third of the cohort.

Expected result: A primary metric stated as numerator, denominator, window, lag and exclusions; two guardrails each tied to a named failure mode; and checklist completion explicitly demoted to a diagnostic with the reason given.

Verify it yourself

The denominator includes cohort users who never returned. If it is built from users with any event, the metric is conditioned on survival and will read several points too high.
Recomputing a cohort's activation rate three days after first publication must return the same number. If it moves, the right-hand window bound or the late-arrival rule is missing.
The per-surface cohort counts must sum to the unsplit cohort count, so confirm signup_surface IN ('invite','sso_provisioned') is broken out rather than dropped. Note the limit while you are there: neither dim_user nor fct_event carries a pre-signup identifier, so whether those users were ever shown the checklist is not answerable from these two tables — the surface split is the only handling available, and the metric definition has to say that rather than imply exposure was verified.

Follow-up

Activation rises three points but week-4 retention is flat. What do you tell the team, and what would you need to distinguish a real gain from pulled-forward activity?
The checklist ships on web only. What changes in the denominator, and what breaks if you leave every surface in?
Signup mix shifted toward 'invite' the same week. How would you show whether the activation move was mix or behaviour?

Tell a pipeline outage from a collapse in usage

Medium · pipeline-failure · instrumentation · event-volume

Weekly active accounts completing a core action fell 9%, and almost the entire fall sits in accounts whose events carry surface = 'ios'. App crash rates and store reviews are unchanged. You have fct_event with occurred_at_utc, received_at_utc, event_name, is_core_action, app_version and surface, plus fct_session and the ingestion job run log. Establish within the hour whether iOS engagement fell or iOS events stopped arriving, name the evidence that distinguishes them, and say what you would publish on the dashboard in the meantime.

Approach

Compare the event-name composition inside surface = 'ios' against the prior four weeks as shares, not counts. A behaviour collapse scales most event names together; a dropped event definition or a broken downstream filter hits specific event_name values while page_view and session-opening events hold steady. That shape difference is the fastest discriminator available.
Profile the received_at_utc minus occurred_at_utc distribution per day for surface = 'ios'. A stalled-then-backfilling pipeline shows a fat upper tail and a recovering p99; a silently dropped stream shows an unchanged lag distribution over a smaller volume. The two failure modes have different remedies and different histories.
Cut by app_version. A logging SDK change arrives with one build and ramps with its adoption curve; an infrastructure fault arrives across every build within the same hour. Checking this costs one group-by and rules out half the hypothesis space.
Cross-check against a signal that does not travel the suspect path: server-emitted events with session_id NULL, and subscription or billing activity for the same accounts. If those accounts are still transacting, the users did not leave.
Publish an ex-iOS total with an explicit annotated break rather than a blended total. A blended number during a known ingestion gap is wrong in a direction you can already name, and republishing it daily spreads the artefact into every downstream report.

Follow-up

Suppose the events do eventually backfill. What is your policy for restating the published weekly numbers, and who needs to be told?
What monitor would have caught this before a human noticed the weekly metric, and what would it alert on?
If is_core_action is maintained in the tracking plan, what governance would stop a change to that list from silently moving a north-star metric?

Suggested practice checklist

Four days spend equal time on query work, statistics, modelling and product judgement at deliberately shallow depth, which produces a scored map of where you actually stand. The last three days spend everything on the two areas the role weights most, and close by re-running day one to measure movement.

Day 1 — Breadth pass: query fluency

Solve six prompts spanning aggregation, joins, window functions and date arithmetic in 60 minutes total, stopping at 10 minutes each whether or not it works, and mark every prompt as solved, solved slowly, or stuck.
For each unsolved prompt write the single blocking sentence (I lost the grain, I did not know the frame clause, I could not express the date boundary) instead of reading the solution.
Translate one pandas transformation you know well into SQL and one SQL query into pandas, checking that both return the same row count and the same totals.

Deliverable: A scored six-row table, one line per prompt, saved for the day-seven re-run.

Day 2 — Breadth pass: statistics and inference

Answer ten short questions in writing with nothing open: what a p-value is conditional on, what a 95 percent interval covers across repeated samples, when a paired test is the right one, what the bootstrap estimates, why multiple comparisons inflate false positives, how controlling the family-wise error rate differs from controlling the false discovery rate, what power depends on, what a missed real effect costs a product, the three situations where the central limit theorem does not rescue you (small n, very heavy tails, dependent observations), and what a standard error is the standard deviation of.
Grade yourself against a reference and count only the answers that were exactly right, not the ones that were nearly right.
Rewrite the two weakest answers the following morning from memory in full sentences.

Deliverable: Ten graded answers with an honest count of exact hits.

Day 3 — Breadth pass: modelling

Take one tabular dataset end to end in 90 minutes: a leakage-safe split, a baseline that is not a model (majority class or historical mean), one regularized linear model, one gradient-boosted tree, and a single evaluation metric chosen before you look at any result.
Write why that metric fits the cost structure: precision at a fixed recall for alerting, calibration for anything feeding a price or a threshold, ranking metrics for retrieval, and note that area under the ROC curve is insensitive to class balance in a way that can flatter a rare-positive problem.
Name the leak you were most likely to introduce (an encoding fit on all rows before splitting, or a feature computed after the label's timestamp) and write the check that would have caught it.

Deliverable: A notebook whose first cell states the metric and the baseline, plus two lines on what beat what and by how much.

Day 4 — Breadth pass: product judgement

Answer three case prompts aloud at 15 minutes each, timing how long passes before you state a success metric.
For one case write the first segmentation you would run and the row counts you expect per segment, so that a tiny segment cannot quietly drive the conclusion.
Take a metric definition you did not write, from a public dashboard, a textbook, or documentation you already have open, and list every place two analysts implementing it would diverge: which rows the denominator admits, whether the unit is an account or a person, what the time window is anchored to, and what happens to data that arrives late. Then write the one question that would close the largest of those gaps.

Deliverable: Three recorded case answers plus an ambiguity list for a metric someone else defined, ending in the single question you would ask about it.

Day 5 — Depth, first area

Rank the four areas by how many bullet points in the role description each one covers, pick the top one, and spend the entire day inside it.
Work the six hardest problems you can find in that area and for each write the generalizable move you should have reached for first, rather than the answer.
Re-solve the two you failed the same evening with notes closed.

Deliverable: Six generalizable moves written as instructions to yourself, not as solutions.

Day 6 — Depth, second area, and the seam between them

Repeat the depth protocol on the second-ranked area with the same six-problem structure.
Construct one problem that requires both areas at once, for example a metric redefinition whose effect you must validate with a test whose readout you then have to query.
Solve your own combined problem end to end and note where the handoff between the two areas cost you time.

Deliverable: One combined problem, solved end to end, with the handoff failure written down.

Day 7 — Integration and re-measurement

Re-run the six prompts from day one under the same clock and compare both correctness and time.
Run a 60-minute mixed mock that moves between areas without warning, since switching cost is what breadth passes do not train.
Write the two areas you would still fail on, and the sentence you will use in the interview when you hit one of them.

Deliverable: A before-and-after score table plus a written plan for the two remaining gaps.

Your part, not the team's

Most data work is done by groups, so an interviewer has to work out which piece was yours. An answer that runs on 'we' for several minutes gets interrupted with a question about what you personally did, and by then the answer sounds defensive even when it is true. Mark your own contribution as you go, and name the parts that belonged to someone else instead of leaving them ambiguous. Keep a few specifics back as well, like the name of the metric or who actually objected, so a probe can be answered with something you had not already said.

Give an example of a time you took ownership of a project that was failing. What did you do to turn it around?

Medium · behavioural and stakeholder questions

Approach

Pick a story where you drove the decision, not one where you observed it.
State the situation in two sentences and spend the rest on your reasoning.
Quantify the outcome, including what you would not claim credit for.

Follow-up

What did you decide not to do, and why?
How did you know the outcome was caused by your change?

Walk through an analysis you got wrong and what changed

Easy · postmortem · data quality · self-assessment

Describe an analysis of yours that turned out to be wrong after somebody had already acted on it. You have four minutes. The account must name the defect mechanically, the join, the filter, the window or the identity key, rather than describing it as a communication problem. It must also say who did what because of the wrong number, how the error surfaced, how long it stood, and what control you put in place so that class of error cannot reach a decision again. Do not pick an error nobody acted on.

Approach

Recognise what is being probed: whether you can be specific about your own failure without minimising it or performing contrition. The discriminator is whether the defect has a mechanism the listener could reproduce in their own warehouse.
Choose the case by blast radius rather than by comfort. An error nobody acted on tests nothing, and picking one signals that you are managing the interview instead of answering it.
Structure the account in six beats: the number, the decision it drove, the defect, the detection, the correction, the control. Keep the defect to one reproducible sentence, for example an inner join to fct_subscription_period that dropped accounts with no subscription row and so computed retention over payers only.
State the direction of the bias, not only its existence. A filter or join that removes rows usually moves a metric predictably, and knowing which way shows you diagnosed the mechanism rather than patched the symptom.
Be exact about detection and elapsed time. 'A colleague noticed' and 'the row-count assertion failed before publication' are different answers about the same organisation, and the second one is the one your control is supposed to produce next time.
End on the control, its cost, whether it has fired since, and one thing it does not cover.

Follow-up

What did the control cost, and has it fired since? If it never has, how do you know it works?
How long did the wrong number stand before anyone questioned it, and what does that say about the review path it went through?
What is the equivalent mistake you are most likely to make in this role, given the tables you would be working in?

Explain a wide interval to a non-technical executive

Medium · communication · uncertainty · pricing

A pricing change is under consideration. Your best estimate of its effect on trial-to-paid conversion is a 1.8pp drop, with a 95% interval from a 4.6pp drop to a 1.0pp rise, read from a geo holdout rather than a randomised test. An executive preparing a board slide asks you for 'the number'. You have ninety seconds and one slide, and the words confidence interval, p-value and significance are not usable with this audience. Deliver the slide headline, the single supporting line, and what you say aloud.

Approach

Recognise what is being probed: whether you can carry uncertainty into a decision instead of either hiding it or hiding behind it. The generic answer promises to explain the interval in plain English; the strong one replaces the question 'what is the number' with 'across this range, where does the decision change'.
Find the threshold before you draft anything. Ask what the pricing case assumes, then compute the conversion drop at which the higher price stops adding revenue: price uplift on the conversions kept against the revenue lost from conversions forgone. That single figure is what makes the range legible.
Restate the estimate and both bounds in the unit the audience already reasons in. Convert percentage points into monthly first-paid conversions at current trial volume, then into mrr_cents_constant_fx, so the slide reads as money per month rather than as statistics.
Place the range against the break-even and say which part of it sits on each side. If most of the range clears the threshold, that is a recommendation to proceed with a monitoring plan; if the range straddles it, that is a recommendation to narrow the range first.
Name what would narrow it and what that costs in weeks, then give one recommendation with an explicit condition for revisiting it. Uncertainty stated without a next step is read as indecision and the midpoint gets used anyway.

Follow-up

The executive says to give the midpoint and they will manage the risk. What do you do?
How does the slide change if the interval were a 4.6pp to 0.2pp drop, with no positive outcomes in range?
Why is a geo holdout the credible read here rather than the attributed channel numbers you already have?