{"id":7031,"date":"2026-03-23T21:47:45","date_gmt":"2026-03-23T21:47:45","guid":{"rendered":"https:\/\/www.wizbrand.com\/tutorials\/causal-impact\/"},"modified":"2026-03-23T21:47:45","modified_gmt":"2026-03-23T21:47:45","slug":"causal-impact","status":"publish","type":"post","link":"https:\/\/www.wizbrand.com\/tutorials\/causal-impact\/","title":{"rendered":"Causal Impact: What It Is, Key Features, Benefits, Use Cases, and How It Fits in Attribution"},"content":{"rendered":"\n

Causal Impact is the discipline of estimating what actually changed<\/em> because of a marketing action\u2014separating true incremental lift from changes that would have happened anyway. In Conversion & Measurement<\/strong>, it answers the question every team eventually faces: \u201cDid this campaign cause more conversions, or did we just observe them?\u201d In Attribution<\/strong>, it provides the missing ingredient that correlation-based reporting often can\u2019t: a credible counterfactual, or \u201cwhat would have happened without the marketing.\u201d<\/p>\n\n\n\n

Causal Impact matters because modern marketing is noisy. Seasonality, promotions, pricing changes, competitor moves, and algorithm shifts can all influence performance at the same time. Without causal thinking, teams may over-credit channels, underfund high-impact programs, and optimize toward metrics that look good in dashboards but don\u2019t drive incremental business outcomes. When Causal Impact is embedded into your Conversion & Measurement strategy, you can make decisions with confidence\u2014especially when budgets tighten and accountability rises.<\/p>\n\n\n\n

What Is Causal Impact?<\/h2>\n\n\n\n

Causal Impact<\/strong> is a set of methods used to estimate the incremental effect<\/em> of an intervention (like a campaign, feature launch, bid change, or email program) on an outcome (like conversions, revenue, sign-ups, or retention). The key idea is comparing reality to a counterfactual<\/strong>: an estimate of what would have happened if the intervention had not<\/em> occurred.<\/p>\n\n\n\n

At a beginner level, you can think of it as:\n– Observed outcome<\/strong> = what you measured after the campaign\n– Baseline (counterfactual)<\/strong> = what likely would have happened without it\n– Causal impact<\/strong> = observed outcome \u2212 baseline<\/p>\n\n\n\n

The business meaning is straightforward: Causal Impact helps you quantify true lift so you can allocate spend and effort to what drives growth. In Conversion & Measurement<\/strong>, it sits at the intersection of analytics, experimentation, and decision-making. Within Attribution<\/strong>, it complements or corrects multi-touch and last-click models by focusing on incrementality rather than credit assignment based purely on touchpoint presence.<\/p>\n\n\n\n

Why Causal Impact Matters in Conversion & Measurement<\/h2>\n\n\n\n

Causal Impact is strategically important because most marketing data is observational, not experimental. Users self-select into channels, platforms optimize delivery, and budgets change over time\u2014creating confounding factors that can mislead standard reporting.<\/p>\n\n\n\n

In practical Conversion & Measurement<\/strong> work, Causal Impact delivers value by helping you:<\/p>\n\n\n\n

    \n
  • Avoid false wins:<\/strong> A conversion spike might be caused by seasonality or PR, not ads. <\/li>\n
  • Detect hidden value:<\/strong> Some channels (e.g., upper-funnel) may show weak last-click Attribution<\/strong> but strong incremental lift. <\/li>\n
  • Improve budget allocation:<\/strong> Fund what causes lift, not what merely correlates with conversions. <\/li>\n
  • Support executive decisions:<\/strong> Incrementality-based measurement is easier to defend than \u201cthe model says so.\u201d<\/li>\n<\/ul>\n\n\n\n

    Organizations that operationalize Causal Impact gain a competitive advantage: they learn faster, waste less spend, and optimize with fewer measurement blind spots\u2014especially when privacy changes reduce user-level tracking.<\/p>\n\n\n\n

    How Causal Impact Works<\/h2>\n\n\n\n

    Causal Impact is more of a practical measurement workflow than a single metric. In Conversion & Measurement<\/strong>, it typically follows a repeatable process:<\/p>\n\n\n\n

      \n
    1. \n

      Input (intervention + outcome definition)<\/strong>\n You define the action being evaluated (e.g., launching a new paid search campaign) and the success metric (e.g., purchases, qualified leads, revenue). You also specify the timing (pre\/post period) and unit of analysis (user, geo, store, market, or time series).<\/p>\n<\/li>\n

    2. \n

      Analysis (build a credible counterfactual)<\/strong>\n You estimate what would have happened without the intervention. This might be done with randomized experiments, matched control groups, or statistical time-series modeling. The goal is to reduce bias from confounders like seasonality, demand shifts, or concurrent campaigns.<\/p>\n<\/li>\n

    3. \n

      Execution (validate assumptions and run the study)<\/strong>\n You check balance between test\/control groups, ensure tracking is stable, verify no major contamination, and run diagnostics (e.g., pre-period fit, placebo tests, sensitivity checks). This step is where many Attribution<\/strong> disagreements get resolved: the method forces clarity about what\u2019s being measured.<\/p>\n<\/li>\n

    4. \n

      Output (incrementality + uncertainty)<\/strong>\n You produce an estimate of lift (absolute and percent), plus uncertainty (confidence or credible intervals). The output is used to decide: scale, pause, refine targeting, change creative, adjust bids, or re-allocate budget across channels.<\/p>\n<\/li>\n<\/ol>\n\n\n\n

      Key Components of Causal Impact<\/h2>\n\n\n\n

      Strong Causal Impact measurement depends on several components working together:<\/p>\n\n\n\n

      Data inputs<\/h3>\n\n\n\n
        \n
      • Conversion events (purchases, leads, subscriptions) and revenue<\/li>\n
      • Spend, impressions, clicks, reach, frequency<\/li>\n
      • Time variables (day-of-week, seasonality, holidays)<\/li>\n
      • Context signals (pricing changes, promotions, inventory, competitor actions)<\/li>\n
      • Segmentation attributes (geo, device, audience cohorts)<\/li>\n<\/ul>\n\n\n\n

        Measurement processes<\/h3>\n\n\n\n
          \n
        • Experiment design or quasi-experimental design selection<\/li>\n
        • Pre\/post period selection and sanity checks<\/li>\n
        • Data quality monitoring (tagging consistency, pipeline stability)<\/li>\n
        • Clear rules for inclusion\/exclusion (e.g., excluding outage periods)<\/li>\n<\/ul>\n\n\n\n

          Metrics and reporting<\/h3>\n\n\n\n
            \n
          • Incremental conversions and incremental revenue<\/li>\n
          • Incremental ROAS \/ iROAS and marginal ROI<\/li>\n
          • Confidence intervals and decision thresholds<\/li>\n
          • Documentation of assumptions and limitations<\/li>\n<\/ul>\n\n\n\n

            Governance and responsibilities<\/h3>\n\n\n\n
              \n
            • Marketing owns hypotheses and decision-making criteria<\/li>\n
            • Analytics\/data science owns method selection, validity checks, and uncertainty quantification<\/li>\n
            • Engineering\/data engineering ensures event tracking and pipelines support Conversion & Measurement<\/strong><\/li>\n
            • Finance ensures incrementality maps to business accounting and budgeting<\/li>\n<\/ul>\n\n\n\n

              Causal Impact isn\u2019t only a model\u2014it\u2019s an operating system for trustworthy Attribution<\/strong> decisions.<\/p>\n\n\n\n

              Types of Causal Impact<\/h2>\n\n\n\n

              Causal Impact doesn\u2019t have \u201ctypes\u201d in the way ad formats do, but there are common approaches and contexts used in Conversion & Measurement<\/strong>:<\/p>\n\n\n\n

              1) Randomized experiments (A\/B tests)<\/h3>\n\n\n\n

              The gold standard when feasible. Random assignment reduces confounding and makes causal interpretation straightforward. Examples include conversion lift tests, holdouts, or randomized geo experiments.<\/p>\n\n\n\n

              2) Quasi-experimental methods<\/h3>\n\n\n\n

              Used when randomization is difficult or impossible:\n– Difference-in-differences:<\/strong> Compare changes over time between a treated group and a control group.\n– Synthetic control \/ time-series counterfactuals:<\/strong> Build a baseline from a weighted combination of similar markets or pre-period patterns.\n– Matching and propensity scoring:<\/strong> Construct comparable groups from observational data.<\/p>\n\n\n\n

              3) Incrementality by level of aggregation<\/h3>\n\n\n\n
                \n
              • User-level impact:<\/strong> Powerful but increasingly constrained by privacy and tracking limitations. <\/li>\n
              • Geo\/store-level impact:<\/strong> Common for omnichannel brands and offline conversions. <\/li>\n
              • Time-series impact:<\/strong> Useful when interventions apply broadly (e.g., site-wide change).<\/li>\n<\/ul>\n\n\n\n

                Each approach shapes what you can claim in Attribution<\/strong> and how confidently you can tie marketing to business outcomes.<\/p>\n\n\n\n

                Real-World Examples of Causal Impact<\/h2>\n\n\n\n

                Example 1: Measuring incremental lift of branded search<\/h3>\n\n\n\n

                A brand sees strong branded search performance in last-click Attribution<\/strong> and assumes it\u2019s the primary growth driver. They run a controlled holdout in select geographies (or a time-based holdout with safeguards) to estimate Causal Impact on total conversions. The result often shows that branded search captures demand created elsewhere; incremental lift may be lower than last-click suggests. In Conversion & Measurement<\/strong>, this leads to a reallocation toward channels that create demand, while maintaining enough branded coverage to protect against competitors.<\/p>\n\n\n\n

                Example 2: Evaluating a new lifecycle email series<\/h3>\n\n\n\n

                A team launches a new onboarding email sequence and observes a higher conversion rate among recipients. But recipients might already be higher intent. Using a randomized holdout (some new users do not receive the series), the team measures Causal Impact on activation and purchases. The analysis reveals true incremental lift and identifies which messages drive it, improving both Attribution<\/strong> and lifecycle optimization.<\/p>\n\n\n\n

                Example 3: Assessing a paid social creative refresh<\/h3>\n\n\n\n

                A creative refresh coincides with a seasonal spike. Standard reporting credits the new creatives, but the team uses a geo-split test to isolate the change. They estimate Causal Impact on incremental revenue and iROAS. The outcome shows modest lift overall, but significant lift in a specific audience cohort\u2014guiding smarter scaling and targeting within the overall Conversion & Measurement<\/strong> plan.<\/p>\n\n\n\n

                Benefits of Using Causal Impact<\/h2>\n\n\n\n

                When Causal Impact is integrated into Conversion & Measurement<\/strong>, teams commonly gain:<\/p>\n\n\n\n

                  \n
                • More accurate ROI:<\/strong> Incremental revenue and iROAS outperform naive ROAS for decision-making. <\/li>\n
                • Lower wasted spend:<\/strong> Reduced investment in channels that \u201cget credit\u201d but don\u2019t drive lift. <\/li>\n
                • Faster learning cycles:<\/strong> Clear hypotheses and test structures speed up optimization. <\/li>\n
                • Better customer experience:<\/strong> Fewer redundant touches (e.g., over-retargeting) once you know what truly moves outcomes. <\/li>\n
                • Stronger cross-team alignment:<\/strong> Finance, marketing, and analytics can agree on a shared definition of impact\u2014improving Attribution<\/strong> governance.<\/li>\n<\/ul>\n\n\n\n

                  Challenges of Causal Impact<\/h2>\n\n\n\n

                  Causal Impact is powerful, but it\u2019s not effortless. Common challenges include:<\/p>\n\n\n\n

                    \n
                  • Confounding and contamination:<\/strong> Test and control groups may not be truly comparable, or marketing spillover can blur results. <\/li>\n
                  • Insufficient scale:<\/strong> Small budgets or low conversion volume can produce wide uncertainty intervals. <\/li>\n
                  • Measurement gaps:<\/strong> Offline conversions, delayed conversions, and incomplete event tracking can weaken Conversion & Measurement<\/strong> quality. <\/li>\n
                  • Concurrent changes:<\/strong> Pricing updates, site releases, PR events, or stock issues can invalidate assumptions. <\/li>\n
                  • Organizational friction:<\/strong> Teams accustomed to deterministic Attribution<\/strong> may resist results that contradict familiar dashboards. <\/li>\n
                  • Privacy constraints:<\/strong> User-level tracking limitations push teams toward aggregated methods that require stronger statistical rigor.<\/li>\n<\/ul>\n\n\n\n

                    The solution is not to abandon causal methods, but to right-size them and document uncertainty clearly.<\/p>\n\n\n\n

                    Best Practices for Causal Impact<\/h2>\n\n\n\n

                    To make Causal Impact dependable and repeatable in Conversion & Measurement<\/strong>, apply these practices:<\/p>\n\n\n\n

                      \n
                    1. \n

                      Start with a decision, not a dashboard<\/strong>\n Define what you will do based on outcomes (scale\/pause\/shift budget) before running the analysis.<\/p>\n<\/li>\n

                    2. \n

                      Prefer randomization when feasible<\/strong>\n Even small, well-designed holdouts can outperform complex observational Attribution<\/strong> models.<\/p>\n<\/li>\n

                    3. \n

                      Choose the right unit of randomization<\/strong>\n Use user-level when possible; use geo or time when user-level is constrained or spillover is high.<\/p>\n<\/li>\n

                    4. \n

                      Protect the experiment<\/strong>\n – Keep targeting rules stable during the test\n – Avoid overlapping experiments in the same populations\n – Monitor spend delivery and frequency to prevent drift<\/p>\n<\/li>\n

                    5. \n

                      Validate with pre-period checks and placebo tests<\/strong>\n If your model can\u2019t fit the pre-period, it\u2019s unlikely to estimate credible Causal Impact post-intervention.<\/p>\n<\/li>\n

                    6. \n

                      Report uncertainty explicitly<\/strong>\n Present lift ranges and confidence\/credible intervals, not only point estimates. In executive settings, uncertainty increases trust.<\/p>\n<\/li>\n

                    7. \n

                      Operationalize learnings into Attribution and planning<\/strong>\n Use incrementality results to calibrate channel weights, bidding strategies, and budget forecasts.<\/p>\n<\/li>\n<\/ol>\n\n\n\n

                      Tools Used for Causal Impact<\/h2>\n\n\n\n

                      Causal Impact is not tied to a single product category, but it relies on an ecosystem of tools that support Conversion & Measurement<\/strong> and Attribution<\/strong>:<\/p>\n\n\n\n

                        \n
                      • Analytics tools:<\/strong> Event analytics and web\/app analytics to define conversions, segments, and funnels. <\/li>\n
                      • Experimentation platforms:<\/strong> A\/B testing and feature flag systems to randomize exposure and manage holdouts. <\/li>\n
                      • Ad platforms:<\/strong> For running controlled lift tests, geo experiments, and budget split tests (when supported). <\/li>\n
                      • CRM and marketing automation:<\/strong> For lifecycle experiments, suppression lists, and controlled messaging. <\/li>\n
                      • Data warehouses and pipelines:<\/strong> To join spend, exposure, and conversion data reliably and reproducibly. <\/li>\n
                      • Reporting dashboards \/ BI:<\/strong> To communicate incremental lift, uncertainty, and business impact across stakeholders. <\/li>\n
                      • Statistical computing environments:<\/strong> For time-series modeling, synthetic controls, and robustness checks.<\/li>\n<\/ul>\n\n\n\n

                        The most important \u201ctool\u201d is often the process: disciplined experiment design and governance around Conversion & Measurement<\/strong> definitions.<\/p>\n\n\n\n

                        Metrics Related to Causal Impact<\/h2>\n\n\n\n

                        Causal Impact shifts attention from \u201ccredited\u201d performance to incremental outcomes. Common metrics include:<\/p>\n\n\n\n

                          \n
                        • Incremental conversions:<\/strong> Additional conversions caused by the intervention. <\/li>\n
                        • Incremental revenue \/ profit:<\/strong> Lift in revenue, ideally tied to gross margin where possible. <\/li>\n
                        • Incremental ROAS (iROAS):<\/strong> Incremental revenue divided by incremental spend; more decision-useful than standard ROAS. <\/li>\n
                        • Cost per incremental acquisition (CPIA):<\/strong> Spend divided by incremental conversions. <\/li>\n
                        • Marginal ROI \/ diminishing returns:<\/strong> The incremental gain from the next dollar spent\u2014critical for budget scaling. <\/li>\n
                        • Lift percentage:<\/strong> Relative increase versus the counterfactual baseline. <\/li>\n
                        • Confidence\/credible intervals:<\/strong> The uncertainty range around lift estimates\u2014essential for trustworthy Attribution<\/strong> decisions. <\/li>\n
                        • Time-to-impact \/ lag:<\/strong> How long it takes for lift to appear (important for consideration-heavy products).<\/li>\n<\/ul>\n\n\n\n

                          Future Trends of Causal Impact<\/h2>\n\n\n\n

                          Causal Impact is evolving quickly within Conversion & Measurement<\/strong> due to technology and privacy shifts:<\/p>\n\n\n\n

                            \n
                          • Privacy-first measurement:<\/strong> As identifiers become less available, aggregated experiments (geo, cohort, time-series) will become more common, and causal modeling will move upstream into planning. <\/li>\n
                          • Automation of experimentation:<\/strong> More teams will automate holdouts, incremental lift reporting, and budget experiments to create continuous learning systems. <\/li>\n
                          • AI-assisted causal analysis:<\/strong> AI can help detect anomalies, recommend experiment designs, and accelerate modeling\u2014but it won\u2019t remove the need for causal assumptions and validation. <\/li>\n
                          • Better integration with marketing mix modeling (MMM):<\/strong> Incrementality tests will increasingly calibrate MMM outputs, improving channel-level Attribution<\/strong> at scale. <\/li>\n
                          • Incrementality as a planning standard:<\/strong> Finance-aligned forecasting will rely more on causal lift curves and marginal ROI rather than last-click reports.<\/li>\n<\/ul>\n\n\n\n

                            The direction is clear: Causal Impact becomes the backbone of resilient Conversion & Measurement<\/strong> as tracking becomes less deterministic.<\/p>\n\n\n\n

                            Causal Impact vs Related Terms<\/h2>\n\n\n\n

                            Causal Impact vs Attribution<\/h3>\n\n\n\n

                            Attribution<\/strong> assigns credit for conversions across touchpoints; it often answers \u201cwhich channels were involved?\u201d Causal Impact<\/strong> answers \u201cwhich actions caused additional conversions?\u201d Attribution can be descriptive, while Causal Impact is explicitly incremental. The strongest measurement programs use Causal Impact to validate and calibrate Attribution models.<\/p>\n\n\n\n

                            Causal Impact vs Correlation<\/h3>\n\n\n\n

                            Correlation means two variables move together; it does not prove one caused the other. Causal Impact is designed to reduce confounding and estimate what would have happened otherwise. In Conversion & Measurement<\/strong>, confusing correlation with causation is one of the most expensive mistakes teams make.<\/p>\n\n\n\n

                            Causal Impact vs A\/B Testing<\/h3>\n\n\n\n

                            A\/B testing is one method to estimate Causal Impact through randomization. Causal Impact is broader: it includes A\/B tests plus quasi-experimental and time-series approaches when randomization is impractical.<\/p>\n\n\n\n

                            Who Should Learn Causal Impact<\/h2>\n\n\n\n
                              \n
                            • Marketers:<\/strong> To make smarter budget, channel, and creative decisions beyond surface-level Attribution<\/strong>. <\/li>\n
                            • Analysts:<\/strong> To produce defensible insights, quantify uncertainty, and improve Conversion & Measurement<\/strong> credibility. <\/li>\n
                            • Agencies:<\/strong> To prove incremental value, retain clients longer, and avoid optimizing to misleading KPIs. <\/li>\n
                            • Business owners and founders:<\/strong> To understand what truly drives growth and avoid over-investing in \u201cfeel-good\u201d metrics. <\/li>\n
                            • Developers and data engineers:<\/strong> To build tracking, experimentation infrastructure, and data pipelines that enable reliable causal analysis.<\/li>\n<\/ul>\n\n\n\n

                              Summary of Causal Impact<\/h2>\n\n\n\n

                              Causal Impact estimates the incremental effect of marketing actions by comparing observed outcomes to a credible counterfactual. It matters because modern marketing data is full of confounders, and traditional Attribution<\/strong> can over-credit channels that happen to be present near conversions. Embedded into Conversion & Measurement<\/strong>, Causal Impact improves ROI decisions, increases learning speed, and creates measurement confidence by reporting lift with uncertainty\u2014turning analytics into action.<\/p>\n\n\n\n

                              Frequently Asked Questions (FAQ)<\/h2>\n\n\n\n

                              1) What is Causal Impact in marketing measurement?<\/h3>\n\n\n\n

                              Causal Impact is the estimated incremental change in conversions, revenue, or other outcomes caused by a marketing intervention, compared to what would have happened without it.<\/p>\n\n\n\n

                              2) How is Causal Impact different from standard ROAS?<\/h3>\n\n\n\n

                              Standard ROAS usually reflects credited revenue (often influenced by Attribution<\/strong> rules). Causal Impact supports incremental ROAS (iROAS), which measures revenue that was actually caused by the spend.<\/p>\n\n\n\n

                              3) Do I need randomized experiments to measure causal impact?<\/h3>\n\n\n\n

                              Randomized tests are ideal, but not required. In Conversion & Measurement<\/strong>, teams often use quasi-experimental methods like difference-in-differences, synthetic controls, or matched controls when randomization isn\u2019t feasible.<\/p>\n\n\n\n

                              4) Which is more important: Attribution or Causal Impact?<\/h3>\n\n\n\n

                              They serve different purposes. Attribution helps describe journeys and allocate credit; Causal Impact determines incrementality. For budgeting and true performance evaluation, Causal Impact is often the deciding layer that validates Attribution.<\/p>\n\n\n\n

                              5) What data do I need to run a Causal Impact analysis?<\/h3>\n\n\n\n

                              You need reliable outcome tracking (conversions\/revenue), a clear intervention date or exposure definition, enough historical data to establish baseline patterns, and contextual variables (seasonality, promos, spend) to support Conversion & Measurement<\/strong> validity.<\/p>\n\n\n\n

                              6) How long should a causal impact test run?<\/h3>\n\n\n\n

                              Long enough to capture typical conversion lag and stabilize variability. Many teams start with 2\u20136 weeks depending on volume, but the correct duration depends on conversion rates, seasonality, and the minimum detectable effect.<\/p>\n\n\n\n

                              7) What are common reasons Causal Impact results are inconclusive?<\/h3>\n\n\n\n

                              Low volume, noisy outcomes, poor control selection, overlapping campaigns, tracking issues, or major external changes (pricing, outages, inventory) can widen uncertainty and make lift hard to detect\u2014even if the intervention had some effect.<\/p>\n","protected":false},"excerpt":{"rendered":"

                              Causal Impact is the discipline of estimating what *actually changed* because of a marketing action\u2014separating true incremental lift from changes that would have happened anyway. In **Conversion & Measurement**, it answers the question every team eventually faces: \u201cDid this campaign cause more conversions, or did we just observe them?\u201d In **Attribution**, it provides the missing ingredient that correlation-based reporting often can\u2019t: a credible counterfactual, or \u201cwhat would have happened without the marketing.\u201d<\/p>\n","protected":false},"author":10235,"featured_media":0,"comment_status":"open","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[1888],"tags":[],"class_list":["post-7031","post","type-post","status-publish","format-standard","hentry","category-attribution"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/posts\/7031","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/users\/10235"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/comments?post=7031"}],"version-history":[{"count":0,"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/posts\/7031\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/media?parent=7031"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/categories?post=7031"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/tags?post=7031"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}