# HVAC.Science > HVAC.Science is a digital marketing and business consulting service for HVAC and heating companies in Canada. We are not an HVAC contractor and do not install or repair equipment. Owners and marketing leads of HVAC and heating companies across Canada who want proof before they spend HVAC.Science is part of the Sedighi.ca and SAZ.ca group of companies, a Canadian business headquartered in Vancouver, British Columbia, led by Ali Sedighi, MBA. Coverage: Canada. Contact: call or text (604) 632-4959, or email Ali@Sedighi.ca. There are no forms: call, text or email only. ## Key pages - [Home](https://hvac.science/): HVAC.Science brings experimental method to HVAC marketing: clean lead measurement, tests sized for your real traffic, and holdouts that show what your ads actually add. We serve heating and cooling companies across Canada. - [Services](https://hvac.science/services/): We offer four services that follow one sequence: find the leak, measure it properly, test a fix, then check that the fix and your ad spend are really adding jobs. - [Areas](https://hvac.science/areas/): We work with HVAC companies in every province and territory. The method stays the same everywhere; what changes is when you can test, which services have the volume to test, and which outside events can distort a result. - [About](https://hvac.science/about/): HVAC.Science is the testing and measurement arm of our HVAC marketing work. It is Canadian, based in Vancouver, part of the Sedighi.ca and SAZ.ca group, and led by Ali Sedighi, MBA. - [Results](https://hvac.science/results/): These are real, named outcomes from our HVAC marketing work. They are portfolio results, not controlled experiments, so we explain what each one shows and which lessons transfer to a testing program. - [Pricing](https://hvac.science/pricing/): HVAC.Science uses HVAC.Agency family pricing: monthly plans from $2,998 and websites from $3,500, in Canadian dollars. Here is what each plan covers, what drives cost, and how to pick one for a testing program. - [FAQ](https://hvac.science/faq/): Short, direct answers about price, contracts, timelines, ownership, reporting and what testing can and cannot do for an HVAC company. - [Contact](https://hvac.science/contact/): Call, text or email, whichever is easiest. One number handles calls and texts, (604) 632-4959, and email reaches Ali@Sedighi.ca directly. ## Services - [Conversion research](https://hvac.science/services/conversion-research/): Before anything is redesigned or tested, we find out where homeowners drop off and why, using your own analytics, calls and pages. You get a ranked list of problems with the evidence for each. - [CRO experiments](https://hvac.science/services/cro-experiments/): We design, build and read conversion tests for HVAC websites. Each test is sized for your actual traffic, has its stopping rule written before launch, and is judged on qualified leads rather than clicks. - [Holdout testing](https://hvac.science/services/incrementality-testing/): Attribution says which ad was clicked before a call. A holdout says whether the call would have come anyway. We design and read holdouts so you can move budget from spend that only takes credit to spend that adds jobs. - [Measurement setup](https://hvac.science/services/measurement-setup/): If GA4, Google Ads and your office disagree about how many leads you had, every later decision is built on sand. We fix the counting first, so you can trust the numbers you test and spend on. ## Coverage - [Alberta](https://hvac.science/areas/alberta/): Alberta's HVAC demand is gas-heated, cold and concentrated in two large metros. That gives you volume to test, expensive clicks worth checking with holdouts, and chinooks that can fake a result in a week. - [British Columbia](https://hvac.science/areas/british-columbia/): BC is really two heating markets: a mild, wet coast and a much colder Interior and North. Any test plan has to respect that split, along with the CleanBC rebate changes of July 2026. - [Manitoba](https://hvac.science/areas/manitoba/): Manitoba concentrates most HVAC demand in Winnipeg and has one of southern Canada's longest heating seasons. Its active heat-pump programs make program dates a key part of any test plan. - [New Brunswick](https://hvac.science/areas/new-brunswick/): New Brunswick is a small, bilingual market where heat pumps are already a main heating system in many homes. Tests need low-volume designs, language segments and a careful eye on program dates. - [Newfoundland and Labrador](https://hvac.science/areas/newfoundland-and-labrador/): Newfoundland and Labrador is electrically heated, has a long, windy heating season on the island and a far colder one in Labrador, and runs on its own half-hour time zone. Each detail affects how tests are scheduled and measured. - [Nova Scotia](https://hvac.science/areas/nova-scotia/): Nova Scotia's heating base is unusually mixed, with oil, electricity and heat pumps all significant, and its rebate programs changed several times in 2025 and 2026. Both facts shape how a test must be read. - [Ontario](https://hvac.science/areas/ontario/): Ontario has more testable HVAC traffic than anywhere else in Canada, which makes classic split tests practical for many companies. It also has Save on Energy programs and a north-south climate gap to plan around. - [Prince Edward Island](https://hvac.science/areas/prince-edward-island/): PEI is too small for most classic A/B tests, and heat pumps are already the most common main heating system. Measurement, research and a few bold, well-timed tests are the realistic program. - [Quebec](https://hvac.science/areas/quebec/): Quebec is electrically heated, French-first and full of dated program changes. Each of those shapes test design: which pages have volume, which variants you may run, and which weeks a result can be trusted. - [Saskatchewan](https://hvac.science/areas/saskatchewan/): Saskatchewan's HVAC markets are smaller than Alberta's, so most companies need low-volume test designs. The upside is a stable, gas-heated winter and one dated rebate change to plan around. - [Territories](https://hvac.science/areas/territories/): In the territories, classic A/B tests are rarely possible. Markets are small and dispersed, heating runs most of the year, and Nunavut requires Inuktut in commercial advertising. Careful measurement is the core of the work. ## Guides and articles - [Newsroom](https://hvac.science/news/): Eight method pieces on how to test, measure and read HVAC marketing data. Each one is built on official Google documentation we loaded ourselves and on standard statistics explained in plain language. - [Sample size maths](https://hvac.science/news/ab-test-sample-size-and-duration/): Before you launch a test, decide the smallest lift worth detecting, then let the formula tell you how many visitors that takes. For most HVAC sites the answer is weeks, not days. - [Call tracking](https://hvac.science/news/call-tracking-and-attribution/): Most HVAC leads arrive by phone, so attribution rests on how calls are recorded. Separate calls from ads, calls from the website and taps on a number, then pick one attribution model and stick with it. - [Ads experiments](https://hvac.science/news/google-ads-experiments-and-offline-conversions/): A Google Ads experiment is only as smart as the conversion it optimizes for. Pair custom experiments with offline conversion imports so tests are judged on booked HVAC jobs, not on calls or clicks. - [Holdout tests](https://hvac.science/news/holdout-tests-for-hvac-ads/): Attribution reports tell you which ad was clicked before a call. A holdout tells you whether the call would have happened anyway. For brand search and remarketing, the gap can be large. - [Reading GA4](https://hvac.science/news/reading-ga4-for-hvac-leads/): GA4 rarely lies, but it often answers a slightly different question from the one you asked. Five settings and behaviours explain most of the confusion HVAC owners run into. - [Reading results](https://hvac.science/news/reading-test-results-with-intervals/): A test result is a range of plausible effects, not a single winning number. Read the interval, compare it with what a change is worth to your business, and only then decide. - [Seasonality controls](https://hvac.science/news/seasonality-controls-for-heating-tests/): In HVAC, the weather moves demand more than any page change. A test is only readable if something in its design cancels out the season: a concurrent control, a demand index or a matched comparison. - [Testing with few calls](https://hvac.science/news/testing-with-few-calls/): A shop with 40 calls a month can still learn from experiments. It has to change how it measures and how it decides, not pretend it has the traffic of a national brand. ## Optional - [Full text](https://hvac.science/llms-full.txt) - [Parent company](https://hvac.agency)