What is the best coding class in Mullingar?
Mullingar records 22,470 usual residents in the census town tables and 8,171 households, 6,636 of which report broadband. For a learner here, a lesson with us means a teacher on video at a fixed hour, twice in most weeks, alongside a few others working at the same stage or entirely one to one, at any age between six and sixty-seven. The introductory lesson is free. Afterwards the monthly fee is USD 100 for a group place and USD 150 for private teaching.
Most figures anybody quotes come from a survey: a few hundred people asked, and the answer scaled up. The census is different. Of the 7,440 Mullingar households that answered its internet question, 6,636 reported broadband, so the true share is known exactly: 89.19%. That makes the town a rare chance to check what a survey would have said. We ran a thousand imaginary surveys of 100 households each, drawn at random from those 7,440, with a fixed seed so anybody can repeat them. The middle 95% of those surveys reported anything from 83.0% to 95.0%, and the unluckiest said 78%. Four times as many households per survey halved the spread. That is the whole project, and it changes how a learner reads every poll for the rest of their life.
Facts last verified 19 September 2026. Teaching is online; no Mullingar branch is claimed.
Age and interest suggest a course; the introductory hour with the teacher who runs it confirms the choice.

Scratch games built on chance, where rolling the dice a hundred times teaches what one roll cannot.
See the syllabus
Probability and averages through programs that simulate thousands of trials in a second.
See the syllabus
Sampling, simulation and margins of error in Python, checked against real census data.
See the syllabus
For adults who commission surveys or read them, and want to know what the sample size is worth.
See the syllabusBrowse the course atlas for more than one hundred options and use the coding roadmap to check prerequisites.
The four we are known for
These run underneath everything above. Every one is live and online, placed by ability rather than by age, and the first class is free.

Python, web and AI projects where the learner still owns the thinking.
See the syllabus
Automate the work you already do, then let AI carry part of it.
See the syllabus
Train a model, read what it learned, and be able to say why it is wrong.
See the syllabus
Run AI coding agents on real work without losing control of the codebase.
See the syllabusA thousand simulated surveys at each of three sizes, drawn without replacement from the 7,440 Mullingar households that answered the census internet question. The truth is known: 6,636 broadband households, 89.19%. The simulation is ours, seed 20220403, and gives identical results every time it is run.
| Households per survey | Middle 95% of surveys | Most extreme of 1,000 | Formula margin |
|---|---|---|---|
| 100 | 83.0% to 95.0% | 78.0% to 98.0% | plus or minus 6.0 points |
| 400 | 86.0% to 92.0% | 84.5% to 94.5% | plus or minus 3.0 points |
| 1,600 | 87.9% to 90.5% | 86.6% to 91.4% | plus or minus 1.3 points |
Going from 100 households to 400 cut the spread from six points either side to three. Going to 1,600 cut it again. Precision improves with the square root of the sample size, which is why the last few points of accuracy are always the most expensive.
One of the thousand surveys of 100 households reported 78% and another 98%. Nobody running a single survey knows which kind they got, which is exactly why a result without its margin of error is only half a result.
At 1,600 households a survey covers over a fifth of the town, and the usual formula has to be corrected for that. With the correction it predicts 1.3 points either side, which matches what the simulation actually produced.
Voting intention, customer satisfaction, app ratings, a school survey of parents: nearly every percentage in public life comes from asking some people and inferring the rest. The honest version always carries two numbers, the estimate and how far it could be out, and the difference between two surveys means nothing until it is bigger than both of their margins. Learners who have watched a thousand surveys scatter around a known truth never quite trust a lone percentage again, and that is a healthy thing to carry into adult life.
The learner rebuilds the simulation themselves: a list of 7,440 households with 6,636 marked as broadband, a seeded random generator, a sampler that draws without replacement, and a loop that runs a thousand surveys at each size and sorts the results. They check that rerunning with the same seed gives the same table, change the seed and see the edges move a little while the pattern holds, and then compare their spread with the textbook formula. The last step is a sentence of the kind a newspaper should print: a survey of 400 households would put Mullingar's broadband share at about 89%, give or take three points.
Published for the built-up area Mullingar, Co Westmeath, in the Census 2022 small area tables.
| Measured | Count |
|---|---|
| Usual residents | 22,470 |
| Households | 8,171 |
| Households reporting broadband | 6,636 |
| Households that answered the internet question | 7,440 |
| Working residents in the travel table | 9,495 |
| Children under fifteen in childcare | 1,397 |
The simulation uses only the households that answered the question: 6,636 broadband, 172 another connection and 632 none. The 731 that did not state are left out, because a survey cannot sample an answer nobody gave. That choice is ours and it is stated.
Of the 9,495 working residents, 5,319 drive, 1,056 walk, 687 give home as their main answer, 528 travel as a car passenger, 180 by bus, 176 by bicycle and 130 by train, with 824 not stating.
Of 5,961 journeys to school, college or childcare, 3,048 are as a car passenger, 1,382 on foot, 322 by bus, 174 by bicycle and 142 by train.
The station
Irish Rail gives Mullingar station as Green Bridge, Mullingar, Co. Westmeath, Eircode N91 HKR4, staffed from 05:30 to 21:30 on weekdays with shorter weekend hours, and a booking office open on weekday mornings until 14:00.
What the simulation teaches, turned into checks a reader can run on a figure in a newspaper or a report.
| Question | Why it matters, shown in Mullingar |
|---|---|
| How many were asked? | At 100 households a survey could land anywhere from 83% to 95% in most cases; at 1,600, between 87.9% and 90.5% |
| Is a difference bigger than the margin? | Two surveys of 100 reporting 85% and 92% are not evidence of any change; both sit inside the ordinary scatter |
| Who could not be asked? | The 731 households that did not answer the census question are outside every simulated survey, and in a real one they would be too |
Because every household was asked, the census has no sampling error at all. The simulation exists precisely because that rare complete count gives us a truth to test surveys against.
A seeded random generator produces the same sequence every run, which lets an experiment built on chance be checked, shared and repeated. That is one of the more surprising and useful ideas in programming.
A huge sample drawn badly, only households with a landline, say, can be further from the truth than a small random one. The simulation assumes a fair draw; real surveys have to earn that.
The arts centre and the house
Mullingar Arts Centre gives its address as Lower Mount Street, Mullingar, Co. Westmeath, N91 K7XK, and describes its mission as promoting excellence, innovation and participation in the arts. Belvedere House, Gardens and Park, which describes itself as a Georgian country house near Mullingar dating to 1740, gives N91 EF80 and notes that its interior is closed during conservation works while the gardens and park remain open. We have no connection with either and reproduce no prices.
Twice a week, at an hour you choose, with a teacher who stays for the whole of it.
Block coding and games of chance, where a hundred rolls of a dice turn into a first experiment.
Python, websites and AI projects across the junior and senior cycles, with real data wherever it fits.
Adult learners arrive with every level of experience, and 2,101 working residents here already work from home for part of the week.
The railway station, the arts centre and Belvedere House are quoted from their own published pages, and none of them, nor Westmeath County Council, is connected with us. Census counts appear as the Central Statistics Office published them. The simulation is ours: its population, seed, method and every result are written out on this page so that anybody can rerun it and get the same table, which is the only kind of experiment worth publishing.
Use the ages as a rough guide; the introductory lesson sets the level.
Dice, spinners and coin flips in block code, and noticing that one roll tells you little.
Scratch Coding for KidsCoding for KidsSimulations in Python that repeat an experiment thousands of times and chart what happens.
Maths Through CodingPython and AI for KidsSampling real data, measuring the scatter, and comparing it with the formula.
Data Science for TeensPython for TeensSizing a survey, reading someone else's, and knowing when a change is real.
Data and AI Analytics for Non-Programmers (Excel, Sheets, Power BI)Python Automation CourseIt will usually find a story in the gap.
Give an assistant two survey results, 85% and 92%, and ask what happened, and the reply often explains the rise. It rarely asks how many people each survey reached, even though at 100 respondents both numbers sit comfortably inside the scatter we measured for Mullingar, and the honest answer is that nothing can be said.
A learner who has run the simulation asks for the sample sizes first and compares the gap with the margins before explaining anything. That habit turns a confident paragraph into a correct one, and it is quick to apply.
Machines are fluent with percentages. Knowing how much a percentage can be trusted is a skill people still have to bring, and it starts with watching surveys miss. The longer argument is in what makes coding worth learning today.
The practical side.
A real teacher, present for the full hour, reacting to the learner's own screen.
Five to ten learners at one stage, from Mullingar, elsewhere in Ireland and other countries.
Around eight lessons a month at the hour agreed when the course starts.
Holidays, mid-terms and exam weeks are planned in from the outset.
A computer rather than a tablet or phone, audio that works both ways, and a line that will carry a live call for an hour.
They cover the cases a group cannot: an unusual level, or hours that suit nobody else.
No sampling in the placement
We do not guess a learner's level from their age or a form. The introductory hour is a direct measurement, the one-household census rather than the survey.
Three lines cover everything.
The introductory lesson, taught in full and assessed, free of charge.
A month in a group of five to ten at one level, about eight live lessons.
A month of private lessons on the same weekly schedule.
One rate, in US dollars, charged monthly and identical for every family outside India, with no euro figure printed beside it. Nothing is invoiced for the introductory hour or before a course and a time have been chosen, and the pricing page sets out what happens during holidays, after an absence, or when a learner moves between a group and private lessons.
Rated 4.9 across 547 Google reviews. These are real reviews, reproduced as written.
★★★★★
"The one step solution for my son. Modern Age Coders make learning coding so simple that kids love it. The teachers explain complex concepts clearly with practical exercises and interactive content."
Ria Mukherjee
Parent
★★★★★
"Modern Age Coders has been a game-changer for me. I struggled to grasp IT concepts and coding before joining, but their classes transformed everything. I can now confidently write complex programs with ease."
Samriddha Mondal
Student
★★★★★
"One of the most wonderful education centres out there. Education is not limited to school syllabus but focuses on skill development."
Vansh Agarwal
Student
★★★★★
"My child Dhairya is really enjoying the Modern Age Coders classes. This is his first online class and he eagerly looks forward to it. I can already see his improvement, and the teachers are very cooperative."
Sonam Oswal
Parent of Dhairya
★★★★★
"Modern Age Coders have wonderful teachers who teach in a clear, easy and practical way. The teacher boosts students' confidence and inspires them to learn without hesitation."
Sonu Goyal
Parent
★★★★★
"I highly recommend this computer coding class! The teachers are incredibly knowledgeable and passionate about coding."
Ritu Kedia
Parent
Tell us the learner's age and what catches their interest. We shape the first hour around that, and it might finish with a game, a working script, or a thousand dice rolls charted in a few seconds.
What families in Mullingar usually want to know.
Census 2022 small area tables count 22,470 usual residents in the built-up area of Mullingar, in 8,171 households. The Westmeath page draws on the census town list instead, which counts on a different basis and gives a different figure.
Learners simulate a thousand surveys of Mullingar households at three sizes, drawn from the 7,440 that answered the census internet question, and compare the results with the true broadband share of 89.19%. A seeded random generator makes every run identical and checkable.
Because precision grows with the square root of the sample. In our simulation, surveys of 100 households scattered six points either side of the truth, surveys of 400 three points, and quadrupling again to 1,600 brought it close to one point.
Of the 9,495 working residents in the travel table, 5,319 drive, 1,056 walk, 687 give working mainly at or from home, 528 travel as a car passenger, 180 take a bus, 176 cycle and 130 take a train, with 824 not stating.
After school, in the evening and on weekend mornings. Our teaching day in India runs later than yours: add four and a half hours to an Irish summer evening, or five and a half in winter, and you have the teacher's clock. The weekly slot is fixed around that.
Yes. People up to sixty-seven learn with us, plenty of them from scratch, and whether an adult joins a matched group or learns privately is decided in the introductory hour.
No. The probability and statistics on this page are taught through the project itself, one step at a time, and the computer does the arithmetic.
No, and we never imply one. Teaching is live over video only, with no premises in Ireland. A learner needs a laptop or desktop, working sound and a steady connection, and the number shown here belongs to India.
The first lesson is free. After that a shared place costs USD 100 a month and brings two live lessons a week, about eight monthly, with five to ten learners; one to one on the same schedule is USD 150 a month. Everything is agreed before payment.
Five to ten, grouped by ability, pace and goal rather than age or address. Where nothing suitable meets at a workable hour, we teach one to one instead.
The rest of the county is on the County Westmeath page, with Athlone to the west and Portlaoise to the south, inside Leinster. Families comparing online providers can start from this overview, and the Ireland hub holds the full list of places.