Regression intercept calculator
For x of 1 to 5 with y values 2, 4, 5, 4 and 5, the least-squares line crosses the y axis at 2.2. Enter paired x and y lists of the same length to get the intercept of the best-fitting straight line. Free in your browser.
- Free
- Runs in your browser
- No sign-up
- Your data stays on your device
Run — free
Worked example
- X
- 1, 2, 3, 4, 5
- Y
- 2, 4, 5, 4, 5
- Intercept
- 2.2
The regression intercept is the point where a fitted least-squares line crosses the y axis. Give this calculator two equal-length numeric arrays, one for x and one for y, and it returns the intercept of the ordinary least-squares line. The calculation is deterministic and validates every pair before fitting. If all x values are identical, their variance is zero, so a unique slope and intercept cannot be determined; in that case the calculator returns an input error instead of a misleading number.
What the regression intercept represents
A simple linear regression describes a relationship with a fitted line commonly written as y = mx + b. In that expression, m is the slope and b is the intercept. The value can be meaningful when zero is a realistic or important x value, such as a baseline dose, elapsed time, or instrument input.
When zero lies far outside the observed x range, the intercept is still mathematically defined, but it is an extrapolation and should be interpreted cautiously. A precise computed intercept does not prove that a straight-line model is appropriate, that the relationship is causal, or that the baseline has a useful real-world meaning. Plotting the observations and checking model assumptions remain important steps in serious analysis.
How the least-squares calculation works
The arrays are paired by position: the first x value belongs with the first y value, the second x value belongs with the second y value, and so on. After validating that both arrays contain at least two finite numbers and have equal lengths, the calculator finds the mean of each series. It then computes the centered x sum of squares and the centered cross-product between x and y.
Dividing the cross-product by the x sum of squares gives the ordinary least-squares slope. Finally, the intercept is calculated as mean y minus the slope multiplied by mean x. These formulas select the line that minimizes the sum of squared vertical differences between observed and fitted y values.
Centered, incremental accumulation is used to avoid unnecessarily large raw-square totals and to keep the result stable for ordinary numeric inputs. No random initialization or iterative optimization is involved. The same arrays always produce the same result.
Valid input, zero variance, and practical use
Each entry must be a finite JavaScript number; strings, missing elements, NaN, and infinite values are rejected. At least two pairs are required. The most important mathematical failure occurs when every x value is identical.
In that situation, x has zero variance, the denominator of the least-squares slope is zero, and infinitely many slopes can be paired with intercepts to pass through the same fitted point. Do not work around that error by adding arbitrary noise. Instead, collect observations at more than one x value or reconsider whether regression is the right analysis.
Typical uses include extracting a calibration baseline, checking a textbook regression exercise, validating a result produced by a spreadsheet, and supplying one stable statistic to an automated pipeline.
What you can do with it
Find a calibration baseline
Calculate the fitted response at zero input from paired reference readings and measured outputs.
Check statistics coursework
Verify the y-intercept obtained from a hand calculation or spreadsheet for a set of paired observations.
Validate an analytics pipeline
Use deterministic paired data to confirm that another regression implementation returns the expected intercept.
FAQ
What formula is used for the intercept?
The calculator uses ordinary least squares: slope = Sxy / Sxx, then intercept = mean(y) − slope × mean(x).
What does the regression intercept mean in practice?
It is the fitted value of y when x is 0. It is meaningful when zero is a realistic x value, such as a baseline dose, the start of elapsed time or an instrument input.
Can I trust the intercept when my x values are far from zero?
It is still mathematically defined, but it is an extrapolation beyond your data, so read it with caution. A precise number does not prove that a straight line fits or that the baseline is meaningful.
Why do I get an error when all x values are the same?
Because x then has no spread, so the slope cannot be found and infinitely many lines fit equally well. The calculator refuses instead of returning a misleading intercept.
Does it also give me the slope?
No. The slope is computed along the way, since the intercept is the mean of y minus the slope times the mean of x, but only the intercept is returned.
Related tools
For developers — API access
Everything on this page is available programmatically. This section is for teams who want to wire it into their own systems; everyone else can just use the tool above.
API endpoint
Prefer to automate it? One authenticated POST creates the task; the result comes back by webhook or a signed link. The same capability also runs here on the web, by email and from Telegram — and soon from our app too.
Call it from your stack
curl -X POST https://api.kit.forhosting.com/stat/regression-intercept \
-H "Authorization: Bearer $KIT_KEY" \
-H "Content-Type: application/json" \
-d '{"x":[1,2,3,4,5],"y":[2,4,5,4,5]}'const res = await fetch("https://api.kit.forhosting.com/stat/regression-intercept", {
method: "POST",
headers: {
"Authorization": `Bearer ${process.env.KIT_KEY}`,
"Content-Type": "application/json"
},
body: JSON.stringify({
"x": [
1,
2,
3,
4,
5
],
"y": [
2,
4,
5,
4,
5
]
})
});
const { task_id } = await res.json();import os, requests
res = requests.post(
"https://api.kit.forhosting.com/stat/regression-intercept",
headers={"Authorization": f"Bearer {os.environ['KIT_KEY']}"},
json={
"x": [
1,
2,
3,
4,
5
],
"y": [
2,
4,
5,
4,
5
]
},
)
task_id = res.json()["task_id"]<?php
$res = file_get_contents("https://api.kit.forhosting.com/stat/regression-intercept", false, stream_context_create([
"http" => [
"method" => "POST",
"header" => "Authorization: Bearer " . getenv("KIT_KEY") . "\r\nContent-Type: application/json",
"content" => '{"x":[1,2,3,4,5],"y":[2,4,5,4,5]}',
],
]));
$task = json_decode($res, true);body := bytes.NewBufferString(`{"x":[1,2,3,4,5],"y":[2,4,5,4,5]}`)
req, _ := http.NewRequest("POST", "https://api.kit.forhosting.com/stat/regression-intercept", body)
req.Header.Set("Authorization", "Bearer "+os.Getenv("KIT_KEY"))
req.Header.Set("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)Example request
{
"x": [
1,
2,
3,
4,
5
],
"y": [
2,
4,
5,
4,
5
]
}Example response
{
"task_id": "tsk_a1b2c3d4e5f6a1b2c3d4e5f6",
"type": "stat.regression_intercept",
"status": "queued",
"_links": {
"result": "/tasks/tsk_…/result"
}
}The API is asynchronous: the call returns a task_id immediately and the result arrives by webhook. Polling is capped at 1 req/s per task.
Pricing
Published price — no tokens, no invented credits. A failed task is never charged.
Errors
| HTTP | Code | Meaning |
|---|---|---|
401 | unauthorized | Missing or invalid API key. |
402 | insufficient_balance | Your balance doesn't cover the task price. |
404 | unknown_type | That task type doesn't exist. |
429 | rate_limited | Too many requests. Use the webhook instead of polling. |
Technical notes
What the regression intercept represents
The intercept is the fitted value of y at x = 0, which is also where the line crosses the vertical axis on a standard graph. This calculator focuses specifically on b. It accepts paired observations stored in two arrays, estimates the ordinary least-squares slope internally, and then returns the corresponding intercept.
How the least-squares calculation works
The response contains the intercept alone because that is the capability’s specific contract, even though the slope is calculated internally as an essential intermediate value.
Valid input, zero variance, and practical use
Provide x and y as JSON arrays of numbers, with the same number of entries in each array. There is therefore no unique regression intercept under the usual y-on-x ordinary least-squares model, so this capability returns invalid_input. Browser calculations are available without charge; successful API requests cost $0.002 per item.
Technical questions
Why must x and y have equal lengths?
Values are paired by array position. Unequal lengths leave one or more observations without a partner, so the request is invalid.
What happens when x variance is zero?
The request returns invalid_input because a constant x array makes the least-squares slope denominator zero, so the intercept is not uniquely determined.
Does an intercept always have a practical meaning?
No. It represents fitted y at x = 0, but interpretation may be weak when zero is impossible or far outside the observed x range.
How much does an API calculation cost?
Each successful API request costs $0.002 per item. Invalid input is rejected before a result is returned.