Regresi linier

sederhana

Dalam statistika , regresi linier sederhana adalah model regresi linier dengan variabel
penjelas tunggal . [1] [2] [3] [4] [5] Artinya, ini menyangkut titik sampel dua dimensi dengan satu
variabel independen dan satu variabel dependen (secara konvensional, koordinat x dan y
dalam sistem koordinat Cartesian ) dan menemukan a fungsi linier (garis lurus non-vertikal )
yang, seakurat mungkin, memprediksi nilai variabel dependen sebagai fungsi dari variabel
independen. Kata sifat sederhanamengacu pada fakta bahwa variabel hasil terkait dengan
satu prediktor.

Hukum Okun dalam ekonomi makro adalah contoh dari regresi linier sederhana. Di sini variabel dependen
(pertumbuhan PDB) dianggap memiliki hubungan linier dengan perubahan tingkat pengangguran.
Adalah umum untuk membuat ketentuan tambahan bahwa metode kuadrat terkecil biasa
(OLS) harus digunakan: akurasi setiap nilai prediksi diukur dengan sisa kuadratnya ( jarak
vertikal antara titik kumpulan data dan garis yang dipasang), dan tujuannya adalah untuk
membuat jumlah deviasi kuadrat ini sekecil mungkin. Metode regresi lain yang dapat
digunakan sebagai pengganti kuadrat terkecil biasa termasuk deviasi absolut terkecil
(meminimalkan jumlah nilai absolut residu) dan estimator Theil-Sen (yang memilih garis yang
kemiringannya adalah median dari lereng yang ditentukan oleh pasangan titik sampel).
Regresi Deming(kuadrat terkecil total) juga menemukan garis yang cocok dengan
sekumpulan titik sampel dua dimensi, tetapi (tidak seperti kuadrat terkecil biasa, deviasi
absolut terkecil, dan regresi kemiringan median) itu sebenarnya bukan turunan dari regresi
linier sederhana, karena memang demikian. tidak memisahkan koordinat menjadi satu
variabel dependen dan satu variabel independen dan berpotensi mengembalikan garis
vertikal sesuai kecocokannya.

Sisa artikel mengasumsikan regresi kuadrat terkecil biasa. Dalam hal ini, kemiringan garis
yang dipasang sama dengan korelasi antara y dan x yang dikoreksi oleh rasio standar deviasi
variabel-variabel ini. Perpotongan garis yang dipasang sedemikian rupa sehingga garis
melewati pusat massa ( x , y ) dari titik data.

Menyesuaikan garis regresi

Consider the model function

which describes a line with slope β and y-intercept α. In general such a relationship may not
hold exactly for the largely unobserved population of values of the independent and
dependent variables; we call the unobserved deviations from the above equation the errors.
Suppose we observe n data pairs and call them {(xi, yi), i = 1, ..., n}. We can describe the
underlying relationship between yi and xi involving this error term εi by

This relationship between the true (but unobserved) underlying parameters α and β and the
data points is called a linear regression model.

The goal is to find estimated values and for the parameters α and β which would provide
the "best" fit in some sense for the data points. As mentioned in the introduction, in this
article the "best" fit will be understood as in the least-squares approach: a line that minimizes
the sum of squared residuals (see also Errors and residuals) (differences between actual
and predicted values of the dependent variable y), each of which is given by, for any
candidate parameter values and ,

In other words, and solve the following minimization problem:

By expanding to get a quadratic expression in and we can derive values of and that
minimize the objective function Q (these minimizing values are denoted and ):[6]

Here we have introduced

and as the average of the xi and yi, respectively

rxy as the sample correlation coefficient between x and y

sx and sy as the uncorrected sample standard deviations of x and y

and as the sample variance and sample covariance, respectively

Substituting the above expressions for and into

yields

This shows that rxy is the slope of the regression line of the standardized data points (and
that this line passes through the origin). Since then we get that if x is some
measurement and y is a followup measurement from the same item, then we expect that y
(on average) will be closer to the mean measurement than it was to the original value of x.
This phenomenon is known as regressions toward the mean.
Generalizing the notation, we can write a horizontal bar over an expression to indicate the
average value of that expression over the set of samples. For example:

This notation allows us a concise formula for rxy:

The coefficient of determination ("R squared") is equal to when the model is linear with a
single independent variable. See sample correlation coefficient for additional details.

Intuition about the slope

By multiplying all members of the summation in the numerator by : (thereby

not changing it):

We can see that the slope (tangent of angle) of the regression line is the weighted average of

that is the slope (tangent of angle) of the line that connects the i-th point to the

average of all points, weighted by because the further the point is the more
"important" it is, since small errors in its position will affect the slope connecting it to the
center point more.

Intuition about the intercept

Given with the angle the line makes with the

positive x axis, we have

Intuition about the correlation

In the above formulation, notice that each is a constant ("known upfront") value, while the
are random variables that depend on the linear function of and the random term .
This assumption is used when deriving the standard error of the slope and showing that it is
unbiased.

In this framing, when is not actually a random variable, what type of parameter does the
empirical correlation estimate? The issue is that for each value i we'll have:
and . A possible interpretation of is to imagine that defines a random
variable drawn from the empirical distribution of the x values in our sample. For example, if x
had 10 values from the natural numbers: [1,2,3...,10], then we can imagine x to be a Discrete
uniform distribution. Under this interpretation all have the same expectation and some
positive variance. With this interpretation we can think of as the estimator of the
Pearson's correlation between the random variable y and the random variable x (as we just
defined it).

Simple linear regression without the intercept term (single regressor)

Sometimes it is appropriate to force the regression line to pass through the origin, because x
and y are assumed to be proportional. For the model without the intercept term, y = βx, the
OLS estimator for β simplifies to

Substituting (x − h, y − k) in place of (x, y) gives the regression through (h, k):

where Cov and Var refer to the covariance and variance of the sample data (uncorrected for
bias).
The last form above demonstrates how moving the line away from the center of mass of the
data points affects the slope.

Sifat numerik

1. The regression line goes through the center of mass point, , if the model includes
an intercept term (i.e., not forced through the origin).

2. The sum of the residuals is zero if the model includes an intercept term:

3. The residuals and x values are uncorrelated (whether or not there is an intercept term in
the model), meaning:

4. The relationship between (the correlation coefficient for the population) and the
population variances of ( ) and the error term of ( ) is:[7]: 401 

For extreme values of this is self evident. Since when then . And
when then .

Properti berbasis model

Description of the statistical properties of estimators from the simple linear regression
estimates requires the use of a statistical model. The following is based on assuming the
validity of a model under which the estimates are optimal. It is also possible to evaluate the
properties under other assumptions, such as inhomogeneity, but this is discussed elsewhere.

Unbiasedness

The estimators and are unbiased.

To formalize this assertion we must define a framework in which these estimators are
random variables. We consider the residuals εi as random variables drawn independently
from some distribution with mean zero. In other words, for each value of x, the corresponding
value of y is generated as a mean response α + βx plus an additional random variable ε
called the error term, equal to zero on average. Under such interpretation, the least-squares
estimators and will themselves be random variables whose means will equal the "true
values" α and β. This is the definition of an unbiased estimator.

Confidence intervals

The formulas given in the previous section allow one to calculate the point estimates of α and
β — that is, the coefficients of the regression line for the given set of data. However, those
formulas don't tell us how precise the estimates are, i.e., how much the estimators and
vary from sample to sample for the specified sample size. Confidence intervals were devised
to give a plausible set of values to the estimates one might have if one repeated the
experiment a very large number of times.

The standard method of constructing confidence intervals for linear regression coefficients
relies on the normality assumption, which is justified if either:

1. the errors in the regression are normally distributed (the so-called classic regression
assumption), or

2. the number of observations n is sufficiently large, in which case the estimator is

approximately normally distributed.

The latter case is justified by the central limit theorem.

Normality assumption

Under the first assumption above, that of the normality of the error terms, the estimator of
the slope coefficient will itself be normally distributed with mean β and variance

where σ2 is the variance of the error terms (see Proofs involving

ordinary least squares). At the same time the sum of squared residuals Q is distributed
proportionally to χ2 with n − 2 degrees of freedom, and independently from . This allows us
to construct a t-value

where

is the standard error of the estimator .

This t-value has a Student's t-distribution with n − 2 degrees of freedom. Using it we can
construct a confidence interval for β:

at confidence level (1 − γ), where is the quantile of the tn−2 distribution. For
example, if γ = 0.05 then the confidence level is 95%.

Similarly, the confidence interval for the intercept coefficient α is given by

at confidence level (1 − γ), where

The US "changes in unemployment – GDP growth" regression with the 95% confidence bands.

The confidence intervals for α and β give us the general idea where these regression
coefficients are most likely to be. For example, in the Okun's law regression shown here the
point estimates are

The 95% confidence intervals for these estimates are

In order to represent this information graphically, in the form of the confidence bands around
the regression line, one has to proceed carefully and account for the joint distribution of the
estimators. It can be shown[8] that at confidence level (1 − γ) the confidence band has
hyperbolic form given by the equation

When the model assumed the intercept is fixed and equal to 0 ( ), the standard error of
the slope turns into:

With:

Asymptotic assumption

The alternative second assumption states that when the number of points in the dataset is
"large enough", the law of large numbers and the central limit theorem become applicable,
and then the distribution of the estimators is approximately normal. Under this assumption
all formulas derived in the previous section remain valid, with the only exception that the
quantile t*n−2 of Student's t distribution is replaced with the quantile q* of the standard
1
normal distribution. Occasionally the fraction n−2 is replaced with n1 . When n is large such a
change does not alter the results appreciably.

Contoh numerik

This data set gives average masses for women as a function of their height in a sample of
American women of age 30–39. Although the OLS article argues that it would be more
appropriate to run a quadratic regression for this data, the simple linear regression model is
applied here instead.

Height
1.47 1.50 1.52 1.55 1.57 1.60 1.63 1.65 1.68 1.70 1.73 1.75
(m), xi

Mass
52.21 53.12 54.48 55.84 57.20 58.57 59.93 61.29 63.11 64.47 66.28 68.10 6
(kg), yi
 1 1.47 52.21 2.1609 76.7487 2725.8841

2 1.50 53.12 2.2500 79.6800 2821.7344

3 1.52 54.48 2.3104 82.8096 2968.0704

4 1.55 55.84 2.4025 86.5520 3118.1056

5 1.57 57.20 2.4649 89.8040 3271.8400

6 1.60 58.57 2.5600 93.7120 3430.4449

7 1.63 59.93 2.6569 97.6859 3591.6049

8 1.65 61.29 2.7225 101.1285 3756.4641

9 1.68 63.11 2.8224 106.0248 3982.8721

10 1.70 64.47 2.8900 109.5990 4156.3809

11 1.73 66.28 2.9929 114.6644 4393.0384

12 1.75 68.10 3.0625 119.1750 4637.6100

13 1.78 69.92 3.1684 124.4576 4888.8064

14 1.80 72.19 3.2400 129.9420 5211.3961

15 1.83 74.46 3.3489 136.2618 5544.2916

24.76 931.17 41.0532 1548.2453 58498.5439

There are n = 15 points in this data set. Hand calculations would be started by finding the
following five sums:

These quantities would be used to calculate the estimates of the regression coefficients, and
their standard errors.
Graph of points and linear least squares lines in the simple linear regression numerical example

The 0.975 quantile of Student's t-distribution with 13 degrees of freedom is t*13 = 2.1604, and
thus the 95% confidence intervals for α and β are

The product-moment correlation coefficient might also be calculated:

Lihat juga

Design matrix#Simple linear regression

 Line fitting

Linear trend estimation

Linear segmented regression

Proofs involving ordinary least squares—derivation of all formulas used in this article in
general multidimensional case

Referensi

1. Seltman, Howard J. (2008-09-08). Experimental Design and Analysis (http://www.stat.cmu.edu/~hsel

tman/309/Book/Book.pdf) (PDF). p. 227.

2. "Statistical Sampling and Regression: Simple Linear Regression" (http://ci.columbia.edu/ci/premba_te

st/c0331/s7/s7_6.html) . Columbia University. Retrieved 2016-10-17. "When one independent
variable is used in a regression, it is called a simple regression;(...)"

3. Lane, David M. Introduction to Statistics (http://onlinestatbook.com/Online_Statistics_Education.pd

f) (PDF). p. 462.

4. Zou KH; Tuncali K; Silverman SG (2003). "Correlation and simple linear regression". Radiology. 227
(3): 617–22. doi:10.1148/radiol.2273011499 (https://doi.org/10.1148%2Fradiol.2273011499) .
ISSN 0033-8419 (https://www.worldcat.org/issn/0033-8419) . OCLC 110941167 (https://www.world
cat.org/oclc/110941167) . PMID 12773666 (https://pubmed.ncbi.nlm.nih.gov/12773666) .

5. Altman, Naomi; Krzywinski, Martin (2015). "Simple linear regression". Nature Methods. 12 (11): 999–
1000. doi:10.1038/nmeth.3627 (https://doi.org/10.1038%2Fnmeth.3627) . ISSN 1548-7091 (https://
www.worldcat.org/issn/1548-7091) . OCLC 5912005539 (https://www.worldcat.org/oclc/591200
5539) . PMID 26824102 (https://pubmed.ncbi.nlm.nih.gov/26824102) .

6. Kenney, J. F. and Keeping, E. S. (1962) "Linear Regression and Correlation." Ch. 15 in Mathematics of
Statistics, Pt. 1, 3rd ed. Princeton, NJ: Van Nostrand, pp. 252–285

7. Valliant, Richard, Jill A. Dever, and Frauke Kreuter. Practical tools for designing and weighting survey
samples. New York: Springer, 2013.

8. Casella, G. and Berger, R. L. (2002), "Statistical Inference" (2nd Edition), Cengage, ISBN 978-0-534-
24312-8, pp. 558–559.

Tautan eksternal

Wolfram MathWorld's explanation of Least Squares Fitting, and how to calculate it (http://
mathworld.wolfram.com/LeastSquaresFitting.html)

Mathematics of simple regression (Robert Nau, Duke University) (http://people.duke.edu/~

rnau/mathreg.htm)
Retrieved from
"https://en.wikipedia.org/w/index.php?
title=Simple_linear_regression&oldid=108588820
8"

Terakhir diedit 3 bulan yang lalu oleh 2A02:908:C33:D160:0:0:0:9E4C