Imibuzo Nengxoxo Yesibonelo Sokuhlehla Okuqondile
Ukuhlehla okuqondile kuyindlela yezibalo esetshenziselwa ukunquma ubudlelwano phakathi kweziguquguquko ezimbili noma ngaphezulu. Le ndlela isetshenziswa kabanzi emikhakheni ehlukahlukene, okuhlanganisa ezomnotho, ibhizinisi, isayensi yezenhlalo, kanye nesayensi yemvelo. Kulesi sihloko, sizoxoxa ngokuhlehla okuqondile, ukuthi singakubala kanjani, futhi sinikeze izibonelo eziningana zezinkinga ngezincazelo ukusiza abafundi baqonde lo mqondo ngokujulile.
Ukuqonda Ukuhlehliswa Okuqondile
Ukuhlehla okuqondile kuyindlela yokuhlaziya esetshenziselwa ukulingisa ubudlelwano phakathi kwenguquko eyodwa noma ngaphezulu ezimele (izibikezelo) kanye nenguquko exhomeke (impendulo). Ukuhlehla okulula okuqondile kuhilela inguquko eyodwa ezimele kanye nenguquko eyodwa exhomeke, kuyilapho ukuhlehla okuqondile okuningi kuhilela inguquko engaphezu kweyodwa ezimele.
Isibalo somugqa olula wokuhlehla komugqa yilesi:
\[ Y = a + bX \]
Di mana:
– \( Y \) iyi-variable exhomeke kuyo.
– \( X \) yi-variable ezimele.
– \( a \) yi-intercept, okuyinani lika-Y uma u-X = 0.
– \( b \) yi-regression coefficient, okungukuthi, ukuthi u-Y ushintsha kangakanani uma u-X eshintsha ngeyunithi eyodwa.
Izinyathelo Zokuhlehlisa Okuqondile
1. Qoqa Imininingwane: Okokuqala, qoqa imininingwane ezohlaziywa.
2. Idatha Yesakhiwo: Dala isakhiwo sokuhlakaza ukuze ubone ukuthi kukhona yini ubudlelwano obuqondile phakathi kweziguquguquko.
3. Bala i-Regression Coefficient: Sebenzisa indlela ye-least squares ukuthola umugqa ongcono kakhulu.
4. Ukuhlola Imodeli: Hlola ukubaluleka kwama-coefficients okubuyela emuva nge-t-test bese unquma inani eliyisikwele esingu-R ukuze ubone ukuthi imodeli ifanelana kahle kangakanani nedatha.
Imibuzo Eyisibonelo Nengxoxo
Isibonelo Umbuzo 1: Ukuhlehliswa Okulula Komugqa
Umbuzo:
Umcwaningi ufuna ukwazi ubudlelwano phakathi kwenani lamahora okufunda (X) kanye namaphuzu abafundi okuhlolwa (Y). Imininingwane etholakele yilena elandelayo:
| Amahora Okufunda (X) | Amaphuzu Okuhlolwa (Y) |
|———————–|——————–|
| 2 | 70 |
| 3 | 75 |
| 5 | 80 |
| 7 | 85 |
| 8 | 90 |
Yenza i-equation yokubuyela emuva okuqondile kusuka kule datha!
Ingxoxo:
1. Ukubala Isilinganiso:
\[
\bar{X} = \frac{2 + 3 + 5 + 7 + 8}{5} = 5
\]
\[
\ibha{Y} = \frac{70 + 75 + 80 + 85 + 90}{5} = 80
\]
2. Ukubala i-Regression Coefficient \( b \):
\[
b = \frac{\sum (X_i – \bar{X})(Y_i – \bar{Y})}{\sum (X_i – \bar{X})^2}
\]
\[
\sum (X_i – \bar{X})(Y_i – \bar{Y}) = (2 – 5)(70 – 80) + (3 – 5)(75 – 80) + (5 – 5)(80 – 80) + (7 – 5)(85 – 80) + (8 – 5)(90 – 80)
\]
\[
= (-3)(-10) + (-2)(-5) + (0)(0) + (2)(5) + (3)(10) = 30 + 10 + 0 + 10 + 30 = 80
\]
\[
\sum (X_i – \bar{X})^2 = (2 – 5)^2 + (3 – 5)^2 + (5 – 5)^2 + (7 – 5)^2 + (8 – 5)^2
\]
\[
= 9 + 4 + 0 + 4 + 9 = 26
\]
\[
b = \frac{80}{26} \cishe 3.08
\]
3. Ukubala i-Intercept \( a \):
\[
a = \bar{Y} – b\bar{X}
\]
\[
a = 80 – 3.08 \izikhathi 5 = 80 – 15.4 = 64.6
\]
4. Isibalo Sokuhlubuka:
\[
Y = 64.6 + 3.08X
\]
Ngakho-ke, i-linear regression equation yedatha ingu-\( Y = 64.6 + 3.08X \). Lokhu kusho ukuthi ihora ngalinye elengeziwe lokufunda kulindeleke ukuthi likhuphule amaphuzu okuhlolwa ngamaphuzu angu-3.08.
Isibonelo Umbuzo 2: Ukuhlolwa Kwemodeli Nokuhumusha
Umbuzo:
Uqhubeka nedatha efanayo, bala inani le-R-squared (R²) ukuze ulinganise ukuthi imodeli ifanelana kahle kangakanani nedatha. Futhi, hlola ukubaluleka kwe-regression coefficient \( b \).
Ingxoxo:
1. Bala Isamba Sezikwele (SST), Isamba Sokuhlushwa Kwezikwele (SSR), kanye Nesamba Sephutha Sezikwele (SSE):
\[
I-SST = \sum (Y_i – \bar{Y})^2
\]
\[
I-SST = (70 – 80)^2 + (75 – 80)^2 + (80 – 80)^2 + (85 – 80)^2 + (90 – 80)^2 = 100 + 25 + 0 + 25 + 100 = 250
\]
\[
I-SSR = \sum (\hat{Y}_i – \bar{Y})^2
\]
Lapho \( \hat{Y}_i \) kuyinani elibikezelwe le-regression equation:
\[
\hat{Y}_i = 64.6 + 3.08X_i
\]
\[
\hat{Y} = [67.76, 70.84, 76.0, 82.16, 85.24]
\]
\[
\ibha{Y} = 80
\]
\[
I-SSR = (67.76 – 80)^2 + (70.84 – 80)^2 + (76.0 – 80)^2 + (82.16 – 80)^2 + (85.24 – 80)^2
\]
\[
I-SSR = (-12.24)^2 + (-9.16)^2 + (-4.0)^2 + 2.16^2 + 5.24^2 = 149.8
\]
2. Ukubala i-SSE:
\[
I-SSE = I-SST – I-SSR = 250 – 149.8 = 100.2
\]
3. Ukubala i-R-squared:
\[
R^2 = \frac{SSR}{SST} = \frac{149.8}{250} \cishe kube ngu-0.6
\]
Inani eliyisikwele esingu-R elingu-0.6 libonisa ukuthi le modeli ichaza cishe u-60% wokwehluka kwedatha. Lokhu kubonisa ukuthi umugqa wokubuyela emuva ufanelana kahle nedatha.
4. Ukuhlolwa kwe-t kokubaluleka kwe-Coefficient \( b \):
\[
t = \frac{b}{SE(b)}
\]
\[
SE(b) = \sqrt{\frac{SSE}{n-2}} / \sqrt{\sum (X_i – \bar{X})^2}
\]
\[
SE(b) = \sqrt{\frac{100.2}{5-2}} / \sqrt{26}
\]
\[
SE(b) = \sqrt{33.4} / \sqrt{26} \cishe kube ngu-1.13
\]
\[
t = \frac{3.08}{1.13} \cishe kube ngu-2.73
\]
Nge-\( t-statistic \approx 2.73 \), uma sisebenzisa umkhawulo ojwayelekile wokubaluleka (α = 0.05), siyawuqhathanisa nethebula le-t. Isibonelo, ku-\( df = 3 \), okubalulekile \( t \) cishe kungu-2.353. Bese kuba yi-\( t-observed > t-critical \), okubonisa ukuthi i-coefficient ibalulekile.
Isiphetho
Kulesi sihloko, simboze izisekelo ze-linear regression, indlela yokubala i-regression coefficient kanye ne-intercept, kanye nendlela yokuhumusha imiphumela sisebenzisa izinkinga zesibonelo. Ukuzijwayeza njalo ngamasethi edatha ahlukahlukene kubalulekile ukuze ube nekhono ekusebenziseni le ndlela. I-linear regression iyithuluzi eliwusizo ekuhlaziyweni kwedatha futhi inganikeza ukuqonda okujulile ngobudlelwano phakathi kweziguquguquko.
