Berikut ini adalah penjelasan dan demonstrasi tentang analisis regresi linear.
Melakukan pemeriksaan secara deskriptif atas variabel-variabel penelitian (bagian 1). Bagian ini terdiri dari informasi statistik deskriptif dan density sekaligus histogram setiap variabel penelitian.
| Descriptives | ||||
|---|---|---|---|---|
| neu | trust | hi | mandiri | |
| N | 400 | 400 | 400 | 400 |
| Missing | 0 | 0 | 0 | 0 |
| Mean | 19.9 | 18.0 | 20.0 | 15.3 |
| Median | 20.0 | 17.4 | 20.2 | 15.7 |
| Standard deviation | 7.63 | 4.52 | 7.44 | 6.94 |
| Minimum | 3.86 | 6.55 | 1.16 | -4.10 |
| Maximum | 36.9 | 35.7 | 34.9 | 36.1 |
Ini merupakan scatterplot antara kemandirian dan neuroticism
Berikut ini adalah output regresi di bagian 1, latihan 1
| Model Fit Measures | |||||||
|---|---|---|---|---|---|---|---|
| Overall Model Test | |||||||
| Model | R | R² | Adjusted R² | F | df1 | df2 | p |
| 1 | 0.598 | 0.357 | 0.356 | 221 | 1 | 398 | <.001 |
Note. Models estimated using sample size of N=400 | |||||||
Model regresi kita cukup baik menjelaskan tren pada data (F(1,398)=221, p=.001) dan mampu menjelaskan 35.7% varians tingkat kemandirian.
| Omnibus ANOVA Test | |||||
|---|---|---|---|---|---|
| Sum of Squares | df | Mean Square | F | p | |
| neu | 6874 | 1 | 6874.4 | 221 | <.001 |
| Residuals | 12359 | 398 | 31.1 | ||
Note. Type 3 sum of squares | |||||
| [3] | |||||
Sum of squares residual jauh lebih besar daripada neu -- artinya, banyak varians tingkat kemandirian yang tidak bisa dijelaskan oleh neu saja.
| Model Coefficients - mandiri | |||||||
|---|---|---|---|---|---|---|---|
| 95% Confidence Interval | |||||||
| Predictor | Estimate | SE | Lower | Upper | t | p | Stand. Estimate |
| Intercept | 4.467 | 0.7808 | 2.932 | 6.002 | 5.72 | <.001 | |
| neu | 0.544 | 0.0366 | 0.472 | 0.616 | 14.88 | <.001 | 0.598 |
Kecenderungan neuroticism ibu dapat menjelaskan variasi kemandirian anak (B = 0.544 95% CI [0.472, 0.616], SE = 0.036, t = 14.88, p = .001).
| Cook's Distance | ||||
|---|---|---|---|---|
| Range | ||||
| Mean | Median | SD | Min | Max |
| 0.00241 | 9.95e-4 | 0.00396 | 2.49e-10 | 0.0338 |
Apabila outlier tidak disertakan dalam analisis, maka perubahan rerata, median, dan standar deviasi keseluruhan sampel kurang dari 1 dari nilai asalnya
Garis diagonal dari Q-Q Plot tandanya residual berdistribusi normal dan memenuhi asumsi OLS.
Nilai residual tidak berubah mengikuti nilai fitted Y artinya model regresi ini homokedastik dan memenuhi asumsi OLS.
Nilai residual tidak berubah mengikuti nilai prediktor/X artinya model regresi ini homokedastik dan memenuhi asumsi OLS.
Ini adalah output bagian 1, Latihan 2
| Model Fit Measures | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Overall Model Test | |||||||||
| Model | R | R² | Adjusted R² | AIC | BIC | F | df1 | df2 | p |
| 1 | 0.549 | 0.301 | 0.300 | 2547 | 2559 | 172 | 1 | 398 | <.001 |
| 2 | 0.650 | 0.423 | 0.420 | 2472 | 2488 | 146 | 2 | 397 | <.001 |
Note. Models estimated using sample size of N=400 | |||||||||
Model 2 (F(2,397) = 146, p = .001, Adj. R2 = .420) dapat menjelaskan varians tingkat kemandirian anak lebih baik daripada Model 1 (F(1,398) = 172, p = .001, R2 = .300), dengan overlapping variances sebesar 42% dibanding 30%.
| Model Comparisons | |||||||
|---|---|---|---|---|---|---|---|
| Comparison | |||||||
| Model | Model | ΔR² | F | df1 | df2 | p | |
| 1 | - | 2 | 0.122 | 83.7 | 1 | 397 | <.001 |
Ketika dibandingkan, Model 1 dan Model 2 berbeda signifikan (F(1,397) = 83.7, p = .001. ΔR2 = .122), artinya selisih R2 Model 1 dan Model 2 = .122 atau R2 naik sebesar 12.2%
| Omnibus ANOVA Test | |||||
|---|---|---|---|---|---|
| Sum of Squares | df | Mean Square | F | p | |
| hi | 5799 | 1 | 5798.8 | 172 | <.001 |
| Residuals | 13435 | 398 | 33.8 | ||
Note. Type 3 sum of squares | |||||
| [3] | |||||
| Model Coefficients - mandiri | |||||||
|---|---|---|---|---|---|---|---|
| 95% Confidence Interval | |||||||
| Predictor | Estimate | SE | Lower | Upper | t | p | Stand. Estimate |
| Intercept | 5.064 | 0.8346 | 3.423 | 6.704 | 6.07 | <.001 | |
| hi | 0.513 | 0.0391 | 0.436 | 0.589 | 13.11 | <.001 | 0.549 |
| Cook's Distance | ||||
|---|---|---|---|---|
| Range | ||||
| Mean | Median | SD | Min | Max |
| 0.00242 | 0.00104 | 0.00405 | 6.47e-9 | 0.0331 |
| Collinearity Statistics | ||
|---|---|---|
| VIF | Tolerance | |
| hi | 1.00 | 1.00 |
| [3] | ||
| Omnibus ANOVA Test | |||||
|---|---|---|---|---|---|
| Sum of Squares | df | Mean Square | F | p | |
| hi | 460 | 1 | 460.4 | 16.5 | <.001 |
| neu ✻ trust | 2339 | 1 | 2338.8 | 83.7 | <.001 |
| Residuals | 11096 | 397 | 28.0 | ||
Note. Type 3 sum of squares | |||||
| [3] | |||||
| Model Coefficients - mandiri | |||||||
|---|---|---|---|---|---|---|---|
| 95% Confidence Interval | |||||||
| Predictor | Estimate | SE | Lower | Upper | t | p | Stand. Estimate |
| Intercept | 4.2209 | 0.76501 | 2.7169 | 5.7248 | 5.52 | <.001 | |
| hi | 0.2002 | 0.04932 | 0.1032 | 0.2971 | 4.06 | <.001 | 0.54856 |
| neu ✻ trust | 0.0195 | 0.00213 | 0.0153 | 0.0237 | 9.15 | <.001 | -0.00271 |
Pendapatan keluarga dapat menjelaskan variasi kemandirian anak (B = 0.200 95% CI [0.103, 0.297], SE = 0.04, t = 4.06, p = .001).
Interaksi antara neuroticism dengan trust in organismic development juga signifikan dalam menjelaskan varians kemandirian anak (B = 0.019 95% CI [0.015, 0.023], SE = 0.002, t = 9.15, p = .001).
| Cook's Distance | ||||
|---|---|---|---|---|
| Range | ||||
| Mean | Median | SD | Min | Max |
| 0.00243 | 8.68e-4 | 0.00439 | 1.08e-7 | 0.0423 |
| Collinearity Statistics | ||
|---|---|---|
| VIF | Tolerance | |
| hi | 1.92 | 0.521 |
| neu ✻ trust | 1.92 | 0.521 |
| [3] | ||
VIF masih pada taraf yang aman (<5 ) sehingga multikolinearitas bukan problem yang perlu dikuatirkan
Ibu dengan trust in organismic development yang tinggi (+1SD), korelasi antara kecenderungan neuroticism dengan kemandirian anak juga semakin positif/menguat.
[4]
[1] The jamovi project (2025). jamovi. (Version 2.7) [Computer Software]. Retrieved from https://www.jamovi.org.
[2] R Core Team (2025). R: A Language and environment for statistical computing. (Version 4.5) [Computer software]. Retrieved from https://cran.r-project.org. (R packages retrieved from CRAN snapshot 2025-05-25).
[3] Fox, J., & Weisberg, S. (2024). car: Companion to Applied Regression. [R package]. Retrieved from https://cran.r-project.org/package=car.
[4] Lenth, R. (2025). emmeans: Estimated Marginal Means, aka Least-Squares Means. [R package]. Retrieved from https://cran.r-project.org/package=emmeans.