Mencocokkan model logistik

Banyak permasalahan bisnis memerlukan prediksi variabel respons biner. Calon atasan Anda mungkin perlu mendeteksi email spam, penipuan kartu kredit, atau penyakit langka.

Model logistic regression adalah metode andalan untuk permasalahan klasifikasi biner.

Pada latihan ini, Anda akan menggunakan himpunan data Parkinson dari repositori UCI. Himpunan data ini berisi berbagai pengukuran suara biomedis dari orang dengan dan tanpa penyakit Parkinson.

Anda akan menggunakan variabel berikut dari himpunan data:

status - 1 - jika seseorang mengidap penyakit Parkinson, 0 - jika tidak,
NHR - ukuran rasio komponen derau terhadap komponen tonal dalam suara,
DFA - eksponen penskalaan fraktal sinyal.

Himpunan data tersedia sebagai parkinsons.

Latihan ini adalah bagian dari kursus

Latihan Pertanyaan Wawancara Statistik di R

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

# Plot status vs NHR
___(status ~ ___, data = ___)

# Plot status vs DFA
___(___ ~ ___, ___ = ___)

Edit dan Jalankan Kode

Latihan ini adalah bagian dari kursus

Latihan Pertanyaan Wawancara Statistik di R

SkillTag.level.advancedSkillTag.label

4.7+

Mulai Kursus Gratis

Want to increase your odds of acing your job interview? If so, brush up on your knowledge of probability theory. In this chapter, we'll roll dice and shoot baskets to explain probabilities using real-life examples.

Exercise 1: Discrete distributions Exercise 2: Probability functions Exercise 3: Bernoulli trials Exercise 4: Binomial distribution Exercise 5: Continuous distributions Exercise 6: Uniform distribution Exercise 7: Shape of normal distribution Exercise 8: Sample from normal distribution Exercise 9: Central limit theorem Exercise 10: Law of large numbers Exercise 11: Simulating central limit theorem

If the job description appeals to you review descriptive statistics before the interview. In this chapter, you will practice exploratory data analysis (EDA) using natural gas prices and data from a survey analysis.

Exercise 1: Descriptive statistics Exercise 2: Centrality measures Exercise 3: Variability measures Exercise 4: Categorical data Exercise 5: Survey analysis Exercise 6: Data encoding Exercise 7: Time series Exercise 8: Time series object Exercise 9: Wrangling time series Exercise 10: Principal Component Analysis Exercise 11: PCA - rotation Exercise 12: PCA - dimension reduction

March confidently into your job interview after reviewing confidence intervals. We'll review the t-test, ANOVA, and normality tests to prepare you for statistics-based coding questions.

Exercise 1: Normality tests Exercise 2: Shapiro-Wilk test Exercise 3: Q-Q plot Exercise 4: Inference for a mean Exercise 5: Confidence interval Exercise 6: One-sample t-test Exercise 7: Comparing two means Exercise 8: Two-sample t-test Exercise 9: Paired test Exercise 10: ANOVA Exercise 11: Comparing groups Exercise 12: ANOVA for plant growth

Is your potential employer planning to test your R skills? Make sure you’re prepared and practice model evaluation beforehand. In this chapter, we will fit and evaluate linear and logistic regression models using various biomedical datasets. By the end of this chapter, you’ll be fully prepared to answer any question the interviewer throws your way!

Exercise 1: Kovarians dan korelasi Exercise 2: Menghitung kovarians secara manual Exercise 3: Hubungan linear Exercise 4: Hubungan nonlinier Exercise 5: Model regresi linear Exercise 6: Mengestimasi model linear Exercise 7: Memprediksi dengan model linear Exercise 8: Model regresi logistik Exercise 9: Mencocokkan model logistik

Latihan Saat Ini

Exercise 10: Memprediksi dengan model logistik Exercise 11: Evaluasi model Exercise 12: Pendekatan validation set Exercise 13: Evaluasi regresi Exercise 14: Evaluasi klasifikasi Exercise 15: Penutup