Eğitmen: Dr. H. Sait Ölmez
Eğitimin İçeriği:
Descriptive Statistics
- Introduction
- Major types and characteristics of data
- Experiment design and setup: Identifying the target and predictor variables; Collecting and preparing data for analysis
- Exploratory Data Analysis (EDA): Visualization techniques for summarizing and displaying
- Univariate Analysis of Data
- Tabular presentation of data: Histograms (frequency distribution)
- Common shapes of distributions and skewness
- Measure of central tendency in data (mean, median, mode, range)
- Measure of spread (variability) in data (variance and standard deviation)
- Quantile-Quantile plots
- Bivariate Analysis of Data from a visualization perspective
- Relations between any combinations of categorical and continuous variables
- A primer on Probability
- Basic rules of probability
- Conditional probability (Bayes’ rule)
- Discrete probability distributions
- Continuous probability distributions
- Properties of a Normal Distribution
- Standard Normal Distribution and its applications
Inferential Statistics
- Point/Interval Estimators
- Basic terminology in sampling process
- Description and calculation of point estimators
- The use and importance of interval estimators
- Forming and interpreting the uncertainty around a point estimation using confidence intervals
- Hypothesis Testing
- Forming a proper hypothesis
- Critical components of a hypothesis test: Significance level and the p-value
- 1-sample z-test vs 1-sample t-test
- 2-sample t-tests
- Types of errors (Type I and Type II)
- Power of a hypothesis test and the factors that affect power
- Problems with hypothesis tests and why the p-value isn’t enough
- Effect size and its importance from a practical standpoint
- Statistical Tests
- A summary on statistical tests and which one to use when
- Pearson’s correlation
- Spearman’s rank-order correlation
- Point-Biserial correlation
- Chi-square test
- One-way ANOVA test
- Simple/Multiple Linear Regression
- Simple Linear Regression
- Ordinary Least Squares solution
- Multiple Linear Regression
- Interpretation of regression coefficients
- Assessing the overall quality of a regression
- Assumptions of a Linear Regression solution and how to check them
- Outliers in Linear Regression and interpretation of Cook’s distance
- Converting nominal predictors to numerical values and the dummy variable trap
- Model selection process
- Regularization in Linear Regression
- What is regularization and why do we need it?
- Ridge and Lasso regularization
Eğitimin Hedef Kitlesi: Kurum içinde “Veri Analisti” ve/veya “Veri Bilimci” olarak çalışanlar.
Eğitimin Seviyesi: Başlangıç-Orta
Eğitim Süresi: 5 gün
Ek Bilgiler: Katılımcıların Python programlama dilini pratik seviyede kullanabildikleri varsayılmaktadır.