Final Exam: Statistical Analysis and Modeling in R

WHAT YOU WILL LEARN

• 

  Recall the sets of statistical tools used to understand data
  

  compare and contrast population metrics with sample metrics
  

  recall the characteristics of discrete and continuous probability distributions
  

  analyze data that follows a uniform distribution
  

  interpret qq plots for normally and non-normally distributed data
  

  sample and analyze data that follows a uniform distribution
  

  recall measures of central tendency and measures of dispersion
  

  estimate parameters of the population and interpret confidence intervals
  

  construct hypothesis statements in the context of a statistical test
  

  posit the null hypothesis and alternative hypothesis of a statistical test
  

  recall implications of the p-value and significance level alpha
  

  recall the assumptions made by the one-sample t-test
  

  recall the assumptions made by the two-sample t-test
  

  summarize the differences and use cases for parametric and non-parametric models
  

  recall the assumptions made by the anova test
  

  perform the wilcoxon signed-rank test
  

  check the assumptions of the paired samples t-test
  

  implement the one-sample t-test and interpret results
  

  examine and interpret the data for regression
  

  examine and visualize data for regression
• 

  perform regression using decision trees
  

  perform regression using random forest
  

  outline the main characteristics of ensemble learning
  

  perform the one-sample t-test and interpret results
  

  recall the basic characteristics of machine learning models
  

  fit a straight line on data to build a regression model and evaluate the model
  

  explore and visualize the relationships in data
  

  perform simple linear regression with a single predictor
  

  recall the key metrics to evaluate classifiers
  

  fit and interpret the s-curve of logistic regression
  

  train and evaluate a logistic regression model
  

  recall the basic structure of decision tree models
  

  explore and pre-process data before model fitting
  

  train a model on an imbalanced dataset
  

  use decision tree models for prediction
  

  recall the techniques used to evaluate clustering models
  

  investigate and visualize data before fitting a model
  

  find the optimal number of clusters using the elbow method and silhouette score
  

  recall characteristics of overfitted and underfitted models
  

  describe the bias-variance trade-off