Logistics

  1. ​Umaima Afifa- uafifa13@g.ucla.edu
  2. Trevor McCarthy- trevormccarthy2014@gmail.com
  3. Brian T. - brianta46@gmail.com
​​​

Statistical analysis resources

Here are some of the resources to learn about different Statistical Methods used in modern research. 
  • Resources
    • ​Zotero Library
      • This library contains Links to books and online resources that outline different statistical methods as well as good example papers that uses ANOVA test. 
    • HandBook of Biological Statistics - This book outlines different relevant Statistical methods applied to biological research and which method is applicable to what type of data. ​

MATLAB Materials

These videos cover many of the basic coding principles and skills. They are additional resources available to you beyond the training sessions and lectures. They are tailored for complete novices, and teach you the tools you need to begin creating more complex programs

​

Data Analysis

This section includes videos explaining key statistics concepts, as well as videos walking through the application of these concepts to the data obtained in our first Visual Acuity paper using MATLAB

The statistics concepts are important for any researcher, and Patrick's MATLAB application of them to his data analysis can be adapted to fit your needs. Many of the MATLAB videos provide additional explanation of the concepts.

Videos with important statistics concepts are marked with an asterisk (*)
  • Basic Analysis in MATLAB (Scatter Plot & Linear Fit)
  • Chi^2 Concepts
  • Basic Chi^2 Fitting in MATLAB
  • Improved Chi^2 Fitting in MATLAB​​
    • Code
    • Part 1 (3:59) *
      • Removing Outliers
      • Normalized Distribution (y/x) 
    • Part 2 (3:36) 
      • Removing Outliers in MATLAB
      • removeOutliers function
    • Part 3 (1:29)
      • Organizing Your Data
    • Part 4 (6:53)
      • Reading in Data in MATLAB
      • readCsv function
    • Part 5 (5:32) *
      • Estimating Standard Errors of Measurements
      • calculateStandardErrors function 
    • Part 6 (11:44) *
      • Using the readCsv function to get our data
      • Using our improved estimation of the standard errors to improve our fit quality
    • Part 7 (6:59)
      • Creating a pointSlope function to graph our scatter plots
    • Part 8 (7:17) *
      • Fixed intercept Chi^2 minimization fit (y = ax)
    • Part 9 (6:15) *
      • Evaluating reduced Chi^2 (goodness of fit)
    • Part 10 (7:56)
      • Creating functions for our y = ax and y = ax + b Chi^2 fitting
    • Part 11 (17:07) *
      • Graphing Chi^2 vs. slope parameter (y = ax fit)
    • Part 12 (15:08) *
      • Estimating standard error of y = ax fit parameters from Chi^2 contour
      • Improving graph of Chi^2 vs. slope parameter
    • Part 13 (11:47) *
      • Estimating standard error of y = ax + b fit parameters from Chi^2 contour
    • Part 14 (18:35)
      • Graphing Chi^2 vs. slope and intercept parameters (y = ax + b fit)
    • Part 15 (15:39)
      • Graphing Chi^2 vs. slope and intercept parameters (y = ax + b fit) cont.
    • Part 16 (11:34)
      • Adapting our analysis to automatically analyze and graph every protocol for a given subject
    • Part 17 (6:23)
      • Auto-saving plots
    • Part 18 (9:10)
      • Creating templates for structs to store fit parameters for output
    • Part 19 (10:09)
      • Storing fit parameters and Chi^2 values in structs
    • Part 20 (5:33)
      • Outputting fit parameters and Chi^2 values to central spreadsheet
    • Part 21 (3:30)
      • Getting a list of all subjects in the data folder (getSubjects function)
    • Part 22 (9:26)
      • Adapting our analysis to automatically run every subject
  • Assessing Correlation
    • Advantages over population statistics​
    • Plotting correlation in MATLAB
      • Code
  • Hypothesis Testing 
  • Hypothesis Testing in MATLAB
​​