Present Remotely

Send the link below via email or IM

• Invited audience members will follow you as you navigate and present
• People invited to a presentation do not need a Prezi account
• This link expires 10 minutes after you close the presentation

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

Statistics

No description
by

Claudia Vallin

on 10 January 2013

Report abuse

Transcript of Statistics

Statistics Heidi Y. Matos Galicia
Lashawn Peña
Chavely Valdes
Claudia Vallin MIT Quantifying Biology Workshop 2013 Overview Statistics are a tool to analyze and interpret numerical data

Two main branches : descriptive and inferential.

Descriptive: used to say something about a set of information that has been collected.

Inferential: used to make predictions or comparisons about a larger group (a population) using information gathered about a small part of that population. Examples Descriptive Statistics Inferential Statistics Mean: average
Median: middle value Standard deviation: how the mean varies
Standard error: how accurate the sample represents the population Which tells us HOW is our sample Involves generalizing beyond the data, something that descriptive statistics does not do.

How likely is something to happen or comparing differences between groups. Applications With such predictions, you can test the probability, which is the likelihood that a specific event will occur.

Measured comparisons of groups can be mathmatically stated if groups are different or have a pattern rather than just chance.

This analysis of prediction or comparisons becomes a tool to test the proposed explanation of a phenomenon (h a vs. h n). Some tests include:
T-test
ANOVA
Analysis of Correlation
..and some more Why MatLab? Functionality for basic numerical computations.

Contains umpteen variety of toolboxes that allows users to perform a wide range of applications. Users may also create their own toolboxes.

Stores information in matrices, making data analysis easier.

Easy to use and common in many fields. Calculator
Graphs and and visualization of dataPlotting (x,y) and (x,y,z) data, bar graphs, histograms
Statistics Toolbox
Standard deviation, average or mean value of array, regression techniques (including linear, non linear), max valyes, median, most frequent value Examples Wild et al. 2011 "R" Statistic
Software Examples Kolmogorov-Smirnov Test

ANOVAs

T-test Pfannkuche et al., 2011 Applications Bartlett Test of Homogeneity of Variances (“stats” package)
different age groups (24hr,48hr & 96hr)
Robust fitting of linear model (“mass” package)
Other tests such as: Mann-Whitney U-Tests, Wilcoxon matched-pairs signed rank tests T-tests & ANOVAs. Python Programming language

1. Faster and more effective