Outline Class Intros Overview of Course Example Research Project.

Outline

• Class Intros

• Overview of Course

• Example Research Project

• What are your goals?

• What types of problems? datasets?

• Which software do you currently use?

Introductions

Breadth vs. Depth vs. Relevancy

Class

Project

Question

Hypothesis

Data

Analytics

Charts

Answer

57 59 61 63 65 67 69 71 73 75 77150

170

190

210

230

250

270

Height (inches)

Wei

ght (

poun

ds)

Are height and weight related?

Question

Hypothesis

Data

Analytics

Charts

Answer

Can we put a person on Mars by 2025?

Question

Hypothesis

Data

Analytics

Charts

Answer

What determines housing prices?

LocationSquare Feet

Crime

Number of VariablesAnalyzed

Week

1 2 3 4 5 6 7

6+

5

4

3

2

1

Data Visualization - MathematicsMean

StandardDeviation

Correlation

Base Camp: Standard Deviation

85 95 105 115 125 135 1450

5

10

15

20

25

30

Bins

Freq

uenc

y

Temperature Variation Across Cities in 2011

San Francisco

Boston

30 60 90

Austin

30 60 90

30 60 90

San Diego

30 60 90

30 60 90

Tampa Bay

Normal Distribution

Distribution of Height

Normal Distribution

Outliers

Identify

Remove?

Correlation• To what degree are two variables related?

57 59 61 63 65 67 69 71 73 75 77150

170

190

210

230

250

270

Height (inches)

Wei

ght (

poun

ds)

Excel Pivot Table

Excel Analysis Pak

Write Code/ Program- Input Data- Analyze- Graphics

Datasets, etc.

Enter CommandsView Results

R / R-Studio

Currently, how many R Packages?

At the command line enter: dim(available.packages()) available.packages()

Correlation Matrix

Multivariate Regression

Y

X’s

HeightY

X4X3X2X1

Frequently Used Algorithms

Predictive AnalyticsData AnalysisSoftware Statistics Data Mining