## HW Readings |
## Data sets |

Intro to Data - print, read, highlight/annotate and answer Q 1.2 and 1.3
Read this link of standard deviation. Data Dredging - read, take notes or outline. Stats/Nature of Science ReadingsStats Average Stats Std Deviation vs MAD Stats Ritual Stats Significance The New Yorker Articles (and other sources)Salmonella should scare the crap out of you! ## Resources for UnitsLearning Excel - go hereInteractive Graphs and whatnotTABLEAUIntro to TableauMeasures of Central Tendency Distributions What is Central Tendency Balancing activity Guided lesson on mean, median and mode Learning RGo here: Datacamp R CHEAT SHEETCreate an account and start enroll in Intro to RGraphing in R:Sites for InfographicsInformationisbeautiful.com https://marketplace.visual.ly/infographics http://piktochart.com/ OptimizationOptimization instructions Bathing Friends file Optimization problems Use Optima for Animals pg 18, 70, 85 - Use solver for Moose data K-Means ClusteringExcel Wine Data Clustering Instructions Network AnalysisNetwork graphs with Fusion Tables Further explanation Even further explanation H Band Class template B Band Class Template ...And the results Linear RegressionIntro to Correlation and Regression Spurious Correlations Assumptions of Regression 1st Data set - Lions, black noses and ages 2nd Data set - Face width and penalty minutes **How to make sense of the 2nd data set 3rd dataset - Iron and Phytoplankton growth First lesson on Regression in Excel BEST EXPLANATION OF CORRELATION VS. REGRESSION ## Experimental Design PowerPoint## Experimental design project guidelinesDesign an experiment1. Research the topic. 2. Design your experimental protocol by considering the following: - How will you collect your data?
- How will you get an appropriate sample of your target population? What sampling protocol are you going to use and why?
- What are your explanatory and response variables?
- What confounding variables should you be aware of?
- What is your control group? Experimental group?
- How will manage the 4 principles of experimental design?
## Mini data projectUsing the included Motor Trend cars dataset calculate the following:
- Mean and median mpg by cylinder number
- Mean and median hp by cylinder number
- Mean and median qsec by cylinder number
- Create a boxplot of mpg by cylinder
- Create a bar chart of hp per car model
THEN... do the same sort of thing but for either one of the datasets above or a dateset of your own choosing. ## Infographics activity1. Scour the web for 2 excellent data visualizations/infographics.
For each write a short paragraph to answer each of the following questions: - Why did you pick this visualization? - Explain the data that is displays. How many axes are shown? How many data points? (Estimate this) Are there any summary stats shown, and if so which ones? - What makes it good? How does it accomplish something more than displaying numbers... - How could it be improved? |
Geyser data Baseball salary data, instructions click here Dissolved oxygen data, instructions click here Cigarette data Tufte Dataset Data for histogram Good histogram data Practice data setsed spending - best graph choice deaths from tigers - best graph choice salmon length and mass - best choice to demonstrate relationship sea anemone startle response times: - best way to demonstrate "personality" of individual anemones.
- frequency distribution of 1st startle measurement.
Confidence Intervals and T-testsBlackbird Beer and mosquitoes Weddell seals Rat reciprocity T test Mini ProjectPairedData descriptions Anorexia data Blink ChickWeight Corn Grapefruit Horses BloodLead Google Fusion TablesBaseball data Instructions for Activity Tableau datasetsPopulation by County ## Quiz data for 10/3/14Graphing Test doc*** Immediately save as FirstLast_DataGraphingQuiz Q2 - Endangered species Q3 - Spermatophore masses Q4 - Fruits and photosynthesis Q5 - Hurricanes ## Quiz data for 12/12/14## Data Analysis in Practice- Create a group of 3 members.
- Research an application of data analysis/modeling that interests you. There are no repeats so act fast to reserve the topic you like.
- You should pick an example that provides sufficient detail on the analytic technique or procedure so that you can explain it to the class.
- You will produce a 10 min presentation on your topic.
- Brief overview of the application of the technique. Introduce the story.
- More detail on the technique itself. You may have to do some research on the technique to better understand how it works or what it does.
- Explain how the technique improved/enhanced/simplified the situation. In other words how did the data modeling produce better results or understanding?
**Read this NYTimes article for a good sample**
## PBA stuffThe flowchart from class
Old Rubric outline:**5 categories @ 4 pts each, 20 points total.**- Exploratory Data Analysis - how well did you explore your data set?
- Questions - were they interesting? Adequately answered using data analysis?
- Graphs - clear, well labeled, appropriate type.
- Grammar/Spelling - self explanatory.
- Summary - how well did you wrap up the story?
- RUBRIC
New PBA Data Project Tasks- Initial question - clear and concise, testable
- Background information - cited
- Data collection
- Data merging, refinement and cleaning
- Analysis
- Graphs of findings
- All content on a website (weebly, wix, etc.)
- Unique creative visualization
## Miscellaneous resources |