layout:true <div class="header" style="display:block; text-align: left; color:gray; font-size:1em; position: fixed; top: 0px; left: 0px; height: 30px;vertical-align:middle;margin:7px 0 0 0;width:100%;background: #fcfcfc; background: -moz-linear-gradient(top, #fcfcfc 0%, #d1d1d1 100%); background: -webkit-linear-gradient(top, #fcfcfc 0%,#d1d1d1 100%); background: linear-gradient(to bottom, #fcfcfc 0%,#d1d1d1 100%); filter: progid:DXImageTransform.Microsoft.gradient( startColorstr='#fcfcfc', endColorstr='#d1d1d1',GradientType=0 );"> <img src="images/datapolitan_transparent_small.png" style="position: fixed;top: 2px; left: 5px; width: 14%;"> <p style="display:block;text-align:left;color:gray;font-size:1em; position: fixed; top: 0px; left: 155px; height: 30px;vertical-align:middle;margin:7px 0 0 0; ">Leveraging Analytics</p> </div> <div class="footer" style="display:block;color:gray;position:fixed;bottom: 0px;left:0px;height:30px;vertical-align:middle;margin:0 0 0 0;width:100%;background: #fcfcfc;background: -moz-linear-gradient(top, #fcfcfc 0%, #d1d1d1 100%);background: -webkit-linear-gradient(top, #fcfcfc 0%,#d1d1d1 100%);background: linear-gradient(to bottom, #fcfcfc 0%,#d1d1d1 100%);sfilter: progid:DXImageTransform.Microsoft.gradient( startColorstr='#fcfcfc', endColorstr='#d1d1d1',GradientType=0 );"> <p class="footer"> <span xmlns:dct="http://purl.org/dc/terms/" property="dct:title">Leveraging Analytics</span> by <a xmlns:cc="http://creativecommons.org/ns#" href="http://www.datapolitan.com" property="cc:attributionName" rel="cc:attributionURL">Richard Dunks</a> and <a xmlns:cc="http://creativecommons.org/ns#" href="https://www.tinypanther.com/" property="cc:attributionName" rel="cc:attributionURL">Julia Marden</a> is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/">Creative Commons Attribution-ShareAlike 4.0 International License</a>.<a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/"><img alt="Creative-Commons-License" style="border-width:0" src="https://i.creativecommons.org/l/by-sa/4.0/80x15.png" /></a> </p> </div> -- class:center, middle  # Leveraging Analytics - - - ## Instructor: Richard Dunks and Elana Shneyer ### Follow along at: http://bit.ly/leveraging-analytics #### See the code at: http://bit.ly/leveraging-analytics-code --- class:center,middle # Welcome --- # Data Driven Culture  --- # A Few Ground Rules -- + Step up, step back -- + Be curious and ask questions! -- + Assume noble regard and positive intent -- + Respect multiple perspectives -- + Listen deeply -- + Be present (phone, email, social media, etc.) --- # Introduce Yourself to Your Neighbor + Who are you? + Where do you work? + What has been the proudest moment in your job? ??? + Participants engage in a collaborative introduction exercise to engage their fellow participants and begin the day talking + Participants relax into the container created by the facilitators --- # What to Expect Today + 10:00 – Data Analytics 101 + 10:15 - Introduction to Problem Ideation + 10:45 – Process Mapping + 12:15 – Lunch + 12:45 – Data Analytics Exercise + 1:30 – Building a Data-Driven Culture + 2:30 – Dismissal --- # Housekeeping -- + We’ll have 30 minutes for lunch -- + Class will start promptly after breaks -- + Feel free to use the bathroom if you need during class -- + Please take any phone conversations into the hall to not disrupt the class --- # The Value of Data -- + Data tells a story about something that's happened -- + Can describe what happened directly or indirectly --  --- class: center,middle # Are All Data Points Created Equal? --- class:middle > Facts do not "speak for themselves." They speak for or against competing theories. Facts divorced from theory or visions are mere isolated curiosities. ##-Thomas Sowell *A Conflict of Visions* --- # Data Driven Decisions Require Humans  .caption[Image Credit: 100 lion, [CC BY-SA 4.0](http://creativecommons.org/licenses/by-sa/4.0), via [Wikimedia Commons](https://commons.wikimedia.org/wiki/File%3AIphone-62.jpg)] ## [How Intel lost out on the contract of a lifetime](http://appleinsider.com/articles/13/05/16/intel-chips-could-have-powered-first-iphone-ceo-otelini-says) --- exclude:true # Being data-driven doesn't mean blindly following data  .caption[Image Credit: zhouxuan12345678, [CC BY-SA 2.0](https://creativecommons.org/licenses/by/2.0/), via [Flickr](https://www.flickr.com/photos/53921113@NO2/5453212152)] --- > Data is only as valuable as the decisions it enables. ### -[Ion Stoica](https://twitter.com/databricks/status/810190036624875520) -- > If data is enabling important decisions, then the data is important too ### - [Richard Dunks](https://twitter.com/Datapolitan/status/921435585386033153) ??? + Facilitators emphasize data as a strategic resource for managers --- # What is Analysis? -- >“Analysis is simply the pursuit of understanding, usually through detailed inspection or comparison” ## - [Carter Hewgley](https://www.linkedin.com/in/carterhewgley), Senior Advisor for Family & Homeless Services, Department of Human Services, District of Columbia --- exclude:true class:center, middle # Data Analysis Should Drive Decision Making #   ##   --- exclude:true class:center, middle # Data Analysis Should Drive Decision Making # This is what it means to be "data driven" ##   --- exclude:true class:center, middle # Data Analysis Should Drive Decision Making # This is what it means to be "data driven" ## And good analysis should lead to good decisions --- class:center,middle # What Analysis Isn't --- # Writing a report  .caption[Image Credit: RRZEicons, [CC BY-SA 3.0](http://creativecommons.org/licenses/by-sa/3.0), via [Wikimedia Commons](https://commons.wikimedia.org/wiki/File:Report.svg)] --- # Creating a dashboard  .caption[Image Credit: Chabe01, [CC BY-SA 4.0](http://creativecommons.org/licenses/by-sa/4.0), via [Wikimedia Commons](https://commons.wikimedia.org/wiki/File%3ADashboard_OS_X.svg)] --- # Generating an alert  .caption[Image Credit: Tokyoship, [CC BY-SA 3.0](http://creativecommons.org/licenses/by-sa/3.0), via [Wikimedia Commons](https://commons.wikimedia.org/wiki/File%3ASimple_Alert.svg)] --- name:avp # It's Putting Them All Together  --- class: middle > "If you do not know how to ask the right question, you discover nothing." ## - W. Edward Deming --- # Our Method For Generating Ideas --  + **Ideate** - On your own, generate at least 3 ideas (ideally more), each on their own Post-It Note ####    --- # Our Method For Generating Ideas  + **Ideate** - On your own, generate at least 3 ideas (ideally more), each on their own Post-It Note + **Discuss** - Review the ideas generated --- # Our Method For Generating Ideas  + **Ideate** - On your own, generate at least 3 ideas (ideally more), each on their own Post-It Note + **Discuss** - Review the ideas generated + **Decide** - Come to a consensus as a group --- # Exercise - Reducing Noise Complaints in NYC + Between 1 Jan and 30 Sept 2017, there were an average of 1,271 noise-related 311 service requests a day + The same period in 2016 had an average of 1,180 noise-related 311 service requests a day + You've been tasked with decreasing noise complaints in the city + .red[What questions would you ask to kick off a data analysis?]  ??? + A facilitated group ideation exercise to get them thinking about key questions and problems + Task to participants: (1) take 5 minutes to come up with your own questions and be prepared to share with the group (2) take 5 minutes and discuss with your partner (3) discuss the questions as a group + Facilitator helps scope an analytical question that will be developed throughout the morning lecture session + Group should have written down a series of questions to be discussed --- name:process-map # Process Mapping -- + Allows you to identify and strategize for key steps in your analysis -- + Helps sequence tasks and identify gaps in understanding -- + Provides a basis for documenting work --- # Process Mapping  .caption[By Scottsm1991 (Own work) [CC BY-SA 3.0](http://creativecommons.org/licenses/by-sa/3.0), via Wikimedia Commons] ??? + Facilitator does the "I do" phase by describing a past project that was mapped out --- # Process Mapping (Our method)  --- exclude:true # Process Map  .caption[Analyzing pet licensing compliance in San Jose. Image Credit: Datapolitan [CC BY-SA 4.0](http://creativecommons.org/licenses/by-sa/4.0/)] --- # How to Create a Process Map --  + Identify the key challenge -- + Identify the outcome -- + Identify key way to validate the outcome (outputs)<br> -- _**How do we know we've got it right?**_ --- # Outcomes vs Outputs -- + Outcomes are the larger benefits and/or achievements you're trying to realize<br> -- (happiness, health, well-being, etc.) -- + Outputs are the tangible parts of your outcome<br> -- (survey responses, measured results, etc.) -- + Outputs enable us to find outcomes -- + Without outcomes, there is no need for outputs --- # How to Create a Process Map  + Identify the key challenge + Identify the outcome + Identify key way to validate the outcome (outputs)<br>_**How do we know we've got it right?**_ -- + Identify the key inputs (data, partners, etc) -- + Sequence the key questions to turn inputs into outputs --- # Key Tips  + Place each step on a Post-It Note ####    --- # Key Tips  + Place each step on a Post-It Note + Order and reorder as necessary -- + Some steps will need to be broken down ??? + Facilitator identifies the key parts of the process based on the graphic presented + Faciliator reminds participants to follow the process that works best for them --- # Reducing Noise Complaints  -- + Identify the key question/challenge -- + Identify the key outcome -- + Identify the outcome measures -- + Identify the key inputs -- + Sequence the key questions to turn inputs into outputs  .caption[[Image](https://www.flickr.com/photos/jackdorsey/272873611/) by [Flickr user Jack Dorsey](https://www.flickr.com/photos/jackdorsey/) [CC BY 2.0](https://creativecommons.org/licenses/by/2.0/)] ??? + The more involved "We do" phase where we do this together --- class:center,middle # 4 Concerns --- # 1. Technical -- + Having the right tools -- + Having the people who can use them -- + Making everything work together -- + _Potential trap: having a solution in search of a problem_ --- # 2. Legal -- + Laws -- + Regulations -- + Precedence/Past Practices -- + _Potential trap: not doing something because of mistaken assumptions_ --- exclude:true # When HIPAA Gets In The Way of Health Care  .caption[Image Credit: Hipaa Nurse Shredding Papers, by [Atlantic Training](http://www.atlantictraining.com/blog/hipaa-compliance-paper-shredding-illustration2/), [CC BY-SA 3.0](https://creativecommons.org/licenses/by-sa/3.0/deed.en_US)] [Learn more](http://www.nytimes.com/2015/07/21/health/hipaas-use-as-code-of-silence-often-misinterprets-the-law.html?_r=1) --- # 3. Cultural -- + “We’ve always done it this way” -- + “I’m not sure I understand how this works” -- + _Potential trap: being afraid of rocking the boat_ --- # 4. Political -- + Inter-departmental -- + Intra-departmental -- + Public relations -- + _Potential trap: not putting the necessary effort into something that will pay dividends to your office and ultimately to the organization as a whole_ --- class:center,middle # Do You Have An Example of This? --- # Benefits -- + Time, money, lives saved -- + Better delivery of services to stakeholders -- + More transparency -- + More accountability --- # What did you notice about this process? -- + Knowing the problem and sequencing the steps can be harder than working with data -- + Having these answers can make the analysis much easier -- + This is a process you can do with any challenge, no matter how big -- + Everyone has something to add, no matter how technical (or non-technical) they are ??? + Facilitator reflects with participants on the process mapping exercise --- class:center,middle # What is your role in this process? #   --- class:center,middle # What is your role in this process? # What are your concerns about this role? --- class:center,middle # WRAP-UP --- class:center,middle # LUNCH --- class:center, middle # WELCOME BACK! --- class: center,middle # Let's get some data --- # Definition of Open Data -- > Open data is data that can be freely used, shared and built-on by anyone, anywhere, for any purpose ## - [Open Knowledge International](http://blog.okfn.org/2013/10/03/defining-open-data/) --- # Key Features of Open Data -- + Availability and access -- + Reuse and redistribution -- + Universal participation --- # Open Data Benefits -- + Transparency -- + Releasing social and commercial value -- + Participation and engagement --- # New Yorkers Save Millions In Parking Tickets  .caption[Image Credit: [Ken Lund](https://www.flickr.com/photos/kenlund/7236966946), [CC BY-SA 2.0](https://creativecommons.org/licenses/by-sa/2.0/)] [Learn more](http://iquantny.tumblr.com/post/144197004989/the-nypd-was-systematically-ticketing-legally) --- # Open Data Concerns -- + Privacy (Personally identifiable information (PII), Mosaic Effect) -- + Confidentiality -- + Security --- # When Good Data Goes Bad  .caption[Image Credit: Kenny Louie, [CC BY 2.0](http://creativecommons.org/licenses/by/2.0), via [Wikimedia Commons](https://commons.wikimedia.org/wiki/File%3ANYC_TAXI_(7038011669).jpg)] [Gawker matches Taxi and Limousine Data with Paparazzi Photos](http://gawker.com/the-public-nyc-taxicab-database-that-accidentally-track-1646724546) --- class:center,middle # Links to NYC Open Data Portal for Exercise ## <a href="https://data.cityofnewyork.us/" target="_blank">NYC Open Data Portal</a> --- # Data for Exercise  #### [Click to download if you have problems](data/20160101_20160331_311NoiseContains.csv) --- # 5 Data Analytics Tasks -- 1. Sorting -- 2. Filtering -- 3. Aggregating (PivotTable) -- 4. Manipulating -- 5. Visualizing --- # Sorting -- + Reorganize rows in a dataset based on the values in a column -- + Can sort on multiple columns --- # Sorting by Date  --  --- # Sorting by Date   --- # Sorting by Date   --- # Filtering -- + Only show rows that contain some value -- + Can filter by multiple values -- + Can filter by values in multiple columns --- # Filtering by Agency Name  --- # Filtering by Agency Name  --- # PivotTables -- + A data summarization tool -- + Useful to quickly understand data -- + Can use to graph data totals --  --- # Creating a PivotTable  -- + Should default to all your data .red[unless you have any cells selected] -- + Should default to a new worksheet --- # Creating a PivotTable  ## Drag and drop fields to visualize + Row labels + Values + Filter + Column Labels --- # Creating a PivotTable  --- class:center,middle # Manipulating Data ## (In a good way...) --- # Extracting Hour From Timestamp --  --- class:middle,center [](https://support.office.com/en-us/article/HOUR-function-e2833b50-0db0-499b-acc5-e9ae03de8fbb) --- # Extracting Hour From Timestamp  --- # Extracting Hour From Timestamp  --- # Extracting Hour From Timestamp  --- # Extracting Hour From Timestamp  --- # Extracting Hour From Timestamp  --- # Extracting Hour From Timestamp  --- class:center,middle # When Are Noise Complaints Received?  --- # Charting Noise Complaints by Hour  + Refresh PivotTable --- # Charting Noise Complaints by Hour  + Refresh PivotTable + Find `Hour` and add it to "Rows" --- # Charting Noise Complaints by Hour + Refresh PivotTable + Find `Hour` and add it to "Rows" + Style the chart  --- exclude:true # Finding Context  --- exclude:true # Exploratory Data Analysis + Goal -> Discover patterns in the data + Understand the context + Summarize fields + Use graphical representations of the data + Explore outliers ####Tukey, J.W. (1977). Exploratory data analysis. Reading, MA: Addison-Wesley --- exclude:true # Question-Driven Analysis + Goal -> Answer a specific problem or concern + Have a question or problem in mind when analyzing data + “I need to know X” + Problem-focused discovery with the data --- exclude:true # Exercise - Vision Zero (dB) + Given 311 noise complaint data, assist enforcement efforts by identifying community districts that have a high volume of noise complaints and the time frame enforcement resources should be deployed to combat the noise issue at its peak + Identify the prevalent types of noise complaints in these areas to guide enforcement in each community district --- exclude:true #NYC Community Districts  <!-- .caption[Image Credit: Fitnr, CC BY-SA 4.0, via [Wikimedia](https://commons.wikimedia.org/wiki/File%3ANew_York_City_community_districts.svg)] --> --- exclude:true # Links to Other Open Data Portals + New York State - https://data.ny.gov + US Federal Government - https://www.data.gov/ --- name:ddc class:center,middle # BUILDING A DATA-DRIVEN CULTURE --- # Data Driven Culture  --- # Data Driven Culture  --- # Data Driven Culture  --- # Data Driven Culture  --- # Data Driven Culture  --- # Data Driven Culture  --- # Data Driven Culture  --- # Data Driven Culture  --- # Data Driven Culture  --- # Data Driven Culture  --- # Data Driven Culture  --- # Data Driven Culture > “Do you have data to back that up?” should be a question that no one is afraid to ask (and everyone is prepared to answer) ## - [Julie Arsenault](https://www.pagerduty.com/blog/how-to-create-a-data-driven-culture/) --- class:center,middle # How does your agency currently reflect the values of a data-driven organization? # Where could it improve? --- class:center,middle # WRAP-UP --- # What We've Covered -- + Elements of a data-driven culture -- + Leading with data -- + What else that was valuable to you today? --- name:final # Final Thoughts - [What Makes a Data Leader](https://medium.com/@Datapolitan/what-is-a-data-leader-26fcef32007c?source=friends_link&sk=83f34c6abdb15f99a19608df1548ba5e) -- + Able to discern fact from opinion -- + Facilitate data-driven conversations -- + Can avoid [the data distraction](http://www.governing.com/blogs/bfc/col-data-distraction-existing-processes-underlying-problems.html) -- + Enable the talents of others -- + Seek truth, not blame -- + Able to articulate outcomes rather than just outputs --- exclude:true # Technical Support + [Microsoft Office Support](http://office.microsoft.com/en-us/support/) - Documentation on various MS Office products + [Excel Tips](http://excel.tips.net/) - Various tips and tricks for using Excel + [Data Science Cheatsheet](https://github.com/govex/Data-Science) - Includes various terms and concepts related to data science + [Open Data Handbook](http://opendatahandbook.org/) - Guides, case studies and resources for government & civil society on the "what, why & how" of open data --- # Resources -- + [Data Driven New Orleans - Nolalytics](https://datadriven.nola.gov/home/) -- + [Harvard Government Performance Lab](https://govlab.hks.harvard.edu/) [Results-Driven Contracting](https://govlab.hks.harvard.edu/results-driven-contracting) -- + Carl Anderson [_Creating a Data-Driven Organization_](http://shop.oreilly.com/product/0636920035848.do) -- + DJ Patil & Hilary Mason [_Data Driven: Creating a Data Culture_](https://www.oreilly.com/ideas/data-driven) -- + [IDEO Design Kit](http://www.designkit.org/) - Resource for design thinking techniques -- + [Data Driven Dialogue](http://www.schoolreforminitiative.org/download/data-driven-dialogue/) - how to lead data-driven conversations -- + [Datapolitan training classes](http://training.datapolitan.com/) -- + [Copy of today's handout](workbook.pdf) --- # .center[Contact Information] ## Richard Dunks + Email: richard[at]datapolitan[dot]com + Website: http://www.datapolitan.com + Blog: http://blog.datapolitan.com + Twitter: [@datapolitan](https://twitter.com/datapolitan) ## Elana Shneyer + Email: elana[at]datapolitan[dot]com --- class:center, middle #THANK YOU! --- name:nola class:center,middle # Types of Analysis [](https://datadriven.nola.gov/home/) [](https://datadriven.nola.gov/home/) Based on the work of the [City of New Orleans, Office of Performance and Accountability](https://datadriven.nola.gov/home/) Graphics: Copyright © [Harvard University Ash Center](https://ash.harvard.edu/)(Used with Permission) ??? + Facilitator goes through the types of analysis with participants to introduce key ideas + Facilitator connects each type to either the process map they've created or to the their own work --- class:center,middle  --- # Finding a Needle in Haystack  -- + Challenge: Targets are difficult to identify or locate within a broader population -- + Opportunity: Data analysis and predictive modeling to identify targets based on existing data --- # New Orleans Distributes Smoke Alarms  .caption[Image Credit: Michael Barnett [CC BY-SA 2.5](http://creativecommons.org/licenses/by-sa/2.5), via Wikimedia Commons] --- # Targeted Outreach Saves Lives  .caption[Image Credit: City of New Orleans, via [nola.gov](http://nola.gov/performance-and-accountability/nolalytics/files/full-report-on-analytics-informed-smoke-alarm-outr/)] --- # Targeted Outreach Saves Lives  .caption[Image Credit: City of New Orleans, via [nola.gov](http://nola.gov/performance-and-accountability/nolalytics/files/full-report-on-analytics-informed-smoke-alarm-outr/)] --- # Prioritizing Work for Impact  -- + Challenge: Services do not categorize high-priority cases early -- + Opportunity: Data analysis and predictive modeling to prioritize cases --- # NYC Restaurant Inspectors Save Time  .caption[Image Credit: Grease Trap Cover Asphalt by [Christopher Sessums](https://www.flickr.com/photos/csessums/4740455231), [CC BY 2.0](https://creativecommons.org/licenses/by/2.0/)] .center[Source: http://www.nyc.gov/html/bic/downloads/pdf/pr/nyc_bic_dep_mayoroff_policy_10_18_12.pdf] --- # Early Warning Tools  -- + Challenge: Resources overly focused on reactive services -- + Opportunity: Developing tools to predict need based on historic patterns --- # Using Data to Fight Fires  .caption[Image Credit: [NYC Mayor's Office of Data Analytics](http://www1.nyc.gov/site/analytics/index.page), [2013 Annual Report](https://assets.documentcloud.org/documents/1173791/moda-annual-report-2013.pdf)] --- # Better, Quicker Decisions  -- + Challenge: Repeated decisions are made without access to all relevant information -- + Opportunity: Developing recommendation tools for operational decisions --- # Cincinnati Targets Urban Blight  .caption[Image Credit: Wholtone, via [Wikimedia Commons](https://commons.wikimedia.org/wiki/File:Abandoned-Over-the-Rhine-building.jpg)] [Learn more](https://dssg.uchicago.edu/2015/08/20/blight-prevention-building-strong-and-healthy-neighborhoods-in-cincinnati/) --- # Optimizing Resource Allocation  -- + Challenge: Assets are scheduled or deployed without input of latest service data -- + Opportunity: Use data to drive decisions on the deployment of resources --- # Shortening Public School Bus Rides  Image Credit: [Patrick Hudepohl](https://www.flickr.com/photos/patrick-hudepohl/), used under [Creative Commons BY-NC-SA 2.0 license](https://creativecommons.org/licenses/by-nc-sa/2.0/). [Source](http://www.datakind.org/blog/datakind-and-sas-to-help-boston-public-schools-shorten-school-bus-rides-lower-costs) --- # Experimenting for What Works  -- + Challenge: Services have not been assessed for impact -- + Opportunity: Experimental testing and improvement of service options --- # Redesign of NYC Summonses  Image credit [City of New York](https://www1.nyc.gov/site/criminaljustice/work/summons_reform.page). [Click for more information](http://www.ideas42.org/blog/new-behaviorally-informed-nyc-summonses-hit-streets/) --- exclude:true # Value of Good Operational Analysis  .caption[Image Credit: Money by Andrew Magill, [CC BY 2.0](https://creativecommons.org/licenses/by/2.0/), via Flickr] ## City of Cincinnati saved $130,000 in late fees to utility company [Learn more](http://www.charlotteobserver.com/news/business/article32617293.html) --- exclude:true # Tracking Hurricane Sandy Relief Funds  .caption[Image Credit: The City of New York, via [NYC.Gov](http://www1.nyc.gov/sandytracker/#2891665754)] --- # A Word on Performance Metrics -- + If it doesn't change your behavior, it's a bad metric  .caption[Image Credit: Jurgen Appelo, [CC BY 2.0](https://creativecommons.org/licenses/by/2.0/), via [Flickr](https://www.flickr.com/photos/jurgenappelo/8485492756)] --- # Performance Metrics + What metrics do we have in our process map? + Will they influence what we do? + Do we need more/better ones? --- # Goodhart's Law -- >“When a measure becomes a target, it ceases to be a good measure.” ## - Charles Goodhart, Economist -- # .orange[**How might this relate to our map?**]