Getting Started with Data Science: Making Sense of Data with Analytics

Description

Master Data Analytics Hands-On by Solving Fascinating Problems You’ll Actually Enjoy!

Harvard Business Review recently called data science “The Sexiest Job of the 21st Century.” It’s not just sexy: For millions of managers, analysts, and students who need to solve real business problems, it’s indispensable. Unfortunately, there’s been nothing easy about learning data science–until now.

Getting Started with Data Science takes its inspiration from worldwide best-sellers like Freakonomics and Malcolm Gladwell’s Outliers: It teaches through a powerful narrative packed with unforgettable stories.

Murtaza Haider offers informative, jargon-free coverage of basic theory and technique, backed with plenty of vivid examples and hands-on practice opportunities. Everything’s software and platform agnostic, so you can learn data science whether you work with R, Stata, SPSS, or SAS. Best of all, Haider teaches a crucial skillset most data science books ignore: how to tell powerful stories using graphics and tables. Every chapter is built around real research challenges, so you’ll always know why you’re doing what you’re doing.

You’ll master data science by answering fascinating questions, such as:
• Are religious individuals more or less likely to have extramarital affairs?
• Do attractive professors get better teaching evaluations?
• Does the higher price of cigarettes deter smoking?
• What determines housing prices more: lot size or the number of bedrooms?
• How do teenagers and older people differ in the way they use social media?
• Who is more likely to use online dating services?
• Why do some purchase iPhones and others Blackberry devices?
• Does the presence of children influence a family’s spending on alcohol?

For each problem, you’ll walk through defining your question and the answers you’ll need; exploring how
others have approached similar challenges; selecting your data and methods; generating your statistics;
organizing your report; and telling your story. Throughout, the focus is squarely on what matters most:
transforming data into insights that are clear, accurate, and can be acted upon.

The book’s website (www.ibmpressbooks.com/title/9780133991024) offers additional pages and software codes to illustrate every method from the book in R, SPSS, Stata, and SAS. The additional content and code files will be available for download by 1/26.

Downloads

Downloads

Download the code files:

Chapter 4 (444 KB .zip)

Chapter 5 (2.37 MB .zip)

Chapter 6 (769 KB .zip)

Chapter 7 (813 KB .zip)

Chapter 8 (909 KB .zip)

Chapter 9 (3.51 MB .zip)

Chapter 10 (1.89 KB .zip)

Chapter 11 (294 KB .zip)

Chapter 12 (43 KB .zip)

Sample Content

Table of Contents

Preface     xix
Chapter 1  The Bazaar of Storytellers     1
Data Science: The Sexiest Job in the 21st Century     4
Storytelling at Google and Walmart     6
Getting Started with Data Science     8
    Do We Need Another Book on Analytics?    8
    Repeat, Repeat, Repeat, and Simplify     10
    Chapters’ Structure and Features     10
    Analytics Software Used     12
What Makes Someone a Data Scientist?    12
    Existential Angst of a Data Scientist     15
    Data Scientists: Rarer Than Unicorns     16
Beyond the Big Data Hype     17
    Big Data: Beyond Cheerleading     18
    Big Data Hubris     19
    Leading by Miles     20
    Predicting Pregnancies, Missing Abortions     20
What’s Beyond This Book?    21
Summary     23
Endnotes     24
Chapter 2  Data in the 24/7 Connected World    29
The Liberated Data: The Open Data     30
The Caged Data     30
Big Data Is Big News     31
It’s Not the Size of Big Data; It’s What You Do with It     33
Free Data as in Free Lunch     34
    FRED     34
    Quandl     38
    U.S. Census Bureau and Other National Statistical Agencies     38
Search-Based Internet Data     39
    Google Trends     40
    Google Correlate     42
Survey Data     44
    PEW Surveys     44
    ICPSR     45
Summary     45
Endnotes     46
Chapter 3  The Deliverable     49
The Final Deliverable     52
    What Is the Research Question?    53
    What Answers Are Needed?    54
    How Have Others Researched the Same Question in the Past?    54
    What Information Do You Need to Answer the Question?    58
    What Analytical Techniques/Methods Do You Need?    58
The Narrative     59
    The Report Structure     60
    Have You Done Your Job as a Writer?    62
Building Narratives with Data     62
     “Big Data, Big Analytics, Big Opportunity”    63
    Urban Transport and Housing Challenges     68
    Human Development in South Asia     77
    The Big Move     82
Summary     95
Endnotes     96
Chapter 4  Serving Tables     99
2014: The Year of Soccer and Brazil     100
    Using Percentages Is Better Than Using Raw Numbers     104
    Data Cleaning     106
    Weighted Data     106
    Cross Tabulations     109
    Going Beyond the Basics in Tables     113
Seeing Whether Beauty Pays     115
    Data Set     117
    What Determines Teaching Evaluations?    118
    Does Beauty Affect Teaching Evaluations?     124
    Putting It All on (in) a Table     125
Generating Output with Stata     129
    Summary Statistics Using Built-In Stata     130
    Using Descriptive Statistics     130
    Weighted Statistics     134
    Correlation Matrix     134
    Reproducing the Results for the Hamermesh and Parker Paper     135
    Statistical Analysis Using Custom Tables     136
Summary     137
Endnotes     139
Chapter 5  Graphic Details     141
Telling Stories with Figures     142
    Data Types     144
Teaching Ratings    144
The Congested Lives in Big Cities     168
Summary     185
Endnotes     185
Chapter 6  Hypothetically Speaking     187
Random Numbers and Probability Distributions     188
Casino Royale: Roll the Dice     190
Normal Distribution     194
The Student Who Taught Everyone Else     195
Statistical Distributions in Action     196
    Z-Transformation     198
    Probability of Getting a High or Low Course Evaluation     199
    Probabilities with Standard Normal Table     201
Hypothetically Yours     205
    Consistently Better or Happenstance     205
    Mean and Not So Mean Differences     206
    Handling Rejections     207
The Mean and Kind Differences     211
    Comparing a Sample Mean When the Population SD Is Known     211
    Left Tail Between the Legs     214
    Comparing Means with Unknown Population SD     217
    Comparing Two Means with Unequal Variances     219
    Comparing Two Means with Equal Variances     223
Worked-Out Examples of Hypothesis Testing     226
    Best Buy–Apple Store Comparison    226
    Assuming Equal Variances     227
Exercises for Comparison of Means     228
Regression for Hypothesis Testing     228
Analysis of Variance     231
Significantly Correlated     232
Summary     233
Endnotes     234
Chapter 7  Why Tall Parents Don’t Have Even Taller Children     235
The Department of Obvious Conclusions     235
    Why Regress?     236
Introducing Regression Models     238
    All Else Being Equal     239
    Holding Other Factors Constant     242
    Spuriously Correlated     244
    A Step-By-Step Approach to Regression     244
    Learning to Speak Regression     247
    The Math Behind Regression     248
    Ordinary Least Squares Method     250
Regression in Action     259
    This Just In: Bigger Homes Sell for More     260
    Does Beauty Pay? Ask the Students     272
    Survey Data, Weights, and Independence of Observations     276
    What Determines Household Spending on Alcohol and Food     279
    What Influences Household Spending on Food?    285
Advanced Topics     289
    Homoskedasticity     289
    Multicollinearity     293
Summary     296
Endnotes     296
Chapter 8  To Be or Not to Be     299
To Smoke or Not to Smoke: That Is the Question     300
    Binary Outcomes     301
    Binary Dependent Variables     301
    Let’s Question the Decision to Smoke or Not     303
    Smoking Data Set     304
Exploratory Data Analysis     305
What Makes People Smoke: Asking Regression for Answers     307
    Ordinary Least Squares Regression     307
    Interpreting Models at the Margins     310
The Logit Model     311
Interpreting Odds in a Logit Model     315
Probit Model     321
    Interpreting the Probit Model     324
    Using Zelig for Estimation and Post-Estimation Strategies     329
Estimating Logit Models for Grouped Data     334
Using SPSS to Explore the Smoking Data Set     338
    Regression Analysis in SPSS     341
    Estimating Logit and Probit Models in SPSS     343
Summary     346
Endnotes     347
Chapter 9  Categorically Speaking About Categorical Data     349
What Is Categorical Data?    351
Analyzing Categorical Data     352
Econometric Models of Binomial Data     354
    Estimation of Binary Logit Models     355
    Odds Ratio     356
    Log of Odds Ratio     357
    Interpreting Binary Logit Models     357
    Statistical Inference of Binary Logit Models     362
How I Met Your Mother? Analyzing Survey Data     363
    A Blind Date with the Pew Online Dating Data Set     365
    Demographics of Affection     365
    High-Techies     368
    Romancing the Internet     368
    Dating Models     371
Multinomial Logit Models     378
    Interpreting Multinomial Logit Models     379
    Choosing an Online Dating Service     380
    Pew Phone Type Model     382
    Why Some Women Work Full-Time and Others Don’t     389
Conditional Logit Models     398
    Random Utility Model     400
    Independence From Irrelevant Alternatives     404
    Interpretation of Conditional Logit Models     405
    Estimating Logit Models in SPSS     410
Summary     411
Endnotes     413
Chapter 10  Spatial Data Analytics     415
Fundamentals of GIS     417
GIS Platforms     418
    Freeware GIS     420
    GIS Data Structure     420
GIS Applications in Business Research     420
    Retail Research     421
    Hospitality and Tourism Research     422
    Lifestyle Data: Consumer Health Profiling     423
    Competitor Location Analysis     423
    Market Segmentation     423
Spatial Analysis of Urban Challenges     424
    The Hard Truths About Public Transit in North America     424
    Toronto Is a City Divided into the Haves, Will Haves, and Have Nots     429
    Income Disparities in Urban Canada     434
    Where Is Toronto’s Missing Middle Class? It Has Suburbanized Out of Toronto     435
Adding Spatial Analytics to Data Science     444
Race and Space in Chicago     447
    Developing Research Questions     448
    Race, Space, and Poverty     450
    Race, Space, and Commuting     454
    Regression with Spatial Lags     457
Summary     460
Endnotes     461
Chapter 11  Doing Serious Time with Time Series    463
Introducing Time Series Data and How to Visualize It     464
How Is Time Series Data Different?    468
Starting with Basic Regression Models     471
What Is Wrong with Using OLS Models for Time Series Data?    473
    Newey–West Standard Errors     473
    Regressing Prices with Robust Standard Errors     474
Time Series Econometrics     478
    Stationary Time Series     479
    Autocorrelation Function (ACF)    479
    Partial Autocorrelation Function (PCF)    481
    White Noise Tests     483
    Augmented Dickey Fuller Test     483
Econometric Models for Time Series Data     484
    Correlation Diagnostics     485
    Invertible Time Series and Lag Operators     485
    The ARMA Model     487
    ARIMA Models     487
    Distributed Lag and VAR Models     488
Applying Time Series Tools to Housing Construction     492
    Macro-Economic and Socio-Demographic Variables Influencing Housing Starts     498
Estimating Time Series Models to Forecast New Housing Construction     500
    OLS Models     501
    Distributed Lag Model     505
    Out-of-Sample Forecasting with Vector Autoregressive Models     508
    ARIMA Models     510
Summary     522
Endnotes     524
Chapter 12  Data Mining for Gold     525
Can Cheating on Your Spouse Kill You?    526
    Are Cheating Men Alpha Males?    526
    UnFair Comments: New Evidence Critiques Fair’s Research     527
Data Mining: An Introduction     527
Seven Steps Down the Data Mine     529
    Establishing Data Mining Goals     529
    Selecting Data     529
    Preprocessing Data     530
    Transforming Data     530
    Storing Data     531
    Mining Data     531
    Evaluating Mining Results     531
Rattle Your Data     531
    What Does Religiosity Have to Do with Extramarital Affairs?    533
    The Principal Components of an Extramarital Affair     539
    Will It Rain Tomorrow? Using PCA For Weather Forecasting     540
    Do Men Have More Affairs Than Females?    542
    Two Kinds of People: Those Who Have Affairs, and Those Who Don’t     542
    Models to Mine Data with Rattle     544
Summary     550
Endnotes     550
Index    553

Updates

Submit Errata