Data Management Using Stata A Practical Handbook

Using simple language and illustrative examples, this book comprehensively covers data management tasks that bridge the gap between raw data and statistical analysis. Rather than focus on clusters of commands, the author takes a modular approach that enables readers to quickly identify and implement the necessary task without having to access background information first. Each section in the chapters presents a self-contained lesson that illustrates a particular data management task via examples, such as creating data variables and automating error checking. The text also discusses common pitfalls and how to avoid them and provides strategic data management advice. Ideal for both beginning statisticians and experienced users, this handy book helps readers solve problems and learn comprehensive data management skills.

Introduction Using this book Overview of this book Listing observations in this book Reading and Writing Datasets Introduction Reading Stata datasets Saving Stata datasetsReading comma-separated and tab-separated files Reading space-separated files Reading fixed-column files Reading fixed-column files with multiple lines of raw data per observationReading SAS XPORT files Common errors reading files Entering data directly into the Stata Data Editor Saving comma-separated and tab-separated files Saving space-separated files Saving SAS XPORT files Data Cleaning IntroductionDouble data entry Checking individual variables Checking categorical by categorical variables Checking categorical by continuous variables Checking continuous by continuous variables Correcting errors in data Identifying duplicates Final thoughts on data cleaning Labeling Datasets Introduction Describing datasets Labeling variables Labeling values Labeling utilities Labeling variables and values in different languages Adding comments to your dataset using notes Formatting the display of variables Changing the order of variables in a dataset Creating Variables Introduction Creating and changing variables Numeric expressions and functions String expressions and functions Recoding Coding missing values Dummy variables Date variables Date-and-time variables Computations across variables Computations across observations More examples using the egen command Converting string variables to numeric variables Converting numeric variables to string variables Renaming and ordering variables Combining DatasetsIntroduction Appending: Appending datasets Appending: Problems Merging: One-to-one match-merging Merging: One-to-many match-merging Merging: Merging multiple datasets Merging: Update merges Merging: Additional options when merging datasets Merging: Problems merging datasets Joining datasets Crossing datasets Processing Observations across Subgroups Introduction Obtaining separate results for subgroups Computing values separately by subgroups Computing values within subgroups: Subscripting observationsComputing values within subgroups: Computations across observationsComputing values within subgroups: Running sums Computing values within subgroups: More examples Comparing the by and tsset commands Changing the Shape of Your Data Introduction Wide and long datasets Introduction to reshaping long to wideReshaping long to wide: ProblemsIntroduction to reshaping wide to longReshaping wide to long: ProblemsMultilevel datasetsCollapsing datasets Programming for Data ManagementIntroductionTips on long-term goals in data managementExecuting do-files and making log filesAutomating data checkingCombining do-filesIntroducing Stata macrosManipulating Stata macrosRepeating commands by looping over variablesRepeating commands by looping over numbersRepeating commands by looping over anythingAccessing results saved from Stata commandsSaving results of estimation commands as dataWriting Stata programs Additional ResourcesOnline resources for this bookFinding and installing additional programsMore online resources Appendix: Common elements Index

Michael N. Mitchell is a senior statistician in health services research. For 12 years, he worked in the Statistical Consulting Group of the UCLA Academic Technology Services.