Data Analysis and Business Disciplines PDF

**[Data Work:]** - Types of Variables - Numerical Variables - Dummy Variables - Categorical Variables - Continuous Variables - String Variables (text) - Outliers - What are outliers? - Outliers as a part of the data cleaning process...

**[Data Work:]** - Types of Variables - Numerical Variables - Dummy Variables - Categorical Variables - Continuous Variables - String Variables (text) - Outliers - What are outliers? - Outliers as a part of the data cleaning process - Identifying outliers as the goal of the empirical analysis - Merging Data - Combining variables from two data sets using a common variable in both sets **[Data Analyses:]** - A/B Testing (also called Randomized Control Trials); Diff in Diff - Create two identical worlds, vary one input, and then compare outcomes - Can apply to real experiments (marketing case) or - Natural Experiments - \*\*ADD Details\*\* (economics case) - Z-scores - Use z-scores to identify outliers - Good outliers = high performers or hard workers - Bad outliers -- detect corruption or low-performers - T-tests to evaluate differences in mean values - Descriptive and Diagnostic Analyses with Summary Stats - Evaluating diffs in Quit Rates across workers to assess why quit rates so high - Evaluating diffs in Default Rates across borrowers to assess risk and who represents the riskiest borrowers **[Excel Work:]** - Pivot Tables - Pivot Charts - Vlookup (and/or Xlookup) - Merge Data - IF and IFS functions - Create Dummy Variables and Categorical Variables **[Discipline-Specific Analytics]** - Analytics in Marketing - Market Research - Research to identify business opportunities - Customer Segmentation - Research to identify new customers - Recommendation systems as customer segmentation - Evaluating Marketing Campaigns - Analytics in Management - Evaluative Analytics: What gets measured, gets managed. - Develop and oversee Key Performance Indicators (KPIs) of firm success over time and across groups - Customer Churn Rates - Inventory Analysis - Evaluating Employee Performance - Analytics for Accounting - Financial Statements as Descriptive Analysis. - Understanding financial statements as diagnostic analyses - Forecasting financial statements as predictive analytics - Forensic Accounting - Associated with detecting fraud and identifying outliers. - Analytics for Finance - Valuing Assets - Fundamental Analysis - Technical Analysis - Assessing Financial Risks - Default Rates - Insurance Risk - Portfolio Risk - Predicting Macro Aggregates such as interest rates - Analytics for Economics - Focused more on understanding causality, which aligns with prescriptive analysis - Long history of analytics in economics used to: - Test theories of firm and consumer behavior - Evaluating competition in markets - Estimating economic parameters - Forecast macro aggregates - Evaluating impacts of governmental interventions in markets **[How is Analytics Changing the Different Business Disciplines]** - Broad takeaway is that analytics is not changing any of the business disciplines in terms of their broad objectives, instead analytics represents a new tool for each of the business disciplines to be more effective. - Marketing - Market segmentation gets more and more sophisticated - Personalization of marketing via smartphones and social media - Management - Individual managers can now effectively manage more people and processes - Business shift away from reactionary and towards anticipatory management - Should make managerial decisions less subjective and help reduce biases - Accounting - More frequent reporting - Accountants' move away from reporting (that is being automated) and towards advising and consulting.