Statistics can HELP answering the following questions:
*Calculate/Compare/Contrast/Explain/Question future event(s) based on methodologically curated dataset(s) with visualization(s).
*Explaining incident(s) discarding false/wrong/biased assumptions/confusions.
*Pointing out and discarding ambiguity and seemingly logical assumptions that are NOT logical under the hood.
*Analysing/conducting experiments, finding out practical solution(s), visualising relationship/patterns of real life probelme(s)/solution(s).
*Filtering out relevant information, making the ‘best’ decision(s)/solution(s).
Chapter 1: What’s the Point
—Description and Comparison among data
—Summarisation and visualisation of data
—Numbers represent an accessible idea of complex information set(s)
—Making ‘the best’ decisions based on facts and well calculated data set(s)
—Assessment of future probability of incident(s)
—Relationship between/among events
—Filtering out necessary information from available data for making the ‘best’ solutions fit for real life problems
Chapter 2: Descriptive Statistics
—Median, Mean and Outlier
—Basics of descriptive statistics, shortcomings and loopholes
—Frequency Distribution, Percentile, Standard Deviation, Percentage against given context(s) for visualising data.
—Test statistical findings against common sense
Chapter 3: Correlation
—Relationship between two phenomena
—Correlation Coefficient, encapsulation
—Discrepancy management
—Correlation doesn’t imply causation
Chapter 5: Probability
—What is LIKELY to happen, NOT what will happen
—Doesn’t ensure what will happen
—Probability Density Function, not mentioned directly, concept—Frequency of incident(s)
—Risk Management
Chapter 5 ½: Monty Hall Problem
—Probability comes in handy when we have more detailed data
Chapter 6: Probability Problems
—Probability sometimes does not/ cannot be predicted based on past data sets.
—Each dataset has a unique characteristic. Point it out and calculate.
—Some common statistical mistakes
—Statistical bias and discrimination
—Reversion to the mean
OFFTOPIC: A poster hero and coming back to average performance. Wanna be a real guitar hero or a poster boy?
Chapter8: Central Limit Theorem
—A mathematical intuition/summary
—Standard Deviation and Standard Error
—OFFTOPIC: Zoom In (Less Data) / Zoom Out (More Data) Effect
Chapter 9: Inference
—Techniques for drawing the ‘best’ decisions from statistics data
—Fixing thresh holds for accepting/rejecting null/alternative hypothesis
—P value… the value that defines the probability of a statistical finding being outcome(s) by chance
Chapter 10: Polling
—A statistical tool to conduct a ‘poll’.
—Some strategies to check its pitfalls.
Chapter 11: Regression Alalysis
— RA lets infer a data set controlling different variables.
—Quantify relationships between a variable and an outcome.
—A statistical tool to quantify/visualize relationships between a particular variable and an outcome controlling other factors.
— It’s hard to determine the particular variable.
— Regression analysis seeks to find the ‘best fit’ for a linear relationship between two variables.
—Ordinary Least Square
—Dependent variable, Explanatory variable, Regression Coefficient.
—R2 = How much variation around the mean in associated with differences in a variable.
—t-distribution = a family of ‘probability density function’; that vary as per the size of a distribution.
—Degrees of Freedom (df)
Chapter 12: Common Regression Mistakes:
—Some common regression mistakes like Correlation != Causation, Reverse Causality, Omitted Variable Bias etc.
—A warning before wrong or arbitrary use of the statistical tool.
Chapter 13: Programme Evaluation
—Different strategies of conducting and exploiting statistical experiments.
Comments
Post a Comment