Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
What Statistics Can Offer to Decision Makers
-
Descriptive Statistics
- Basic statistics - Identifying which statistical measures (e.g., median, mean, percentiles) are most relevant for different data distributions
- Graphs - Understanding the significance of accuracy (e.g., how graph design influences decision-making)
- Variable types - Determining which variables are easier to manage
- Ceteris paribus - Recognizing that variables are always in motion
- Third variable problem - Strategies for identifying the true influential factor
-
Inferential Statistics
- Probability value - Understanding the meaning of the P-value
- Repeated experiments - Techniques for interpreting results from repeated trials
- Data collection - Acknowledging that while bias can be minimized, it cannot be entirely eliminated
- Understanding confidence levels
Statistical Thinking
-
Decision-making with limited information
- Methods for assessing whether sufficient information has been gathered
- Prioritizing goals based on probability and potential return (benefit-to-cost ratio, decision trees)
-
How errors accumulate
- The butterfly effect
- Black swan events
- Analogies: What Schrödinger's cat and Newton's apple represent in business contexts
-
The Cassandra Problem - Measuring forecast accuracy when the course of action alters the outcome
- Case study: Google Flu Trends and the reasons for its failure
- How decisions rendered forecasts obsolete
-
Forecasting - Methods and practical application
- ARIMA models
- Why naive forecasts often prove more responsive
- Determining the appropriate historical look-back period for forecasts
- Explaining why increased data volume can sometimes lead to poorer forecasts
Statistical Methods Useful for Decision Makers
-
Describing Bivariate Data
- Distinctions between univariate and bivariate data
-
Probability
- Reasons for variability in measurements
- Normal Distributions and normally distributed errors
-
Estimation
- Independent sources of information and degrees of freedom
-
Logic of Hypothesis Testing
- Understanding what can be proven and the concept of falsification (why results often contradict initial assumptions)
- Interpreting hypothesis testing results
- Testing means
-
Power
- Strategies for determining an optimal (and cost-effective) sample size
- Balancing false positives and false negatives, and understanding the inherent trade-offs
Requirements
Strong mathematical skills are essential. Additionally, prior exposure to basic statistics, such as collaborating with teams who perform statistical analysis, is required.
7 Hours
Testimonials (3)
knowledge of the trainer, tailor based, all topics covered
eleni - EUAA
Course - Forecasting with R
The variation with exercise and showing.
Ida Sjoberg - Swedish National Debt Office
Course - Econometrics: Eviews and Risk Simulator
The real life applications using Statcan and CER as examples.
