What are two important qualities for ideal early analytics projects?
- Quick win - have the ability to demonstrate success immediately rather than improving something in the future and waiting for results.
- Uncover an insight or have a business impact that will create interest among senior leaders
3.7.2
List the nine steps to gather and organize data.
- Define the question to be answered.
- Set clear reserach objectives (what to measure and how)
- Conduct a data audit (any data available already)
- Design the data collection and analysis strategies
- Collect the data
- Analyze the data
- Interpret the results
- Report the results
- Evaluate the process
3.7.2
Why must the TD professional design th data collection and analysis strategies before collecting the data.
- Everyone will agree on the approach (stakeholders, etc.)
- Agreement creates road map. This is valuable documentation and can be replicated in the future.
3.7.2
What considerations must go into collecting data.
- What information exists (from step 3 - data audit)
- how data is stored and filed
- how to collect data
- cost
- bias
- confidentiality
3.7.2
How must the TD professional go about interpretting the results of data.
- Organize the data to answer the original question.
- Use visuals to present data to ensure a productive conclusion was found.
- Know the number of respondents and total number of ideal respondents (sample size)
- Determine response rate
This leads into the next step (Report Results) because you need to know a) who expects the data and b) in what format.
3.7.2 & 3.7.4
When evaluating your data gathering project, what questions should be answered when you evaluate the process?
- What worked?
- What didn’t work?
- How can the process be improved?
- What’s the ROI of this project?
3.7.2
When making recommendations about future analytics projects, what two items must be considered?
- Level of impact of the project
- Ease of implementation
3.7.2
What best practices should be followed when selecting future analytics projects?
- Ensure talent strategy aligns with organizational success
- Engage multiple stakeholders
- Determine the support needed
- Don’t over promise.
3.7.2
How does the TD professional ensure analytics projects align talent strategy and organizational success?
By having a clear understanding of how the organization makes money, TD professionals a) ensure leadership is interested in the results of TD initiatives and b) demonstrate that the TD function is valuable.
3.7.2
What things are important to know about stakeholders for your analytics projects?
- Determine their power and influence (critical first steps, especially in needs analysis)
- What they want and need to know (goals, motives, and requirements)
3.7.3
How can you segment stakeholder groups?
- Hierarchy (team lead, director)
- Function or department (sales, marketing, operations)
- Decision-making authority (different than hierarchy… stakeholder can have responsibility across departments)
3.7.3
What methods can be used to begin analyzing your data?
- Plotting data (identify correlations)
- Pivot table
- Mean, mode, median, max, min, standard deviation
You may need to collect more data or ask different questions to obtain necessary data.
3.7.4
List six consequences of poor data analysis.
- Jumping to conclusions - or starting with a conclusion
- Unconscious bias
- Overusing mean, and avoiding mode and median
- Incorrectly defining the sample size
- Hypothesis testing without accounting for the Hawthorne effect or placebo effect
- Assuming correlation implies causation
3.7.4
Why can you not assume correlation implies causation?
It is impossible to deduce a relationship between two events solely based on an observed correlation.
3.7.4
What is the difference between quantitative data and qualitative data?
Quantitative = numerical data
Qualitative data = verbal/open response
3.7.4
How should the TD professional use both quantitative and qualitative data when interpretting results?
Quantitative is a good place to start. It’s easier to compare and provides initial direction for results.
Qualitative data should be compiled after numbers are quantified. Use it to provide rationale for the quantitative data message.
3.7.4
Define correlation and causation.
Correlation = 2 variables move at the same time
Causation = 1 variable directly causes a change in the other
3.7.4
It is not possible to prove a hypothesis true. Why is this an important fact?
No matter how much data is collected, chance could always interfere with the results.
You can only “fail to reject” the hypothesis.
3.7.4
What questions should the TD professional ask to help determine the legitimacy and usefulness of their data analysis conclusions?
- Are the conclusions likely to be beneficial?
- Do the results answer the original question?
- Does the analysis explore all perspectives?
- Does the data address any objections?
If these are all yes, you likely have a useful conclusion.
3.7.4
When would a TD professional choose to use a the method to present data?
- Show relationships
- Show distribution
- Show comparisons over time or among items
- Static composition
3.7.4
When would a TD professional choose to use crosstab tables to present data?
Show a pictoral comparison of two or more questions relating to:
* Demographics
* Organization position
* Between departments
* Longevity
3.7.4
Why is scaling an important principle in data visualization?
Scaling shows proportions and relationships
3.7.4
Why is integrity an important principle in data visualization?
Integrity focuses on the presentation’s truthfulness and accuracy
3.7.4
How do TD professionals ensure a graph delivers the message as best as possible?
- Viewers think about the message, not the methodology, design, or technology to create graph.
- Avoid distorting what the data says (tell the truth).
- Make large data sets coherent
- Encourage viewers’ eye to compare different pieces of data.
- Show data at several levels of detail (from braod overview to finer structure)
- Show clarity (descriptions, exploirations, tabulation, or decoration)
3.7.4
-
Critical - EVERY DAY34
-
Step-by-step Processes only42
-
1.1 Communication16
-
1.2 Emotional Intelligence10
-
1.3 Collaboration and Leadership28
-
1.4 Cultural Awareness and Inclusion6
-
1.5 Project Management12
-
1.6 Compliance and Ethical Behavior9
-
2.1 Learning Sciences51
-
2.2 Instructional Design22
-
2.3 Training Delivery and Facilitation0
-
2.4 Technology Application7
-
2.5 Knowledge Management14
-
2.6 Career and Leadership Development29
-
2.7 Coaching22
-
2.8 Evaluating Impact32
-
3.1 Business Insight14
-
3.2 Consulting and Business Partnering46
-
3.3 Org Development and Culture49
-
3.4 Talent Strategy and Management42
-
3.5 Performance Improvement20
-
3.6 Change Management18
-
3.7 Data and Analytics37
-
3.8 Future Readiness35
-
New Comp 3 Critical0
