Data driven decision making Final review

Interpret a simple regression analysis including correlation

-

Use the Pareto rule to identify drivers

- 80/20 rule - best used by leaders eager to identify which solutions will have the biggest impact when implemented. -The 80-20 rule maintains that 80% of outcomes (outputs) come from 20% of causes (inputs).

Use the 5 Why's

- A problem solving tool that helps you find the underlying reason that a problem occurred ● Not repeatable ● Good starting point for a complicated problem

Establish success criteria

- Defined: How will you know if the goals/intended outcomes have been achieved? What standards/criteria will you use to judge whether or not it has been successful (i.e. what defines the success of the project

Use data visualizations to communicate data persuasively

- Drowning in plastic visual (Drowning in Plastic is a visualization by Reuters Graphics and does a great job of making a statement about how we are covering the earth in plastic.) - A View of Despair ( It tells the story of all the people who took their life in The Netherlands in 2017. Each natural symbol represents how life was lost, along with the size representing age.)

Apply ethical reasoning

- Ethical reasoning is the ability to identify, assess, and develop ethical arguments from a variety of ethical positions -is how to think about issues of right or wrong.

Perform a fishbone analysis

- Start off by identifying a problem that you are facing and write the effect of that problem on the right side of paper - 6 M's: ○ Machines ○ Methods ○ Materials ○ Mother-nature ○ Manpower ○ Measurements - 6 P's ○ People ○ Process ○ Policy ○ Plant ○ program ○ Product

Create a Decision Matrix

- Use a decision matrix when you need to assess a situation from a logical viewpoint and you have enough comparable variables to weigh. - A decision matrix is a series of values in columns and rows that allow you to visually compare possible solutions by weighing variables based on importance. -The decision matrix process is best used when deciding on something that does not require a sense of emotion, as it is a logical tool by nature. - It's best to use a decision matrix to assess a situation from a logical viewpoint and have enough comparable variables to conduct a weighted analysis.

Assess data quality

- relevance - accuracy - Timeliness - Comparability - Completeness - Data quality is important to business and government for a number of obvious reasons. First, a reputation for world-class quality is profitable, a "business maker." As the examples of Section 3.1 show, high-quality data can be a major business asset, a unique source of competitive advantage.

Distinguish between causes and symptoms

A symptom is a sign or indication of a root cause, but it is not, by itself, a cause. Most often, symptoms lack specificity and are difficult to categorize. It is very difficult to develop solutions to directly address a symptom

Create a Dashboard

-A Dashboard should be one page that offers a quick visual snapshot to those stakeholders of how close the organization is to meeting its goals. -Dashboard is set of data visualizations, showing the organization's progress toward meeting the targets set out in the Balanced Scorecard.

Create and evaluate Key Performance Indicators, including leading and lagging

-A Key Performance Indicator (KPI) is simply a metric - a number you track and measure that helps you solve a problem or gives you insight to drive the results you expect. -KPIs are those things that are associated with either goals or objectives -A leading indicator looks forward at future outcomes and events. -A lagging indicator looks back at whether the intended result was achieved.

Establish a good problem statement

-A problem statement defines project success -A problem statement is you charter, it will: ○ Outline goals ○ Map boundaries ○ Define success ○ Acknowledge constraints ○ Articulate assumptions ○ Identify stakeholders ○ Establish timelines -Seek to understand why a solution is needed

Create a compelling infographic

-An infographic is simply meant to visually illustrate a set of data or supporting arguments for one main point.

Evaluate descriptive statistics in order to analyze data

-Descriptive statistic ○ Shows the strength of a relationship Step 1: Describe the size of your sample. Step 2: Describe the center of your data. Step 3: Describe the spread of your data. Step 4: Assess the shape and spread of your data distribution. Compare data from different groups.

Create SMART goals

-For example: ○ Financial: Increase overall profitability (Objective), as measured by earnings per share (Measure), by 10% over the next 12 months (Targets).

Prioritize with pairwise comparisons

-It requires that you compared each item head to head against each other in order to establish relative importance ● Here are some tips on facilitating a good pairwise prioritization process: ○ 1.) Clearly define the goal of the prioritization process. ○ 2.) Clearly define each alternative ○ 3.) Understand and communicate the speed of the process, as it starts slow and participants gain a deeper understanding of the alternatives as the comparisons are made ○ 4.) Recognize the real power of the voting process is the discussion among participants as to why they prefer one alternative over another

Use a T Chart

-The T-chart is the simplest, and is something you have likely used in your own life even if on an informal basis - This chart is used when weighing the pluses and minuses of the options. It ensures that all the positives and negatives are taken into consideration when making a decision. This is also known as creating a pros and cons list.

Create decision trees

-This is a graph or model that involves contemplating each option and the outcomes of each. Statistical analysis is also conducted with this technique. ● Rectangles represent the decision or choice. ● Circles correspond to uncertain outcomes, with each following branch describing an outcome with a specified probability. ● Triangles signify the end of a path through the decision tree. ---As a result, the decision making tree is one of the more popular classification algorithms being used in Data Mining and Machine Learning.

Conduct a SWOT Analysis

-is a simple business tool used to guide decision-making based on internal and external factors. -SWOT stands for strengths, weaknesses, opportunities and threats, which is exactly what this planning tool assesses.

Conduct bench-marking

Benchmarking is a process to discover what is the best standard of performance seen in a specific company, by a particular competitor or by a completely different industry.

Identify stakeholders

Identify Stakeholders is the first process of the Project Communications Management Knowledge Area, and part of the Initiating process group. This process involves identifying and documenting all the stakeholders on the project, including their interests, impact, and potential negative influences on the project

Create a balance scorecard

In constructing a Balanced Scorecard, the entries horizontally should read like a SMART goal. For example: ○ Financial: Increase overall profitability (Objective), as measured by earnings per share (Measure), by 10% over the next 12 months (Targets).

Distinguish between quantitative and qualitative data

N/A

Identify data types

Nominal ■ Uses numbers as names ■ Each number uniquely identifies a person or an object ■ Numbers on team jerseys area good example ■ Categorical data Ordinal ■ Numbers begin to take on meaning ■ A higher numbers means a greater amount of a property ■ The Mohs scale of hardness of minerals is an example ■ Difference between numbers don't mean anything Interval ■ Differences between days start to take meaning ■ Celcius and Fahrenheit are good examples ■ The difference between 20* and 30*is the same between 50* and 60* ■ Ratio statements don't make sense ■ 50* is not twice as hot as 25* Ratio ■ We can make statements like "twice as much" or "half as much" ■ Includes a Zero point, the complete absence of a measured property ■ It makes sense to say 4 inches is twice as long as 2 inches ■ The Kelvin scale does have a meaningful zero ● It's called absolute Zero ● Absence of heat = no molecular motion ● 200 kelvin is twice as hot as 100 kelvin In summary, nominal variables are used to "name," or label a series of values. Ordinal scales provide good information about the order of choices, such as in a customer satisfaction survey. Interval scales give us the order of values + the ability to quantify the difference between each one. Finally, Ratio scales give us the ultimate-order, interval values, plus the ability to calculate ratios since a "true zero" can be defined.

Differentiate between quantitative and qualitative data

Quantitative Data: - Quantitative data gets you the numbers to prove the broad general points of your research. -Quantitative research methods are designed to collect numerical data that can be used to measure variables. -Quantitative data is structured and statistical; its results are objective and conclusive -------------------- Qualitative Data: - Qualitative data brings you the details and the depth to understand their full implications. -Qualitative research is a methodology designed to collect non-numerical data to gain insights. -It is non-statistical and unstructured or semi-structured. - RELYS on data collected based on a research design that answers the question "why." -Qualitative data collects information that seeks to describe a topic more than measure it. This type of research measures opinions, views, and attributes vs. hard numbers that would be presented in a graph or a chart.

Use a decision matrix

○ The decision matrix process is best used when deciding on something that does not require a sense of emotion, as it is a logical tool by nature. ○ It's best to use a decision matrix to assess a situation from a logical viewpoint and have enough comparable variables to conduct a weighted analysis.

Use the So What's

○ The seven So-Whats ■ A thinking tool that reveals the consequences of an action ○ Looking at making recommendation as your sele, "so what" and ask 7 times

Understand the DMAIC process

● DMAIC is a problem solving and process improvement model. ● The steps in DMAIC - Define, Measure, Analyze, Improve, and Control ● The DMAIC model is used in the Six Sigma methodology. -DMAIC (an acronym for Define, Measure, Analyze, Improve and Control) refers to a data-driven improvement cycle used for improving, optimizing and stabilizing business processes and designs

Research and evaluate external data

● When utilizing secondary data to help make important marketing decisions, failing to check the reliability of that data could lead to inaccurate analyses and poor business decisions. -Utilizing external data is only going to benefit you if it is correct. ------------------- ● What was the research provider's purpose in presenting the data? ● Who collected the data? ● When was the data collected? ● How was the data collected? ● What type of data was collected? ● Is the data consistent with data from other sources?