Key Points from Chp. 7 ISDS
Chapter 7 Overview
Focus on simple calculations.
Importance of understanding specific project parts.
Sigma Notation
Clarify which sigma symbol is being referenced.
Sigma $(ar{x})$ is crucial for calculations.
Confidence Level
Definition: $1 - \alpha$ represents confidence level.
Common calculation involves $3^{\alpha}$.
Understanding p Bar
Determine how to reformulate questions to ask for $\bar{p}$ (sample proportion).
Example: Assessing the percentage of female frequent flyers.
Sample Average vs. Proportions
Distinction between average $(x_1)$ and percentages in data.
Emphasis on correct interpretation of sample data.
Normal Distribution Assumptions
Understand that normal distribution may not always apply; check provided assumptions.
Chapter 7 Overview
Focus on simple calculations, which often involve basic statistical measures like means, proportions, and standard deviations, crucial for initial data analysis in project management.
Importance of understanding specific project parts, which helps in identifying relevant data for analysis and applying appropriate statistical methods to each component of a project.
Sigma Notation
Clarify which sigma symbol is being referenced: \Sigma (uppercase sigma) denotes summation, while \sigma (lowercase sigma) represents the population standard deviation. It's essential to distinguish them based on context.
The sample mean (\bar{x}) and standard deviation (\sigma or the sample standard deviation S) are crucial for various calculations in statistical analysis.
Confidence Level
Definition: 1 - \alpha represents the confidence level, meaning the probability that a population parameter (such as the mean or proportion) falls within a specified range of values, known as the confidence interval.
Common calculations involve determining critical values (e.g., z{\alpha/2} for large samples or t{\alpha/2, df} for small samples) based on the desired 1 - \alpha level. If a specific calculation like 3^{\alpha} is referenced, it should be applied as specified within the context of that particular framework.
Understanding p Bar
Determine how to reformulate questions to ask for \bar{p} (sample proportion) by identifying inquiries that seek percentages or frequencies of attributes within a sample, rather than numerical averages. Examples include questions like "What proportion of…" or "What percentage of…"
Example: Assessing the percentage of female frequent flyers directly asks for a proportion, making \bar{p} the relevant statistic.
Sample Average vs. Proportions
Distinction between average (\bar{x}) and percentages in data: The sample average (\bar{x}) is used for quantitative data (e.g., average height, average salary, average project duration), while the sample proportion (\bar{p}) is used for categorical data (e.g., proportion of successes, percentage of a specific demographic, rate of defective items).
Emphasis on correct interpretation of sample data, as misinterpreting data types can lead to using the wrong statistical tests and drawing incorrect conclusions.
Normal Distribution Assumptions
Understand that normal distribution may not always apply; always check provided assumptions. Many statistical tests assume data are normally distributed.
If normal distribution assumptions are not met (e.g., small sample size, skewed data, or heavy tails), alternative non-parametric tests or data transformations may be necessary. Specific checks can include normality tests (e.g., Shapiro-Wilk test) or visual inspection of data distributions (e