Introduction to Statistics: Descriptive and Inferential Methods

Statistics is a multi-step analytical process that involves the following core actions:
- Collecting data to gather the necessary information for study.
- Organizing data to make it manageable and clear.
- Summarizing data to highlight key findings or trends.
- Analyzing data to draw definitive conclusions or answer specific questions.

Descriptive Statistics:
- This branch is focused entirely on the methods used for organizing and summarizing data.
- Its goal is to provide a clear picture of the specific data collected without making claims about a larger group.
- Common methods include creating tables, graphs, and calculating numerical summaries like percentages or averages for the group at hand.
Inferential Statistics:
- This branch involves generalizing beyond the specific data that was actually collected.
- The objective is to take a limited set of local data and use it to make assertions about a much larger population.
- Inferential statistics is inherently difficult because it deals with uncertainty and the limitations of having incomplete information.

To demonstrate descriptive statistics, data was collected regarding favorite colors within a classroom environment.
Collection Phase: The individual responses gathered were: Pink, Purple, Black, Blue, Blue, Pink, Orange, Pink, Green, Yellow, Red, Purple, Purple, Blue, Green, Pink, Yellow, Green, Blue, Blue, Green, Green, Pink, Red.
Organization Phase: The data was organized into a frequency table to count occurrences:
- Pink: $6$
- Blue: $6$
- Green: $6$
- Purple: $6$ (Note: adjusted count from initial listing)
- Red: $3$
- Black: $3$
- Yellow: $2$
- Orange: $1$
Summarization Phase: Out of a total of $33$ students, $6$ chose pink. This can be summarized as a percentage:
- $6 / 33 \approx 18\%$
- The summary statement is: " $18\%$ of students in this local class like pink."

Inferential statistics asks whether the classroom data (where $18\%$ chosen pink) can be used to describe the entire student body at VSU ( $10,000+$ students).
Limitations of Generalization:
- One cannot comfortably assert that $18\%$ of all VSU students like pink based on a single small class.
- The sample size of $33$ is too small relative to the total population.
- Results vary depending on the sample; a different class might have Yellow or Blue as the most popular color.
The "X" Variable: In inferential statistics, we assume there is a true percentage ( $x\%$ —the parameter) for all VSU students, but because we cannot realistically survey every student, we use our local sample (the statistic) to try and estimate it. We may never know the true value of $x$ .

Population:
- The entire group of individuals or items that is being studied.
- Example: The entire student body of VSU.
- In statistics, a population is not limited to physical people; it can include abstract entities such as exam scores, whale lifespans, or the gas mileage of automobiles.
Sample:
- A subset of the population used to represent the whole.
- A subset is any smaller collection of items taken from a larger list.
- Example: If a list contains numbers $1$ through $8$ , a subset could be even numbers ( $2, 4, 6, 8$ ), odd numbers, or even a single number like $4$ .
Parameter:
- A numerical summary of a population.
- Example: The average age of every single student who has ever started college.
Statistic:
- A numerical summary of a sample.
- Example: The average age of $50$ students chosen from a single university.

Whale Lifespans: To determine how long whales live on average, a researcher might only be able to track $5$ whales. Because it is impossible to analyze the lifespan of every whale on the planet, the researcher must work with that limited data set to make an estimate for all whales. The true average lifespan (parameter) remains unknown.
Modern Technology Constraints: Despite modern technology, many parameters remain elusive (e.g., the favorite color of every person in Georgia) because gathering data on a complete population requires immense time and financial resources.

Scenario 1: Calculus Exam Scores
- Question: If the average score on an exam for a calculus class is $82$ , is $82$ a parameter or a statistic?
- Answer: Parameter.
- Reasoning: In this context, the population is defined as that specific calculus class. Since the score describes every student in that specific population, it is a parameter.
Scenario 2: National Color Survey
- Question: In a national survey of $1018$ students, $24\%$ of them like the color green. Is $24\%$ a parameter or a statistic?
- Answer: Statistic.
- Reasoning: The word "survey" indicates that data was collected from a sample. A group of $1018$ is a small subset of all students in the nation.
Scenario 3: Moon Walkers
- Question: Out of every $12$ men that walked on the moon, $25\%$ of them were age $33$ . Is $25\%$ a parameter or a statistic?
- Answer: Parameter.
- Reasoning: This refers to the entire population of men who have walked on the moon (totaling only $12$ ). Because it describes every member of that specific group, it is a parameter.
Scenario 4: VSU Smartphone Use
- Question: VSU asked $35$ students what type of smartphone they have; $80\%$ said they had an iPhone. Is $80\%$ a parameter or a statistic?
- Answer: Statistic.
- Reasoning: VSU has thousands of students, but only a sample of $35$ was studied.