What is the primary difference between a parameter and a statistic?

A parameter is from a population, a statistic is from a sample.

Understanding Data Representation

This cheat sheet covers the fundamental concepts of data representation, including populations, samples, variables, and various methods for collecting and visualizing data. It also highlights common pitfalls and misleading graphical representations.

Core Principles

Population: The entire group of interest.
Individual: A single member of the population.
Variable: A characteristic of interest for individuals.
Data: Observations of variables.
Sample: A subset of the population used for study.
Census: Data collected from every individual in the population.
Parameter: A calculation from population data.
Statistic: A calculation from sample data.
Descriptive Statistics: Organizing and summarizing data.
Inferential Statistics: Drawing conclusions about a population from a sample.
Qualitative Variables: Categorical data (e.g., color, name).
Quantitative Variables: Numerical data (e.g., height, count).
Discrete Variables: Countable numerical data.
Continuous Variables: Measurable numerical data.
Sampling Methods: Simple Random, Stratified, Systematic, Cluster, Convenience.
Observational Studies: Observing without interference.
Designed Experiments: Applying treatments and observing effects.
Types of Observational Studies: Cross-sectional, Case-control, Cohort.
Types of Designed Experiments: Randomized Control Trial (RCT), Matched Pairs.
Types of Errors: Sampling Error (unavoidable), Non-sampling Error (flawed).
Types of Bias: Sampling Bias, Nonresponse Bias, Response Bias.
Graphical Representations: Bar Graphs, Pareto Charts, Pie Charts, Histograms, Stem-and-Leaf Plots, Time-Series Plots.
Misleading Graphs: Issues with axes, proportions, and pictographs.

Action Steps

1. Identify the research question and population.
2. Determine individuals and variables.
3. Choose an appropriate sampling method.
4. Collect data using the chosen method.
5. Organize and summarize data using descriptive statistics.
6. Draw conclusions using inferential statistics.
7. Visualize data using appropriate graphs.
8. Be critical of graphical representations to avoid misleading conclusions.

Formulas

Relative Frequency = Frequency / Total

Key Terms

Population: The entire group of individuals or objects that is being studied.
Sample: A subset of the population from which data is collected.
Individual: A single member of the population.
Variable: A characteristic or attribute that can vary among individuals.
Data: The values of variables collected from individuals.
Parameter: A numerical summary of a population.
Statistic: A numerical summary of a sample.
Qualitative Variable: A variable that describes a quality or characteristic (e.g., color, name).
Quantitative Variable: A variable that represents a numerical quantity (e.g., height, age).
Simple Random Sample: A sample where every individual has an equal chance of being selected.
Stratified Sample: A sample obtained by dividing the population into subgroups (strata) and then randomly sampling from each stratum.
Systematic Sample: A sample obtained by selecting individuals at regular intervals from an ordered list.
Cluster Sample: A sample obtained by dividing the population into clusters and randomly selecting entire clusters.
Convenience Sample: A sample selected based on ease of access or availability.
Observational Study: A study where researchers observe and collect data without manipulating variables.
Designed Experiment: A study where researchers manipulate one or more variables and observe their effect on another variable.
Sampling Error: Error that arises from the natural variation between samples; generally unavoidable.
Non-sampling Error: Error that arises from flaws in the study design or execution (e.g., bias).
Bias: Systematic error that leads to unrepresentative results.
Histogram: A bar graph used to represent the distribution of quantitative data.
Pie Chart: A circular graph used to represent the proportion of categories in qualitative data.
Pictograph: A graph that uses images to represent data, which can be misleading if not properly scaled.

Real World Examples

A professor wants to know the average score of all students who took an exam.: The professor calculates the average score of their specific class (sample statistic) to estimate the average score of all students (population parameter).
A city wants to understand how residents commute to work.: They conduct a survey of 50 workers (sample) to estimate the commuting habits of the entire city population.
A farmer wants to test a new fertilizer's effect on tomato yield.: One field gets the new fertilizer (treatment group), while another field uses the standard method (control group). The yield is then compared (designed experiment).
A researcher studies the relationship between smoking and lung cancer.: They collect data from people who currently smoke and people who have lung cancer, comparing their past habits (case-control study).
A news channel shows a bar graph of poll results where the vertical axis starts at 40% instead of 0%.: This makes the difference between the two options appear much larger than it actually is, thus misleading the audience.

Timeline

Present: Cross-sectional studies collect data at a single point in time.
Past: Case-control studies collect data retrospectively.
Future: Cohort studies collect data prospectively over time.
Ongoing: Time-series plots track data over equal increments of time.
Historical: Development of various sampling and graphical methods.

People

Various Researchers/Statisticians: Developed and refined methods for data collection, analysis, and representation.

Quiz

What is the primary difference between a parameter and a statistic?: A parameter is from a population, a statistic is from a sample.
Which sampling method involves dividing the population into subgroups and sampling from each subgroup?: Stratified Sampling
Which type of study can establish cause and effect?: Designed Experiment
A graph where the vertical axis does not start at zero can be considered:: Misleading