Glossary
Bias
A systematic error in a study that leads to an inaccurate estimate of a population parameter. It can occur during data collection or analysis.
Example:
If a survey about internet usage is only given to people with landline phones, it could introduce bias by excluding those who only use cell phones.
Controlled Variables
Variables that are kept constant or accounted for during an experiment to minimize their potential influence on the dependent variable. They help ensure that observed effects are due to the independent variable.
Example:
When testing a new drug, keeping the age and health status of all participants similar ensures these are Controlled Variables.
Data
Numbers or labels collected in a specific context. They are meaningless without understanding their background.
Example:
The numbers 75, 88, 92 are just numbers until you know they are Data representing student test scores in a statistics class.
Data Set
A collection of data points, typically organized for analysis. It groups related observations together.
Example:
All the heights, weights, and ages recorded for every player on a basketball team form a Data Set.
Dependent Variables
The variable being measured or observed in an experiment, whose value is thought to be influenced by changes in other variables. It's the 'effect' in a cause-and-effect relationship.
Example:
In a study examining how fertilizer affects plant growth, the plant's height or yield would be the Dependent Variable.
Descriptive Statistics
The process of organizing, summarizing, and presenting data to describe its main features. It helps in understanding the data at hand.
Example:
Calculating the average test score for a class to understand the typical performance is an example of Descriptive Statistics.
Elements
The individual items or subjects on which data is collected. These are the 'who' or 'what' of your study.
Example:
In a study about student sleep habits, each individual student surveyed is an Element.
Experimental Units
The units on which an experiment is performed; these can be people, animals, plants, or inanimate objects. They receive the treatment in an experiment.
Example:
In an agricultural study testing different fertilizers, the individual corn plants receiving the fertilizer are the Experimental Units.
How (of data)
Refers to the methods used to collect the data, which can include surveys, experiments, or observations. The collection method impacts data quality and potential biases.
Example:
Understanding that data on public opinion was collected via an online poll (the 'How') helps assess potential biases like self-selection.
Independent Variables
The variable that is manipulated or controlled by the researcher in an experiment, thought to influence the dependent variable. It's the 'cause' in a cause-and-effect relationship.
Example:
In an experiment testing the effect of different amounts of sleep on test scores, the 'amount of sleep' is the Independent Variable.
Inferential Statistics
The process of making generalizations or predictions about a larger population based on data collected from a sample. It extends findings beyond the observed data.
Example:
Using a survey of 100 students to estimate the average GPA of all students in a large university involves Inferential Statistics.
Observations
The specific measurements or values recorded for each element. These are the actual pieces of data collected.
Example:
If a student reports sleeping 7 hours, '7 hours' is the Observation for that student's sleep duration.
Respondents
Individuals who provide data by answering questions in a survey. They are the 'who' in survey research.
Example:
When you fill out a questionnaire about your favorite ice cream flavor, you are a Respondent.
Subjects/Participants
Individuals who are involved in an experiment and whose responses or characteristics are measured. They are the 'who' in experimental studies.
Example:
Students who take a new experimental teaching method in a classroom study are considered Subjects or Participants.
Variables
Characteristics or attributes that are measured or observed for each element in a data set. They represent 'what' is being studied.
Example:
In a study of student performance, 'GPA', 'hours studied', and 'major' are all Variables.
When (of data)
Refers to the time period during which data was collected. This context can be crucial for interpreting trends or changes.
Example:
Knowing that survey data on smartphone usage was collected in 2005 (before widespread adoption) provides important 'When' context for the data.
Where (of data)
Refers to the location or setting where data was collected. This context can influence the characteristics of the data.
Example:
Understanding that economic data was collected from a rural farming community versus a bustling city provides important 'Where' context for the data.
Why (of data)
Refers to the purpose or research question guiding the data collection and analysis. It determines the type of analysis performed and conclusions drawn.
Example:
The 'Why' behind collecting student attendance data might be to see if there's a relationship between attendance and academic performance, guiding the analysis.