PSYC*1010 Chapter 1: Intro to Statistics Flashcards
What is a theory?
A principal that attempts to explain the observed relationship between variables and is supported by a wide range of evidence
A ________ is informed by a ___________.
Hypothesis, Theory
What is a hypothesis?
An educated guess about the potential relationship between variables
Hypotheses must be ___________.
Falsifiable
What is an experimental hypothesis?
The prediction made about the outcome of an experiment
Why is an experimental hypothesis different from a theory?
Experimental hypotheses don’t explain the reasoning of findings nor do they contain anything that cannot be directly observed
What are the three goals of the scientific method?
- Objectively observe and describe associations among variables
- Predict new observations by generalizing findings
- Explain why the observed association between variables occured
How are theories tested?
- Select and operationally define variables
- Set a hypothesis
- Determine a study sample
- Attempt to account for sources of error
Can a theory ever be proven?
- No
- Research never “proves” a theory, it simply provides evidence to further support it
What are statistics?
A set of mathematical procedure for organizing, summarizing, and interpreting information
What are the two general purposes of statistics?
- To organize and summarize information
- To determine which general conclusions are justified
What is the difference between a population and a sample?
- Population: the set of all individuals of interest in a study
- Sample: the set of individuals selected from a population
What does every population (or sample) of individuals produce?
A corresponding population (or sample) of scores
What is the goal of a sample?
To generalize the results back to the entire popualtion
How should a sample be identified?
In terms of the population from which it was selected
What are the two types of samples?
- Random
- Convenience
What is the difference between random and convenience samples?
- Random: Everyone has an equal chance of being included in the study
- Convenience: Some people have a chance of being in the study, but most people do not
What are three places error can creep in when testing a theory?
- Construct validity
- Confounds/confounding variables
- Sampling error
What is a variable?
A characteristic or condition that changes for different individuals
What is a datum?
A single measurement or observation
What is a data set
A collection of measurements or observations
What is the difference between a parameter and a statistic?
- Parameter: describes a population
- Statistic: describes a sample
How does research typically begin?
With a question about the population parameter
How are parameters derived?
From measurements of the individuals in the population
How are statistics derived?
From measurements of the individuals in a sample
What does every population parameter have?
A corresponding sample statistic
What are the two classes of statistics?
- Descriptive statistical methods
- Inferential statistical methods
What are descriptive statistics?
Techniques used to summarize, organize, and simplify data
What are inferential statistics?
Techniques that allow for generalizations and inferences about the populations from which a sample was selected
What do inferential statistics help differentiate between?
Whether a discrepancy between samples was caused by the IV or a sampling error
Which type of statistics helps determine what conclusions were justified by the results?
Inferential statistics
What is a sampling error?
A naturally occurring discrepancy or error between a sample statistic and the corresponding population parameter
How are individual variables typically described in descriptive research when they consist of numerical values?
By statistical techniques
How are individual variables typically described in descriptive research when they consist of non-numerical values?
By computing the proportion or percentage in each category
What are the two main types of research methods and statistical techniques?
- Correlational method
- Experimental and quasi-experimental methods
What is a correlational study?
A study in which one group of individuals is observed and two (or more) variables for each individual are measured to determine if there’s a relationship between them
T or F: Variables in a correlational study are not manipulated.
True
How are the variables in a correlational study observed?
As they exist naturally
What is a correlation?
A statistic that measures and describes the relationship between the numerical scores of two variables
What are the limitations of a correlational study?
They can’t demonstrate a cause-and-effect relationship.
How is the relationship between variables examined in experimental and quasi-experimental studies?
By using an independent variable to define the groups, then measuring the dependent variable to obtain scores for each group
How are numerical scores typically evaluated in experimental and quasi-experimental studies?
By computing the average score for each group and comparing them
How are non-numerical scores typically evaluated in experimental and quasi-experimental studies?
By computing and comparing proportions for each group
What is the main distinction between experimental and quasi-experimental methods?
- The main distinction is how the relationship between variables is interpreted
- Experimental methods: allow for a cause-and-effect relationship to be demonstrated
- Quasi-experimental methods: do not permit a cause-and-effect explanation
What is the experimental method?
One variable is manipulated while the other is observed and measured
What is the goal of an experimental study?
To demonstrate a cause-and-effect relationship between two variables
What two characteristics differentiate experiments from other types of research studies?
- Manipulation
- Control
How is manipulation used in an experimental study?
The independent variable is manipulated to observe if it has an effect on the dependent variable
What are the two categories of variables that must be controlled in an experiment?
- Participant variables
- Environmental variables
What are participant variables?
Characteristics that vary between individuals (ex. age, gender, intelligence, etc)
What are environmental variables?
Characteristics of the research environment (ex. lighting, time of day, weather conditions, etc)
When does a confounded study occur?
When an unambiguous conclusion cannot be made because there is more than one explanation for the results
How do confounds/confounding variables affect a study?
Confounds make it difficult to determine what the actual association between variables might be
What is a confound/confounding variable?
An extraneous variable that makes the relationship between variables unclear
What are three basic techniques that control other variables?
- Random assignment
- Matching
- Holding variables constant
What is random assignment?
Each participant has an equal chance of being assigned to each of the treatment conditions
What is the goal of random assignment?
To distribute the participant characteristics evenly, so neither group has an advantage or disadvantage
How can random assignment be used to control environmental variables?
By randomly assigning participants to different testing environments
What is the difference between random assignment and random sampling?
- Random assignment: Determines who out of the sample receives which treatment condition
- Random sampling: Determines who out of the population is selected for the sample
What is the goal of matching?
To ensure equivalent groups or environments (ex. each group is 60% female and 40% male)
How are participant variables held constant?
By using only a certain demographic of participants
What is the difference between an independent and dependent variable?
- Independent variable: manipulated by the researcher
- Dependent variable: measured and observed as the independent variable changes
How does the measurement of variables differ between correlational and experimental/quasi-experimental methods?
- Correlational study: both the dependent and the independent variables are being measured
- Experimental/quasi-experimental: only the dependent variable is being measured
What are antecedent conditions
The conditions of a variable before manipulation has occurred
Which type of variable consists of antecedent conditions?
Independent variables
What is the difference between a control condition and an experimental condition?
- Control condition: individuals don’t receive the experimental treatment
- Experimental condition: individuals receive the experimental treatment
What is the goal of a control condition?
To provide a baseline for comparison with the experimental condition
What are non-equivalent groups?
Groups of participants that are formed under naturally occurring circumstances
Why are studies with nonequivalent groups not considered true experiments, and instead are classified as quasi-experiments?
Because the researcher does not have control over the assignment of individuals to certain groups
What is the goal of a pre-post study?
To evaluate the effect of an intervening treatment or event
How is the goal of a pre-post study achieved?
By comparing observations made before vs after a treatment
Why are pre-post studies not considered true experiments, and instead are classifies as quasi-experiments?
Because the researcher does not have control over the passage of time or other variables related to time
What is a quasi-independent variable?
The variable in a study that changes between groups/is used to create the groups, but is outside the researcher’s control
What is a construct/hypothetical construct?
Internal attributes that are intangible and cannot be directly observed
What is the goal of an operational definition?
To define a construct in terms of external behaviours that are observable and measurable
What provides construct validity?
An appropriate operational definition
What is a discrete variable?
Consists of separate, indivisible categories that are whole and countable
T or F: Observations that differ qualitatively are considered continuous variables.
- False
- Observations that differ qualitatively are discrete variables
What is a continuous variable?
Has an infinite number of possible values that fall between any two observed values
T or F: Continuous variables consist of measurement categories that must be defined by boundaries.
True
T or F: It is common to obtain identical continuous variable measurements for two different individuals
- False
- It is rare to obtain identical continuous variable measurements for two different individuals
What is a real limit?
The boundaries of intervals for scores that are represented on a continuous number line
How is the real limit separating two adjacent scores defined?
The real limit of two adjacent scores is located exactly halfway between the two scores
T or F: The boundary between two intervals does not necessarily belong to one interval
- True
- The placement of a score on the boundary between two intervals depends on the rule being used to round numbers (up or down)
How can discrete variables be classified?
Nominal or ordinal
How can continuous variables be classified?
Interval or ratio
What are the four main scales of measurement?
- Nominal
- Ordinal
- Interval
- Ratio
What is a nominal scale of measurement?
Consists of measurements that are labelled and categorized, but don’t have any quantitative distinction between them
What is an ordinal scale of measurement?
Consists of a set of categories that are organized directionally, but the magnitude of the directional sequence is unclear
What do interval and ratio scales of measurement consist of?
A series of ordered categories that form a series of intervals that are exactly the same size
What is the difference between interval and ratio scales of measurement?
- The nature of the zero point
- Interval scale: zero point is arbitrary and doesn’t define the absence of a variable
- Ratio scale: anchored by a non-arbitrary zero-point that represents the absence of a variable
T or F: measuring a construct inherently involves a nominal scale.
- False
- A construct is not inherently a nominal, ordinal, interval, or ratio measurement
- A construct is operationalized to decide how it will be measured in a study
What is the difference between numerical and non-numerical scores?
- Numerical score: compatible with basic arithmetic operations
- Nonnumerical score: not compatible with basic arithmetic operations
What are raw scores?
The original, unchanged scores obtained in a study
Scores for a particular variable are typically represented by which letter(s)?
X or Y
Which letter is used to represent the number of scores in a population?
N (uppercase)
Which letter is used to represent the number of scores in a sample?
n (lowercase)
What is the summation notation?
Sigma (Σ) represents the sum of a set of scores
In the order of operations, when is the summation process (Σ) computed?
The summation process follows multiplication/division and proceeds any other addition and/or subtraction.
