Lesson 4 - Quantitative research strategies Flashcards
What paradigm is closely associated with Quants?
Positivism
Describe the goal of cross-sectional research designs
To establish that a relationship exists between two variables and DESCRIBE the nature of the relationship (not explain)
*no attempt to manipulate/control/interfere with variables
What is the goal of experimental research?
- to demonstrate a cause-and-effect relationship between two variables
A correlation coefficient measures and describes…..
…the relationship between two variables
What 3 characteristics are given by the correlation coefficient?
- direction
- form
- consistency/strength
Name and briefly describe the 3 applications of a correlation coefficient
Prediction - use knowledge about one variable (predictor) to help predict or explain the second variable (criterion).
Regression - using one var (predictor) to predict the other (criterion) - find most accurate equation
Reliability and Validity - a measure of this
Give 3 strength of correlational research
- Describes relationship between variable
- Non-intrusive
- High external validity
Give 4 weaknesses of correlational research
- Cannot assess causality
- Third-variable problem
- Directionality problem
- Low internal validity
Multiple regression is a statistical procedure for….
….studying multivariate relationships
How does experimental research go about establish cause-and-effect relationships between two variables?
- manipulation of the one variable, while isolating the two variable being examined from the influence of other variables
- want to show that consistent differences in the dependent variable and caused by the the independent variable
What are the 4 basic characteristics of experimental procedures
- Manipulation of one variable
- Measurement of a second variable
- Comparison of scores between
treatments - Control of all other variables
Participants background is an example of an…… (if it influences the dependent variable)
extraneous variable
List and briefly describe 3 ways in which one can control for extraneous variable
- Holding a variable constant (parts. observed @ same time in same room by some researcher)
- Matching values across the treatment conditions (e.g. average age)
- Randomization - disrupts any systematic relations between ext. vars. and the independent variable (stops ext. vars. from becoming confounding vars.) - achieved through RA
What are 3 ways one can can bring about control in an experiment
- Control group - provides a standard of normal behaviour/ a baseline
- Placebos
- Manipulation checks - include assessing how parts. received and interpreted the manipulation etc
Randomization can be used to control both….and….
- environmental variables
- extraneous variable
Statistical significant differences between the two groups must be big enough to rule out …..
- difference due to sampling variability (random fluctuations)
What 3 things must be precisely describe in the research procedure write-up
- how the vars. were manipulated, regulated and measured
- How many indis were involved
- How the parts. will process through the course of the study
Threats to validity of a study are any factor that….
….generates doubts about the accuracy of the results, or raises questions about the interpretation of the results
It is important to always be mindful of a studies ……., and not always take their conclusions at face value
threats to validity
List 5 threats to generalization across participants
- selection bias
- over-reliance on college students
- volunteer bais
- participant characteristics
- cross-species generalizations
Briefly outline the difference between within-subjects and between-subjects design
- Within-subjects design
- Different sets of scores are obtained from the same group
of participants. - Between-subjects design
- Each set of scores is obtained from different groups of
participants
A two-factor design has two….
independent variables
What 3 criteria determine the selection of a research strategy
- the object of the research (availability of enough info to establish relationship? Can the variables be manipulated/controlled)
- the aim of the research (do you want correlational or causal results)
- the nature of the data to be collected (how capable/sophisticated are the techniques for data collection?)
What has positivism been criticized for?
- it’s prioritization of quantitative data and focus of observable phenomena at expense of subjective experiences
*despite this, it continues to be an influential philosophical approach to understanding the world
