Chapter 9 Flashcards
Correlations represent
A method of research
Correlational Method of Research
The variables are not manipulated or controlled. We measure any naturally occurring changes between the 2 variables and see if there is any relationship between them (Helps make predictions).
Correlations can help us predict
one variable from another.
Scatterplot
is a type of graph that represents correlational data. Each dot in the scatterplot represents the value of two variables for that given person.
In a scatterplot, if the dots are haphazardly scattered (no pattern)
There is no relationship between both of the variables.
In a scatterplot, if the dots follow a straight-line pattern,
There is a very strong relationship between the variables.
The stronger the correlation,
the more closely the dots follow a linear pattern, the better we can predict the value of one variable from the other variable.
The Correlation Coefficient “r” consists of
A + or a - sign and a number.
The number of a correlation coefficient tells you
How strongly the 2 variables are correlated.
The + or - of the correlation coefficient tells you
the direction of the relationship between the 2 variables.
0 indicates
no relationship, no predictability
1.00 indicates
perfect relationship, perfect predictability.
.50 correlation coefficient is indicative of a
Moderate relationship
If the coefficient has a + sign, that means that
The values of both variables are going in the same direction.
If the coefficient has a - sign, that means that
The values of both variables are changing in the opposite direction.
Inferential statistics still need to be used in order to determine whether
The correlation coefficient is statistically significant.
Linearity
Some relationships aren’t linear and we can determine that by looking at the scatterplot.
Restriction of Range
When only a narrow range of scores is used for one or both variables which misrepresents the correlation.
In correlational research, it is essential to have a
Large sample so that it includes a wide range of scores, providing more accuracy.
Restriction of range reduces
Predictability
The larger the sample….
The greater the range of scores.
Regression Analysis
Making predictions on the basis of correlational research. Knowing the size of correlation and the value of X (predictor variable), allows you to predict Y (criterion variable).
The regression line (line of the best fit) provides
the best way of summarizing the points on the scatterplot and is the line used for making predictions.
Bivariate Analysis
examines the relationship between 2 variables.
Multivariate Analysis
examines the relationship between 3 or more variables.
Regression analysis is bivariate or multivariate?
Bivariate (you predict Y from X)
Multiple Regression Analysis
Involves 2 or more predictor variables and a criterion variable. Enables us to determine whether each X variable can predict the Y variable and determine the relative strength of the predictions.
Predictions are usually greater when
More than one predictor variable is used.
Outliers
A score that is extremely different from the other scores and can distort “r”.
Coefficient of Determination “r squared”
Measures the percentage of variability in one variable that can be determined from it relationship with the other variable.
The coefficient of determination will always be a
Positive number and a smaller number than “r”.
Interpretational Problems with Correlations
You cannot infer causation hence we don’t manipulate or control the variable.
Two types of Interpretational Problems with Correlations
1- Directionality Problem
2-Third Variable Problem
Directionality Problem
variables might be correlated but we don’t know which variable is the cause and which is the effect.
Cross-Lagged Panel Correlation
Is a technique that can help us determine which variable is the cause and which is the effect.
Third Variable Problem
A third variable is any uncontrolled variable that could underlie and be responsible for a correlation between X and Y.
Two types of Third Variables:
1-Mediator Variable
2-Moderator Variable
Mediator Variable
Explains how or why the relationship between two variables exists.
Moderator Variable
Explains under what conditions the relationship between the two variables exists.
Partial Correlation
Provides a way of potentially controlling a third variable.
Survey
is a structured set of questions to measure people’s attitudes, beliefs, and behaviors.
Disadvantages of a survey
-Need a larger sample
-Cannot infer causation
Two Types of Sampling
1- Probability Sampling
2-Nonprobability Sampling
Probability sampling
Used if we wanna learn something about the population from a sub-group (sample).
Self-selection of Nonresponse Bias
When a sample is composed only of those who voluntarily respond to a survey.
If the return rate is less than 60%,
You probably have a self-selection problem
Simple Random Sampling
Every member of the population has an equal chance of being selected for this sample.
Types of Probability Sampling
1-Simple Random Sampling
2-Stratified Sampling
3-Cluster Sampling
Stratified Sampling
Proportions of important sub-groups in the population are exactly representative in your sample.
Cluster Sampling
Randomly selecting a group that has a common feature.
Non-probability Sampling
Subjects are not randomly chosen.
Types of Non-probability Sampling
1-Convenience Sampling
2-Purposive Sampling
3-Quota Sampling
4-Snowball Sampling
Convenience Sampling
Recruiting subjects from a group of available people who meet the general requirements of the study.
Purposive Sampling
A convenience sampling strategy is where a specific type of person is recruited.
Quota Sampling
You stop recruiting after you get the number of subjects you need in a subgroup.
Snowball Sampling also known as referral sampling
Asking a S to recruit their friends of coworkers, etc.
Type of Survey Questions
1- Open-ended
2- Closed Questions
Open-ended questions
Written out, descriptive answers. The disadvantage is that it is difficult to score and not all Ss are willing to put effort into this question.
Close-ended questions
Ss are usually asked to rate how much they agree/disagree with something.
Likert Scale
Consisting of either 5 or 7 points.
