PSYU2248 Design & Statistics Flashcards
Define mean median mode
mean is the average, median is the middle, mode is the most frequent number
What is the difference between an experimental design and non experimental design?
Experimental research has a variable that is being manipulated in order to determine its effect on the control group.
A non-experimental research design does not have any manipulation or control of any variables. Can not find a cause-effect relationship, methods of study are often correlational or case studies.
What is the difference between correlation and regression?
Correlation and regression are inter-related analyses; regression is an extension of correlation.
Regression; predict Y from X
Correlation; relations between X and Y
Where Y is the IV
Where X is the DV
The most commonly used techniques for investigating the relationship between two quantitative variables are correlation and linear regression.
Correlation quantifies the strength of the linear relationship between a pair of variables
Regression expresses the relationship in the form of an equation.
Why do research?
Psychological scientists want to
Describe human behaviour (what is going on?)
Predict human behaviour (use information about one thig to make a decent guess at something else)
Explain human behaviour (understand why things are related)
Control human behaviour (make change)
What does the regression line predict?
A regression line predicts the score of Y for any given value of X.
What is the Regression Model?
A regression model is able to show whether changes observed in the dependent variable are associated with changes in one or more of the explanatory variables. It does this by essentially fitting a best-fit line and seeing how the data is dispersed around this line.
What is the total sums of squares (TSS)
Total Sum of Squares (TSS): The TSS is the sum of all squared differences between the mean of a sample and the individual values in that sample.
The degree of variability is represented by the total sums of squares.
Explaining true variability between scores and why they exist.
Regression line - what does if actual scores are closer to the predicted scores?
This means that the better the model predicts y, the less variability around the line there is.
Regression line - what does if actual scores are further away from the predicted scores?
This means the worse the model predicts y, the more variability around the line there is.
What is a residual?
Difference between predicted Y and actual Y for any given value of X.
What is the method of least squares?
The method of least squares is a parameter estimation method in regression analysis based on minimizing the sum of the squares of the residuals made in the results of each individual equation. The most important application is in data fitting.
The line of best fit is also known as….
A regression line
What is the regression model (equation)?
Y (hat) = alpha + beta x
predicted Y (DV) = alpha is the intercept estimate point, beta steepness, flatness, slope
Describe what each of the following formulas are looking for
1.Total Sum of Squares
2.Residual Sum of Squares
3.Regression or Model Sum of Squares
1.Total sum of squares measuring how close the data points are to the mean
2.Residual sum of squares measuring the variation around the regression line
3.Regression sum of squares the difference between the TSS and the RSS
Define p-value
The P value is defined as the
probability under the assumption of no effect or no difference (null hypothesis),
of obtaining a result equal to or more extreme than what was actually observed.
The P stands for probability and measures how likely it is that any observed difference between groups is due to chance.
Define F ratio
The F-ratio is the ratio of the between group variance to the within group variance. It can be compared to a critical F-ratio, which is determined by rejecting or accepting the null hypothesis, which determines whether or not there are no differences between groups.
What is the correlation coefficient?
Numerical measurement of some type of correlation (a statistical relationship between two variables).
The number between +1 and -1 calculated so as to represent the linear interdependence of two variables or sets of data.
When dealing with the relationship between two variables, we are concerned with……
Correlation
What is the difference between correlation and correlation coefficient?
The correlation is the relationship between two variables
The correlational coefficient is the measure of the degree or strength of this relationship.
What is the Pearson correlation coefficient?
The Pearson correlation coefficient (r) is the most common way of measuring a linear correlation.
It is a number between –1 and 1 that measures the strength and direction of the relationship between two variables.
What diagram is best for examining the relationship between two variables?
Scatterplot
The independent variable sits on which part of the axis?
On the x axis (horizontal)
What is the formula for
Y(hat)=a+betaX
R-squared in linear regression. If you are given a result of lets say 0.327, this is the EXPLAINED variance, the proportion of the variation in the DV that is predicted from the IV.
How could we express this in a sentence? If 0.327 is the DV PWB(psychological well being) and the IV is internet addiction?
33% of the variation in PWB is explained from internet addiction.
That much variance of your DV (33%) is explained by your IV /s. Large effect.
In a linear regression analysis, if you have a B (beta) result -0.613 what does this mean?
How could we express this in a sentence? DV PWB(psychological well being) and the IV is internet addiction?
The slope in the regression line, negative or downwards slope, negative effect.
As internet addition increases PWB decreases
For every one point increase in the IV (internet addiction) the DV would decrease by .613 units.
In the linear regression analysis, what does the t value and significant (p) value tell us?
P value will tell us if we have a significant result.
So we have a statistically significant effect, we get this from the p value, that corresponds to the t statistic (degrees of freedom)
so the effect of internet addition is statistically significant, significantly in predicting PWB
Reading the data output from the variables table, please identify the:
DV
IV
and
Interpret the pred variable scores
and
Resid variable scores
DV - support for redistribution
IV - political preference
Used to run the regression
The DV values you expect to get for that value of X - pred variable
Example - Based on our regression line if someone had a political preference score of 5 we predict their predict for redistribution would be 3.75 - predicted valuables
- resid variable - number 7 political preference of 4 we would predict their support for redistribution is a score of 4.05 and their actual score is 4.25.
Take home message:
Not predicting the DV using scores on the IV, you will not perfectly predict anything, how well we predict is partly what the regression model is telling us. How well we are predicting scores in the DV based on scores on the IV, is actually what the regression model tells us that is also what the r2 tells us, its how much variance in the DV we’re actually predicting / explaining purely using scores on the IV. We never perfectly everything. How big that difference is for any individual person is what the residual is telling us. It tells us how big the discrepancy is between their predicted score of Y and their actual score of Y.
