Exam_2_Part_2_PSY_395

.docx

School

Michigan State University *

*We aren’t endorsed by this school

Course

395

Subject

Statistics

Date

Jan 9, 2024

Type

docx

Pages

Uploaded by doobers

Week 5 Conceptually, what is an effect size? Give three examples of effect sizes, what they mean, and in what situations they would be used. - Conceptually, effect size is used in statistics to measure the strength of a relationship or the difference between variables. It quantifies the size of an effect which makes it easier to use as comparison amongst different studies or experiments and dictate how strong an effect is. The three examples of effect sizes are Cohen’s d, Pearson’s r, and the coefficient of determination. Cohen’s d measures the difference between means across two groups or single sample differences like t-tests or z-tests. Situations where you would use Cohen’s d is in educational research or clinical trials. Pearson’s r shows the strength and direction of linear relationships between two numeric variables. The range of Pearson’s r is -1 to 1 where -1 is a perfect negative linear relationship and 1 is a perfect positive linear relationship. 0 would mean that there is no relationship between the variables. Pearson’s r would be used in fields of economics or social sciences. The Coefficient of determination represents how well the independent variable explains the variability of the dependent variable. It is calculated as the sum of squares over the total sum of squares. The closer this number is to one, the better it explains the variability of the dependent variable. Situations where the coefficient of determination can be used are regression analyses and model comparisons. Week 6 What are the four possible levels of measurement for variables? Describe the properties of each, and give an example of each. - The four possible levels of measurement for variables are nominal, ordinal, interval, and ratio. At the nominal level, data is categorized without a specific order. It is used for unordered groups and cannot be translated into other levels of measurement. An example would be the category of colors because it cannot be measured as any greater or lesser than the other. The ordinal level contains a meaningful order but the differences between the variables in the order are not significant. For example, your grade in school can be ordered as high school being above middle school, but the difference between these categories are not consistent. In interval measurement, numbers, oftentimes, follow a meaningful order and the values between these numbers are consistent. There is no true zero in an interval measurement. Interval measurements are used in situations like the year. 2021 will always be one year away from 2020, as 2020 is to 2019. Finally, ratio measurements are like interval measurements but also contain a true zero. We are able to take ratios of the quantities in a ratio scale. Weight is an example of a ratio measurement. Weight has a true zero as something weighing 0 pounds just wouldn’t exist and negative weight is not a thing. Week 7 What is an independent variable, and what is a dependent variable? How does the independent

variable relate to conditions in an experimental design? How is the dependent variable treated in an experimental design? - An independent variable is the variable that is being manipulated in an experiment. This is what the researcher aims to test. The dependent variable is what, hence the name, depends on the independent variable. It is what is hypothesized to be influenced by the manipulations of the independent variable. Dependent variables are the results of the influenced target variable. Encompassing the conditions in an experimental design, an independent variable must fall under at least two different conditions. Although it is possible to run an experiment with only one condition, the results would face many limitations. If there is not a variance in the conditions, the independent variable would just be constant. The dependent variable is used to measure the variations in the manipulated independent variable. The measure in variations allows us to find causal relationships. For example, an experiment’s design to measure whether studying by yourself or with peers performs better on a test, the independent variable would be studying. The two conditions would be studying by yourself and then studying with friends. Performance on a test would be the dependent variable as the results would vary depending on the manipulation. This could help us establish a relationship between studying habits and performance. Week 8 What are four threats to internal validity of research that only appear in within-subject designs? Describe each of these four threats, and give an example of what each might look like in actual research. - The four threats to internal validity of research that only appear in within-subject designs are maturation effects, history effects, regression threats, and attrition threats. Maturation effects are when participants change from the initial measure of the dependent variable to the second measure. This maturation is unrelated to the independent variable. An example of this would be a participant’s ability to deescalate a street fight having improved just by being wiser due to age. The threat of history effects are external influences that are unrelated to the independent variable and impact the dependent variable. An example of an external influence that could impact results are major life changes. If a participant loses a loved one, their abilities are influenced and impact the dependent variable in an unintentional way. Regression threats occur when the first measure of the dependent variable is extraneous but the second measure regress closer to the average. An example of this would be if a participant performed extremely well during a pretest due to luck but the posttest proved the score to be closer to the mean. Finally, attrition threats are when participants drop out of the study in between measures due to an aspect of the independent variable or dependent variable. An example would be if participants dropped out mid-study due to the tedious requirements resulting in results that may not be representative of the initial group.

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version