Submit a first draft of your Methods and Results sections for this assignment. For best results, please carefully review the Milestone Four Guidelines and Rubric. Use the rubric’s critical elements as subheadings to reduce the possibility of missing an element.
Now that you have completed your data collection, it is important to revise your Methods section so it accurately reflects the participants, materials, and methodological procedures used in your study.
In your Results section, you should first describe how you reduced your raw data for analysis (e.g., how your questionnaires were summed or averaged to get a composite score to analyze). Your Results section should also include a table of the relevant descriiptive statistics and a narrative explanation of the descriiptive statistics. Then you should describe the statistical test you chose to run and explain the test findings. It is essential that you follow APA manuscriipt standards when writing this section. Please refer to Chapters 2, 3, 5, and 7 of your APA manual for further instructions on how best to write a Methods and Results section.
Submit your assignment here. Make sure you’ve included all the required elements by reviewing the guidelines and rubric.
Important Tips: Raw Data
Remember that raw data refers to how you reduced your data for analysis.
Suppose you have response categories of strongly disagree, disagree, neutral, agree, and strongly agree. Your data analysis would be stronger with fewer categories, so you may want to reduce your data to disagree, neutral, and agree. You would recode your variables in a case like this one. Or you might find that in the race variable, you have 3 Black, 3 white, 1 Pacific Islander, 1 Native American, 1 Asian, 1 biracial, and 1 other. Since you have so few participants in five of those categories, your data might be more meaningfully recoded into Black, white, and other.
Sometimes you’ll need to recode your scale as instructed by the survey scoring guide information.
Surveys often have items that require recoding from negative to positive or vice versa.
You may not need to recode variables. However, do not skip this critical element. If you do not need to recode variables, tell the reader that the raw data was not reduced for statistical analysis. This way, you show that you clearly understand the meaning and address the critical element.
Important Tips: Descriiptive Statistics
Begin your analysis with descriiptive statistics, an expected and beneficial approach.
If age is given in years, you can report measures of central tendency (mean, mode, median) and measures of variability (range and SD).
You could analyze other types of data, such as the number of siblings, pets, hours at work, hours of school, etc., in the same way.
With nominal variables such as race or gender, you can report the percentages of respondents with a particular characteristic; however, the mean of nominal level data is meaningless. For example, if your data is coded as 1 for male, 2 for female, 3 for non-binary, and 4 for other, you cannot add the number of ones and twos to obtain a mean. The number stands for the category. You can, however, say you surveyed X number of males (x%), X number of females (x%), X number of non-binary (x%), and X number of other (x%).
Be sure to include an APA formatted table in your descriiptive data.
Important Tips: Statistical Tests
Think about your research question. What variables could help answer the question?
You will not have the number of responses necessary to use inferential statistics. However, you will use them as part of your learning experience. This exercise is educational, and you would need a higher sample of participants in real-world data collection.
What test will give you answers to the research question?
The level of data you collected decides the statistical tests that are proper to use. For instance:
Suppose you want to look at gender (coded as M for male, F for female, and O for other) and ask, “do you wear a mask in public?” (responses of yes or no). You may use a chi-square to explore the relationship between nominal variables in a situation like this one.
Is your data ordinal or rank order? That would be a Spearman rank-order correlation.
With interval or ratio data, you can examine means with t-tests (independent or dependent). For instance, you could use gender, race, or mask-wearing status (yes/no) and compare means.
If you would like to compare means for more than two ratio or interval variables, use an ANOVA.
If you want to predict a dependent variable using multiple independent variables, review multiple regression.
ATTACHED IS THE DATA COLLECTED SO FAR. ITS NOT MUCH BUT PER PROFESSOR IT IS OKAY. PLEASE USE THIS DATA. IF YOU HAVE ANY QUESTIONS MESSAGE ME!!