I’m working on a Statistics exercise and need support.
Descriptive Statistics Project: For this project you will be collecting data on some type of group difference and performing a variety of descriptive statistics using SPSS and the skills learned in class. First, you will need to collect data on some type of group difference. For example, a group difference you might want to investigate is gender differences. In society there are many perceived gender differences. Some of these perceived gender differences may exist and others may only be false stereotypes. If you want, you can use gender as one of your variables and then select a second variable you wish to investigate. Choose a variable that is of interest to you such as academics, a hobby, or even a stereotype you believe may be inaccurate. If you are not interested in gender differences, there are many other groups that you could investigate. For example, you could examine students in a Greek organization versus students not in a Greek organization. You could study students who live on-campus versus students who live off-campus, or even people who exercise daily versus people who do not exercise at all. First, select the two groups of people you want to study (eg., men & women). Then select a variable you wish to investigate (e.g., number of study hours per week a freshman studies). The more creative you are, the better! Further, collect data that you might be able to utilize for future projects in this course. (**Please note that RR#2 is an Independent Samples t-test. Therefore, we would hope that you could use your same data for RR#1 AND RR#2. Using Interval or Ratio data for a Dependent Variable is necessary. Nominal or Categorical Data for your Dependent Variable would not be appropriate)! **Make sure that your dependent variable meets the Institutional Review Board’s (IRB) criteria. Pages 212-216 of the Homework Packet provides information on which variables and topics are NOT exempt from receiving automatic institutional approval. Collect data from exactly 16 people in your first group, and exactly 16 people in your second group. (So if you are investigating gender differences, for example, collect data from exactly 16 females and 16 males). Ask each participant your question or get your measurement. Please try and keep the subject responses confidential (you will be more likely to get honest and accurate answers—this also protects the subject). Record your data in a table that includes the participants’ group and their response. 2 **When completing this project, please watch for differences between the project guidelines, the versions of SPSS, and the instructions in the Homework Packet** Complete the following: 1. Write an introduction explaining the following: (3 points) a) how and where you collected your data b) what you controlled for and could not control for as a researcher (That is, explain what other influences or independent variables that you could/did not control that may have resulted in your data set not accurately representing your groups. [That is (for example), what kinds of factors can control how much sleep a person gets? Were those factors that you could control or did not have control over while collecting your data?] c) why you are studying these particular variables d) what you expect to find, and WHY! e) **be sure to add a copy of your data** 2. What is your independent variable? What is your dependent variable? For each variable identify the following: a) type of data: categorical or measurement (2 points) b) scale of measurement: nominal, ordinal, interval, ratio c) Is the dependent variable discrete or continuous? 3. Using SPSS, construct a frequency distribution for each group. Include output here. Discuss your findings [For example, what scores did most of your participants get; were the scores grouped together, or all spread out; etc…]. (1 point) 4. Using SPSS, construct a histogram for each group. Include output here. Be sure the axes are clearly labeled. Based on the graphs, describe the shape and modality of each distribution. (Hint: You will need to split your file in SPSS) [For example, are your distributions normal? This could impact how you answer question 5c] (1 point) 5. Using SPSS calculate the mean, median, and mode for each group. Include your output. Based on your findings, answer the following: (2 points) a) What is the average score in each distribution? b) What score corresponds to the 50th percentile in each distribution? c) Which measure of central tendency is the better one to report for each of your distributions and explain why? 6. Using SPSS, calculate the range, variance, and standard deviation for each distribution. Include your output. (1 point) a) Interpret the standard deviation for each group. b) Do you have much variability in your data? c) Which distribution has more variability? 7. Using SPSS create a z-distribution for each group. Include/provide your output. (3 points) a) What raw score best corresponds to the top 20% for each distribution? b) What raw score best corresponds to the 30th percentile for each distribution? (Hint: Look up the corresponding z-scores in your tables and find which values in each of your distributions best (is closest to) the z-score you looked up) [Using Howell, find the z-scores at the 30th percentile, and the top 20% or 80th percentile. Now look at your z-distribution for each of your 2 groups and find the zscores that are closest….what are the corresponding raw scores?] 8. Summarize your project. In your summary, make sure that you address all control factors that you discussed in your introduction. Further, provide insight on why you got the results that you did. (2 points)