Assignment Learning Outcomes
1. Create a codebook
2. Identify scales of measurement for different variables
3. Generate relevant descriiptive statistics (i.e., tables, graphs, measures of central tendency and variability) using jamovi
4. Interpret descriiptive statistics, frequency distribution tables and graphs for a given dataset
This assignment has two sections:
(1) Applied conceptual questions
(2) Examine your data using jamovi and interpret the results
PART #1: Applied Conceptual Questions [6 marks total]
1. Why does the mean have the lowest value in a negatively skewed distribution? (1 mark)
2. The data for two research participants who completed a series of reaction time tests over several trials are summarized in the table below.
Participant A Participant B
Mean reaction time across trials (in seconds) 35 47
Standard deviation (in seconds) 1.75 4
Which participant appears to be more consistent in their reaction time on the task? What evidence did you use to draw this conclusion? (2 marks)
3. On an exam you obtain a score of X = 78. Which set of descriiptive statistics would you prefer the exam to have? Please explain the reasoning behind your choice (2 marks)
Option A M = 72, s = 2
Option B M = 72, s = 3
4. Using the same two options as in #3 above, and assuming that both distributions of exam scores were normally distributed, what proportion of scores on the exam would be beneath your score for each option? How do these proportions further support your response to question #3 above? (1 mark)
PART#2: Examine your data using jamovi and interpret the results [28 marks total]
Data can be found in the corresponding Excel file on eClass: Employee Survey.csv
This data set contains data from an Employee Survey used to measure employee engagement and job satisfaction of all employees at a local tech startup. For all employees, engagement and job satisfaction were measured in January and again in December. Engagement and job satisfaction scores (both at start and end of year) were calculated for each employee by averaging across multiple items of the questionnaire, which yielded continuous scores ranging from 0 to 20; scores were rounded to the nearest whole number for the final dataset. This year, the startup also wanted to track employees who were designated as “work from home” vs. “in office” to ultimately determine if there may be differences in engagement or job satisfaction across work locations. This information was recorded for each employee based on the nature of their job descriiptions. More details about the variables in this dataset are included below.
Variables
The dataset includes 200 cases and 6 variables:
Employee ID
Group (1 – work in office, 2 – work from home)
Engage_Jan– Start of year engagement scores (continuous scores ranging from 0 – 20)
JobSat_Jan – Start of year job satisfaction scores (continuous scores ranging from 0 – 20)
Engage_Dec – End of year engagement scores (continuous scores ranging from 0 – 20)
JobSat_Dec – End of year job satisfaction scores (continuous scores ranging from 0 -20)
1. Present a descriiption of your variables: Provide a codebook in table format with the following four columns: (1) Variable name; (2) Variable descriiption; (3) Variable levels/values; and (4) scale of measurement (i.e., nominal, ordinal, interval, ratio). This should be able to fit on a single page and include sufficient information about each of the variables in your dataset for other researchers to understand your data. (9 marks)
2. Examine your data using jamovi: Produce appropriate descriiptive statistics, graphs and/or tables for your overall data from jamovi as appropriate for the variables in the data – examples of these are measures of central tendency and variability, frequency tables, histograms and/or bar charts. Be sure to only calculate the descriiptive statistics, graphs, and/or tables that are appropriate for your data and its characteristics. Include your output as your response to this question. (5 marks)
3. Interpret your variables’ distributions: Use the information from your descriiptive analysis from question #2 to give a detailed descriiption of each variable’s distribution of scores. Be sure to mention all relevant features of each variable that can be determined based on your full examination of the data. Provide a brief explanation of the statistical evidence that supports your summary of these characteristics as is relevant. Your response should not exceed one page in length.
(13 marks)
4) What is one possible research hypothesis that you could propose based on these data? (1 mark)
