CJ Statistics Homework #3 - Spring 2021 PDF

Preview

Summary

These are the answers for the third Criminal Justice Statistics homework at Temple University with Professor Ryan Setner....

Description

Homework 3 Part 1 The following questions must be completed on SPSS. You will need to use the GSS18 dataset located on Canvas. Please provide the appropriate measures of central tendency (mean, median, mode, skewness, frequency table) and dispersion (variation ratio, range, minimum, maximum, variance, standard deviation) SPSS outputs and charts (pie, bar or histogram) for the variables listed below. Write an analysis that describes the outputs and charts for each variable. *** Important Notes 

You will lose points if you include unnecessary measures of central tendency or dispersion for each variable



Many of the levels of measurement in the data set are incorrect. Be sure to check out the values to determine the proper level of measurement for each variable.



Be sure to thoroughly describe the variable you are analyzing. What exactly do these statistics mean? For example, do not just say the mean is some number. What does the number tell us about each particular variable?

Each variable is worth 5 points (worth 15 points) 1. #28 – AGE  Ratio

     

N valid: = 2,351. This means that 2,351 people responded to how old they were. N missing: = 7. This means that 7 people did not respond to this question. Considering it is a straightforward question, that explains why not many people did not answer the question. Mean: 48.97. The average age of the respondents was 48.97, nearly 49 years old. Median: 48.00, Half of the respondents were over the age of 48 while the other half were under 48 years of age Mode: 34. Most people in the dataset were 34. Skewness: .222, The data is normal

    

Minimum: 18. The youngest age in the dataset was 18. Maximum: 89. The oldest people in the dataset were in the category “89 or older” Range: 71 Variance: 326.195 Standard deviation: 18.061, This tells us that most people are between 30.9 and 67 years of age. The SD is not a good representation of the mean because considering it is such a large number, it means that the data is spread out from the average.

This frequency table shows that 65 people in the dataset are 34 years old, but the table allows you to get a better view of how spread out the ages are. For example, the second most common age with 55 people responding is 39 years old. Only 5 people in the dataset are 87 years old.

Like the frequency table, this histogram shows that people’s ages are spread out producing a normal skew. Very few people are around the age of 20 or in their 80’s.

2. #251 – FINRELA  Ordinal

 

 



N Valid: 2,321. This means that 2,321 of the people that participated in the GSS2018 dataset responded the question regarding their opinion on their family income. N Missing: 27. This means that 27 people of the people that participated in the GSS2018 dataset did not answer this question. It is possible that they felt uncomfortable sharing this information or did not know in what category they belong. Mode: 3. (which means “average”). This tell us that the most frequent response was that people felt their family income was average Median: 3. (which means “average”). This tells us that half of the people feel as though their family income is below to far below average, and the other half of people feel that their family income in above average or far above average. Skewness: -0.88, This tells us there is a negative skew. Most of the data is around “average” to “far below average”

This frequency table shows that roughly 45% of people’s opinion are that their family income is “average”. With only 2.3% feeling as though their family income is far above average. The variation ratio for this variable is 55.1%. This tells us that the mode is not the best representation of the data because more responses fall outside the mode, but it should still be acknowledged that the mode makes up nearly double the responses compared to the other categories.

This pie chart clearly shows that most people’s opinion is that their family income is “average”, and that people who believe their family income is above average make up a very small percent of the data.

3. #292 – GRASS  Nominal

N Valid: 1,447. This means that 1,447 people responded to the question whether marijuana should be made legal. N Missing: 901. 901 people did not respond to this question. There is a possibility that they have conflicting opinions on the subject. Mode: 1. (which means legal). Most people think marijuana should be made legal.

This frequency table shows that 938 of respondents believe marijuana should be made legal compared to their counterparts, 509 people, that feel as though it should remain illegal. The variation ratio is 35.2%. The mode is slightly dominating the data, but there is still a good amount of people against the idea of legalizing marijuana.

This pie chart illustrates that roughly 65% of people in the US feel as though marijuana should be made legal. Still, there are people that oppose the idea, I could infer these are probably older populations. Part 2

Below are 2 Z scores. Discuss the following for each   

The probability of scoring between that Z score and the mean The probability of scoring higher than that Z score The probability of scoring lower than that Z score

Each Z score is worth 3 points (worth 6 points total) 4. -0.28 ; Z table  0.1103 The probability of scoring between that Z score and the mean  11.03% The probability of scoring higher than that Z score  61.03% The probability of scoring lower than that Z score  38.97%

5. 1.39 ; Z table  0.4177 The probability of scoring between that Z score and the mean  41.77% The probability of scoring higher than that Z score  8.23% The probability of scoring lower than that Z score  91.77%

*Part 3 is on the following page*

Part 3

The following questions must be completed using SPSS. You will need to use the GSS18 dataset located on Canvas. For the variables located below, create and include the proper confidence interval tables from SPSS. After creating the tables, analyze what they say. Each variable is worth 5 points (10 points total). 6. #343 – HRS1

According to the top chart, the average numbers of hours worked last week in the US were 41.28 hours. With 95% confidence, the average number of hours worked last week across the US were between 40.52 and 42.05 hours. 7. #597 – NUMPETS

According to the top chart, the average number of pets a family has is roughly 1-2. With 95% confidence, the average number of pets a family has is 1 pet, possibly two.

Part 4

This week I’m going to give you two random questions. Each question is worth 1 point. Again, please be brutally honest with your answers. Feel free to type as much as you want. 8. Overall, how well do you think zoom classes/meetings work? 9. Most of the responses I get on these random questions are usually pretty negative. So I want to change that. For this question, tell me the best or favorite thing that you did or happened to you over the past few months. It can be a general thing (like new job, new friend, moving to a new place, etc.) or a specific event (like a party, night out, dinner, etc.)...