SPSS – 1 Paragraph Response to 2 Classmate’s (2 Paragraphs Total)

By Day 5

Respond to at least two of your colleagues’ posts and comment on the following:

1. Do you think the variables are appropriately used? Why or why not?
2. Does the analysis answer the research question? Be sure and provide constructive and helpful comments for possible improvement.
3. As a lay reader, were you able to understand the results and their implications? Why or why not?

Classmate 1: (Natalie)

“Variables

The independent variable for the categorical data analysis using the General Social Survey dataset is “Respondent’s Sex” which is measured on a nominal scale. The dependent variable using the same dataset is “Should marijuana be made legal” which is also measured on a nominal scale.

Research Question

What is the relationship between the respondent’s sex and if marijuana should be made legal?

Null Hypothesis

There is no relationship between the respondent’s sex and if marijuana should be made legal.

Research design

This research design seeks to discover if there is a relationship between two categorical variables. The Case Processing Summary shows 1,574 valid cases in the analysis with 964 cases missing and out of the 2,538 cases some of the respondents did not answer. The Crosstabulation table indicates that 55.3% of the respondents believe that marijuana should be legalized and 44.7% of the respondents believe that marijuana should not be legal. The Chi-Square Test shows the Pearson Chi-square value of 14.913 with an associated p-value of 0.000 (χ(1) = 14.913, p = .000) which is below the alpha level of .005. Therefore, the researcher can reject the null hypothesis and conclude that there is a statistically significant relationship between the respondent’s sex and if marijuana should be made legal. The Symmetric Measures shows the Phi and Cramer’s V which explains the strength of the relationship. A value of 0 indicates no relationship whereas a value of 1.0 indicates a strong perfect relationship. The Phi and Cramer’s V value of .097 indicates there is a very weak relationship between the variables.

Case Processing Summary
	Cases
	Valid		Missing		Total
	N	Percent	N	Percent	N	Percent
SHOULD MARIJUANA BE MADE LEGAL * RESPONDENTS SEX	1574	62.0%	964	38.0%	2538	100.0%

SHOULD MARIJUANA BE MADE LEGAL * RESPONDENTS SEX Crosstabulation
			RESPONDENTS SEX		Total
			MALE	FEMALE
SHOULD MARIJUANA BE MADE LEGAL	LEGAL	Count	427	443	870
		% within SHOULD MARIJUANA BE MADE LEGAL	49.1%	50.9%	100.0%
		% within RESPONDENTS SEX	60.7%	50.9%	55.3%
		% of Total	27.1%	28.1%	55.3%
	NOT LEGAL	Count	277	427	704
		% within SHOULD MARIJUANA BE MADE LEGAL	39.3%	60.7%	100.0%
		% within RESPONDENTS SEX	39.3%	49.1%	44.7%
		% of Total	17.6%	27.1%	44.7%
Total		Count	704	870	1574
		% within SHOULD MARIJUANA BE MADE LEGAL	44.7%	55.3%	100.0%
		% within RESPONDENTS SEX	100.0%	100.0%	100.0%
		% of Total	44.7%	55.3%	100.0%

Chi-Square Tests
	Value	df	Asymptotic Significance (2-sided)	Exact Sig. (2-sided)	Exact Sig. (1-sided)
Pearson Chi-Square	14.913a	1	.000
Continuity Correctionb	14.522	1	.000
Likelihood Ratio	14.961	1	.000
Fisher’s Exact Test				.000	.000
Linear-by-Linear Association	14.904	1	.000
N of Valid Cases	1574
a. 0 cells (0.0%) have expected count less than 5. The minimum expected count is 314.88.
b. Computed only for a 2×2 table

Symmetric Measures
		Value	Approximate Significance
Nominal by Nominal	Phi	.097	.000
	Cramer’s V	.097	.000
N of Valid Cases		1574

Classmate 2: (Kathy)

“ Categorical Data Analysis

A Bivariate Categorical Data Analysis creates a model equation that estimates the

possible relationship between two categorical variables, and if a significant relationship exists, also discovering the possible

strength, and direction of the relationship (Frankfort-Nachmias, and Leon-Guerrero, 2018). This

discussion utilizes a Chi-Square Test for Independence, and Phi & Cramers V for the associated

measures of effect from the Symmetric Measures Table (Laureate Education, Inc. 2016a).

The Independent Categorical Variable and its Level of Measurement

The independent variable is Respondent’s Sex and the level of

measurement is nominal.

The Dependent Categorical Variable and its Level of Measurement

The dependent variable is Should Marijuana Be Made Legal and the level of

measurement is nominal.

Research Question

What is the relationship between the (IV) Respondent’s Sex and the (DV)

Should Marijuana Be Made Legal?

Null Hypothesis

There is no relationship between the (IV) Respondent’s Sex and the (DV)

Should Marijuana Be Made Legal.

Research Design

This research design is a correlational design which measures to what extent is there a

relationship between the variables of (IV) Respondent’s Sex and (DV) Should Marijuana Be

Made Legal, as completed by the respondent in the General Social Survey dataset (Laureate

Education, Inc., 2009).

If you found significance, what is the strength of the effect?

The Chi-Square Test Table below shows the significance value of .000 and therefore the

null hypothesis is rejected at the level of P<.01, since the alpha level was set at .05.

Effect Size: (0 = no relationship, 1= perfect relationship)

The very weak effect size, Cramers V value of .097 in the Symmetric Measures Table, shows a

very weak relationship between the (DV) Should Marijuana Be Made Legal as explained by the

variation in the (IV) Respondent’s Sex (West, C., 2016).

Explain your results for a lay audience, explaining the answer to the research question.

The case processing summary table gives us the total respondents that answered this research question in the GSS

dataset, and that total is 1574, which was 68% of the possible respondents. The Crosstabulations Table tells us that 55.3% of the

total of males and females said yes to legalizing marijuana and 44.7% said no to the legalization of marijuana.

These results show the Respondent’s Sex variable is a statistically significant predictor of the Should Marijuana Be

Made Legal variable (West, C., 2016). Although statistically significant, the correlation analysis

being a measure to examine the association and strength of a relationship of an independent

variable affecting a dependent variable, along with the direction of the relationship; we can say

these results are of a positive and very weak correlation of variables (Frankfort-Nachmias, and

Leon-Guerrero, 2018). Therefore, these statistical significant results are not necessarily

meaningful in a real world application.