University of Maryland School of Nursing:     NRSG 795 Analysis #3:  Associations/Relationships (10 points) Background and Objectives   In Analysis 1 & 2, you described the characteristics of a sample using appropriate descriptive statistics and graphs and also performed hypothesis testing for research questions that explored differences in the means

Subject:StatisticsPrice:15.99 Bought16

Share With

University of Maryland School of Nursing:     NRSG 795

Analysis #3:  Associations/Relationships (10 points)

Background and Objectives

 

In Analysis 1 & 2, you described the characteristics of a sample using appropriate descriptive statistics and graphs and also performed hypothesis testing for research questions that explored differences in the means.

 In Analysis #3, you will begin to examine relationships among two variables. Not only will you describe the relationships with scatterplots and crosstabulations (frequencies and proportions), but you will also use inferential statistics to determine if there is a significant association in the population, based on information from the sample.

You will demonstrate your ability to:

1)         test hypothesis about relationships between variables that are both measured at nominal or ordinal level -- and between variables that are both interval or ratio level.  

2)         Conduct scatterplots, correlation, simple linear regression, cross tabulations and chi square; and

3)         Summarize findings as you would in a journal article or report.

 

You will use the dataset: NRSG795_teens_F20.  This fictional dataset represents the results of a survey distributed to teens seen at an emergency care clinic. The survey explored factors that impact the respondents’ psychological adjustment and well-being.  A subset of cases and variables were selected for this class. 

Assignment

 

Start by examining the data and the coding of the data (variable names and values of variables) for the variables you will examine in the hypotheses below. 

1. Conduct the appropriate analysis to test the following hypotheses and summarize your findings.

Hypothesis 1a.  There is a negative correlation between aspirations for the future and the suicide indication score.

Hypothesis 1b.  Aspirations for the future has a predictive relationship with suicide indication score.

Hypothesis 2.  There is a relationship between gender and smoking history.

 

For each hypothesis summarize the information for the following steps in your write up:

1.  State the null hypothesis.
2. Decide how to analyze the relationship.
3. Check the necessary assumptions for the statistical tests you choose (show evidence that you checked).
4. Create scatterplot or crosstabulation table as appropriate.
5. Calculate the p-value for the appropriate statistical test, and assess whether the hypothesis was supported or not.

2. Prepare a summary of the findings in a paragraph, citing both the descriptive results and the testing of the hypothesis.  Include figures or tables to show your findings. Note: you may integrate the summary for hypothesis 1a & 1b together but remember to still mention test specific information
3. Include EXCEL output or IS raw output view showing your work.

 

See the examples below for descriptions of findings from another database. The paragraphs can be SINGLE SPACED (save a tree). This whole assignment should be no more than 2-3 pages. 
 

• Example of how a result may be written for a Pearson correlation:

The scatterplot of the scores on the Beck Depression Inventory and the scores for Quality of Life showed that the points are in a narrow cigar shape from the upper left hand corner to the lower right hand corner.  This would indicate a moderate to strong negative relationship between depression and quality of life.  The strength and significance of the relationship between depression and quality of life was investigated using the Pearson Product Moment correlation. There was a large, negative correlation between the two variables (r=-.54, n=156, p=.007), with higher levels of depression associated with lower levels of quality of life.

• This is an example of how results may be written for a Chi-Square test:

 The crosstabulation of smoking by gender showed that the proportion of women who smoked (18%) was similar to men (20%).  A Chi-square test for independence indicated no significant association between gender and smoking (p=.34, n=220).

• This is an example of how results may be written for a simple linear regression:

A simple linear regression was conducted to assess the ability of Internal Locus of Control to predict Perceived Stress.  Locus of control explained 6% of the variance in perceived stress (R²=.06). The Model was significant (F=13.2, p=.008).  For each point increase in locus of control, perceived stress decreased by 2.4 points (beta=-2.4, p=.01).