Regression, Part 1

Jamie asks: When you did blogs on several of the statistical analyses, you did not do one on regression. Would that be one you would consider blogging about? I've been getting stuck on that.  

Of course, Jamie! I am going to assume that you are interested in multiple regression. This is a little more complicated to try to cover in a blog post, but let's give it a try! Multiple regression is a more sophisticated extension of correlation and is used when you want to explore the predicative ability of a set of independent variables (IV) on one continuous dependent measure (DV). There are different types of multiple regression that allow you to compare the predictive ability of particular independent variables ad find the best set of variables to predict a dependent variable. I will be looking at a standard multiple regression. 

An example might be the time to complete an exam (IV₁), the person's grade on the exam (IV₂), and perceived stress (DV). Our research questions are – 1) How well does time on the exam and grade on exam predict perceived stress? How much variance in perceived stress scores can be explained by scores on these two IVs? 2) Which is the best predictor of perceived stress: time or grade? 

Let's do an example of a multiple regression together. So open SPSS, first go to Edit on the menu, select Options and make sure there is a check in the box No scientific notation for small numbers in tables. Enter the following data for your sample: 

Under Variable view (see tab at bottom of page), It should look like: 

Name	Type	Width	Decimals	Label	Values	Ignore the rest
Examtime	numeric	8	0	Time to complete exam	None	Ignore the rest
Grade	numeric	8	0	Exam grade	None	Ignore the rest
Stress	numeric	8	0	Perceived stress	None	Ignore the rest

 

Go back to Data View and enter the following: 

Examtime	Grade	Stress
20	63	85
45	89	65
36	75	82
59	92	45
56	96	50
27	66	90
39	70	77
52	89	70
43	82	85
55	99	47

 

Go to Analyze/ Regression/Linear. Move your continuous DV (stress) into the Dependent box. 

Move your IVs (exam time and grade) into the independent box 

For Method, make sure Enter is selected.

Click on the Statistics button

             Select the following: Estimates, Confidence Intervals, Model fit, Part and partial correlations, and Collinearity diagnostics

             In the Residuals section, select Casewise diagnostics and Outliers outside 3 standard deviations. Click on Continue.

Click on the Plots button

             Click on *XRESID and move to the Y box

             Click on *ZPRED and move to the X box

In the section labeled Standardized Residual Plots, tick the normal probability plot option. Click on continue

Click on the Save button

             In the section labeled Distances, select Mahalanobis box and Cook's

Click on Continue and then OK 

Next time we will look at the output and interpretation. Do you have an issue or a question that you would like me to discuss in a future post? Would you like to be a guest writer? Send me your ideas! Send me an email with your ideas. leann.stadtlander@waldenu.edu 

What is alignment?

Marietta writes: "Alignment was a key word at my recent residency- any insights on that? What is alignment all about?" 

Alignment is one of those tricky issues that you know when you see it. J It is getting at the idea that your research questions, hypotheses, methods, analysis, as well as the literature all align or are consistent with each other. It seems obvious when I say it, but the problem is that students are writing the paper over time, and sometimes things drift away from the original plan as you discover new literature and have new ideas. 

Here is where the outlines come in handy- laying out your plan in an explicit way helps to keep everything aligned. Going back and frequently reviewing your research questions and hypotheses help. Keeping a research journal (see 4/22) makes a big difference! Have near the front of the journal or add a sticky note as a marker to the page with your research questions and hypotheses, so it is easy to reread them.  

There is no easy way to make sure everything is aligned, you will have to check and recheck as you write. Have a sticky note on your monitor: "Is everything still aligned and consistent?" Make sure that when you are writing about your research method, the language is correct for that method. We often see qualitative studies talking about correlations – there are no correlations in qualitative research! This is not aligned. 

Right before you start working on descriptions of your research method, pull out a book on that method and refresh yourself on how things are worded and phrased.  

Thanks to Marietta for the idea for this topic. Next time, we will take a look at regression analyses. Do you have an issue or a question that you would like me to discuss in a future post? Would you like to be a guest writer? Send me your ideas! Send me an email with your ideas. leann.stadtlander@waldenu.edu

Index

I will be posting an index of all of the blog posts once a month, in order for it to be easier to find specific topics.

 

Current to 9/27

Topic	Dates of Posts
Dissertation, general	7/5, 8/16, 8/19, 9/27
Selecting a Topic	4/23, 7/8, 7/10
Organization	4/22
Committee Members	4/17, 5/3, 6/10, 7/19, 8/21
URR	5/8, 5/27
Overview of Process	4/19, 9/18
Premise	4/17, 9/6
Proposal	4/22, 9/9
C. 1	5/6
C. 2 (literature related)	4/26, 5/29, 6/3, 6/12, 6/17, 6/28, 9/16
C. 3	5/1
Defense	4/23, 5/8
IRB	5/10
Data Collection	5/13, 5/15
Quantitative Analysis	5/17, 7/24, 7/26, 7/29, 7/31, 8/2, 8/5
Qualitative Analysis	5/20
Mixed Methods	5/22
C. 4	517, 5/20, 5/22, 7/17
C. 5	5/24, 9/20
Final Defense	4/23, 5/27/ 9/11
Career	7/12
Goal Form	8/12
Motivation	6/5, 6/26, 7/1, 8/16, 8/23, 9/2, 9/18
Secondary Data	5/31
Support, Getting	4/26, 6/5, 6/24, 8/16
Writing	4/26, 4/29, 6/12, 6/21, 7/3, 8/9, 8/14, 9/4, 9/23,9/25
Other	4/18, 6/7, 6/14, 6/19, 6/24, 6/26, 7/1, 7/8, 7/15, 7/19, 7/22, 8/7, 8/16, 8/19, 8/26, 8/28, 8/30, 9/2, 9/13, 9/18

 

Next time, we will take a look at alignment. Do you have an issue or a question that you would like me to discuss in a future post? Send me an email with your ideas. leann.stadtlander@waldenu.edu

 

Scientific method

Psychological research is based on the scientific method and an understanding of the method allows for a better grasp of the requirements for your dissertation research. What are the parts of the scientific method? 1) Formulation of a question. 2) Hypotheses. 3) Prediction. 4) Testing. 5) Analysis. Let's take a look at how these fit within the dissertation requirements. 

1) Formulation of a question. This step is why are required to do a thorough literature review, so you understand where the gap exists in the literature and why the study is needed. This step forms the basis of your problem statement and research questions. 

2) Hypotheses. Notice that these are formed before you do the study, this is an important aspect because you are laying out where you are going before the study is ever started. You are not allowed to change these once the proposal is approved- so spend some time on them.  

3) Prediction. In the dissertation this is done through your theoretical framework. Your theory should lead to specific predictions, which may or may not be the same as the hypotheses. 

4) Testing. This is first related to your research method, which you must lay out in advance, and you must have permission to change once the proposal has been approved. A key issue here is that it must be replicable, meaning someone else should be able to do the study based on your detailed description. The second part of this step is when you go out and collect your data.  

5) Analysis. Merely collecting the data is not enough, you must also make sense of it- this is the analyses portion. Along with this comes fitting your results in to the literature and making sense of it based on your theory – did it come out as predicted? If not, why not? 

Next time, I will post an index for all of the posts to date. Do you have an issue or a question that you would like me to discuss in a future post? Send me an email with your ideas. leann.stadtlander@waldenu.edu

Outlines

I have had several questions on how to do outlines of dissertation chapters. My approach is to think of the outline in terms of headings or main topics. What are the main issues that you want to discuss in the chapter? A great way to start, if you are staring at blank piece of paper, is with the dissertation checklist. Write down all of the parts that are required. Then go back through each part and think about what do you want to discuss in that section? Let's try an example together. Let's use my oldest old and opinions about their primary health provider (PHP) paper (Stadtlander et al., 2013) as the basis for an outline of c. 2. 

This is a mixed method study, so let's begin with the mixed method template and write down the headings from that checklist, I am also going to put in an outline format. 

Chapter 2 (Mixed Methods)

A. Introduction

B. Literature Search Strategy

C. Theoretical Foundation

D. Literature Review of Key Variables

             1. Qual

             2. Quant

E. Summary & Conclusions 

Now I will think about my study and what needs to be discussed. I plan to conduct interviews (the qual portion) and locus of control (LOC), resilience, and self-efficacy surveys (the quant portion). I will now add in the main topics under each heading (I am also using the checklist to determine the topics, this info is in italics. 

Chapter 2 (Mixed Methods)

 

A. Introduction

1. Restate the problem and the purpose.

2. Provide a concise synopsis of the current literature that establishes the relevance of the problem.

             a. Who are Oldest old

             b. Oldest Old and health costs

             c. Oldest old and PHP

3. Preview major sections of the chapter. 

B. Literature Search Strategy

1. List accessed library databases and search engines used.

2. List key search terms and combinations of search terms

3. Describe scope of literature review  

C. Theoretical Foundation

             1. Patient-by treatment interactive model

a. Provide origin or source of the theory.

b. Describe major theoretical propositions

c. Provide a literature- and research-based analysis of how the theory has been applied previously in ways similar to the current study.

d. Provide the rationale for the choice of this theory. 

e. Describe how and why the selected theory relates to the present study and how the research questions relate to, challenge, or build upon existing theory.   

D. Literature Review of Key Variables

1. Describe studies related to the constructs of interest and chosen methodology and methods

             a. Aging and oldest old

             b. Aging and health care

2. Describe ways researchers in the discipline have approached the problem and the strengths and weakness inherent in their approaches.

             3. Quantitative

                           a. Locus of control (LOC)

                                        1) LOC and aging

                                        2) LOC and health care

                                        3) LOC, aging, health care

b. Resilience

1) Resilience and aging

                                        2) Resilience and health care

                                        3) Resilience, aging, health care

c. Self-efficacy

1) Self-efficacy and aging

                                        2) Self-efficacy and health care

                                        3) Self-efficacy, aging, health care

4. Qualitative

             a. Review and synthesize studies related to the key concepts and/or phenomena under investigation

                           1) Oldest old and relationships with PHP

                           2) Oldest old and health care practices

b. Review and synthesize studies related to the research questions and why the approach selected is meaningful. 

E. Summary & Conclusions

1. Concisely summarize the major themes in the literature.

2. Summarize what is known as well as what is not known in the discipline related to the topic of study.

3. Describe how the present study fills at least one of the gaps in the literature and will extend knowledge in the discipline.

4. Provide transitional material to connect the gap in the literature to the methods described in chapter 3. 

Next time, we will take a look at the scientific method. Do you have an issue or a question that you would like me to discuss in a future post? Send me an email with your ideas. leann.stadtlander@waldenu.edu 

Stadtlander, L., Giles, M., Sickel, A., Brooks, E., Brown, C., Cormell, M., Ewing, L., Hart, D., Koons, D., Olson, C., Parker, P., Semenova, V., & Stoneking, S. (2013). Independent Living Oldest-Old and Their Primary Health Provider: A Mixed Method Examination of the Influence of Patient Personality Characteristics. Journal of Applied Gerontology. (Available in Walden Library's Psychology/ Sage database)