RESEARCH QUESTONS AND HYPOTHESES

1|Page
 TABLE OF CONTENTS

1.0 TITLE PAGE

2.0 DEDICATION

3.0 ACKNOWLEDGEMENT

4.0 CHAPTER ONE

4.1 INTRODUCTION…………………………………………………..5

4.2 RESEARCH QUESTIONS……………………………………………..5

5.0 CHAPTER TWO

5.1 HYPOTHESES…………………………………………………………….8

5.2 TYPES OF HYPOTHESES………………………………………………..9

6.0 CHAPTER TWO

6.1 SIMPLE VS COMPLEX HYPOTHESES…………………………………11

6.2 STATISCAL VS RESEARCH HYPOTHESES……………………………...13

TESTABLE HYPOTHESES……………………………………………………….14

CONCLUSION

REFERENCES

2|Page
 CHAPTER ONE

INTRODUCTION

RESEARCH QUESTIONS
A research question is a clear, concise, interrogative statement that is worded in the present

tense, includes one or more variables, and is expressed to guide the implementation of studies.

The foci of research questions in quantitative studies are description of variable(s), examination

of relationships among variables, use of independent variables to predict a dependent variable,

and determination of differences between two or more groups regarding selected variable(s).

These research questions are usually narrowly focused and inclusive of the study variables and

population. It is really a matter of choice whether researchers identify objectives or questions in

their study but, more often, questions are stated to guide descriptive and correlational

quantitative studies. Hypotheses should be developed to direct quasi-experimental and

experimental quantitative studies (Shadish et al., 2002). Hernandez, Morgan, and Parshall (2016,

p. 481) conducted a descriptive correlational study to examine the “resilience, stress, stigma, and

barriers to mental healthcare in U.S. Air Force [USAF] nursing personnel.” These researchers

identified a purpose and research questions to direct the implementation of their study, presented

in Research Example 5.3. The critical appraisal guidelines for examining research objectives or

questions in a study, presented earlier, were applied to this example.

Research Questions 1. What are USAF nursing personnel’s levels of stigma and barriers to

accessing MH services, stress, and resilience? 2. What are the magnitude and direction of

associations among stigma and barriers to accessing MH services, stress, and resilience in USAF

nursing personnel? 3. Are the demographic characteristics, military grade, past deployment, and

access to MH services related to stigma and barriers to accessing MH services, stress, and

3|Page
resilience among USAF nursing personnel? (Hernandez et al., 2016, p. 482) Critical Appraisal

Hernandez and colleagues (2016) clearly stated their study purpose, and the research questions

evolved from the purpose and clarified the goals of their study. Question 1 focused on a

description of nursing personnel’s levels of stigma and barriers to accessing MH services.

Questions 2 and 3 focused on examining relationships or associations among the study variables.

These questions were addressed by the study methodology, results, and findings. Hernandez et

al. (2016, p. 481) found that a large percentage of the USAF nursing personnel had “concerns

that accessing MH services may adversely affect their careers and how they are viewed by unit

leaders and peers. In addition, higher levels of concern about stigma were associated with higher

levels of stress and lower levels of resilience.

The research questions directing qualitative studies are often limited in number, broadly focused,

and inclusive of variables or concepts that are more complex and abstract than those of

quantitative studies. Marshall and Rossman (2016) indicated that the questions developed to

direct qualitative research might be theoretical, which can be studied with different populations

or in a variety of sites, or the questions could be focused on a particular population or setting.

The study questions formulated are very important for the selection of the qualitative research

method used to conduct the study (Creswell & Poth, 2018). Roll and Bowers (2017) conducted a

qualitative study to describe how healthy aging is promoted for individuals with developmental

disabilities. These investigators developed research questions to guide their study. The purpose

and questions from this study are presented in Research Example 5.4.

Research Questions (Roll & Bowers, 2017, p. 237) 1. Why did this community outreach nursing

program (CONP) for people with I/DD emerge? 2. What is the daily work of the community

outreach nurses in this program with the goal of promoting healthy aging of individuals with

4|Page
I/DD in the community? Critical Appraisal Roll and Bowers (2017) clearly identified their study

purpose and the research questions clarified the goals of the study. Question 1 focused on

identifying and describing why the CONP for people with I/DD emerged, and question 2 focused

on a description of the daily work of nurses in the CONP. These questions were the focus of data

collection and analysis and provided organization to the discussion of findings. Roll and Bowers

(2017, p. 234) found that the CONP was implemented to improve communication between

primary care providers and individuals with I/DD. The nurses’ daily work included “health

education, advocacy for the safe return home,… and enabling social participation” of individuals

with I/DD

CHAPTER TWO

5|Page
 HYPOTHESES

A hypothesis is a formal statement of the expected relationship(s) between two or more variables

in a specified population. The hypothesis translates the research problem and purpose into a clear

explanation or prediction of the expected results or outcomes of selected quantitative studies. A

clearly stated study hypothesis includes the independent variables to be manipulated or

measured, indicates the proposed outcomes or dependent variables to be measured, and identifies

the population to be studied. Different types of variables are discussed in more detail at the end

of this chapter. Hypotheses also influence the study design, sampling method, data collection and

analysis process, and interpretation of findings (Fawcett & Garity, 2009; Grove & Cipher, 2017).

Quasiexperimental and experimental quantitative studies are conducted to test the effectiveness

of a treatment or intervention; these types of studies should include hypotheses to predict the

study outcomes. Predictive correlational studies that measure independent variables to predict a

dependent variable often include hypotheses (Gray et al., 2017). In this section, types of

hypotheses are described, and the elements of a testable hypothesis are discussed, so that you can

critically appraise hypotheses in published studies. Types of Hypotheses Different types of

relationships and numbers of variables are identified in hypotheses. A study might have one,

four, or more hypotheses, depending on its complexity. The type of hypothesis developed is

based on the purpose of the study. Hypotheses can be described using four categories and

described in this section.

TYPES OF HYPOTHESES
• Associative versus causal hypotheses

6|Page
• Simple versus complex hypotheses

• Non directional versus directional hypotheses

• Statistical versus research hypotheses

Associative versus causal hypotheses

The relationships identified in hypotheses are associative or causal. An associative

hypothesis proposes relationships among variables that occur or exist together in the real world

so that when one variable changes, the other changes (Gray et al., 2017). Associative hypotheses

identify relationships among variables in a study but do not indicate that one variable causes an

effect on another variable. McKee, Long, Southward, Walker, and McCown (2016) conducted a

predictive correlation study to determine the factors that were predictive of childhood obesity.

They “hypothesized that children of overweight or obese parents are more likely to be obese”

(McKee et al., 2016, p. 197). This associative hypothesis predicts two positive relationships

between overweight parents and obese children and between obese parents and obese children.

A causal hypothesis

This proposes a cause and effect interaction between two or more variables, referred to as

independent and dependent variables. The independent variable (treatment or intervention) is

manipulated by the researcher to cause an effect on the dependent or outcome variable. The

researcher then measures the dependent variable to examine the effect created by the

independent variable (Waltz, Strickland, & Lenz, 2017). A format for stating a causal hypothesis

is the following. Study participants in the experimental group, who are exposed to the

independent variable (intervention), demonstrate greater change, as measured by the dependent

7|Page
variable, than those in the comparison group who received standard care. The study by Ruiz-

González et al. (2016), presented earlier, was conducted to examine the long term effects of a

DEP (independent variable) on biomedical and psychosocial measures (dependent variables).

This study included the following causal hypothesis: “after the DEP, patients will have lower

levels of A1c hemoglobin, greater theoretical and practical knowledge about diabetes, fewer

barriers [to self-care], higher frequency of self-care, and greater self-efficacy.” This hypothesis

included seven variables—one independent variable (DEP) that was implemented to create an

effect on the six dependent variables (HbA1c, theoretical and practical knowledge about

diabetes, barriers to self-care, self-care, and self-efficacy).

CHAPTER THREE

8|Page
 Simple versus complex hypotheses

Hypotheses are either simple or complex. A simple hypothesis states the relationship

(associative or causal) between two variables. McKee and colleagues (2016, p. 197) stated a

simple associate hypothesis in their study of predictors of childhood obesity. They hypothesized

those children whose weight status is “misperceived by their parents are more likely to be

obese.”

The study by McKee et al. (2016) supported this hypothesis because 86.2% of the parents

misperceived their child’s weight as healthy when the child was actually overweight or obese.

These researchers found that the parents’ misperception of their child’s weight status was the

strongest predictor of childhood obesity.

A complex hypothesis states the relationships (associative or causal) among three or more

variables. The study by Ruiz-Gonzalez and colleagues (2016) included the following complex

causal hypothesis: “the DEP patients will show improvements in biomedical measures,

particularly in cardiovascular risk factors such as cholesterol (total and LDL [low density

lipoprotein]) and body mass index [BMI]” (Ruiz-Gonzalez et al., 2016, p. 14).

The researchers examined the effect of DEP (an independent variable) on the dependent

variables of total cholesterol, LDL, and BMI. This hypothesis was not supported because no

changes were observed in the BMI or the total and LDL cholesterol values. Thus the Ruiz-

González et al. (2016) study had mixed results, with one hypothesis supported and the other not

supported.

Nondirectional versus directional hypotheses a nondirectional hypothesis states that a

relationship exists but does not predict the nature (positive or negative) of the relationship. If the

9|Page
direction of the relationship being studied is not clear in clinical practice or in the theoretical or

empirical literature, the researcher has no clear indication of the nature of the relationship. Under

these circumstances, nondirectional hypotheses are developed, such as “hours playing video

games is related to body mass index in school-age children.” This is an example of a simple (two

variables), associative, and nondirectional hypothesis. A directional hypothesis states the nature

(positive or negative) of the interaction between two or more variables. The use of terms such as

positive, negative, less, more, increase, decrease, greater, higher, or lower in a hypothesis

indicates the direction of the relationship. Directional hypotheses are developed from theoretical

statements (propositions), findings of previous studies, and clinical experience. As the

knowledge on which a study is based increases, researchers are able to make a prediction about

the direction of a relationship between the variables being studied. For example, McKee and

colleagues (2016, p. 197) stated a directional hypothesis: “parents will be more likely to

misperceive the weight status of younger children.” The italicized word indicates the nature of

the relationship in this simple, associative, directional hypothesis.

The study by McKee et al. (2016) supported this hypothesis because the parents significantly

misperceived the weight status of their younger children as being healthy when they were

actually overweight or obese. A causal hypothesis predicts the effect of an independent variable

on a dependent variable, specifying the direction of the relationship. The independent variable

increases or decreases each dependent variable; thus all causal hypotheses are directional.

Huang, Chang, and Lai (2016) conducted a quasi-experimental study to determine the effects of

music and exercise on insomnia in older adults. One of the hypotheses examined in this study

was that “Participants who perform brisk walking exercise combined with music in the evening

10 | P a g e
for two nights exhibit higher sleep quality scores than no-exercise baseline scores”. ” (Huang et

al., 2016, p.105).

Statistical versus research hypotheses

Hypotheses are either research or statistical .The statistical hypothesis, also referred to as a

null hypothesis (H0), is used for statistical testing and for interpreting statistical outcomes. Even

if the null hypothesis is not stated, it is implied because it is the converse of the research

hypothesis (Grove & Cipher, 2017). Some researchers state the null hypothesis because it is

more easily interpreted on the basis of the results of statistical analyses. The null hypothesis is

also used when the researchers believes that there is no relationship between two variables and

when theoretical or empirical information is inadequate to state a research hypothesis. Null

hypotheses can be simple or complex and associative or causal but are always nondirectional

because the null hypothesis states there is no relationship between variables or differences

between groups. Huang and colleagues (2016, p. 105) stated the following null hypothesis in

their study: “Subjective sleep quality scores do not differ between listening to soothing music

and performing brisk walking exercise combined with music.” The null hypothesis was

supported because the “results revealed that both the soothing music and brisk walking exercise

combined with music exhibited the same effects on subjective sleep quality” (Huang et al., 2016,

p. 107).

A research hypothesis is the alternative hypothesis (H1 or HA ) to the null or statistical

hypothesis and states that a relationship exists between two or more variables. All the hypotheses

stated earlier in this chapter have been research hypotheses. Research hypotheses can be simple

or complex, nondirectional or directional, and associative or causal.

11 | P a g e
 Testable Hypothesis

The value of a hypothesis ultimately is derived from whether it is testable in the real world.

A testable hypothesis is one that clearly predicts the relationships among variables and contains

variables that are measurable or able to be manipulated in a study. The independent variable

must be clearly defined, often by a protocol, so that it can be implemented precisely and

consistently as an intervention in a study. The dependent variable must be clearly defined to

indicate how it will be precisely and accurately measured (see the next section on defining study

variables). A testable hypothesis also needs to predict a relationship that can be “supported” or

“not supported,” as indicated by the data collected and analyzed. If the hypothesis states an

associative relationship, correlational analyses are conducted on the data to determine the

existence, type, and strength of the relationship between the variables studied. The hypothesis

that states a causal link between the independent and dependent variables is evaluated using

statistical analyses, such as the t-test or analysis of variance (ANOVA), that examine differences

between the means of the dependent variables for the experimental and comparison or control

groups (Grove & Cipher, 2017; see Chapter 11). It is the statistical or null hypothesis (stated or

implied) that is tested to determine whether the independent variable produced a significant

effect on the dependent variable. Hypotheses are clearer without specifying the presence or

absence of a significant difference because determination of the level of significance is only a

statistical technique applied to sample data. In addition, hypotheses should not identify

methodological points, such as techniques of sampling, measurement, and data analysis (Grove

& Cipher, 2017). Therefore such phrases as measured by, in a random sample of, and using

ANOVA are inappropriate because they limit the hypothesis to the measurement methods,

sample, or analysis techniques identified for one study. In addition, hypotheses need to reflect

the variables and population outlined in the research purpose.

In summary, the research objectives, questions, and hypotheses must be clearly focused and

concisely expressed in studies. Both objectives and questions are used in qualitative studies and

descriptive and co relational quantitative studies, but questions are more common. Some co

relational studies focus on predicting relationships and may include hypotheses.

Quasiexperimental and experimental studies should be directed by hypotheses.

13 | P a g e
 REFERENCES

Creswell J.W., Poth C.N. Qualitative inquiry & research design: Choosing among five

approaches. 4th ed. Thousand Oaks, CA: Sage; 2018.

Fawcett J., Garity J. Evaluating research for evidence-based nursing practice. Philadelphia, PA:

F. A. Davis; 2009.

Gray J.R., Grove S.K., Sutherland S. The practice of nursing research: Appraisal, synthesis, and

generation of evidence. 8th ed. St. Louis, MO: Elsevier Saunders; 2017

Grove S.K., Cipher D.J. Statistics for nursing research: A workbook for evidence-based practice.

2nd ed. St. Louis, MO: Elsevier; 2017

Hernandez S.H., Morgan B.J., Parshall M.B. Resilience, stress, stigma, and barriers to mental

healthcare in U.S. Air Force nursing personnel. Nursing Research. 2016;65(6):481–486

Huang C., Chang E., Lai H. Comparing the effects of music and exercise with music for older

192 adults with insomnia. Applied Nursing Research. 2016;32(1):104–110.

Marshall C., Rossman G.B. Designing qualitative research. 6th ed. Los Angeles, CA: Sage; 2016

McKee C., Long L., Southward L.H., Walker B., McCown J. The role of parental misperception

of child’s body weight in childhood obesity. Journal of Pediatric Nursing. 2016;31(2):196–203

Roll A.E., Bowers B.J. Promoting healthy aging of individuals with developmental disabilities:

A qualitative case study. Western Journal of Nursing Research. 2017; 39(2):234–251.

14 | P a g e
Ruiz-González I., Fernández-Alcántara M., Guardia-Archilla T., Rodríquez-Morales S., Molina

A., Casares D., et al. Long-term effects of an intensive-practical diabetes education program on

HbA1c and self-care. Applied Nursing Research. 2016;31(1):13–18.

Shadish W.R., Cook T.D., Campbell D.T. Experimental and quasi-experimental designs for

generalized causal inference. Chicago, IL: Rand McNally; 2002.

Waltz C.F., Strickland O.L., Lenz E.R. Measurement in nursing and health research. 5th ed. New

York, NY: Springer Publishing Company; 2017

15 | P a g e