Your Research Study

• 20 Item Survey• Descriptive Statistics• Inferential Statistics• Test two hypotheses– Two hypotheses will examine relationships

between 2 variables

Activity 1

• With your research goal, problem statement, and sub-problems identified, post them to the course discussion board. Review the other students' research goals and sub-problems.

• What are some potential pitfalls and problems you foresee in conducting the research using a survey instrument? Provide feedback to others through the course bulletin board.

• To get to the discussion area, click on the Discussion icon, then the Module 2, Activity 1 Thread.

Research Plan

• For this week’s assignment, you will be planning your survey research study.

• Your study will be addressing your research goal and sub-problems.

What is the research goal, problem statement, sub-problems?

• State your research goal, problem statement and sub-problems as presented in your first assignment.– If you need to make changes based upon your

feedback in the first assignment, do so in this one.

What are the variables involved?

• What variables will measure the characteristics of the sample necessary to answer the research questions?

• What are the formats of the variables (i.e.: ordinal, nominal, ratio, interval)? – For each sub-problem, identify the variable(s)– Describe how the data will be collected (ie: example

of the survey item, the data format, etc.)– You do not need to create the entire survey

instrument at this time

What data are necessary to answer the research question?

• How relevant will the data be when it is analyzed? Will time be a critical factor?– For this study, data will be available through a

survey research study.

Which research method is applicable to the study?

• The research problem and questions will dictate in part the most appropriate method to be used.– In this study, you are doing this step backwards.

You know you will be running a survey study, therefore, you will ensure the data and problems lend themselves to a survey study.

What instrument is needed to collect the data?

• Does the instrument already exist or will we have to develop one?– For this study, you will be developing a 20 item

survey instrument– In a real study, you would need to pilot test the

instrument.

How and by whom will the results be used?

• Knowledge of your possible audience for the study can give you some insights on how your results may be interpreted and used.– Who will use your results and how?

What are the costs involved?

• Costs associated with research vary tremendously depending on the type of research completed.

• If you were to really conduct this study in the workplace, what costs would be incurred?– I.e.: postage, printing, tech support, labor costs,

etc.

What other resources are necessary to complete the study?

• Do you need data collectors?• Will there be training costs involved?• If you were to really conduct this study in the

workplace, what other resources would you need?

Next Week’s Activity 2

• Two sub-problems will use an inferential statistic to examine the relationship between two variables using the correct correlation procedure and significance test. – For each sub-problem, develop one null and alternative hypothesis.

Next Week’s Activity 3

• Building upon your activity 2, Activity 3 asks you develop your null and alternative hypotheses for the two sub-problems that examine relationships between two variables.

Week 4:Writing Research Hypotheses

• Null and Alternative Hypotheses• The Null Hypothesis states “There is no

significance present”– Represented by H0

• The Alternative Hypothesis states the opposite or that there is significance in the findings present– Represented by H1

Null and Alternative Hypothesis Example

• A researcher wishes to determine if there is a significant difference between the average number of lost work days for males and females

• The null hypothesis would be:– H0: The average number of lost workdays for males =

The average number of lost workdays for females

• The alternative hypothesis would be:– H1: The average number of lost workdays for males ≠

The average number of lost workdays for females

Statistics and Hypothesis Testing

• When using a statistical test, we test to see if the Null hypothesis is true, if it is not, then we reject it and accept the Alternative as being true.

• Using the example with lost work days, we are actually testing to see if the Null hypothesis is true or false, if the Null hypothesis is false, then we reject it and conclude the Alternative is true.

Correlation Test Example

• A researcher develops a research sub-problem that wishes to determine if there is a relationship between the number of workdays lost due to injury and the age of the worker.

Correlation Test Example

• Remember correlation coefficients (r) can range from -1.00 to +1.00 with 0 representing no correlation present.

• Testing a correlation is a two step process• The first step is to calculate the correlation coefficient (r)• The next step is to determine if the correlation coefficient

is significant• To test the significance of a correlation, we use a t-test

procedure to see if the correlation coefficient is significantly different from 0.

http://www.andrews.edu/~calkins/math/edrm611/edrm13.htm

Correlation Hypotheses

• Null Hypothesis– H0: r = 0• (Interpreted as “There is no relationship between the

number of workdays lost and the age of the worker)

• Alternative Hypothesis– H1: r ≠ 0• (Interpreted as “There is a significant relationship

between the number of workdays lost and the age of the worker)

Example Comparing 2 Means

• A researcher develops a research sub-problem that wishes to determine if the average number of days lost per work comp claim is significantly different when comparing males and females.

Test Example for Averages

• The first step is to calculate the average number of days lost per work comp claim form males and do the same for females

• A t-test is an appropriate test statistic for comparing 2 means • To test the significance, we use a t-test procedure to

see if the average for males is equal to the average for females.

Hypotheses for Averages

• Null Hypothesis– H0: Average for Males = Average for Females • (Interpreted as “There is no difference in the averages)

• Alternative Hypothesis– H1: Average for Males ≠ Average for Females • (Interpreted as “The averages are not equal. Do not

interpret this as one group is significantly higher or lower than the other. That requires a null hypothesis that has less than or greater than in it and a result, the t value required to determine significance is different)

Activity 4

• Modify two current sub-problems or write two new ones.

• One sub-problem should examine a relationship between 2 variables and the other examine two means.

• Write a null and alternative hypothesis set for each.

Introduction Chapter

• In you next assignment, you will be writing your Introduction Chapter– Introduction – Statement of the problem – Research questions and/or hypothesis – Rationale or significance for the study – Assumptions – Limitations/delimitations– Definitions– References

Limitations:

• Are those characteristics of design or methodology that impacted or influenced the application or interpretation of the results of your study.

• All studies have limitations• Examples: samples size, Lack of available

and/or reliable data, Self-reported data & Lack of prior research studies on the topic