Homework: Quantitative Processes- Analyze Secondary Data, Archived Data, and Measurement of Variables

This homework consists of three parts:

For Parts I and II:

Go to the NU Library from your home page. Examine the guide to primary and secondary sources to see what is available. This can be found under Research Help → Research Process → Determining Information Needs → Primary and Secondary Resources. Then go back to the library home page and either conduct a search using the NavigatorSearch in the middle of the page or go to the Statista database in the A-Z Databases list to locate data to answer the following questions. The library`s guide on Statistics may also be helpful.

Use tables and figures to explain your determination and support your rationale in answering the question. Be specific. Practice creating your own tables and figures to support your conclusion. You cannot use tables and/or figures from another source without copyright permission in your published dissertation research study. Be sure to cite the source of the table/figure using APA formatting.

Part I: Internet Data Usage and Age Over Time

Does there appear to be a relationship between adult internet usage and age between 2000 and 2018?

Part II: Data Breaches in Health Care Over Time

Has the incidence of data breaches in the health/medical sector increased in the last five years?

Part III: Archived Dataset

Identify one dataset (also referred to as a database) publicly available for research. A list of possible sources is included in this or choose one that may be appropriate for your research study topic. You do not need to open the dataset that includes raw numbers.

To operationalize the dataset, gather the following information about the dataset. Dataset information is most likely contained in a document separate from the dataset and may be identified as a database dictionary, codebook, or program record layout. For the homework response, include the following information using the headings and format outlined here:

Homework Outline

I. Dataset Name

II. Dataset Source

III. Dataset Location

(include link if available)

IV. Dataset Overview

Include three to five sentences to provide context for the Reader. This may include industry, focus, and original purpose for collecting the data.

V. Dataset Timeframe

VI. Four Variables

For each of the four variables, separately list the following information, using separate headings for each variable. If the information is not available, then indicate ‘not available.` Follow the template below for each of the variables/constructs.

1. State Variable Name [include dataset abbreviation if appropriate]

2. Definition of the Variable.

3. Source of Data. (This might be self-reported by business, self-reported by survey, observation, etc.)

4. Scoring of the Variable. For variables, this might be age in years, number of defects per quarter, group membership, etc. For constructs, this might be computation of multiple questions on a survey or multiple variables that make up the construct.

5. Level of Measurement. Below is a reminder of the measurement levels you learned in Statistics 1. Do not include the measurement level definitions in your homework response.

6. Nominal. Nominal data are measured at the discrete level depicting independent categories with no underlying order. Examples of nominal data are sex, race, and organizational department membership.

7. Ordinal. Ordinal data are measured at the discrete level with separate categories that imply an underlying hierarchy. Examples of nominal data are education level, age groups, or simply categories of high, medium, and low. Some Likert scales may be deemed by the researcher as ordinal data.

8. Interval. Interval data are measured on a continuous scale with ‘equal appearing` intervals and without an absolute zero point. Examples of interval data are time, temperature, credit score, and test scores. Some Likert scales may be deemed by the researcher as interval data.

9. Ratio. Ratio data are measured on a continuous scale with equal intervals and an absolute zero point. Examples of ratio data are age, income, and defects per lot. A researcher may deem an otherwise ratio data as interval if, for purposes of the research, the measurement level truncates the zero point or otherwise holds a floor or ceiling effect.

10. Score Range and Interpretation. Include the total possible range of scores for the variable and how to interpret the range. The score range and interpretation might be ‘Six-point Likert scale with ‘1` meaning "Not Satisfied at All," and ‘6` meaning ‘Completely Satisfied;` or perhaps a four-point ordinal scale with ‘1` meaning no use, ‘2` meaning little use, ‘3` meaning moderate use, and ‘4` meaning a lot of use. For nominal variables that form a discrete category then identify the coding scheme, for example 1 = male; 2 = female.

VII. Reflection

Describe advantages, disadvantages, challenges, and benefits that you feel may should be considered if you were to use an archived dataset for your dissertation research study.