UM Variables Involved when Conducting Research Discussion Responses

Respond to These two posts:

1. A Gem of a Study Discussion

    One of the leading biblical principles when conducting research is measurement accuracy and honesty in the collection. The Bible states, “Differing weights and differing measures – the Lord detests them both” (New International Version, 2001, Proverbs 20:10). Therefore, careful consideration of all variables to ensure accuracy when designing a study is crucial to ensure the data is precise and that the study glorifies God.

What are the independent and dependent variables in this study?

The dependent variable (also known as the outcome variable) is directly linked to the primary outcome of the study, according to Kaliyadan in “Types of Variables, Descriptive Statistics, and Sample Size” (2019, p. 82). The dependent variable may also be referred to as the criteria variable, presumed effect variable, response variable, predicted to variable, consequence variable, or measured result variable (Schindler, 2022). It is what is being seen in the study’s or experiment’s results. This economic growth is the dependent variable because the goal of this study is to identify the policies or practices that would encourage GDP growth and job creation (Schindler, 2022).

The outcome, in this case the expansion of the GDP and job creation, is affected by the independent variable, also known as the predictor, putative cause, stimulus, predicted from, antecedent, modified (Schindler, 2022), and explanatory variable (Kaliyadan, 2019). There are several independent variables in this situation. According to constructs like national framework circumstances, entrepreneur framework conditions, entrepreneurial possibilities, and entrepreneurial capacity, the GEM Conceptual Model (Exhibit C) organizes the study (Schindler, 2022). There are numerous additional categories for obtaining these variables inside each construct. Initiatives to increase women’s access to resources, steps to foster an entrepreneurial culture, and programs to improve entrepreneurs’ knowledge and abilities are a few examples of independent factors.

What are some of the intervening, extraneous, and moderating variables that the study attempted to control with its 10-nation design?

The link between the independent variable in the study and the dependent variable may be significantly and differently affected by intervening, extraneous, and moderating variables, which are all independent variables. The degree of creativity required for entrepreneurship is an example of an intervening variable that has an impact on the dependent variable but cannot be reversed and is challenging to assess. An unrelated variable may have an impact on the dependent variable, while a moderating variable has the potential to have a considerable impact on the outcome (Schindler, 2022). Are those with higher earnings more entrepreneurial?

By collecting data from ten countries to diversity the sample, the study attempted to regulate various factors, such as work prospects and social cultures, and therefore reach all people groups. In “Variables in Social Science Research,” Kaur provides four strategies for reducing unimportant variables (2021). Two of these ways, building the extraneous variable right into design and through randomization (Kaur, 2021), the 10-nation design accomplishes.

Can you do a causal study without controlling intervening, extraneous, and moderating variables? 

Controlling these variables is crucial to a causal investigation in order to properly understand which independent variable effects the dependent variable (Schindler, 2022). By definition, intervening, extraneous, and moderating variables are elements that affect the outcome of the dependent variable (Schindler, 2022). Even if they directly change the link between independent and dependent variables, intervening, mediating, and moderating variables nonetheless contribute to the understanding of their causal connection (Flannelly et al., 2014).

Current employment is an intervening variable in the GEM research. A population with a high unemployment rate can find entrepreneurship more appealing. Because so many people are unemployed, not because of the attempts to promote entrepreneurship, the level of interest may increase in all of them. If the variable of gender or religion is not taken into consideration, it may be difficult to determine whether there is a causal relationship between the availability of resources for women and entrepreneurship in a nation where the majority of women are not employed. While a study might theoretically be carried out without regulating these factors, the results would not be accurate and practical.  Complex and difficult business problems are more clearly defined by considering intervening, extraneous, and moderating variables and without identifying these variables, business models are incomplete and therefore are unable to solve real business challenges (Namazi & Namazi, 2016).

What is the impact on study results of using national experts (key informants) to identify and weigh entrepreneurial framework conditions?

The question of “from whom or what (target population) does the data need to be collected and how and from how many (cases)?” needs to be addressed when creating a research study’s sampling design (Schindler, 2022, p. 91). According to the GEM study, they required key informants. Key informants are members of a community who have in-depth knowledge of their field. They typically hold expert positions inside the subject field, which enables them to offer more comprehensive and insightful information than those in other fields. When collecting information is challenging or impossible, informants are deployed. Key informants wouldn’t be used if reliable information could be found easily (Houston & Sudman, 1975).

This study’s key informants or national experts have expertise regarding their country’s government, financial markets, technology, infrastructure, and labor markets (Schindler, 2022). This study’s use of key informants gives more accurate and consistent data about their respective business economies.  

Can you do a causal study when much of the primary data collected is descriptive opinion and ordinal or interval data?

Data can be divided into two categories: qualitative and quantitative. Quantitative data is made up of discrete and continuous data, whereas qualitative data is made up of nominal and ordinal data (Seltman, 2013). Since causal linkages were previously established via quantitative research, the majority of qualitative researchers do not accept qualitative evidence to explain causation (Maxwell, 2012). Although ordinal or interval data and descriptive opinion are both quantitative and qualitative data in this investigation, a causal study can be conducted. According to Maxwell (2012), “qualitative researchers can draw and support causal conclusions” (p. 660), not only by proving that there is a relationship between two variables but also by concentrating on the evolution of this relationship.

2. What are the independent and dependent variables in this study?

        This study’s independent variable is the “promotion of entrepreneurship” through various government policies and initiatives. The dependent variable is the “level of entrepreneurial activity,” which includes business formation, self-employment, and existing business development. It is assumed that there is a linear relationship between the dependent and independent variables (Huque et al., 2018; Mostafa, 2019). In a linear relationship, changes in the independent variable would result in proportionate changes in the dependent variable. If the promotion of entrepreneurship through government policies and initiatives, entrepreneurship activity will also increase.

What are some of the intervening, extraneous, and moderating variables that the study attempted to control with its 10-nation design?

       An intervening variable is something that impacts the thing we are observing. However, we cannot directly control or measure it. Instead, we must determine its effect by examining how the independent and moderating variables influence the dependent variable (Schindler, 2019). In the case study, the intervening variables are the cultural factors and market dynamics. Cultural attitudes towards risk-taking and innovation influence how policies are implemented, and consumer demand can influence the effectiveness of policies in entrepreneurship. An extraneous variable is any variable apart from the one we are studying that could lead to a change in the thing we are trying to understand. Economic conditions such as economic growth, inflation, and economic stability are extraneous variables that may impact entrepreneurial activities. A moderating variable is a second independent variable that impacts the relationship between the first and dependent variables (Schindler, 2019). In the case study, Education and Level of Skills are moderating variables that can impact how people use entrepreneurship opportunities.

Can you do a causal study without controlling intervening, extraneous, and moderating variables?

       Yes, conducting a casual study without having the controlling, intervening, extraneous, and moderating variables is possible. However, this would seriously undermine the credibility and utility of the research. The lack of control may complicate the link between the independent and dependent variables, making it harder to discern actual causation. Uncontrolled variables may hide or exaggerate the effect of the independent variable on the dependent variable. This variable is the same with experimenting. Imagine testing a new medicine to make people feel better than before. There is a responsibility that only medicine affects them, not other things like diet or sleep. If you do not control these other things, you might think the medicine works and is effective when something else makes people feel better. A research study conducted by Joseph P. Simmons, Leif D. Nelson, and Uri Simonsohn (2011) entitled “False-Positive Psychology: Undisclosed Flexibility in Data Collection and Analysis Allows Presenting as Significant” emphasizes the significance of controlling extraneous variables in the research study. The study shows that unreported data collection and analysis flexibility can produce false-positive results, damaging the research’s credibility.

Can you do a causal study when much of the primary data collected is descriptive opinion and ordinal or interval data?

          Casual studies typically require the manipulation of variables to establish causation. While most of the primary data gathered in this study is descriptive opinion and ordinal or interval data, it may not directly facilitate establishing causal relationships. However, descriptive and ordinal data can offer valuable insights into the interactions and correlations among variables. These data types may aid in identifying trends, correlations, and patterns, which could be used to formulate hypotheses for future experimental studies.

          According to a study published in the journal “Explanation and Elaboration Document for the STROBE-Vet Statement: Strengthening the Reporting of Observational Studies in Epidemiology-Veterinary Extension,” controlling or adjusting for the multiple looks of the data may not be practical and desirable and requires more research to confirm or to reject initial observations. Existing data may be used to test new hypotheses on the potential causative factors and can be utilized to confirm or reject the hypotheses. This study reveals that while descriptive opinion and interval data may not be adequate to determine causal relationships, they can still be beneficial in understanding trends and relationships among variables, which can generate new hypotheses for future research studies. It is also possible to conduct causal research using descriptive and ordinal data, but it could be more limited in scope and need careful control of the variables. (O’Connor et al., 2016).