Question 1 Explain how sampling design, inferential statistics, and generalizati
Question 1 Explain how sampling design, inferential statistics, and generalization work together to form the foundation of quantitative research. Your response must be at least 250 words in length. Question 2 Discuss the three primary research designs highlighted in the Unit I Lesson and potential shortcomings of each. Your response must be at least 250 words in length. Question 3 Discuss the advantages, limitations, and researcher considerations when using a qualitative methodological research strategy. Your response must be at least 250 words in length. Question 4 Compare and contrast the four levels of scale measurement. Your response must be at least 250 words in length. Outside sources are not required; however, when directly quoted or paraphrased works of others are used in any manner, the writer is obligated to properly cite the source of the original narrative. Info: For Question 2: Research design refers to the research study blueprint. One’s choice of research methodology, quantitative or qualitative, dictates the type of research design. There are three primary design types: descriptive, causal (explanatory), and exploratory. Descriptive designs are aligned with the quantitative methodology. Descriptive designs are highly structured using statistical analysis to test hypotheses to determine if relationships or differences exist between variables. Descriptive designs are non-experimental and do not use control groups; therefore, descriptive designs cannot make any claims about causality. Although claims of causality cannot be made, the use of inferential statistics enable results from descriptive studies to be generalized to populations of interest. Descriptive designs should not be confused with descriptive statistics, which is an analytical approach to research. Descriptive statistics is depicted in the charts below and will be explained in more detail in a later unit. Causal (explanatory) designs are also aligned with the quantitative methodology. Causal designs test hypotheses to determine if independent variables cause a change in dependent variables or if independent variables cause differences between group means or percentages. These types of designs use extraordinarily controlled experiments and are not typically conducted in general business research given the required investment of time, money, and expertise; however, since causal designs control variables, claims of causality can be made. Additionally, the use of inferential statistics enables results from causal studies to be generalized to populations of interest. Exploratory designs are aligned with the qualitative methodology. Exploratory designs are subjective in nature versus causal and descriptive designs, which are quantitative. Inferential statistics are not used with exploratory studies, and results cannot be generalized to populations. Although results are not generalizable, they normally provide a much deeper and richer understanding of the groups or phenomena under study. For Question 4: Levels of Scale Measurement Measurement scales used in quantitative research refer to the characteristics of data that can be gathered and analyzed. Measurement scales have four major levels: nominal, ordinal, interval, and ratio. Each scale level has unique qualities and implications for statistical analysis. For example, data measured at the nominal or ordinal level generally require the use of non-parametric statistics. Data measured at the interval or ratio level is suitable for the use of more robust parametric statistical procedures, like regression and ANOVA. Interval and ratio data is also referred to as continuous data. The nominal scale is the most basic measurement scale. Data measured on a nominal scale can be categorized but it possesses no intrinsic order. Examples include gender (male/female) and marital status (single/married/divorced/widowed). The data are represented by numbers that can be categorized (e.g., male = 1, female = 2) but the numbers themselves have no value. The ordinal scale is used to measure data that can be ranked or ordered but has no proportionate distance between data values. Likert scales use an ordinal scale measure (e.g., 1 = strongly agree, 2 = agree, 3 = disagree, 4 = strongly disagree). Ordinal scales can be used to evaluate the data’s relative position, but not the magnitude of differences between them. The interval scale has all the characteristics of the ordinal scale, but also possesses equal distance between data values. For example, temperature in Celsius could be measured as 1 = 0°, 2 = 10°, 3 = 20°, 4 = 30°, 5 = 40°. The interval between each data value is equal at 10 degrees but, because data measured on an interval scale have no true zero (e.g., zero degrees still has a value), ratios between data values are meaningless. For example, it would be incorrect to state that 40 degrees Celsius is four times warmer than 10 degrees Celsius. The ratio scale is the most advanced measurement scale. Data measured on a ratio scale possesses all the properties of the previous three measurement scales, plus it has a true zero indicating no value. The true zero characteristic of ratio data makes the ratios between data values relevant. For example, it would be accurate to state that exam scores measured at 100 percent are twice as high as exam scores measured at 50 percent. 1. Each answer to be a little bit over 250 words. 2. Outside sources are not required; however, when directly quoted or paraphrased works of others are used in any manner, the writer is obligated to properly cite the source of the original narrative.