1600 word min due 12/21. 4 Apa format scholarly sources
Week 2 assignment work
Explain the difference between qualitative and quantitative data
Quantitative data is info about measures and thus numbers while qualitative data is expressive explains on concepts that can be experimental but not quantified such as language. Qualitative is non-statistical and in other terms its known to be semi-structured in nature. Qualitative information is not quantified using hard number but it is characterized based on properties, traits, tags and other identifiers. It answers the question "why" as it is always exploratory and open-minded giving room for more research to be conducted. This type of data is generated from qualitative study and used for theorization, clarifications, development of hypothesis and basic understandings, (Almalki, 2016 p.289).
Qualitative data can be generated through various methods that include: texts and papers, auditory and video recordings, imagery and symbols, consultation transcripts and focus groups, observations and records. Identification numbers like driver's license are classified to be qualitative data since they are definite and inimitable to one person. On the other hand, quantitative data can simply be categorized further into either discrete or continuous. Discrete data refers to the type of data that cannot be broken further. It is finite data made of integers running from the negative to the positive it can also be technically categorical. For instance, number of football players last year is discreet. Continuous data refers to the type of data that can be substantially broken down into reduced parts or simply statistics that can fluctuate. Qualitative data is usually time consuming and expensive because its unstructured. Quantitative data is always preferred for data analysis since its structured and can easy be searched for in the relational databases. Simply qualitative data deals with words and meanings and give room for exploration of ideas while quantitative deals with numbers and statistics and gives room for hypothesis testing.
Define the 4 levels of measurement
The level of measurement explains on how each variable is assessed whether qualitative or quantitative and how detailed each variable is. Nominal level the data can only be categorized while ordinal data it can be categorized and ranked. In interval level, the data can be categorized ranked and spaced while in ratio can be categorized, ranked, spaced and the data has a natural zero. Nominal is a identifying scale where variables are just named or labelled without any definite order, (Van, 2017 p.50).
Ordinal scale has all its variables in a definite order beyond naming them. Nominal labels variable into specific classifications but does not involve quantitative value. For instance, the question "where do you live?" answers could be city, town or rural. Ordinal scale maintains descriptional qualities in a given order. For example: "how satisfied are you with our services?" the answers can be: very unsatisfied, unsatisfied, neural, satisfied and very satisfied. Interval is quantitative since it gives difference between variables.
Interval is the third level of measurement which is a quantitative measurement scale that has order. It shows distance between two variables which is usually meaningful and of equal sizes and has an arbitrary presence of zero. It is used in measuring variables that exist along a common scale at equal intervals. Measures applied in estimation of distance between variables are quite reliable. It is preferred to nominal and ordinal which are qualitative in the sense that it can be used to determine difference between two values. Mean and median can be calculated in interval measurement.
Ratio level of measurement contains the features of the other levels of measurement. It is a quantitative level scale and has equivalent intervals between points and has a true zero value. Zero means there is a complete absence of the variable being measured. Examples of ratio scale include: length, area and population. In ratio level of measurement, the values can be categorized, ordered, the values have equal intervals and take on a real zero.
Why are levels of measurement important to research process?
First, identifying the level of measurement helps one choose how to infer data from the given variable. For example, knowing that a measurement is nominal, then it hits that arithmetic values are just but shorter codes for lengthier names. Secondly, identifying the level of measurement aids in the decision making of what type of statistical analysis is suitable for the assigned values. For example, a nominal level of measurement one would not choose t-test as statistical analysis tool on that type of data.
Identification of the levels of measurement is essential for researchers in HRM as it gives basis for data analysis through statistical modelling. Qualitative researchers use nominal and ordinal levels of measurement which are associated with non-parametric statistical techniques used to qualify and analyze qualitative data. These non-parametric techniques do not make assumptions about the shape of the distribution and are not concerned on how covariates affect it. Therefore, such techniques provide alternative series of statistical models and methods that can be used to analyze qualitative data.
Statistics based on categorization and ranks of observation of qualitative data are examples of such statistics and they play a central role in research in HRM. Chi-square tests, Spearman's rank correlation coefficient, Wilcoxon's rank and others form examples of tests that are abundantly applied in qualitative data analysis of the research. In HRM researchers rely on the qualitative data which depends on the levels of measurement especially the ordinal and nominal scales. In organizations nominal and ordinal scales are used in determining relationships between the workers.
Discuss variable, independent variables and confounding variables and how they are used in research
A variable is a quantity that changes within a study or an experiment. There are two types of variables that include dependent and independent variables. A dependent variable is what occurs as a result of the effects of independent variable while independent variable is what influences the dependent variable. On the other hand, a confounding variable affects the relationship between independent and dependent variable. They lead to biasness causing the estimate to differ from the exact value of the population. For instance, in an experiment or study to determine how alcohol consumption affects mortality using two groups of alcohol users who are heavy drinkers and teetotalers. In this case alcohol consumption becomes the independent variable and mortality takes the position of dependent variable. The other factors that could contribute to mortality like healthy eating become confounding variables, (Kaur, 2013 p. 37).
These variables are important in research, independent variables are used by the investigator for manipulation in order to measure the effect of manipulation on the other variable. Dependent variable is used as the variable outcome which links on the influence or manipulation by the independent variable. Confounding variable can be used in research study in the manner which it influences both dependent and independent variables hence not giving the right result. They can be reduced through randomization of the variables in the study groups. Its not usually accounted for in the research equation hence can give results of existence of correlations when they are not actually there. Therefore, researchers use independent variables to control the experiment by manipulating the dependent variable and learning on how effect of one variable affects the other variable in the study while confounding affects the two variables and causes wrong results.
References
Almalki, S. (2016). Integrating Quantitative and Qualitative Data in Mixed Methods Research--Challenges and Benefits. Journal of Education and Learning, 5(3), 288-296.
Van Blerkom, M. L. (2017). Measurement and statistics for teachers. Taylor and Francis.
Kaur, S. P. (2013). Variables in research. Indian Journal of Research and Reports in Medical Sciences, 3(4), 36-38.