Identification
The identification section of the questionnaire comprises of discrete prompts. Consequently, the data collected from the prompts will be interpreted through principal content analysis and general conclusions on the data made based on the discrete values. The identification component is mainly used as a control variable in the study; hence, allowing for the identification of the suitability of the respondents in meeting the objectives of the study. Notably, the data will be assessed using descriptive statistics, which provides a general perspective on the characterization of the respondents in the study.
Income and Wellbeing
The interpretation of the income and wellbeing data requires the construction of an index. The responses from the income and wellbeing prompts will be assessed using the principal content analysis and be used in the combination of various variables under in order to create a single continuous variable. The income and wellbeing prompts and the responses are not ordered on the same scale. However, the combination of data using weighting approaches will enable the combination of the responses into a single variable relevant to the study. The income and wellbeing index will then be used as a key variable in the OLS model as created and defined in this methodology section.
Demographics
The variables in this segment include age, gender, education, geographic location, experience. These variables are majorly binary in nature and consequently, there will be no index construction for the variables under the section. The data collected under the section is purely discrete and not continuous. Grouping of the data and the use of descriptive statistics would be considered as the ultimate level of the analysis of this data. The interpretation of the data will be used purely in the control variables where the age of the respondents among other such observations will be the critical variables of interest. For instance, the analysis will categorize the data on age into two categories based on the 35 years age limit. The two main groups of interest include those below 35 years and the data of respondents above 35 years and it based on this data that he research will determine where the respondent belongs in the category. Other variables considered under the demographics section include the religion, marital status, and number of children in the family. The data includes the geographic data of the respondents with regard to the province of origin as well as the year in which the respondents participated in the Hafiz program. The analysis of the variables will be used in further description of the findings from the study. Notably, these statistics will majorly apply in the linear probability model in the analysis.
The Quality Of Life
The variables considered in the questionnaire to analyze the quality of life for the individuals who participate in the Hafiz program are security and health along with financial capability, mode of transport, as well as individual lifestyle. The prompts focusing on security along with lifestyle patterns such as having a maid or being in debt produce a binary outcome. The analysis for these will apply the linear probability model. Health and mode of transport among other alternatives offer a variety of options that have no particular rating and thus are not continuous dependent variables. Rather, the variables have multinomial categories. The analysis of the data from the prompts will be separated from all prompts with binary categories. The data will then be used in the development of an index that will be applied in the OLS model of a data analysis as presented elsewhere in the paper. The combination of the multinomial and binary categories and data output will be coded through content analysis in order to ensure that the data reflects the best observed phenomenon and is representative of the views of the respondent in general. Where necessary, the prompts with multinomial categories may be analyzed separately if following this interpretation and analysis process will be considered to produce better results for the study. The objective is to ensure that to the greatest extent the data is representative of the populations studied.
In general, how you describe your health?
Excellent
Very good
Good
Fair
Poor
I will combine the responses into fair and poor responses hence making the data responses binary. The implications of this are that I will be able to easily prepare a representative quality of life index that will be used as the main variable in the model of analysis.
Social Activities
The variables considered in the establishment of the social responsibilities include the family relations of the participant, religious activities, family roles, along with social activities. The frequency of participation in family and religious activities as well as social interactions is the measure of outputs. The result is thus qualitative data whose analysis follows the protocol of OLS. The responses allowed for the prompts under the section include frequently, sometimes, and never meaning that the data is not continuous and that it is discrete. The same ordered scale allows for the creation of a representative index and hence making it easy to apply OLS regression. Notably, using principal components analysis requires the construction of indices on if the data use has equal intervals otherwise known as the same ordered scale. The created social activities and responsibility index will used as an independent variable in the OLS regression model.
Civic Activities
Like the social activities data as, the civic activities data also includes same ordered scale and; hence, the approaches employed in the analysis and interpretation will generally be the same. The first prompt in this category produces categorical data as it rates the responses from the most important to the least valuable. The other variables applied in the study of civic responsibilities include the respect for the rule of law, as well as participation in voluntary work and participation in the community activities while embracing charitable work and voting in municipal elections. The nature of civic responsibility goes hand in hand with an individual’s awareness of community programs in particular poverty reduction programs that are the focus of the study. The outcomes measure the frequency of action and participation. Therefore, for civic responsibility, the recommended analysis is the use of PCA to determine the relationship between the variables. The variable obtained from PCA is now subject to OLS regression. The control variable is the acceptable civic responsibility in the overall society. The use of PCA in interpretation and analysis as well as the application of the OLS regression model as created elsewhere in this paper is supported by the same ordered scale for all the prompts under the section. The same ordered scale makes it easy for the analysis to create the civic responsibility or activities index that will be used as an independent variable in the OLS regression model.
Second Survey
The second survey is characteristically similar to the first survey. The purpose of conducting the second survey is to be able to get a 360-degree view of impact of the program on the respondent. Consequently, the second survey will help to see the effect from the perspective of the family member, and to validate the responses of the first survey. This survey will be mainly focusing on measuring the dimensions of the integral approach that related to wellbeing and quality of life, social responsibility, and civic responsibility. Consequently, the study will employ the same approaches and processes in both survey one and survey two with survey two being used as the control for the first survey. The comparative research design provides for the explanation of why similar research approaches ought to be considered under both situations.
