- Part 1: Partial Research Report 3
- Introduction. 3
- Hypothesis. 3
- The materials, participant, design and procedure section. 3
- Result section. 4
- Discussion. 5
- Part 2: Design flaws. 5
- Q1: Identification of statistical analysis tools to analysis the data. 6
- Q2: Explanation of each factor 7
- Q3: Critical evaluation of data. 8
- Reference list 9
- Appendices. 10

The aim of this study is to evaluate respective risk factors that upsurge rate of dropping out of high school. In the study, the independent variables (IV) are risk factors such as low grades, low perceived quality of school, low caregiver involvement with school and absenteeism. Whereas it has been evident that the dependent variables are the effect of risk factors

H1: There is a remarkable link between identified risk factors and increased rate of dropping out of high school.

H0: There is no remarkable link between identified risk factors and increased rate of dropping out of high school.

The study focuses on the attribution rates for high school in the area. The research will give a broad idea about increased rate of dropping out of high school. In order to conduct this research, random sampling method has been used in which 24 years 9 students has been selected from two chosen school i.e., Winterfield Grammar and Summertown High (Koo *et al.* 2016). The two risk factors have been examine by administer Perceived Quality of School Scale out of 100 and Caregiver Engagement Inventory out of 100. Once two factors are critically examine, overall grade percentage for each student in the sample based on all subjects result. At last, all the variable is calculated out of 100 and based on independent variable overall risk factors of each student need be calculated. Moreover, the entire calculated potential risk factors for each student will give significant impact of risk factors on each student.

From critical analysis of data, it can be stated that overall risk factors for each students need to be calculated vigilantly so that exponential rise of dropping out of high school can be analyzed positively. Most of the time, it has been evident that blunder error often witness at the time when an individual checks other work. Therefore, it is requisite to analysis the data critically and vigilantly in order to enhance efficiency of the study positively. Measurement error is one of the effective ways to make entire study more authentic and legitimate by positively mitigation of error in a significant order. Measurement error has been kept top in priority list so that maximum and relevant result can be calculated to enhance the efficiency of study. The above list of errors needs to consider so that possibility of error in design method can be minimized.

There are several types of test can be performed in order to evaluate risks factors to determine significance effects on rise in dropping out high school. In descriptive analysis, it has been evident that cumulative percent is changing from student to student and all the value is greater than 0.5. Moreover, it can be asserted that perceived quality and caregiver involvement are major factor in rising of dropping out students based on calculated risk factors of each student in a systematic manner.

On the other hand, one-sample statistics has also been performed for each risk factor in which the standard deviation of perceived quality is 4.6562 which is greater than test value 1. Therefore, it can be asserted that school needs to maintain perceived quality in order to enhance involvement of students and reduce rise in dropping out high school. It has been evident that perceived quality of school is one of the major factors that need to consider in reducing progressive increase of dropping out high school. On the other hand, mean difference of perceived quality is 68.889 which are larger than 1 that indicates that low grades and absenteeism are equally responsible in large number of dropping out students.

The significance of each risk factors in attrition rates for High schools so that it is easy to determine whether this risk factors are present in New South Wales High Schools or not. From the above descriptive and T- test methods, it has been witness that there is a significant relationship between relevant risk factors as well as increased rate of dropping out of high school. Therefore, it can be asserted that relevant risk factors need to concern in order to reduce increase in number of dropping out students of high school. Based on equivalent result, it is important to consider relevant factors to improve involvement of students.

There are several range of issues that can possible occur while conducting a pilot study. It has been found that these relevant issues may affect interpretation error or testing error. In order to make this research more effective and relevant,

**majorly four issues are considered, which have been illustrated below are as follow:**

** Systematic error:- **It is one of the most common issues that may occur while analyzing relevant outcome of research positively. On the other hand, it has been evident that values may be consistently too low or too high. There are four kinds of systematic error such as instrumental, environmental, observation and theoretical. From the above list of kind, observational and instrumental type of systematic error that may affect interpretation or testing error simultaneously.

** Random error:- **The research has been conducted among 9 students which have been selected randomly so there is a higher chance that random error can occur (Hayes

** Blunder:- **The blunder error represents to a person who may take wrong sample or value while recording a measurement and reading a scale. It is not appreciable because a slightly mistake may reduce the efficiency of the study significantly.

** Non responsive error :- **This type of error mostly occurs or exists when an obtained sample differs from the original selected sample. In order to measure the main variable of interest, some data have been manipulated so that significance of risk factors can be critically evaluated in a systematically.

Measurement error is mostly generated by the measurement process and represent the difference between information require and information generated by the researcher.

Statistical analysis such as regression and t-test are need to use so that each data can be evaluated and analysis in a systematic order (Fitzpatrick *et al.* 2018). In order to analysis relevant data, descriptive statistical analysis tool has been considered that gives a deeper and better understanding of phenomenon.

**a) Historic effects:**Historic effects refer to an event that occurs in the environment, which may change the condition of study significantly. The effects cannot be run out because it is an external factor which is not easy to determine before conducting the research. On the other hand, it has been evident that it may occur at beginning of an experiment or between Post-test and Pre-test.

**b) Maturation effects:**Maturation effects can be defined as a behavior of a person that may change and affects the result of research. These effects can be run out buy proper planning and strategies in a research. It is important to run out because it may ruin entire study such as efficiency and effectiveness.

**c) Mortality effects:**Mortality effects can be defined as a temporary rise in the number of death rate (mortality rate) in a specific population. These effects cannot be run out because it cannot be controlled through manual effects but can be reduced through proper caring. On the other hand, researcher needs to care regarding health of students,

**d) Regressions to the mean:**It can be defined as a process asserted that data is extremely lower or higher than the mean will likely to be closed to mean if it is measured to second time (Fukami, 2015). These effects can be run out critically evaluating regression data in a systematic and efficient order.

**e) Testing effects:**The testing effect can be defined as a retrieval practice or test enhanced learning. It has been evident that it increased learning concept through proper analysis. These effects can be run out by proper devoted to retrieving the remembered information positively. The effects need to consider vigilantly while conducting research in a positive manner.

The T-Test tables signifies that standard deviation mean is 1.730, which is greater than standard deviation 1 that can be asserted that after memory intervention has better result as compared to before memory intervention. On the other hand, 95% confidence interval also varies i.e., Lower is 86.23 and upper is 94.21 so it can be stated that famous cognitive psychologists improve the accuracy and efficiency of memory in a significant manner.

In order to understand change in memory among 9 students, regression test has also been performed that signifies positive change in memory power due to cognitive learning program. On the other hand, it has also been evident that unstandardized coefficient between before memory intervention and after memory intervention are 1.164 and 5.670. At last, it can be asserted that Anova and coefficient tables of regression test signifies that learning program changes memory power of a person based on standardized coefficients (Fitzpatrick *et al.* 2018). From the regression and T-test asserted that standardized memory test play as significant role in enhancing memory power of an individual through cognitive program to improve accuracy and efficiency of a person in a significant order.

- Fitzpatrick, M. D., & Moore, T. J. (2018). The mortality effects of retirement: Evidence from Social Security eligibility at age 62.
*Journal of Public Economics*,*157*, 121-137. http://www.nber.org/papers/w24127.pdf - Fukami, T. (2015). Historical contingency in community assembly: integrating niches, species pools, and priority effects.
*Annual Review of Ecology, Evolution, and Systematics*,*46*, 1-23. http://www.academia.edu/download/40723315/fukami-2015.pdf - Gilman, E., & Huang, H. W. (2017). Review of effects of pelagic longline hook and bait type on sea turtle catch rate, anatomical hooking position and at-vessel mortality rate.
*Reviews in fish biology and fisheries*,*27*(1), 43-52. https://www.wcpfc.int/system/files/EB-IP-01%20Effects%20LL%20hook%20and%20bait%20type%20on%20turtles.pdf - Hayes, A. F., & Rockwood, N. J. (2017). Regression-based statistical mediation and moderation analysis in clinical research: Observations, recommendations, and implementation.
*Behaviour Research and Therapy*,*98*, 39-57. http://download.xuebalib.com/v39VsAuDJ9b.pdf - Koo, T. K., & Li, M. Y. (2016). A guideline of selecting and reporting intraclass correlation coefficients for reliability research.
*Journal of chiropractic medicine*,*15*(2), 155-163. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4913118/