ABSTRACT The study extracts the context of Quantitative Research Methods which are used for statistical analysis. The main purpose of this report is to conduct and executing a quantitative research for better understanding. Descriptive, general regression and correlation methods are used to conclude the research. Clear data interpretation helps to understand the results in more clear manner.
Contents ABSTRACT.....................................................................................................................................2 INTRODUCTION...........................................................................................................................1 METHODS......................................................................................................................................1 Statistical package for the social science (SPSS) software....................................................1 Descriptive..............................................................................................................................1 General linear model..............................................................................................................2 Regression Model...................................................................................................................2 RESULTS........................................................................................................................................2 Participant characteristics.......................................................................................................2 Statistical analysis..................................................................................................................4 Discussion...............................................................................................................................7 CONCLUSION................................................................................................................................9 REFERENCES..............................................................................................................................10 APPENDIX....................................................................................................................................11
INTRODUCTION In the aspect of conducting research there are different types of methods which are being used by researchers. Basically, the quantitative research can be defined as a kind of research which is linked with process of collecting quantifiable data and making analysis by use of mathematical techniques (Barnham, 2015). Due to this kind of quantitative research, effective decision can be taken by researchers on a particular study. Under, the project report quantitative research is done on given range of data about various faculties including their wealth and watching television habit. According toBryman, 2017The sample size of given data is 40 observations of 40 faculties. To conduct this research a vital range of techniques and methods are applied such as general linear model, SPSS software and many more. In addition, two variables are taken from group of data which is provided in order to produce final result. In the further part of project report, final sample is mentioned from drop outs as well as hypotheses test is done on the collected data.As well as produced result is interpreted in order to make proper discussion of the quantitative research. METHODS Statistical package for the social science (SPSS) software This can be defined as a kind of software which is being used for statistical analysis. It is widely used in various type of research such as market research, health research, educational research and many more (Stage and Manning, 2015). In the aspect of above quantitative research of 40 sample size of different faculties, this software is used. It consists different kind of versions and for above research SPSS version 24 is applied. In the research, it helps in reading, writing them data through other statistical packages and spreadsheets. Descriptive This analysis is one a particular section of statistical analysis which describe the numbers in tabular format. It mainly extracts the data in simple tabular format and helps the sample of to measure the variables in more significant manner (Bulmer, 2017). The primary purpose of inferential is to give a brief description of the tests and the actions taken on a significant research. Descriptive statistics, combined with a variety of linear regressions, constitute a major part of nearly all statistical analysis. This method is also used in the quantitative research methods. 1
Paraphrase This Document
Need a fresh take? Get an instant paraphrase of this document with our AI Paraphraser
General linear model The GLM model is a type of model which is being used in research for making comparison about how various kind of variables are effecting continuous variables (Sheppard, 2015). The main difference is that there is independent variable that influences the dependent variable depending on the number of repeat items in general GLM i.e. In the terms of equation, this can be described as below: Data = Model + Error The general liner model acts as foundation of different types of statistical tests such as ANOVA, ANCOVA and many more. The formula of general linear model is as follows: Herein, Y = Dependent variable β0 = Constant value which cannot be change β1 = Coefficient X = Variable In the aspect of above research, this model is used for better understanding about relationship between variables and continuous variables. Regression Model Regression is among the most frequent methods in statistical analysis. It is very strong, essential, and simple to learn (at first glance). It is usually accused of inattention, ignorance intent, and dumbness by readers (Laurie, 2017). But, it can be a minefield for teaching and discussion because it's such a broad topic. Unless the type of correlation predicted by both the expert anduser does not suit only one mentioned by the author, then it is presumed that the writer is misinformed. RESULTS Participant characteristics In this quantitative research method 40 respondents (Male, Female) in total is taken and the variable criteria is categorised in gender, faculty, study (hours), watching television (Hours), and Wealth ($). 2
NMinimumMaximumSumMeanStd. Deviation Wealth($)4041476701472893682.222093.252 Age (Years)401988175143.7815.560 Gender3912571.46.505 Faculty40141012.521.109 Study (Hours)4004561.40.928 Watching television (Hours)4004451.13.939 Valid N (list-wise)39 The above descriptive evaluation states the statistical mean, standard deviation, variance, the for different variables. Descriptive are defined as follows: Wealth:As per the descriptive analysis average wealth of respondents as $3682.2 which is also considered as a mean. Minimum wealth is $414 and maximum wealth is $7670. It is observed that standard deviation is 2093.252. Age:The minimum age of respondents is evaluated as 19 years, maximum age was recorded as 88 years and average or mean age was recorded as 43.78 years. Standard deviation stats the standard difference which is recorded 15.5 years Gender:Descriptive evaluation in respect of male and female is calculated as mean valuate of male which mean male respondents count is greater than the count of female members. Standard deviation between male and female counted as Faculty:the respondents refers to different faculties as agriculture, arts, health and mathematics. In total 9 faculties belongs to agriculture faculty among 3 respondents are male and 6 respondents are female. 11 respondents in total belong to Arts faculty among 10 respondents are male and 1 respondent is female. 10 Respondents in total belong to health faculty among 6 respondents are male and 4 respondents are female. Overall ratio of male respondents is higher than female respondents. Study hours:this is one of the dependent variable on the basis of the study hours will be evaluated. The descriptive statistics presents following results as minimum hours consumed by different faculties were 0 and maximum hours consumed by respondents were recorded as 4 3
hours. Difference in terms of standard deviation among study hours states the following difference as 0.928 hours. An average hour is analyzed as 1.40 hours. WatchingTelevision:thisvariablepresentsthedatawhoconsumetheirtimeon television. It is evaluated that minimum time consumed was recorded as 0 and maximum time consumed as 4 hours. On an average the time consumer was recorded as 1.13 hours. Statistical analysis Hypothesis testing is carried out in order to fulfil the main aim of the quantitative research. as the above data is related to respondent’s different faculties and spending their time upon different variables as (Watching television and Study). Apart from it the wealth is another dependent variable to execute the research in more practical manner. Following two hypotheses can be analysed in order to meet the research objectives. Hypothesis 1: Respondents belong to different faculties consume hours on study Ha:Respondents utilise hours on study H0: Respondents do not utilise hours on study Test of Homogeneity of Variances Gender Levene Statistic df1df2Sig. .171a334.915 a. Groups with only one case are ignored in computing the test of homogeneity of variance for Gender. ANOVA Gender Sum of Squares dfMean SquareFSig. Between Groups1.5274.3821.590.199 Within Groups8.16534.240 4
Secure Best Marks with AI Grader
Need help grading? Try our AI Grader for instant feedback on your assignments.
Total9.69238 The above hypothetical analysis states the F (4,34) = 1.590 and p value is (p = .199). Hence, it is observed that the p value is more than the significant difference level ( p value > 0.05) which mean null hypothesis is rejected. Hypothesis 2: Respondents belong to different faculties consume hours on watching television Ha: Respondents belong to different faculties consume hours on watching television H0: Respondents belong to different faculties do not consume hours on watching television Test of Homogeneity of Variances Gender Levene Statisticdf1df2Sig. .100a234.906 a. Groups with only one case are ignored in computing the test of homogeneity of variance for Gender. ANOVA Gender Sum of SquaresdfMean SquareFSig. Between Groups.4654.116.428.787 Within Groups9.22734.271 Total9.69238 The above hypothetical analysis states the F (4,34) = 0.428 and p value is (p = .787). Hence, it is observed that the p value is more than the significant difference level (p value > 0.05) which mean null hypothesis is rejected. Test of Homogeneity of Variances Faculty Levene Statisticdf1df2Sig. .475a235.626 5
a. Groups with only one case are ignored in computing the test of homogeneity of variance for Faculty. ANOVA Faculty Sum of SquaresdfMean SquareFSig. Between Groups10.33942.5852.404.068 Within Groups37.636351.075 Total47.97539 The above hypothetical analysis states the F (4,35) = 2.404 and p value is (p = .068). Hence, it is observed that the p value is more than the significant difference level ( p value > 0.05) which mean null hypothesis is rejected. Hypothesis 3: Wealth size of respondents is based upon Faculty Ha: Wealth size of respondents is based upon faculty H0: Wealth size of respondents is not based upon faculty Test of Homogeneity of Variances Gender Levene Statisticdf1df2Sig. .100a234.906 a. Groups with only one case are ignored in computing the test of homogeneity of variance for Gender. ANOVA Gender Sum of SquaresdfMean SquareFSig. Between Groups.4654.116.428.787 Within Groups9.22734.271 Total9.69238 6
The above hypothetical analysis states the F (4,34) = 0.428 and p value is (p = .787). Hence, it is observed that the p value is more than the significant difference level (p value > 0.05) which mean null hypothesis is rejected. Discussion Interpretation The descriptive analysis states that the male member consume more hours by watching television along with the average wealth of male respondents is higher than the female respondents. It is also observed that the respondents below more than 50% of male respondents are consuming hours by watching television and on study. Link of results: From the entire results it has been identified that there is a positive relation of the results to the observation selected for research (Leavy, 2017). It has been stated that while collecting data, frequently start by reviewing the main research goals and objective that will mainly help in justification for conducted the research. This will also assist in organizing the overall data and concentrating the research methodology. The results demonstrate that the dependent variable which is the age of male and female have an impactful relation with the faculty, number of hours, total time for watching television and actual wealth. From the correlation and hypothesis test the detail relation of each variable are identified which helps in making more cosine results. In statistical term, correlation is defined as the measure which support in determining the liner connection among the two quantitative variables for example age and wealth. In case this review is helpful in describing the main objective and subjective correlation between the faculty, study and watching hours etc. It also includes some correlation instances, for instance there is a positive correlation in which one variable have higher value and that are correlated to the other variable's high values. Such as in the case of above data the higher value of age is correlated with higher value of wealth. On the other side, negative correlation means that higher value of variable is linked with low value of other variable for example, the higher value of age is connected with lower value of watching television. With the support of Hypothesis testing, the results are determined are more interrelated with the variables selected for research (Litosseliti, 2018). The act in which an analyst test depending upon the nature of information is selected in context of an assumption regarding the large population parameter. 7
Paraphrase This Document
Need a fresh take? Get an instant paraphrase of this document with our AI Paraphraser
Unforeseen events which affected results Thereare number of challenges and unforeseen that arise at the time of conducting research which have a greater negative impact on the results of findings. In the context of above quantitative research it has been identified that some of the major unforeseen events that happen while finding research results are: Interdisciplinary Perspectives:It is stated that when recognizing a question which provides the basis for a research project may arise from social trends and scholarships that emerge from areas beyond the main study area. An interdisciplinary strategy to choosing a study topic does not offer a chance to develop an even more detailed understanding of a quite complex question which may lead to wrong results and can affect the entire research (LoBiondoWood and Haber, 2017). Deduction from theory:It applies to conclusions that the author is acquainted with social philosophy and generalizations expressed in different variables selected for research. Through this analysis, these conclusions from human psychology are then put into an analytical frame of reference that can create more complex results which could lead to major confusion and wrong results. A theoretical question or theory of the predicted results in certain experimental circumstances may be developed by the study that make in developing more adverse outcome for the variable that are selected for conducting research (Patten and Newhart, 2017). Strengths and limitations of research In order to conduct any quantitative research there are can be strength and weaknesses that have a positive and negative impact upon the finding (Regnault and Herdman, 2015). This is because quantitative data are data points which can be calculated and typically collected through questionnaires of large numbers of participants who are selected for participation. Using statistical methods, qualitative information is analysed. It is better to use analytical strategies to address where, when and who concerns and not very well equipped to how and why queries. The main strength and weaknesses of selected method is discussed underneath: StrengthsLimitations 8
Findings can be generalised if selection process is well-designedandsampleisrepresentativeof study population Relatedsecondarydataissometimesnot availableoraccessingavailabledatais difficult/impossible Relatively easy to analyseDifficulttounderstandcontextofa phenomenon Data can be very consistent, precise and reliableData may not be robust enough to explain complex issues Solution to the problem identified In research there are number of problem that affect the results and may leads to wrong fining. Thus, it is required to make proper solution to these determined problems, some of these ways are discussed below: Explore the nature of problem:Many times the interaction among certain factors is directly connected to a topic or issues, and often the correlation is completely insignificant. Thus in the above research the investigator is needed to understand the all dimension that is needed to be consider to draw the meaningful results (Rooney and Evans, 2018). CONCLUSION The above research concludes the concept of quantitative research analysis. By applying statistical analysis, the results are being able to conclude as respondents belong form different faculties utilise their hours by watching television and studying. The motive of conducting research be able to summarise in more significant manner. 9
REFERENCES Books and Journals: Barnham,C.Quantitativeandqualitativeresearch:Perceptualfoundations.International Journal of Market Research;2015 Nov57(6). pp.837-854. Bryman, A. Quantitative and qualitative research: further reflections on their integration. In Mixing methods: Qualitative and quantitative research(pp. 57-78). Routledge.;2017 Jun 26 Bulmer, M.Sociological research methods. Routledge; 2017 Oct 2018 Laurie, H. Multiple methods in the study of household resource allocation. InMixing methods: qualitative and quantitative research(pp. 145-168). Routledge; 2017 Jan 15 Leavy,P.Researchdesign:Quantitative,qualitative,mixedmethods,arts-based,and community-based participatory research approaches. Guilford Publications.2017 feb 13 Litosseliti, L. ed.Research methods in linguistics. Bloomsbury Publishing. 2018 Jan 03 LoBiondo-Wood, G. and Haber, J.Nursing research-E-book: methods and critical appraisal for evidence-based practice. Elsevier Health Sciences. 2017 Mar 18 Patten, M. L. and Newhart, M.Understanding research methods: An overview of the essentials. Routledge; 2017 Aug 11 Regnault, A. and Herdman, M. Using quantitative methods within the Universalist model frameworktoexplorethecross-culturalequivalenceofpatient-reportedoutcome instruments.Quality of Life Research. 2015 Apr 24(1) pp.115-124. Rooney, B. J. and Evans, A. N.Methods in psychological research. Sage Publications. 2018 Apr 11 Sheppard, M. The nature and extent of quantitative research in social work: A ten-year study of publications in social work journals.British Journal of Social Work. 2015 May 17 (6). pp.1520-1536. Stage, F. K. and Manning, K. Eds.Research in the college context: Approaches and methods. Routledge; 2015 Nov 30. <https://www.displayr.com/what-is-correlation 10
Secure Best Marks with AI Grader
Need help grading? Try our AI Grader for instant feedback on your assignments.
APPENDIX General linear model Descriptive Statistics MeanStd. DeviationN Gender1.46.50539 Watching television(Hours)1.10.94039 Correlations GenderWatching television(Hours) Pearson Correlation Gender1.000-.102 Watching television(Hours)-.1021.000 Sig. (1-tailed) Gender..268 Watching television(Hours).268. N Gender3939 Watching television(Hours)3939 Variables Entered/Removeda ModelVariables Entered Variables Removed Method 1 Watching television(Hou rs)b .Enter a. Dependent Variable: Gender b. All requested variables entered. 11
Model Summaryb Mod el RR Square Adjusted R Square Std. Error of the Estimate Change Statistics R Square Change F Change df1df2Sig. F Change 1.102a.010-.016.509.010.391137.535 a. Predictors: (Constant), Watching television(Hours) b. Dependent Variable: Gender ANOVAa ModelSum of Squares dfMean SquareFSig. 1 Regression.1011.101.391.535b Residual9.59137.259 Total9.69238 a. Dependent Variable: Gender b. Predictors: (Constant), Watching television(Hours) Coefficientsa ModelUnstandardize d Coefficients Standardize d Coefficient s tSig.CorrelationsCollinearity Statistics BStd. Error BetaZero - orde r Partia l PartToleranc e VIF 1(Constant)1.522.12712.02 3 .00 0 12
Watching television(Hour s) -.055.088-.102-.626.53 5 -.10 2-.102-.10 21.0001.00 0 a. Dependent Variable: Gender Coefficient Correlationsa ModelWatching television(Hour s) 1 CorrelationsWatching television(Hours)1.000 CovarianceWatching television(Hours).008 a. Dependent Variable: Gender Collinearity Diagnosticsa ModelDimensionEigenvalueCondition Index Variance Proportions (Constant)Watching television(Hour s) 111.7651.000.12.12 2.2352.741.88.88 a. Dependent Variable: Gender Residuals Statisticsa MinimumMaximumMeanStd. DeviationN Predicted Value1.301.521.46.05239 Std. Predicted Value-3.0821.173.0001.00039 Standard Error of Predicted Value.082.267.110.03539 13
Paraphrase This Document
Need a fresh take? Get an instant paraphrase of this document with our AI Paraphraser
Tests the null hypothesis that the residual covariance matrix is proportional to an identity matrix. a. Design: Intercept + Wealth$ + StudyHours b. Weighted Least Squares Regression - Weighted by Watching television(Hours) Tests of Between-Subjects Effectsa SourceDependent Variable Type III Sum of Squares dfMean Square FSig.Partial Eta Square d Noncent. Paramete r Observe d Powerd Corrected Model observation s1767.875b4441.9692.437.07 6.2989.749.603 Gender1.124c4.281.692.60 5.1072.767.191 Intercept observation s6395.01016395.01 0 35.26 6 .00 0.60535.2661.000 Gender30.523130.52375.15 2 .00 0.76675.1521.000 Wealth$ observation s61.870161.870.341.56 5.015.341.087 Gender.5811.5811.430.24 4.0591.430.209 StudyHour s observation s1747.2643582.4213.212.04 2.2959.636.662 Gender.7993.266.656.58 7.0791.968.166 17
Error observation s4170.73023181.336 Gender9.34123.406 Total observation s 25923.00 028 Gender97.00028 Corrected Total observation s5938.60527 Gender10.46527 a. Weighted Least Squares Regression - Weighted by Watching television(Hours) b. R Squared = .298 (Adjusted R Squared = .176) c. R Squared = .107 (Adjusted R Squared = -.048) d. Computed using alpha = .05 General Estimable Functiona,b ParameterContrast L1L2L3L4L5 Intercept10000 Wealth$01000 [StudyHours=0]00100 [StudyHours=1]00010 [StudyHours=2]00001 [StudyHours=3]10-1-1-1 a. Design: Intercept + Wealth$ + StudyHours b. Weighted Least Squares Regression - Weighted by Watching television(Hours) 18