Sign In
Not register? Register Now!
Essay Available:
5 pages/≈1375 words
7 Sources
Mathematics & Economics
Research Proposal
English (U.S.)
MS Word
Total cost:
$ 24.3

Advanced Behavioral Research Design & Analysis: Demographic Variables (Research Proposal Sample)


The study aims to establish how the demographic variables impact two of the Big Five variables that explain personality such as the conscientiousness (consc1-consc5), extroversion (extro1-extro6) and also the general self-efficiency (gse1-gse8).

Advanced Behavioral Research Design & Analysis Student name Institution Advanced Behavioral Research Design & Analysis The study aims to establish how the demographic variables impact two of the Big Five variables that explain personality such as the conscientiousness (consc1-consc5), extroversion (extro1-extro6) and also the general self-efficiency (gse1-gse8). Quantitative analysis usually delves into measuring the objects and the analysis of the numerical data which is collected through the use of the questionnaires, polls and surveys. The computational techniques are employed in manipulating the data (Costello, & Osborne, 2005). The data was tested if it has a missing values, the following were the result from the analysis. Table 1 Summary of Univariate Analysis Univariate Statistics N Mean Std. Deviation Missing No. of Extremesa Count Percent Low High consc 412 3.6214 .86505 36 8.0 5 0 extro 411 3.1350 .93651 37 8.3 0 0 gse 407 3.5811 .73948 41 9.2 3 0 Note. Number of cases outside the range (Q1 - 1.5*IQR, Q3 + 1.5*IQR). From the above output, it is evident that the variables have missing values. This is because the total number of observations are not the same in all the three variables. The general self-efficiency ha the highest number of missing value at 9.2 percent of the total observations, followed closely by the extroversion at 8.3 percent and lastly conscientiousness has the least number of observation. The missing data was addressed by performing data imputation. So that to make the data suitable for data analysis to give the desired results. Further, reverse scoring an item implies that changing the score or the numerical arrangement of a variable in such a way that the scale runs in the opposite direction depending on the questions that are asked and the response of the participants. Often the reverse scoring is employed on the negative question (Hinton, 2014). The positive scoring will not be similar or is always different from the negative scoring, for this reason, scoring needed to be reversed from the score to be easy and added horizontally. In this study, there is no variable that needs to be reverse scored. The data was quantitative both the descriptive and inferential techniques were employed to get the meaning of the data. Descriptive statistics were employed to get the general meaning and describe the data that is under study (Hinton, 2014). The following is the descriptive statistics table. Table 2 Summary of descriptive table Descriptive Statistics N Minimum Maximum Mean Std. Deviation consc 412 1.00 5.00 3.6214 .86505 extro 412 1.00 5.00 3.1350 .93651 gse 412 1.00 5.00 3.5811 .73948 Valid N (listwise) 412 Note. N is the sample size Before performing any test, it is appropriate to test the assumptions of the study. Assumptions are vital since if they are not followed, it makes it difficult for the researcher to perform the analysis to extract important information from the data. When performing the analysis, the following assumptions should not be violated by the variables. The assumption that is concerned with the scale of measurement. It is assumed that that data which is collected follows a continuous or ordinal scale. This assumption is not violated since the data that is collected for the study is measured under the continuous and ordinal scale (Tabachnick & Fidell, 2007). For example, gender follows an ordinal scale since it can be male or female, extroversion is also measured in six levels that range from 1 to 6, and this shows that this variable is nominal. The normality assumption, which explains that the data is distributed normally. To test this assumption, we employ the Shapiro-Wilk normality test. Table 3 Shapiro Test Tests of Normality Are you male or female? Kolmogorov-Smirnova Shapiro-Wilk Statistic Df Sig. Statistic df Sig. Consc Male .089 213 .000 .967 213 .000 Female .113 199 .000 .954 199 .000 Note. The level of significance is 5%, a. Lilliefors Significance Correction From the Shapiro-Wilk test above, the statistic (W) is 0.967, and the p-value is 0.000. Since the p-value is less than 1, then we say that the data is normally distributed. Therefore the assumption of normality is not violated by the variables. The assumption that the dependent variable should be continuous. The dependent variable of the study is conscientiousness which is measured on the continuous scale. This confirms that the assumption of the continuous dependent variable is not violated by the variables (Hinton, 2014). Third, the independent variable(s) should be either continuous or categorical. This means that the variables can be measured by whether the continuous scale or the ordinal/nominal scale (for example the Likert scale). Gender is a categorical variable that is measured on a nominal scale (male or female). Hence, the assumption is not violated by the variables. The variables should be independent. This assumption is applied in both the T-test and the ANOVA test (Tabachnick & Fidell, 2007). Independence means that there is no connection between the groups or the data. The critical value is 0.096. Since the critical value is more than the level of significance, we make a conclusion that there the variables or groups in the study are independent. Hence the assumption is not violated. Lastly the assumption of equal variance. This test is used in the T-test, ANOVA and correlation analysis (Pierce, Block, & Aguinis, 2004). Table 4: Levente test The Levente Test for homogeneity of the variance Test of Homogeneity of Variances Levene Statistic df1 df2 Sig. consc 1.728 25 370 .017 extro 1.478 25 370 .067 Note. 5 % is the level of significance From the above output, the Levente test statistic is 1.78 with critical value 0.017. Since th p-vale is smaller compared to alpha=0.05, then we conclude that the data obeys the assumption of homogeneity or equality of the variance. All these assumptions conform that the assumptions have not been violated. Factor Analysis Factor analysis is an analysis that brings together the inter-correlated variables under the general underlying variables. It aims at explaining the variance of the observed variables in terms of the concealed latent factors (Garson, 2013). Hence, providing a probability of attaining a vivid description of the data also using the output in succeeding analyses. The analysis starts with the inter-correlation between the variables of interest. Table 5 KMO and the Bartlett's Test KMO and Bartlett's Test Kaiser-Meyer-Olkin Measure of Sampling Adequacy. .899 Bartlett's Test of Sphericity Approx. Chi-Square 4001.132 Df 171 Sig. .000 Note. The level of significance is 0.05. The above output is a vital part of factor analysis. Kaiser-Meyer-Olkin (KMO) is a measure that describes how suitable the data is for factor analysis. The KMO statistics range from zero to one. When the value is zero, it explains the total of partial correlations is relatively larger to the total associations. When the KMO is nearing to 1, then it indicates that the order of correlation are relatively impacted thus the factor analysis is definite and reliable (Costello, & Osborne, 2005). From the above output, the KMO is 0.899; this means the total of partial correlations is relatively larger to the total of associations showing the suitability of the factor analysis for the data. Besides, there is Bartlett’s test that investigates the null hypothesis that the initial correlation matrix is an identity matrix. If the results from the test is remarkable, it illustrates that the correlation matrix is not an identity matrix hence there is an association linking the variables we need to include in the analysis. The three variables that need are conscientiousness, general self-efficiency and extroversion. Since the p-value is less than alpha=0.05, then it shows that there is a high significance hence the factor analysis is suitable. Therefore, factor analysis is needed in this analysis. Factor extraction Table 6: factor extraction Summary of the Factor Extraction Total Variance Explained Component Initial Eigenvalues Extraction Sums of Squared Loadings Rotation Sums of Squared Loadings Total % of Variance Cumulative % Total % of Variance Cumulative % Total % of Variance Cumulative % 1 7.495 39.445 39.445 7.495 39.445 39.445 5.119 26.944 26.944 2 1.938 10.199 49.644 1.938 10.199 49.644 2.808 14.781 41.725 3 1.587 8.352 57.996 1.587 8.352 57.996 2.789 14.678 56.403 4 1.297 6.825 64.822 1.297 6.825 64.822 1.600 8.419 64.822 5 .954 5.020 69.842 6 .784 4.124 73.966 7 .604 3.180 77.145 8 .589 3.101 80.247 9 .541 2.849 83.096 10 .476 2.507 85.603 11 .441 2.320 87.923 12 .374 1.967 89.890 13 .355 1.870 91.760 14 .327 1.723 93.482 15 .301 1.582 95.064 16 .284 1.496 96.561 17 .254 1.334 97.895 ...
Get the Whole Paper!
Not exactly what you need?
Do you need a custom essay? Order right now:

Other Topics:

Need a Custom Essay Written?
First time 15% Discount!