Lab Based E-portfolio
- 1. LAB BASED E-PORTFOLIO (PSYC 3100) NAME : NOR KHAMSIAH BT MAT ZIN MATRIC : 1210752 SECTION : 2 INSTRUCTOR : DR. HARRIS SHAH ABD HAMID
- 2. 1) DATA ENTRY For my e-portfolio, I used two set of questionnaire which are Set 1 (Extraversion) and Set 2 (Roserberg Self-Esteem). I distribute my survey form to 42 students of IIUM (hard copy). There are 10 items for each set. Kindly refer my survey file and data collection in MS Excel for references.
- 3. 2) TRANSFORM Step 1: Before start key in the data in SPSS, I have set up the variable using Variable View. There are 25 rows which are 5 rows for demographic background and 20 rows for the 20 items in 2 set of questionnare. Figure 2.1: Set up the Variable View
- 4. Step 2: After finished set up at the Variable view page, I move to the Data View to key in the data. This is my data for 44 participants. Figure 2.2: The Data View
- 5. Figure 2.3: The Data View (cont)
- 6. Step 3: After key in all the data, I compute the data using the Transform Command. First, I compute for the Set 1 then, Set 2. I named the new variable with MarkBall and MarkCall Figure 2.4: Process in Compute the Variable
- 7. ** Before compute the data, I make sure the value label is correct according the type of the question/ statement which are positive or negative towards the psychological construct. If the statement is positive, it used the likert scale and if the statement is negative it used the reversed likert scale. For the Extraversion, question number 3, 6, 7, 8, 10 used reversed likert scale and for Rosernberg Self- Esteem, question number 2, 5, 6, 8, 9 used reversed likert scale. Likert Scale Reverse Likert Scale Figure 2.5: Put the value Label using Likert Scale and Reversed Likert Scale
- 8. 3) RECODE For the total of Extraversion (MarkBall) and Self esteem (MarkCall), I have recode into three groups using Transform command. For Extraversion 1-16 has value label 1 which mean low extraversion, 17-32 has value label 2 which mean medium extraversion and >33 has value label 3 which mean high extraversion. For Self Esteem, the scores 1-13 has value label 1, mean low Self Esteem, 14-26 has value label 2 mean medium self-esteem, and >27 has value label 3 which mean high self-esteem. I recode the total of extraversion and the total of Self esteem to classify the respondent according to their level of extraversion and self esteem. Figure 3.1: Recode using Transform command
- 9. The figures below show the process in recode the different variables. Figure 3.2: Recode process
- 10. There are two new variable produced as a result from the recode command which are LOEX (Level of Extraversion) and LOSE (Level of Self Esteem). Figure 3.3: The new variable (LOEX, LOSE)
- 11. 4) NAMING OF VARIABLE AND CHARACTERISTICS The table below shows the variable view in SPSS data editor. The first five variables are defined as demographic backgrounds which are ID, Gender, Age, Year of birth and Month of Birth. ID refers to the respondent’s ID which is Nominal measurement type of scale. Gender refers to the sex of respondents which are labeled as 1 for Male, 2 for Female. For Age and Year of Birth refer to age and year of birth of the respondent and both are Scale measurement type of scale. The last demographic background is Month, which arranged in ordinal scale. For the items in Set 1 (Extraversion) that consists of 10 items, I have labeled as B1, B2, B3, B4, B5, B6, B7, B8, B9, B10. It is measured in a scale measurement and has 5 possible value ranging 1 to 5 of Likert Scale except B3, B6, B7, B8, B11 used reverse Likert Scale. For the likert scale; 1= Strongly Disagree, 2= Disagree, 3=Neutral, 4=Agree and 5=Strongly Agree. For the reverse Likert Scale; 5= Strongly Disagree, 4= Disagree, 3=Neutral, 2=Agree and 1=Strongly Agree. For the items in Set 2 (Self Esteem) that consists of 10 items, I have labeled as C1, C2, C3, C4, C5, C6, C7, C8, C9, C10. It is measured in a scale measurement and has 4 possible value ranging 1 to 4 of Likert Scale except C2, C5, C6, C8, C9 used reverse Likert Scale. For the likert scale; 1= Strongly Disagree, 2= Disagree, 3=Agree and 4=Strongly Agree. For the reverse Likert Scale; 4= Strongly Disagree, 3= Disagree, 2=Agree and 1=Strongly Agree. For age and all the items have 99 as a missing values because it is least likely value and for the year of birth, has 2016 as a missing values because there are impossible respondents born in 2016 as now is 2014. For the Total Extraversion and Total Self Esteem, I labeled as MarkBall and MarkCall and both are use scale measurement. MarkBall and MarkCall do not have value label. For the level of Extraversion (LOEX), and the level of Self Esteem (LOSE) both are use scale measurement and have value label. For LOEX; 1-16= low extraversion, 17-32=medium extraversion, >33=high extraversion. While LOSE; 1-13=low self esteem, 14-26=medium self esteem, >27=high self esteem.
- 12. Figure 4.1: Variable View
- 13. 5) DATA SCREENING Figure 5.1: Data Screening using Analyze, Descriptive Statistics, Frequencies
- 14. Based on Participant’s Age below, it shows that 1 of the participant has a higher age, which is out from my expectation. My expectation the range of age all the participants are 18 to 25 only. Then, I move to the data view to examine which participant has ‘40’ as his age. After that, in order to make the data clean and clear, I had changed age ‘40’ as a missing value which is 99 in Data view and also change the year of birth of participant 6 from 1974 to 2016 because 2016 is a missing value that I declared earlier in Variable view for Year of Birth. Participant's Age Frequency Percent Valid Percent Cumulative Percent Valid 18 1 2.3 2.3 2.3 20 5 11.4 11.4 13.6 21 10 22.7 22.7 36.4 22 14 31.8 31.8 68.2 23 7 15.9 15.9 84.1 24 5 11.4 11.4 95.5 25 1 2.3 2.3 97.7 40 1 2.3 2.3 100.0 Total 44 100.0 100.0
- 15. Participant's Year of Birth Frequency Percent Valid Percent Cumulative Percent Valid 1974 1 2.3 2.3 2.3 1989 1 2.3 2.3 4.5 1990 5 11.4 11.4 15.9 1991 7 15.9 15.9 31.8 1992 14 31.8 31.8 63.6 1993 10 22.7 22.7 86.4 1994 5 11.4 11.4 97.7 1996 1 2.3 2.3 100.0 Total 44 100.0 100.0
- 16. The frequ dthyerh The tables below show the frequency of Self-esteem 2 and the Total of Self Esteem. As we can see, there has 1 missing in Self-esteem 2 and Total of Self-esteem. After that, I move to the Data View to examine which participant has an error data and I found the participant 30 do not answer the item C2. I had declared it as a missing value, which is I change its value to 99. Self-esteem 2 Frequency Percent Valid Percent Cumulative Percent Valid Strongly Agree 2 4.5 4.7 4.7 Agree 19 43.2 44.2 48.8 Disagree 16 36.4 37.2 86.0 Strongly Disagree 6 13.6 14.0 100.0 Total 43 97.7 100.0 Missing System 1 2.3 Total 44 100.0
- 17. Total of Self Esteem Frequency Percent Valid Percent Cumulative Percent Valid 22 2 4.5 4.7 4.7 23 1 2.3 2.3 7.0 24 1 2.3 2.3 9.3 25 5 11.4 11.6 20.9 26 5 11.4 11.6 32.6 27 2 4.5 4.7 37.2 28 7 15.9 16.3 53.5 29 4 9.1 9.3 62.8 30 7 15.9 16.3 79.1 31 5 11.4 11.6 90.7 32 1 2.3 2.3 93.0 37 2 4.5 4.7 97.7 40 1 2.3 2.3 100.0 Total 43 97.7 100.0 Missing System 1 2.3 Total 44 100.0
- 18. Figure 5.2: Declared the missing value Finally, after cleaning the data I can proceed to next step which is checking the normality of the data.
- 19. 6) NORMAL DISTRIBUTION OF DATA I use two type of graphic to determine the normality of the data. i. Using Histogram Figure 6.1: Form of histogram using Graphs command
- 20. Figure 6.2: Total of Extraversion Figure 6.3: Total of Self-esteem The figure above shows the histogram Total of Extraversion and Total of Self-esteem. The overall shape of the histogram shows that the score are not normally distributed within the normal curve and the distribution of Total Self Esteem possible positively skewed distribution. The histogram of Total Self Esteem is slightly flattered compared to the histogram of Extraversion.
- 21. ii. Using P-P Plots Figure 6.4: P-P Plots command
- 22. Figure 6.5: P-P Plots of Total Extraversion The P-P Plot of Total Extraversion also shows that the scores are slightly scattered around the straight line and most of the dots also deviate from the line. It shows that, the distribution is not a normal distribution. The distance the dots deviate from the normal line ranges from 0.050 to -0.075.
- 23. Figure 6.6: P-P Plots of Total Self Esteem The P-P Plot of Total Self Esteem also shows that the scores are slightly scattered around the straight line and most of the dots also deviate from the line. It shows that, the distribution is not a normal distribution. The distance the dots deviate from the normal line ranges from 0.100 to -0.025.
- 24. Descriptive Statistics N Mean Skewness Kurtosis Statistic Statistic Statistic Std. Error Statistic Std. Error Total of Extraversion 44 34.4773 .488 .357 2.845 .702 Total of Self Esteem 43 28.4419 .941 .361 1.921 .709 Valid N (listwise) 43 Figure 6.7: Table of Skewness and Kurtosis The table above shows the index of Skewness and Kurtosis statistics in SPSS for both variables. For the Total of Extraversion, the skewness statistic is 1.3669 and the kurtosis statistic is 4.0527. For the Total of Self esteem, the skewness statistic is 2.6067 and the Kurtosis statistic is 2.7094. So, it can be concluded that, the first distribution (Extraversion) has a slightly sharper curve compared to the second distribution (Self Esteem). On the other hand, the second distribution (Self Esteem) is slightly more symmetrical compared to the first distribution (Extraversion).