Independent samples T-Test with the Mean of Enjoyment of Activity
| Mean Enjoyment of Activity | T | DF | |
| Head Start | 9.35 | 34.74*** | 67 |
| Andy Taylor Center | 5.00 |
Note: p<.05*, p<.01**, p<.001***
Recode: I kept V19 as my variable when recoding because that was if the families completed the activity. I changed the second variable to V24 because that is the enjoyment of the activity. The final syntax for recoding is: t.test(y$v36~y$Income, conf.level=.99)
t.test(y$v24~y$v19,conf.level=.99)
Interpretation: The mean of enjoyment for the activity for Head Start was 9.55 out of 10 and the mean of enjoyment for the activities for Andy Taylor Center was 5.00 out of 10. The T test value was 34.74 at the .001 significance level. Meaning, the mean for enjoyment of the activity is significantly different at the two schools.
ANOVA Table based on parent involvement and following the activity instructions
| Mean Parent Involvement | F | |
| Yes | 1.00 | 0.92 |
| Partially | 1.25 | |
| No | 1.30 |
Note: p<.05*, p<.01**, p<.001***
Recode: I picked two different variables to recode which was V28- how involved was the family throughout the activity and V26- was your child able to follow instructions. The attributes for that variable were yes, partially and no. The new syntax was:
model <-aov(y$v28~y$v26)
anova(model)
aggregate(v26~v28,data=y, mean)
Interpretation: The dependent variable for the ANOVA was family involvement. This was asked on a 0 to 10 scale. The independent variable for the ANOVA was if your child was able to follow directions. Respondents either chose “yes”, “partially” or “no”. The mean involvement for ‘yes’ was 1.00. The mean involvement for ‘partially’ was 1.25. The mean involvement for ‘no’ was 1.30. According to the ANOVA results (F=0.92) there is a significant difference between the means which means there is no significance at the .5 level.
Chi Squared of Parent Involvement and Income
| Involvement | Income Total | DF | Chi Squared |
| Not at all | 8 | ||
| Moderate | 20 | ||
| Great amount | 24 | ||
| 2 | 4.68*** |
Note: p<.05*, p<.01**, p<.001***
Recode: I used the variable V23 for parent involvement and V36 for the household income. The new coding syntax was:
table(y$v23Invol,y$v36Income2)
chisq.test(y$engaged, y$Income2,correct=TRUE)
Interpretation: The dependent variable for the Chi squared chart is family involvement. The independent variable for the Chi squared chart is family income. The mean for no involvement at all was a total of 8. The mean for moderate involvement was a total of 20. The mean of a great amount of involvement was a total of 24. The total Chi squared was 4.68. This means that we have a weak positive correlation and there is significance at the .001 level.
Conclusion
The findings for the Independent T test table is that there is a difference between the two schools and the enjoyment of the activities. Some families at Andy Taylor Center did not enjoy the activities as much as the families at Head Start. The findings conclusion for the ANOVA table is that there is not much of an effect on being involved in the family activities and following the instructions of the activities. Each mean is close in range meaning they could have interpreted the instructions in their own way. Even if the family did not read the instructions they still had the involvement of the activity that was needed even if it was not 100% right. The findings conclusion for the Chi Squared chart is that income does have an affect on the correlation of involvement with the family activities. People that had lower income most likely are working more and did not have the time to engage in the family activities. When you see that the number jumped from having 8 people not involved with low income to 24 people involved with a decent income, there is a little bit of a difference. All of these findings had been recoded from the original syntax, giving new results and an outcome. These variables were found in the codebook that was used for the survey questions for Head Start and the Andy Taylor Center. Then were put into Rstudio or SPSS to find our results.