For your research design, it sounds like you have a clear research question and have identified relevant dependent variables for your study. Here are some answers to your questions:

1. You can run separate statistical analyses for each dependent variable (i.e., vocabulary, comprehension-literature, comprehension-informational text, total comprehension score, and the percentile). However, it is important to correct for multiple testing to avoid Type 1 errors. One method of correcting for multiple comparisons is the Bonferroni correction, which involves dividing the alpha level (typically set at 0.05) by the number of comparisons being made (in your case, 5). This will give you a more stringent threshold for statistical significance (i.e., a p-value that is lower than 0.01 instead of 0.05).

2. To control for race, gender, and economically disadvantaged status, you can include these variables as covariates in your statistical models. This will allow you to examine the effects of your treatment variable (the vocabulary intervention) while controlling for other factors that may influence your dependent variables. You can use a regression analysis (such as multiple regression) to incorporate multiple predictors. Make sure to ensure that your covariates are not multicollinear, meaning that they are not highly correlated with one another, as this can affect the validity of your results.

Regards,

Ajit Singh Thank you for your help!

Overall, it is important to consult with your dissertation advisor or a statistical consultant to ensure that your analysis is appropriate for your research question and data.

Natha Mohamed This is very helpful. Thank you!