For this assignment, you will need to run descriptive statistics, exploratory data analysis, and correlations on the computer to gain insights regarding possible differences among the characteristics of the students attending Alpha and Beta High Schools. The first step of the assignment involves using statistical software to generate numerical summaries and graphical displays of the CTBS language scores (langnce) for the 159 students enrolled at Alpha and the 157 students enrolled at Beta.

You will need to use the lahigh dataset (see Reading Stata Datasets), for this assignment. You will also need to use the codebook for the dataset as well as the description of the dataset and variables used in the study.

Note: I am not consistant in using either all caps or all lower case for variable names, thus, LANGNCE is the same as langnce.

Part I:

1. Record the five number summaries for LANGNCE for each school.
2. Prepare a table that compares the LANGNCE means, medians, interquartile ranges and standard deviation for the two schools. Which school has the larger mean, median, interquartile range, and standard deviation?
3. Do the LANGNCE distributions appear to be skewed (approximately) in the same direction? If not, what appears to be happening?

Part II:

Generate side-by-side boxplots for the two schools on the variable DAYSABS. How many outliers are recorded for each school? Write up a comparison of the two boxplots.

Part III:

Compare the frequency distributions within each school on Bilingual Status (BILING). What percent of students at each school were in each bilingual category. What do the results suggest?

Part IV:

Suppose the scores for 500 four year old children on the Peabody Picture Vocabulary test follow a normal distribution with a mean of 70 points and a standard deviation of 15 points.

Be sure to show your work.

1. What proportion of the sample score below 70 points?

2. How many children score below 70 points?

3. What proportion of the sample score below 50 points?

4. How many children score below 50 points?

5. What proportion of the sample score between 60 and 70 points?

Intro Home Page