Stata Lab 2

docx

School

Washtenaw Community College *

*We aren’t endorsed by this school

Course

128

Subject

Health Science

Date

Feb 20, 2024

Type

docx

Pages

Uploaded by MegaPenguinMaster801

Columbia University Mailman School of Public Health Dept of Health Policy & Management P8502 Research Methods Spring 2023 Prof. Jamie Daw LAB 2 Descriptive Statistics and Hypothesis Testing Part 1: Open and Review the Data Open and review the dataset Session2.dta. This dataset contains data on a random sample of births from one hospital in 2018. Be sure to set a working directory, start a new .do file and log file. Take a look at the data using the data browser. Part 2: Inspect Variables and Descriptive Statistics Inspect the dataset: i. What is the unit of analysis, i.e. what does each observation represent? ii. How many observations are there? How many variables? iii. What general information is contained in this dataset? iv. Are there missing values for any of the variables? Inspect key variables: i. What is the average maternal age? What is the confidence interval for this estimate? ii. Create a histogram of prenatal care visits. Add titles to the axes. iii. What is the average and median number of prenatal visits? iv. What is the average and median number of visits among births with >0 visits? Rename and create new variables: i. The variable ftv contains information on the number of prenatal care visits in the first trimester. Rename this variable to something more intuitive. ii. Create a categorical age variable from the continuous variable age . You can choose the age cut- offs. Label the categories of this variable. iii. Create an indicator variable (binary 0/1) for low birthweight (<2500g). iv. What proportion of the total sample is low birthweight? Part 3: Inspect the Relationship Between Two Variables You are interested in the relationship between first trimester prenatal care visits and low birthweight. i. Create a cross tabulation of low birthweight and prenatal care visits. What % of infants with no prenatal care have low birthweight? ii. Create a bar graph showing the mean birthweight by the number of prenatal care visits. iii. Based on this analysis, how would you describe the relationship between birthweight and prenatal care visits? Part 4: Conduct Hypothesis Tests You are asked by the hospital performance manager to examine a number of questions relating to maternal age and birthweight. You can use the ttest command to address each question. For each test state: (1) the null and alternative hypotheses, (2) sample estimate, (3) test statistic, (4) confidence interval, (5) p-value. Also include a one sentence interpretation of the result.

1. Is the maternal age for this hospital the same as the U.S. average (27 years)? 2. What is the difference in mean birthweight for women over and under age 25? You will first need to create an indicator variable indicating age over 25. Finished early? Further explore the relationship between two other variables of your choice in this dataset. Create graphical displays showing this relationship and conduct a related hypothesis test. Stata Commands Needed For This Lab: EXAMINE DATASET Count the number of observations count Describe the variables in the dataset describe Show detailed information on how each variable is defined, summary statistics and missing values codebook CALCULATE SUMMARY STATISTICS Examine summary statistics for all variables summarize Examine summary statistics for a specific variable (e.g. age) with additional details (medians etc.) summarize age, detail Calculate the mean and 95% CI for a variable mean e.g. mean age Tabulate a variable (or two) tab e.g. tab age tab age smoke You can add row, col or if statements after tabulate to tab for specific subsets or to return percentages down the rows or columns of the table e.g. tab age smok, row tab age smok, col tab smoke if age<20 Limit any command to a subgroup if e.g.

tab age if age_u20==1 note Stata language requires two equal signs for “if” clauses histogram age if bwt>2500 CREATING AND LABELING VARIABLES Create a new binary variable (0/1) gen e.g. gen age_u20=(age<20) Create a new binary variable equal to a certain value for all observations gen e.g. gen age_cat=. This creates an “empty” variable where all values are missing (Stata language denotes missing values with a period. Edit values of an existing variable replace e.g. replace age_cat=1 if age<20 replace age_cat=2 if age>20 Rename a variable rename oldname newname e.g. rename age ageinyears GRAPHS Create a histogram (e.g. for age) with axes labels, a title and red bars histogram age, ytitle(Frequency) xtitle(Age) title(Distribution of Age) col(red) Create a bar graph of means (single or over another variable) graph bar (mean) e.g. graph bar (mean) bwt graph bar (mean) bwt, over(low) T-TESTS T-test for a single mean ttest if variable== null_value

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

e.g. ttest if bwt==2500 T-test for difference in means between two groups ttest variable, by(group) unequal e.g. ttest bwt, by(age_u20) unequal

Stata Lab 2

Related Documents