Task 1c: How to Identify and Recode Missing Data in NHANES Using Stata

The first task is to identify missing data and recode it. Here are the steps:

• Identify missing and unavailable values
• Recode unavailable values as missing
• Evaluate extent of missing data

 

Step 1: Identify missing and unavailable values

In this step, you will use the tabstat and nmissing commands to check for missing, minimum and maximum values of continuous variables, and the tabulate command to look at the frequency distribution of categorical variables in your master analytic dataset. The output from these commands provides the number and frequency of missing values for each variable listed in the procedure statement. 

 

Typically the commands, tabstat or summarize are used for continuous variables, and tabulate is used for categorical variables. In the following example, tabstat and tabulate commands are provided on the same set of variables without distinguishing continuous and categorical variables. If you use the tabulate command on a continuous variable with many values, the output could be extensive.

 

Use the tabstat and nmissing commands to determine the minimum values (min), and maximum values (max), and the number of missing observations for the selected variables for participants who were interviewed and examined in the MEC  and who were age 20 years and older.

 

 

tabstat bpq* mcq* if (ridageyr >=20 & ridageyr <.) & ridstatr==2, stat(n min max)
nmissing bpq* mcq* if (ridageyr >=20 & ridageyr <.) & ridstatr==2

 

Use the tabulate command to determine the frequency of each value of the variables listed for participants who were interviewed and examined in the MEC and who were age 20 years and older. Use the missing option to display the missing values.

 

tabulate bpq010 if (ridageyr >=20 & ridageyr <.) & ridstatr==2, missing

 

Highlighted items from the commands tabstat, nmissing and tabulate output:

• The row labeled "N” shows the number of observations with data. This example has 9,376 observations for the variable, BPQ.020, labeled "Ever told had high blood pressure”.
• The missing indicates the number of observations without data. This example has 95 missing observations for the variable BPQ.020.
• Each response value of a variable has a corresponding frequency (check the codebook to determine the definition for each value).  In this example, the variable BPQ.010, labeled "Last blood pressure reading by a doctor,” has seven possible response values labeled ".” (missing), "1,” "2,” "3,” "4,” "5,” and "9”.
• The column labeled "Freq” indicates the frequency with which a particular response value occurs in the dataset. In this example, two observations have a " .” (missing) value and 6,759 observations have a value of "1”.
• The column labeled "Percent” indicates the percentage for which each value of the variable accounts, out of the total. The ".” (missing) and "1” response values of BPQ.010 account for 0.02 and 71.37% of the total, respectively.
• Note for the variable BPQ.070, labeled as "When blood cholesterol last checked”, one observation has a value of "7” and 52 observations have a value of "9”. These represent the frequency of "refused” and "don't know” responses that were obtained for this question. These observations will need to be recoded as missing, which will be covered in the next step.

 

• Watch animation of program and output
• Can't view the demonstration? Try our Tech Tips for troubleshooting help.

 

Step 2: Recode unavailable values as missing

Two options can be used to recode the missing data:

• assign missing values one variable at a time using  if qualifier, or
• assign missing values by group using the foreach loop command.

Option 1 – Assign Missing Values One Variable at a Time

Use the if qualifier to recode "7" and "9" values of a variable as missing.

replace bpq010=. if bpq010==7 | bpq010==9

 

Option 2 - Assign Missing Values by Group

Use the foreach loop command to recode "7" and "9" values of a variable as missing.

Use this option when you want to recode multiple variables that use the same numeric value for "refused" and "don't know".  Use the save command to create a new dataset with the recoded values.

foreach i in bpq020 bpq050a bpq100d bpq070 bpq080 mcq160b mcq160c mcq160d mcq160e mcq160f {
replace `i' =. if `i' >=7
save C:\Nhanes\Data\demo_bp1, replace

 

• Watch animation of program

 

Step 3: Evaluate extent of missing data

In this step you will use the tabulate command to ensure that the recoding done in the previous step was done correctly. As a general rule, if 10% or less of your data for a variable are missing from your analytic dataset, it is usually acceptable to continue your analysis without further evaluation or adjustment. However, if more than 10% of the data for a variable are missing, you may need to determine whether the missing values are distributed equally across socio-demographic characteristics, and decide whether further imputation of missing values or use of adjusted weights are necessary. (Please see Analytic Guidelines for more information.)

 

Check the extent of missing data

Use the tabulate command to determine the frequency of each value of the variables listed for participants who were interviewed and examined in the MEC and who were age 20 years and older. Use the missing option to display the missing values. Use the foreach loop command to get the frequency of multiple variables.

 

tabulate bpq010 if (ridageyr >=20 & ridageyr <.) & ridstatr==2, missing
 
foreach i in bpq020 bpq070 bpq080 mcq160b mcq160c mcq160d mcq160e mcq160f {
    tabulate `i' if (ridageyr >=20 & ridageyr <.) & ridstatr==2, missing
}

 

Highlighted items from the tabulate output for recoding missing values:

• In this example, the variable BPQ.010, labeled as "Last blood pressure reading by a doctor”, now has only five response values instead of the original six observed before recoding — the value "9” is no longer present.  Also note that there are now a total of 18 missing values (instead of two originally).
• Review of this output indicates that the "9” values have been successfully recoded and are now classified as missing (.).
• Note that variable BPQ.030 ("Told had high blood pressure - 2+ times") still has a "9” value present, indicating "don't know” responses. This value was not recoded because this variable is part of a skip pattern.  It is important to NOT assign "refused” or "don't know” values as missing for variables in a skip pattern, such as BPQ.030, because missing values for skipped variables have an entirely different meaning than missing values for variables that are not part of a skip pattern. You will review how to identify and treat skip patterns in the next task.
• Note that 34.71% of the observations for variable BPQ.070, labeled as "When blood cholesterol last checked”, have missing values. 

• Watch animation of program and output

 

Close Window