SAS Quiz 3

When does a data step end?

ch. 10.

When does a data step end?

ch. 10.

When any data set reaches an end of file, the DATA step ends

when merging two data sets you can use the RENAME= data set option to

ch. 10.

rename the variables you are trying to link the observations

SAS will only merge a data set when the

ch.10

BY variable in both data set are the same type

When merging two data sets what occurs if one of the data sets has ID as a character and other has ID as a numeric

ch.10

We then must either convert the numeric to a character variable or the character to a numeric

Can we convert the type of a variable in SAS?

ch.10

No we cannot convert the type of a variable in SAS

We cannot convert the type of a variable in SAS but we can…

ch. 10

create a new variable that has a different type using the old variable

We can convert a character to a numeric using the…

ch.10

INPUT function

We can convert a numeric to a character using…

ch.10

the PUT function

Describe a one-to-many merge

ch.10

If we have one data set with one observation for each BY variable and the other with multiple observations, we can do a one-to-many merge

If you have two data sets that contain the same variables and do a merge, what happens?

ch.10

Values in the second data set overwrite values in the first data set

If the value in the second data set is missing, it will still

ch. 10

overwrite the first data sets value

What does an Update statement do?

ch. 10

Replace values in a data set

What occurs with missing values and an UPDATE statement

ch. 10

overwrite a previous value

What is a SAS function?

ch. 11

A component of the SAS programming language that can accept arguments, perform a computation or other operation, and returns a value

Describe the ROUND function

ch. 11

used to round number to the nearest integer, and you may change the rounding unit

Describe the INT function

ch. 11

returns the integer portion of the number

Describe the FLOOR function

ch. 11

returns the largest integer that is less than or equal to the argument

The CEIL function

ch. 11

returns the smallest integer that is greater than or equal to the argument

You can refer to a missing numeric value with a…

You can refer to a missing character value with a…

ch. 11

period and a missing character value by a single blank space inside quotes

What does the MISSING function do?

ch. 11

Returns a value of true if the argument is a missing value- works with numeric and character variables

What can you use to set values to missing?

ch. 11

a CALL routine, CALL Missing

What are CALL routines used to do?

ch. 11

Used to alter variables values

Name 3 differences between a CALL routine and a function

ch. 11

Functions can accept arguments and returns a single value

The arguments in a CALL routine can have their value changed

CALL routines cannot be used in an assignment statement

Name the functions part of descriptive statistics functions.

ch. 11

1. MEAN function

2. SUM function

3. MAX/MIN function

4. LARGEST/SMALLEST function

5. N function

6. NMISS function

What does the mean function do?

ch. 11

calculate the mean of a set of values

Describe what the SUM function does

ch. 11

sums a group of values

Describe the MAX/MIN function

ch. 11

returns the largest/smallest value

Describe the LARGEST/SMALLEST function

ch. 11

returns the nth largest/smallest value in a group of values

LARGEST (2, of Q1-Q10); returns the 2nd largest value

Describe the N function

ch. 11

Returns the number of non- missing values

Missing values are ignored for which funtions?

ch. 11

MEAN and SUM function

If all values supplied to sum are missing, what occurs?

ch. 11

The default value is missing

Write the code for if we had a variable A1-A10 and B1-B10 and we want to sum and we want the sum to be 0 if all are missing

ch. 11

sumAB = sum (0, of A1-A10, of B1-B10);

Name the SAS functions for common mathematical functions

ch. 11

1. ABS (Absolute value)

2. SQRT (square root)

3. EXP (exponentiation)

4. LOG (natural log)

What does @@ keep SAS from doing? ch. 11

Keeps SAS from moving to the next line of the data set at the bottom of a DATA step

Recalls @ holds the line for another INPUT statement in the DATA step, but will… ch. 11

move to the next line at the bottom of the DATA step

When X is negative what occurs with the square root and natural log? ch. 11

The square root and natural log are missing

Describe the constant function ch. 11

Returns value of common mathematical constants such as pi and e

Also compute the largest integer that can be stored in a specific number of bytes

What is the RAND function used to doing? ch. 11

Generating random numbers from common probability distributions

Name three things that the RAND function is useful for doing? ch. 11

Useful for conducting simulation studies

Selecting random samples

Assigning subjects randomly to groups

Computers are not capable of doing what? What are they capable of doing? ch. 11

producing truly random numbers. Capable of producing pseudo-random numbers that approximate the properties of a random number.

In the RAND function, what determines the starting point for the random number generator

The RAND function provides a seed number which determines the starting point for the random number generator

If you generate a sequence of random numbers in the same way using the same seed what occurs?

ch. 11

You will generate the same sequence every time

Name and list the probability distributions that SAS can generate random numbers from ch. 11

Uniform

X=rand (‘uniform’);

Uniform number between 0 and 1

Normal
X = rand(‘normal’, 10, 2);
Normally distributed with mean 10 and a standard deviation of 2

Bernoulli
X = rand(‘bernoulli’, 0.5);
Probability of success given by 0.5

Binomial
X = rand(‘binomial’, 0.3, 10);
Number of successes in 10 trials with probability of success given by 0.3

Call streaminit (n) is used to…

ch.11

set random seed to n

If we want to do a random subset such as select 10% of the observations in the heart disease data set we can do this using…

ch.11

an IF statement with the RAND function

If you want exactly of a percent, if we want to select exactly 10%

ch.11

we can use PROC SURVEYSELECT

What does INPUT function allow you

ch.11

to read a character value using an informat and assign the resulting value to a SAS numeric variable

May be also used to convert a date saved as a character to a SAS date value

Since we can’t convert a variable, if we want the new variables to have the same name, what do we need to do?

ch.11

rename the initial variables

What does the PUT function do? It is often used to do what?

ch.11

takes a value, formats the value using the supplied format, and writes the results to a variable

Often used to convert a numeric variable to a character variable

The result of a PUT function is

ch.11

always a character value

Why is it difficult for SAS to compute a value for the present observation that uses a value from a previous observation?

ch.11

Because SAS processes data sets observation by observation

Describe what the LAG function does

ch.11

LAG function returns the value of the argument the last time it was executed

can be used to get value from previous observation

LagN can be used to…

ch.11

return the value N times before it was last executed

When do you need to be careful using the LAG function?

ch.11

When you are using it conditionally

What is the DIF function equal to?

ch.11

X-LAG (X)

What is the DifN function used to do..

What is it equal to?

ch.11

calculate differences to earlier observations

equivalent to X-LagN(X)

What does CALL SORTN routine do?

sorts and returns the arguments in ascending order

Suppose x1=7, x2= ., x3=3, and x4=9

Describe the what CALL SORTN would result in

CALL SORTN (of x1-x4); would result in x1=., x2=3, x3=7, x4=9

Suppose you have Suppose x1=7, x2= ., x3=3, and x4=9

How would you sort them in descending order using CALL SORTN?

What would we would lose?

CALL SORTN (x4-x1);

We would lose the original values of the variables after using CALL SORTN

What can we do if we want to keep both original variables?

We can copy the original variables to a new set of variables that we sort using CALL SORTN if we want to keep both