M:\TEACHING\STAT\STAT548\data\FAT.TXT

ID Subject ID

ENERGY total energy intake (kcal/day)

TOTFAT total fat intake (g/day)

TOTPFA total polyunsaturated fat (g/day)

TOTMFA total monounsaturated fat (g/day)

TOTSFA total saturated fat (g/day)

M:\TEACHING\STAT\STAT548\data\PROTEIN.TXT

ID Subject ID

ENERGY total energy intake (kcal/day)

PROTEIN total protein intake (g/day)

VEGPROT total vegetable protein intake (g/day)

ANMPROT total animal protein intake (g/day)

M:\TEACHING\STAT\STAT548\data\SDEMOG.TXT

ID 5 digit Subject ID

SEX 1=MALE, 2=FEMALE

AGE years

FEET HEIGHT (feet)

INCH HEIGHT (inches)

WEIGHT body weight in pounds

SMOKE 1=NEVER, 2=PAST,3=CURRENT

Problem 1 (WRITE answer)

Use a text editor to classify each of the above files as space-delimited, comma-delimited, or fixed fielded.

Problem 2 (turn in CODE, any relevant OUTPUT, and WRITE answer to question)

1. Write a SAS/R program to create a data set (name the data set FAT) that contains the variables from FAT.TXT.

1. Add the following variables to this data set:

PCTOTFAT percent of calories (kcal) from total fat

PCSFA percent of calories (kcal) from saturated fat

PCMFA percent of calories (kcal) from monounsaturated fat

PCPFA percent of calories (kcal) from polyunsaturated fat

STOTFAT saturated fat + monounsaturated fat + polyunsaturated fat (in grams)

OTHERFAT TOTFAT-STOTFAT (in grams)

Hint: 9 kcalories per gram of fat (any type). E.g. pctotfat=totfat*9/energy*100;

1. Get a MEANS on all the variables in the data set FAT.

d) What is the average saturated fat intake (in grams) for the group?

Problem 3 (turn in CODE, any relevant OUTPUT, and WRITE answer to question)

1. Write a SAS/R program to create a data set (name the data set PROTEIN) that contains the variables from PROTEIN.TXT.

1. Add the following variables to this data set:

PCTOTP percent of calories from total protein

PCVEGP percent of calories from vegetable protein

PCANMP percent of calories from animal protein

SPROTEIN animal protein + vegetable protein

OPROTEIN PROTEIN-SPROTEIN

LPROTEIN Log transformation (base e) of PROTEIN

SVEGP square root of VEGPROT

Hint: 4 kcalories per gram of protein (any type).

1. Produce histograms of (default setting for number of levels) of total protein, vegetable protein and their transformations.

1. Did the transformations normalize these variables?

Problem 4 (turn in CODE, any relevant OUTPUT, and WRITE answer to questions)

a) Write a SAS/R program to create a data set (name the data set DEMOG) that contains the variables from SDEMOG.TXT.

1. Add the following variables to this data set:

HTIN total height in inches

1. What is the mean total body height in inches?

1. What percent of the populations are females? What percent of the population currently smoke?

1. What percent of the population are female current smokers(turn in output from SAS with the percent circled)?