Since 1971, the National Center for Health Statistics had been assessing the health and nutritional status of both children and adults in the United States, through periodic National Health and Nutritional Examination Survey (NHANES) surveys. These surveys are an invaluable resource to epidemiological and public health research; the surveys can be used to determine the prevalence of major diseases and risk factors, to assess nutrition and health promotion, and to guide public health policy.

All initial and peer postings should be at least 250-500 words in APA format supported by scholarly sources.

In 2012, the NHANES National Youth Fitness Survey (NNYFS) was conducted in conjunction with NHANES to obtain physical activity and fitness levels of U.S. youths aged 3 through 15. Initial data from the NNYFS were released in 2013 and serve as the basis for this discussion problem.

Begin by downloading the Excel file MHA610_Week 6_Discussion_NNYFS_workingdata.xls. This workbook was created by merging two datasets from the NNYFS: the demographic variables dataset, and the body measures dataset. For the purposes of this discussion, many variables were eliminated from the original datasets, as well as observations with missing data on height and weight. The Excel workbook thus consists of one worksheet, with 1576 rows (the first row contains headers, and the next 1575 rows are observed values for the participants), and 11 columns of variables. The columns in the Excel file are the following:

SEQN the respondent sequence number (index for all the files)

RIAGENDR gender of the participant, 1 = male, 2 = female

RIDRETH1 race/Hispanic origin:

1 = Mexican American

2 = other Hispanic

3 = non-Hispanic white

4 = non-Hispanic black

5 = other

RIDEXAGY age in years at time of physical exam

INDHHIN2 annual household income, categorized

INDFMIN2 annual family income, categorized

INDFMPIR ratio of family income to poverty, 0 to 5

BMXWT weight, in kg

BMXHT height, in cm

BMXBMI body mass index (kg/m^2)

BMDBMIC BMI category:

1 = underweight

2 = normal weight

3 = overweight

4 = obese

. = missing

More detailed descriptions of these variables are given at the data documentation web pages for the NNYFS, at http://www.cdc.gov/nchs/nnyfs/Y_DEMO.htm and at http://www.cdc.gov/nchs/nnyfs/Y_BMX.htm.

For purposes of this discussion, you are asked to answer the three following questions:

• Does BMI vary significantly between boys and girls?

• Does BMI vary significantly among the racial/ethnic groups?

• Is there any trend to BMI with age?

Comments:

There are several ways to address these questions. For example, you might take BMXBMI as your outcome variable of interest: it is continuous, so you could then perform a two-sample t test for (1), a one way analysis of variance for (2), and a simple regression analysis (with age as the predictor variable) for (3).

Alternatively, you might reduce the problem to consideration of binomial probabilities: for example, you could classify everyone as obese or not obese (or maybe, overweight/obese vs underweight/normal), then compare binomial outcomes for (1) and (2) (z tests with the normal approximation or contingency tables), and conduct a t test on ages for (3).

Neither approach is wrong—the key is interpreting your findings!

If you prefer to do the analyses in Statdisk, there is a file, MHA610_Week 6_Discussion_NNYFS_workingdata.csv, ready to be read into Statdisk. (It’s the original Excel workbook, saved as csv.) No need to go through any additional steps, unless you wish to restructure the data in Excel.

Incidentally, the income variables are not needed for these questions, but as a bonus, you might want to investigate whether obesity is related to socioeconomic status (as reflected by family income).

Guided Response: Respond to at least two of your peers who chose a different of analysis that you by Day 7, 11:59PM. Did you arrive at the same conclusions as your colleague even though you chose different methods? If so, which method do you think is preferable and why? If not, which method do you believe produces more credible results and why? (You might consult the text to support your argument.). All initial and peer postings should be at least 250-500 words in APA format supported by scholarly sources.