Hi,

Your question is:  Step -wise approach is best approach for survey of risk factors regarding non- communicable diseases:

The instrument contained:

Survey information: including the location and the time of the interview, the interview condition, in addition to information about the interviewer, and contact information of the participant. 

Step: 1  Demographic information: This including information about age, sex, education, employment, and household income. 

Step: 2  Behavioural information: This including tobacco use, dietary habits regarding fruits and vegetables and oil or fat consumption, physical activity, and history of hypertension or diabetes. 

Step: 3  Physical measurement: This including information about the interviewer and the instruments, in addition to recording anthropometric measurements (height, weight, waist circumference, and hip circumference), and the two or three blood pressure measurement readings.  

Step: 4 Biochemical measurements: This including information about the interviewer, the participant preparation state, the instrument, in addition to recording the levels of fasting blood glucose and fasting total cholesterol. 

use all the four steps in your study, then you will get correct and accurate results.

Thanks.

I wonder if you are referring to "hierarchical regression" rather than "stepwise regression?" Dr. Vasudevan appears to be describing a hierarchical regression, defined by a set of steps (sequence of models) determined a priori, which is a commonly accepted way to test research questions using this type of data. "Stepwise regression," however, is not commonly preferred by statisticians. Here is a link to an informative discussion on stepwise regression:

http://andrewgelman.com/2014/06/02/hate-stepwise-regression/

Yes it is used in logistic  regression  where step wise has two  options forward and backward .  Their meaning are obvious forward from  less to  more significant values and the other is reverse

Mohan, 

I would recommend that you review the WHO PanAmerica stepwise approach, they also have a questionnaire which could assist you with the analysis of a particular communicable disease once you adapt the questions.  The stepwise approach defines a progression which may be useful in your research project.

http://www.paho.org/hq/index.php?option=com_content&view=article&id=1923&Itemid=1670

hi sir,

I should recommend that WHO standerd questions format of non communicable disease.

Here are some of the problems with stepwise variable selection.

It yields R-squared values that are badly biased to be high.

The F and chi-squared tests quoted next to each variable on the printout do not have the claimed distribution.

The method yields confidence intervals for effects and predicted values that are falsely narrow; see Altman and Andersen (1989).

It yields p-values that do not have the proper meaning, and the proper correction for them is a difficult problem.

It gives biased regression coefficients that need shrinkage (the coefficients for remaining variables are too large; see Tibshirani [1996]).

It has severe problems in the presence of collinearity.

It is based on methods (e.g., F tests for nested models) that were intended to be used to test prespecified hypotheses.

Increasing the sample size does not help very much; see Derksen and Keselman (1992).

It allows us to not think about the problem.

It uses a lot of paper.

“All possible subsets” regression solves none of these problems.

Conclusions

“The degree of correlation between the predictor variables affected the frequency with which authentic predictor variables found their way into the final model.”

“The number of candidate predictor variables affected the number of noise variables that gained entry to the model.”

“The size of the sample was of little practical importance in determining the number of authentic variables contained in the final model.”

“The population multiple coefficient of determination could be faithfully estimated by adopting a statistic that is adjusted by the total number of candidate predictor variables rather than the number of variables in the final model.”

References

Altman, D. G. and P. K. Andersen. 1989.

Bootstrap investigation of the stability of a Cox regression model. Statistics in Medicine 8: 771–783.

Copas, J. B. 1983.

Regression, prediction and shrinkage (with discussion). Journal of the Royal Statistical Society, Series B 45: 311–354.

Shows why the number of CANDIDATE variables and not the number in the final model is the number of degrees of freedom to consider.

Derksen, S. and H. J. Keselman. 1992.

Backward, forward and stepwise automated subset selection algorithms: frequency of obtaining authentic and noise variables. British Journal of Mathematical and Statistical Psychology 45: 265–282.

Hurvich, C. M. and C. L. Tsai. 1990.

The impact of model selection on inference in linear regression. American Statistician 44: 214–217.

Mantel, Nathan. 1970.

Why stepdown procedures in variable selection. Technometrics 12: 621–625.

Roecker, Ellen B. 1991.

Prediction error and its estimation for subset—selected models. Technometrics 33: 459–468.

Shows that all-possible regression can yield models that are too small.

Tibshirani, Robert. 1996.

Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society, Series B 58: 267–288.

investigator error and instrumental errors cannot be avoided in any such studies but it can be minimized if proper percussion is taken. No doubt that STEP wise approach is a best method to study risk factors of Non-communicable diseases.

Dear sir

 WHO standerd questions format of non communicable disease are usefull and please check following sites

www.who.int/chp/steps/Printed_STEPS_Report_Nauru.pdf‏

www.ncbi.nlm.nih.gov/pmc/articles/PMC3702362

Dear Sir,

Thanks for sharing above cited document. These will help me to understand the topic in detail.

with Regards

I agree that step-wise approach is a best method to study risk factors of non-communicable diseases.

Hi Sir,

I agree that step-wise approach is the best approach for survey of risk factors of non-communicable diseases.