Nonresponse problems

part of research particularly related to questioner

1. Nonresponse Problems By Syed Yousaf Shah Assistant Professor ION-DUHS

2. Nonresponse Elements that are selected in the sample, and that are also eligible for the survey, do not provide the required.

3. Types of Nonresponse Unit nonresponse: a selected element does not provide any information at all . Item nonresponse: a selected element does answer some questions, but not all of them.

4. Why is nonresponse a problem? Smaller sample size . Nonresponse bias due to selective nonresponse.

5. Causes of nonresponse No-contact Refusal Not-able Unprocessed

6. Response rates  Proportion of eligible elements in the sample for which a questionnaire has been completed : nr/ nE Notation nE = Number of eligible elements in the sample nR = Number of eligible respondents nE = nR + nNC + nRF + nNA Initial sample size n = nE + nOC . So nE = n – nOC . Problem : over-coverage unknown for non-contacts.

7. Method 1: Comparison of Early to Late Respondents Extrapolation based on statistical inferences Operationally define ‘Late Respondents’ Last wave of respondents: Late Respondents Co m p ar e e a r l y an d l a t e r es p o n d e n t s b a se d o n k e y variables of interest. I f n o d i f f er e n c e , re s u l t s ca n b e g e n er a li z e d t o l ar g e r population. METHODS FOR HANDLING NON-RESPONSE

8. Method 2: Using “Days to Respond” as a Regression Variable “Days to respond” is coded as continuous variable and used as IV in regression equation. Prima r y v a r iables of i n t e rest are regress e d on v a r iable “Days to Respond”. If not statistically significant: Assume that respondents are not different from non-respondents. METHODS FOR HANDLING NON-RESPONSE

9. Method 3: Compare Respondents to Non-Respondents Co m p u t e d i f f e r e n c e s b y s a m p lin g n o nr espo n d e n t s and working extra diligently to get their responses. Minimum 20% of responses from nonrespondents should be obtained. I f f e w e r th a n 2 % r e spo n se s ar e o b t a i n ed , M e th o d 1 or 2 should be used by combining the results. METHODS FOR HANDLING NON-RESPONSE

10. Method 4: Compare Respondents on Characteristics known a priori Co m p ar e r esp o n de n t s t o po p u l a t i o n or characteristics known in advance Describe similarities and differences. Method 5: Ignore Non-Response as a Threat to External Validity If above methods are you can choose to ignore. METHODS FOR HANDLING NON-RESPONSE

11. Missing data can be: Due to preventable errors, mistakes, or lack of foresight by the researcher Due to problems outside the control of the researcher D e li be r a t e , i n t e n ded , o r p la n n e d b y t h e r ese a r c h e r t o r ed u c e cost or respondent burden Du e t o d i f f e r e n t ia l a pp l i c a b ili t y o f s o m e i t e m s t o s u b s e t s of respondents Etc. Missing data

12. Non-Response v/s Missing Data M i s s i n g D a t a : W h e r e v a l i d v alu e s o n o n e o r m o r e variables are not available for analysis. i de n t if y t h e th e m is s i n g Researchers primary concern is to patterns and relationships underlying data. w e n e e d t o un d e r s t an d p r o c e s s l e a d i n g t o m is s i n g data to take appropriate course of action. Common in Social Research More acute in experiments and surveys Best way is to avoid it by planning and conscientious data collection. Not uncommon to have some level of missing data. MISSING DATA

13. Lost data Reduces Statistical Power Meaningfully diminishes sample size Bias Parameter Estimates Correlations biased downwards Predictor scores affected Restrict Variance Central Tendency Biased PRIMARY PROBLEMS

14. The data can be missing at three levels: Item- level missingness Construct- level missingness Person-level missingness LEVELS OF MISSINGNESS

15. DETERMINE THE TYPE OF MISSING DATA Is it under the control of researcher? Is it ignorable? Ignorable Missing Data Expected Remedies not needed Allowance for missing data are inherent in the technique Missing data is operating at random Non—Ignorable Missing Data Known to researchers: Some remedies if random Unknown missing data: Process less easy, but remedies available PROCESS FOR IDENTIFYING MISSING DATA AND APPLYING REMEDIES

16. J . R . ( 200 3 ) . T h e h a n d li n g of 1. Dooley, L. M., & Lindner, nonresponse error. Human Resource Development Quarterly , 14 (1), 99-110. R o t h , P . L . ( 19 9 4 ) . M i ss i n g d a ta : A con c e p t u a l r e v i e w f o r applied psychologists. Personnel psychology , 47 (3), 537-560. Blair, E., & Zinkhan, G. M. ( 2006). Nonresponse and generalizability in academic research. Journal of the Academy of Marketing Science , 34 (1), 4-7. 4 . Ne w m a n , D . A . ( 2 1 4 ) . M i ss i n g d a t a f i v e p rac t i c a l guidelines. Organizational Research Methods , 17 (4), 372-411 . 5. Hair, J. F., Black, W. C., Babin, B. J., Anderson, R. E., & Tatham, R. L. (2006). Multivariate data analysis 6th Edition. New Jersey: Pearson Education . REFERENCES