Forced Response in Dichotomous Randomised Response Technique

Abstract

In sample survey research when sensitive information such as illegal drug usage, rape, examination malpractices among students, induced abortion and the likes are to be obtained from individuals or respondents, false or no response is imminent. To correct this bias, this paper proposes a new randomized response model by incorporating the unrelated question in force-response technique. The unbiased estimate and variance of the proposed model were also obtained. The proposed randomized response model is then compared with the Alternative Unbiased Estimator in Unrelated Dichotomous Randomized Response Model, (AEUDRRT) and Alternative Unbiased Estimator in Dichotomous Randomized Response Model, (AEDRRT). The numerical investigation shows that the variance of the proposed model reduces while the V(AEUDRRT) and V(AEDRRT) increases as the sensitive issues increases. Hence, the proposed model has percentage relative efficiency (PRE) as high as 1195.45% and 1977.20% over AEUDRRT and AEDRRT, respectively. Also, the application of the proposed method revealed that it is practically more efficient in estimating the proportion of people involved in sensitive character (cyber threat) than the direct method of data collection. Therefore, the proposed technique is shown to be more efficient than conventional ones.

Keywords

• Cyber Threat
• Dichotomous Variable
• Forced Response
• Relative Efficiency
• Sensitive Attribute

References

1. [1] Tourangeau, R., Yan, T., “Sensitive questions in surveys”, Psychological Bulletin, 133(5): 859–883, (2007). DOI: https://doi.org/10.1037/0033-2909.133.5.859
2. [2] Krumpal, I., “Determinants of social desirability bias in sensitive surveys: a literature review”, Quality & Quantity, 47: 2025-2047, (2013). DOI: https://doi.org/10.1007//s11135-011-9640-9
3. [3] Warner, S.L., “Randomized response: a survey technique for eliminating evasive answer bias”, Journal of American Statistical Association, 60: 63-69, (1965).
4. [4] Greenberg, B.G., Abul-Ela, L.A., Simmons, W.R., Horvitz, D.G., “The unrelated question randomized response model: theoretical framework”, Journal of American Statistical Association, 64: 520-539, (1969).
5. [5] Boruch, R., “Assuring confidentiality of responses in social research: a note on strategies” American Sociologist, 6(4): 308-311, (1971).
6. [6] Mangat, N.S., “An improved randomized response strategy”, Journal of the Royal Statistical Society: Series B (Methodological), 56: 93-95, (1994). DOI: https://doi.org/10.1111/j.2517-6161.1994.tb01962.x
7. [7] Kim, J-M, Warde, W.D., “A stratified Warner’s randomized response Technique”, Journal of Statistical Planning and Inference, 120(1-2): 155-165, (2004).
8. [8] Hussain, Z., Shabbir, J., “Randomized use of Warner’s randomized response model”, Interstat, 1-21, (2007).

9. [9] Ewemooje, O.S., Amahia, G.N., “Improved Randomized Response Technique for Two Sensitive Attributes” Afrika Statistika, 10(2): 839-852, (2015). DOI: https://doi.org/10.16929/as/2015.639.78
10. [10] Adebola, F.B., Adediran, A.A., Ewemooje, O.S., “Hybrid tripartite randomized response technique”, Communications in Statistics - Theory and Methods, 46(23): 11756-11763, (2017). DOI: https://doi.org/10.1080/03610926.2016.1277760
11. [11] Ewemooje, O.S., “Estimating two sensitive characters with equal probabilities of protection”, Cogent Mathematics, 4: 1-14, (2017).
12. [12] Ewemooje, O.S., Adebola, F.B., Adediran, A.A, “A stratified hybrid tripartite randomized response technique” Gazi University Journal of Science, 31(4), 1246-1266, (2018).
13. [13] Adeniran, A.T., Sodipo, A.A., Udomboso, C.G., “A modified force randomized response model”. Journal of the Nigerian Society of Physical Sciences, 2: 36-50, (2020).
14. [14] Harriet, I., Julia, P.G., Freya, A.V., “Asking sensitive questions in conservation using randomized response techniques” Biological conservation, 260: 109191, (2021). DOI: https://doi.org/10.1016/j.biocon.2021.109191
15. [15] Singh, N., Vishwakarma, G.K., Kumar, N. Singh, H.P., “Estimation of Mean of Sensitive Variable Using Multiplicative Scramble Variable Under Measurement Error”, Journal of Statistical Theory and Practice, 16(46): 1-11, (2022). DOI: https://doi.org/10.1007/s42519-022-00272-w
16. [16] Perri, P.F., Elvira, P., Manuela, S., “Estimating Induced Abortion and Foreign Irregular Presence using the Randomized Response Crossed Model”, Social Indicators Research, 129(2): 601–618, (2015). DOI: https://doi.org/10.1007/s11205-015-1136-x
17. [17] Ewemooje, O.S., Amahia, G.N., Adebola, F.B., “Estimating prevalence of induced abortion and multiple sexual partners using improved randomized response technique for two sensitive attributes”, Communications in Statistics: Case Studies, Data Analysis and Applications, 3(1-2): 21-28, (2017). DOI: https://doi.org/10.1080/23737484.2017.1398057
18. [18] Adebola, O.G, Ewemooje, O.S., Adebola, F.B., “Plagiarism and Examination Malpractice: Persistent Examples of Academic Dishonesty”, African Journal of Applied Statistics, 6(2): 723-739, (2019).
19. [19] Adediran, A.A., Ewemooje, O.S., Adebola, F.B., “Unbiased estimator model using unrelated question in dichotomous randomized response” Statistics in transition, 21(5): 119-132, (2020). DOI: https://doi.org/10.21307/stattrans-2020-058
20. [20] Ewemooje, O.S., Adebola, F.B., Amahia, G.N., “Alternative estimator in dichotomous randomized response technique”, Communication in mathematics and statistics, 7: 383-400, (2019).
21. [21] Chaudhuri, A., Stenger, H. “Survey Sampling: Theory and Methods”, 2nd Edition, CRC Press, Boca Raton, FL, (2005). DOI: https://doi.org/10.1201/9781420028638
22. [22] Chaudhuri, A., “Randomized Response and Indirect Questioning Techniques in Surveys”, Chapman & Hall/CRC, Boca Raton, (2011).
23. [23] Ewemooje, O.S., “An Alternative Estimator for Unrelated Questions in Tripartite Randomized Response Technique”, Gazi University Journal of Science, 32(4): 1308-1320, (2019).
24. [24] Ewemooje, O.S., Adebola, F.B., Awogbemila, A.T., “Substance Use disorder prevalence using tripartite randomized technique”, Nigerian Journal of Technological Research, 14(1): 55-61, (2019). DOI: https://doi.org/10.4314/njtr.v14i1.8