雖然許多學者嘗試檢視並實證社會經濟地位與癌症預後的密切關聯，但往往沒有針對這個因果路徑裡的中介變數以及相對應的管理介入進行更深入的探討。
本論文旨在研究社會經濟地位對癌症患者生存時間的直接和間接影響，並採用診斷時之分期及治療方式建立多中介路徑，以分析社經地位影響多種癌症病例（含肺癌、肝癌、結腸直腸癌和胃癌）之存活時間的內在機制。本研究先透過與傳統中介分析比較，在單一中介變數的分析中驗證基於反事實事件中介分析的優點；本研究接著擴展模型，在考慮多個中介變數時，進行基於反事實事件的中介分析。
研究中採用了生存分析常見的 Cox 比例風險模型，並使用美國國家癌症研究所的 SEER 數據集。 研究結果指出與傳統方法相較，基於反事實事件的中介分析法能夠對中介效應的詮釋提供更清楚且更一致的結果，並允許我們對因果關係提出較佳解釋。 此外，使用單一中介變數（即癌症分期）進行的基於反事實事件的中介分析亦指出診斷時之癌症分期部分中介社經地位對存活時間的影響。研究結果亦指出基於反事實事件的中介分析可以處理多個中介路徑，並將社經地位對生存時間的影響拆解成直接效應，以及透過診斷之分期和治療（手術）兩個中介路徑之間接效應。研究結果特別指出對直腸癌和胃癌的案例而言，兩個中介變數存在不一致的中介效應（即其中一個中介變數存在抑製效應）。整體而言，研究指出社經地位可直接或間接影響癌症病患的存活時間，且其通過癌症分期和手術治療的中介效應均為顯著。因此，為擁有不同醫療資源（不管是藥物或治療方式的選擇、醫療保健設施的可達性）的患者設計早期篩檢政策或更公平的治療機制將可明顯減少健康照護之癌症存活差異。

While the association between socioeconomic status (SES) and the prognosis of
cancers has been examined in many studies, few studies have been done to investigate
the mediator variables lie along this causal pathway to identify possible targets for policy intervention. This study aims to investigate the direct and indirect effects of SES on the survival time of cancer patients by using cancer stage and medical treatment (i.e., surgery) to create multiple pathways from SES to health outcomes to facilitate a mechanistic inference on several cancer cases (i.e., lung, liver, colorectal, and stomach cancers). In
particular, this study demonstrates the appropriateness of using the counterfactual eventbased mediation analysis for analyzing a time-to-event outcome (by comparing it with the traditional mediation analysis) and then extends the counterfactual event-based mediation analysis to a model with multiple mediators. A Cox proportional hazards model for survival analysis was applied and the SEER (The Surveillance, Epidemiology, and End Results) data from the National Cancer Institute of the United States were used in this study. Results show that the counterfactual event-based mediation analysis provides clearer and more consistent estimations and decomposition of the effects and allows for a better causal interpretation. Results of the counterfactual event-based mediation
analysis with one mediator also shows that the effect of SES on survival time is partially mediated by stage at diagnosis in lung, liver, and colorectal cancers. When multiple mediators are considered, results show that the effect of SES on survival time can be further decomposed into the direct effect and the indirect effects via pathways mediating through stage at diagnosis and surgery. In particular, the inconsistent mediat ion (or suppression) effects found on colorectal and stomach cancers are especially critical in evaluating counterproductive effects of stage and treatment on survival. Overall, results
of this study shows that SES can either affect cancer survival directly or indirectly, and the mediation analysis revealed that the disparity in timely diagnosis (i.e., stage at diagnosis) and surgery caused by SES are also significant. Opportunities to reduce cancer disparity exist in the design of early detection policies or mechanisms for patients with
varying resources, recovery medication, health care facilities, and access to medical
resources.

Agarwal, S., Ying, J., Boucher, K. M., & Agarwal, J. P. (2017). The association between
socioeconomic factors and breast cancer-specific survival varies by race. PLoS
One, 12(12), e0187018.
Akinyemiju, T., Moore, J., & Pisu, M. (2018). Mediating effects of cancer risk factors on
the association between race and cancer incidence: analysis of the NIH-AARP
Diet and Health Study. Annals of epidemiology, 1(28), 33-40.
Baranowski, T., Anderson, C., & Carmack, C. (1998). Mediating Variable Framework in
physical activity interventions: How are we doing? How might we do better?
American journal of preventive medicine, 13(4), 266-297.
Baron, R. M., & Kenny, D. A. (1986). The Moderator-Mediator Variable Distinction in
Social Psychological Research: Conceptual, Strategic, and Statistical
Considerations. Journal of Personality and Social Psychology, 51(6), 1173-1182.
Berg, I. v., Buettner, S., Braak, R. C., Ultee, K., Lingsma, H., Vugt, J. v., & Ijzermans, J.
(2019). Low Socioeconomic Status Is Associated with Worse Outcomes After
Curative Surgery for Colorectal Cancer: Results from a Large Multicenter Study.
Journal of Gastrointestinal Surgery, 24(11), 2628-2636.
Birkmeyer, N. J., Gu, N., Baser, O., Morris, A. M., & Birkmeyer, J. D. (2008).
Socioeconomic Status and Surgical Mortality in the Elderly. Medical Care, 46(9),
893-899.
Blais, S., Dejardin, O., Boutreux, S., & Launoy, G. (2006). Social determinants of access
to reference care centres for patients with colorectal cancer–a multilevel analysis.
European Journal of Cancer, 42(17), 3041-3048.
Bradley, C. J., Given, C. W., & Roberts, C. (2001). Disparities in cancer diagnosis and
survival. Cancer, 91(1), 178-188.
Campbell, N. C., Elliott, A. M., Sharp, L., Ritchie, L. D., Cassidy, J., & Little, J. (2001).
Rural and urban differences in stage at diagnosis of colorectal and lung cancers.
British Journal of Cancer, 84(7), 910-4.
Clegg, L. X., Reichman, M. E., Miller, B. A., Hankey, B. F., Singh, G. K., Lin, Y. D., . . .
K.E., B. (2009). Impact of socioeconomic status on cancer incidence and stage at
diagnosis: selected findings from the surveillance, epidemiology, and end results: National Longitudinal Mortality Study. Cancer causes & control, 20(4), 417-435.
Coleman, M. P., Gatta, G., Verdecchia, A., Estève, J., Sant, M., Storm, H., . . . Group, t.
E. (2003). EUROCARE-3 summary: cancer survival in Europe at the end of the
20th century. Annals of oncology, 14((suppl_5)), v128–v149.
Collett, D. (2003). Modelling survival data in medical research, 2nd. Boca Raton:
Chapman & Hall/CRC.
Conwell, T., & Boscoe, F. P. (2015). Urban/rural disparities in cancer incidence in New
York State, 2008-2012. PeerJ PrePrints:e1500.
Cox, D. R. (1975). Partial Likelihood. Biometrika, 62(2), 269-276.
Dreyer, M. S., Nattinger, A. B., McGinley, E. L., & Pezzin, L. E. (2018). Socioeconomic
status and breast cancer treatment. Breast Cancer Research and Treatment, 167,
1-8.
Gakidou, E., Nordhagen, S., & Obermeyer, Z. (2008). Coverage of cervical cancer
screening in 57 countries: low average levels and large inequalities. PLoS
medicine, 5(7), e132.
Gillen, D. (2016). The Stratified Proportional Hazards Model. Retrieved November 12,
2017, from http://www.ics.uci.edu/~dgillen/STAT255/Handouts/lecture8.pdf
Gore, J. L., Kwan, L., Saigal, C. S., & Litwin, M. S. (2005). Marriage and mortality in
bladder carcinoma. Cancer: Interdisciplinary International Journal of the
American Cancer Society, 104(6), 1188-1194.
Guyot, P., Ades, A. E., Ouwens, M. J., & Welton, N. J. (2012). Enhanced secondary
analysis of survival data: reconstructing the data from published Kaplan-Meier
survival curves. BMC Medical Research Methodology, 12(1), 1-13.
Herbert, C., Lefevre, H., Gignoux, M., & Launoy, G. (2002). Influence of social and
occupational class and area of residence on management and survival in patients
with digestive tract cancer: a population study in the Calvados area (France).
Revue D'epidemiologie et de Sante Publique, 50(3), 253-264.
Hong, G. (2010). Ratio of mediator probability weighting for estimating natural direct
and indirect effects. Proceedings of the American Statistical Association,
biometrics section (pp. 2401-2415). Alexandria: American Statistical Association.
IARC. (2020). All Cancers (excluding non-melanoma skin cancer) Estimated Incidence,
Mortality and Prevalence Worldwide in 2015. (World Health Organization) Retrieved December 22, 2017, from International Agency for Research on Cancer:
http://globocan.iarc.fr/Pages/fact_sheets_cancer.aspx
Jerath, A., Austin, P. C., Ko, D. T., Wijeysundera, H. C., Fremes, S., McCormack, D., &
Wijeysundera, D. N. (2020). Socioeconomic Status and Days Alive and Out of
Hospital after Major Elective Noncardiac Surgery: A Population-based Cohort
Study. Anesthesiology, 132(4), 713-722.
Judd, C. M., & Kenny, D. A. (1981). Process Analysis: Estimating Mediation in Treatment
Evaluations. Evaluation Review, 5, 602-619.
Kangovi, S., Barg, F. K., Carter, T., Long, J. A., Shannon, R., & Grande, D. (2013). :
Understanding why patients of low socioeconomic status prefer hospitals over
ambulatory care. Health affairs, 32(7), 1196-1203.
Kartsonaki, C. (2016). Survival Analysis. Diagnostic Histopathology, 22(7), 263-270.
Kazdin, A. E. (2007). Mediators and Mechanisms of Change in Psychotherapy Research.
Annu. Rev. Clin. Psychol. , 3, 1-27.
Kingsmore, D., Ssemwogerere, A., Hole, D., & Gillis, C. (2003). Specialisation and breast
cancer survival in the screening era. British journal of cancer, 88(11), 1708-1712.
Kravdal, O. (2000). Social Inequalities in Cancer Survival. Population Studies, 54(1), 1-
18.
Krull, J. L., & MacKinnon, D. P. (1999). Multilevel mediation modeling in group-based
intervention studies. Evaluation Review, 23(4), 418-444.
Kuhn, Y., Koscielny, A., Glowka, T., Hirner, A., Kalff, J. C., & Standop, J. (2010).
Postresection survival outcomes of pancreatic cancer according to demographic
factors and socio-economic status. European Journal of Surgical Oncology
(EJSO), 36(5), 496-500.
Kweon, S.-S., Kim, M.-G., Kang, M.-R., Shin, M.-H., & Choi, J.-S. (2017). Difference
of stage at cancer diagnosis by socioeconomic status for four target cancers of the
National Cancer Screening Program in Korea: Results from the Gwangju and
Jeonnam cancer registries. Journal of Epidemiology, 27, 299-304.
Lange, T., & Hansen, J. V. (2011). Direct and Indirect Effects in a Survival Context.
Epidemiology, 22(4), 575-581.
Lange, T., Rasmussen, M., & Thygesen, L. C. (2014). Assessing Natural Direct and
Indirect Effects Through Multiple Pathways. American Journal of Epidemiology, 179(4), 513–518.
Lange, T., Vansteelandt, S., & Bekaert, M. (2012). A Simple Unified Approach for
Estimating Natural Direct and Indirect Effects. American Journal of Epidemiology,
176(3), 190-195.
Lundqvist, A., Andersson, E., Ahlberg, I., Nilbert, M., & Gerdtham, U. (2016).
Socioeconomic inequalities in breast cancer incidence and mortality in Europe—
a systematic review and meta-analysis. European Journal of Public Health, 26(5),
804-813.
MacKinnon, D. P. (1994). Analysis of mediating variables in prevention and intervention
research. NIDA research monograph, 139, 127-281.
MacKinnon, D. P. (2008). Introduction to Statistical Mediation Analysis. Routledge.
MacKinnon, D. P., & Dwyer, J. H. (1993). Estimating mediated effects in prevention
studies. Evaluation review, 17(2), 144-158.
MacKinnon, D. P., Fairchild, A. J., & Fritz, M. S. (2007). Mediation Analysis. Annual
Review of Psychology,58, 593-614.
MacKinnon, D. P., Krull, J. L., & Lockwood, C. M. (2000). Equivalence of the Mediation,
Confounding and Suppression Effect. Prevention Science, 1(4), 173-181.
MacKinnon, D. P., Warsi, G., & Dwyer, J. H. (1995). A simulation study of mediated
effect measures. Multivariate Behavioral Research, 30(1), 41–62.
O’Keefe, E. B., Meltzer, J. P., & Bethea, T. N. (2015). Health disparities and cancer: racial
disparities in cancer mortality in the United States, 2000–2010. Frontiers in public
health, 3(51).
Olah, M. E., Gaisano, G., & Hwang, S. W. (2013). The effect of socioeconomic status on
access to primary care: an audit study. CMAJ, 185(6), E263-E269.
O'Quigley, J. (2008). Proportional Hazards Regression. New York: Springer.
Ortiz, C. A., Freeman, J. L., Kuo, Y.-F., & Goodwin, J. S. (2007). The influence of marital
status on stage at diagnosis and survival of older persons with melanoma. The
Journals of Gerontology Series A: Biological Sciences and Medical Sciences,
62(8), 892–898.
Pearl, J. (2009). Causality: Models, Reasoning and Inference. New York: Cambrudge
University Press.
Quaglia, A., Lillini, R., Mamo, C., Ivaldi, E., & Vercelli, M. (2013). Socio-economic inequalities: a review of methodological issues and the relationships with cancer
survival. Critical reviews in oncology/hematology, 85(3), 266-277.
Ripping, T. M., Waal, D. v., Verbeek, A. L., & Broeders, M. J. (2016). The relative effect
of mammographic screening on breast cancer mortality by socioeconomic status.
Medicine, 95(31), e4335.
Robert, S. A. (1999). Socioeconomic position and health: the independent contribution of
community socioeconomic context. Annual review of sociology, 25(1), 489–516.
Robert, S. A., Strombom, I., Trentham-Dietz, A., Hampton, J. M., McElroy, J. A.,
Newcomb, P. A., & Remington, P. L. (2004). Socioeconomic Risk Factors for
Breast Cancer: Distinguishing Individual- and Community-Level Effects.
Epidemiology, 15(4), 442-450.
Rochon, J., Bois, A. d., & Lange, T. (2014). Mediation analysis of the relationship
between institutional research activity and patient survival. BMC Medical
Research Methodology, 14(9).
Rodday, A. M., Parsons, S. K., Snyder, F., Simon, M. A., Llanos, A. A., Warren-Mears,
V., . . . Whitley, E. M. (2015). Impact of patient navigation in eliminating
economic disparities in cancer care. Cancer, 121(22), 4025–4034.
Schwartz, K. L., Crossley-May, H., Vigneau, F. D., Brown, K., & Banerjee, M. (2003).
Race, socioeconomic status and stage at diagnosis for five common malignancies.
Cancer Causes and Control, 14(8), 761-766.
Singer, S., Roick, J., Briest, S., Stark, S., Gockel, I., Boehm, A., . . . Danker, H. (2016).
Impact of socio‐economic position on cancer stage at presentation: Findings from
a large hospital‐based study in Germany. International journal of cancer, 139(8),
1696-1702.
Spadea, T., Zengarini, N., Kunst, A., Zanetti, R., Rosso, S., & Costa, G. (2010). Cancer
risk in relationship to different indicators of adult socioeconomic position in Turin,
Italy. Springer Science+Business Media B.V., 21:1117–1130.
Steen, J., Loeys, T., Moerkerke, B., & Vansteelandt, S. (2017). Flexible mediation
analysis with multiple mediators. American Journal of Epidemiology, 186(2),
184-193.
Surveillance Research Program, N. C. (2020). SEER*Stat software version 8.3.5.
Retrieved from https ://www.seer.cance r.gov/
Surveillance Research Program, N. C. (2021). SEER*Stat Software version 8.3.9.2.
Retrieved from https://seer.cancer.gov/seerstat/
Tein, J.-Y., & MacKinnon, D. P. (2003). Estimating Mediated Effects with Survival Data.
New developments in psychometrics, 405-412.
Valeri, L., & Vanderweele, T. J. (2013). Mediation analysis allowing for exposuremediator interactions and causal interpretation: theoretical assumptions and
implementation with SAS and SPSS macros. Psychological methods, 18(2), 137-
150.
VanderWeele, T. J. (2016). Mediation Analysis: A Practitioner's Guide. Annual review of
public health, 37, 17-32.
VanderWeele, T. J., & Vansteelandt, S. (2014). Mediation analysis with multiple
mediators. Epidemiologic Methods, 2(1), 95-115.
Vansteelandt, S., & Daniel, R. M. (2017). Interventional effects for mediation analysis
with multiple mediators. Epidemiology, 28(2), 258-265.
Woods, L. M., Rachet, B., & Coleman, M. P. (2006). Origins of socio-economic
inequalities in cancer survival: a review. Annals of oncology, 17(1), 5-19.
Wrigley, H., Roderick, P., George, S., Smith, J., Mullee, M., & Goddard, J. (2003).
Inequalities in survival from colorectal cancer: a comparison of the impact of
deprivation, treatment, and host factors on observed and cause specific survival.
Journal of Epidemiology & Community Health, 57(4), 301-309.
Wu, C.-C., Chang, C.-M., Hsu, T.-W., Lee, C.-H., Chen, J.-H., Huang, C.-Y., & Lee, C.-
C. (2016). The effect of individual and neighborhood socioeconomic status on
esophageal cancer survival in working-age patients in Taiwan. Medicine, 95(27),
e4140.
Yabroff, K. R., & Gordis, L. (2003). Does stage at diagnosis influence the observed
relationship between socioeconomic status and breast cancer incidence, casefatality, and mortality? Social science & medicine, 57(12), 2265-2279.
Yan, B., Noone, A. M., Yee, C., Banerjee, M., Schwartz, K., & Simon, M. S. (2009).
Racial differences in colorectal cancer survival in the Detroit Metropolitan Area.
Cancer: Interdisciplinary International Journal of the American Cancer Society,
115(16), 3791-3800.
Yin, D., Morris, C., & Allen, M. (2010). Does socioeconomic disparity in cancer incidence vary. Cancer Causes Control, 21, 1721-1730.