2018 12 22 12 1207 2011-2016 2011-2016 31 gross do mestic productgdp R 2 AIC MSE R 512. 91 A 1674-3679201812-1207-05 DOI10. 16462 /j. cnki. zhjbkz. 2018. 12. 002 Temporal-spatial characteristic analysis of AIDS /HIV epidemic during 2011-2016 in China Zhi-mingZHANG Hui-guoHU Xi-jian. 830046 China SUN Shu-man LI College of Mathematics and System Science Xinjiang UniversityUrumqi Abstract Objective In this paperpassenger quantitygdp per capitapopulation density and the number of beds per thousand were investigated to reflect the spatio-temporal trend of AIDS /HIV incidence of 31 provincesmunicipalities and autonomous regions from 2011 to 2016 in China order to provide a reference for controlling the spread of AIDS / HIV. Methods A geographically and temporally weighted Poisson regression model was established. The coefficient function was estimated and visualized according to locally linear geographical weighted regression method and iterative weighted least square estimation. Some spatio-temporal non-stationary properties of AIDS / HIV cases in different time and regions were studied. Result There existed the temporal and spatial characteristics and trend in the high-incidence areas. Macro factors with different times and regions had different influences on the number of AIDS / HIV cases. Conclusion Statistics for goodness of fit R 2 AICMSEshowed GTWPR model was better than Poisson regression modelwhich could reflect spatio-temporal interaction and non-stationary characteristics. Result showed that the spatial and temporal distribution of AIDS / HIV epidemic was closely related to four macro factors. Key words Acquired immunodeficiency syndromemacro factorsgeographically and temporally weighted Poisson regression modelspatio-temporal non-stationary Chin J Dis Control Prev 2018 2212 1207-1210 1215 acquired 2017 3 immunodeficiency syndrome AIDS 69 human immunodeficiency virus HIV 21 1-3 1989 4-5 11661076 16BTJ024 Huang 6 Yan 2016D01C043 7 8 XJEDU2017M001 830046 1993-9 E-mailxijianhu@ 126. com 10
1208 Chin J Dis Control Prev 2018 Dec2212 gross domestic β 2 β 3 β 4 β 5 product GDP GTWPR geographically and temporally weighted poisson regression GTWPR X ij2 + + β 5 μ i v i t i X ij5 2 η ij = Σ 5 μ i v i t j X ijp = β 1 μ i v i t j + β 2 μ i v i t j p = 1 31 31 2011 - β p μ i v i t i p = 2 3 4 5 p 2016 i j Wang 11 1 PR β P 1. 1 μ ij r ij P ij i GTWPR β p j 10 / μ i v i t j 10 10 μ ij = r ij P ij i = 1 2 31 j = 1 2 6 r ij 2 P ij 2012-2017 2. 1 2011-2016 GDP 2012-2017 6 4 /10 18 2016 2 /10 1 2012-2017 31 WGS _1984_Albers 1. 2 12 k = 槡 λ max /λmin λ X T X X k > 15 k = 2. 386 1 2011-2016 Figure 1 Incidences of AIDS /HIV in all provinces2011-2016 < 15 2011-2016 31 R 3. 3. 3 2011-2016 GDP 1 poisson regression model PR GTWPR 0. 93 1. 69 0. 93 2 3. 13 1. 69 3. 13 PR 13 η ij = lnμ ij = lnr ij + lnp ij lnμ ij = Σ 5 β px ijp = β 1 + β 2 X ij2 + + β 5 X ij5 p = 1 1 i = 1 3 3 j = 1 2 6X ij1 = 1 X ij2 2011 2012 2013 2014 2015 2012 2016 X ij3 X ij4 X ij5 i j GDP
2018 12 22 12 1209 Table 1 1 2011-2016 31 /10 AIDS /HIV incidence1 /100 000 in 31 provinces2011-2016 P 25 M P 75 0. 13 0. 93 1. 69 3. 13 18. 15 2. 2. 2 PR GTWPR 3 3 2 Figure 2 2011-2016 Regional changes in high incidence areas of AIDS /HIV2011-2016 2. 2 2. 2. 1 GTWPR Alireza 14 GTWPR PR GTWPR 3 Figure 3 Error mean of mean logarithm of 15 AIDS / HIV incidence in various provinces PR GT- WPR 3 GTWPR Table 2 Spatio-temporal non-stationary test β 1 β 2 β 3 β 4 β 5 GTWPR 1. 741 1. 192 2. 214 4. 046 0. 737 PR 0. 005 0. 003 0. 007 0. 006 0. 004 3 Table 3 Goodness of fit test R 2 AIC D MSE GTWPR 0. 97 295. 24 923. 67 0. 03 PR 0. 15 1 130. 33 135 103. 20 2. 24 GDP 2011-2016 R 2 PR 31 akaike information criterion AIC deviationd mean-square error 28 MSE GTWPR GDP 2 4 5 2011-2016 31 3 GTWPR
1210 Chin J Dis Control Prev 2018 Dec2212 4 2011-2016 31 Figure 4 Regression coefficient distribution of AIDS /HIV macro factors in all provinces2011-2016 PR GDP 5 GTWPR Figure 5 Variance mean distribution of four regression coefficients in GTWPR model 1. J. 2014 GDP 185 369-374. 2. 1996-2014 HIV J. 2017 23 4 296-298 PR 302. 3. J. 2013 302 196-198. 1215 GTWPR
2018 12 22 12 1215 2017 232 93. 4 HIV /AIDS HIV /AIDS 5 J 2018 158-62. 6. J 7Zhang XTang WLi Yet al. The HIV /AIDS epidemic among young people in China between 2005 and 2012Results of a spa- tial temporal analysis J. HIV Med2016. 2007-2017 8. HIV /AIDS HIV /AIDS 1. 2017 12 J. 2018 262 111. 2. 2016 12 J. 3. J. 2011 32 1 42-46.. 2006-2013 J. 2018 1 54-57.. 2010-2016. 2010-2013. 2017 3354-358. 2013-2015 J. 2017 655-659. 9. J. 2011 6539-546. 2018-06-15 2018-10-10 1210 4. J. 2017 47 5 D. 2014. 5. HIV /AIDS 12Wang NMei CLYan XD. Local linear estimation of spatially varying coefficient modelsan improvement on the J. geographically 2014 211 15-18. 6Huang BWu BBarry M. Geographically and temporally weighted regression for modeling spatio-temporal variation in house prices J. Int J Geogr Inf Sci2010 243 383-401. 7Yan NMei CL. A two-step local smoothing approach for exploring spatio-temporal patterns with application to the analysis of precipitation in the mainland of China during 1986 2005 J. Environ Ecol Stat2014 212 373-390. 342 225-228. 9. regression J. Accid Anal Prev2010 422 676-688. J. 2016 17. R 10817-821. 10. 2009 J. 2010 3 164-169 11. 165-170. weighted regression technique J. Environment & Planning A 2008 404 986-1005. 13. M. 201320-28. 14. M. 201249-80. 15Cai ZWFan JQLi RZ. Efficient estimation and inferences for varying-coefficient models J. J Am Stat Asso2000 95451 8. 888-902. J. 2017 16Alireza H Shalaby A S Persaud BN. Development of planning level transportation safety tools using geographically weighted poisson D. 2011. 2018-04-15 2018-06-01