大气污染与肺癌关系的岭回归分析—徐州市1980—1991年大气污染…

采用岭回归模型拟合方法，分析徐州市１９８０－１９９１年大气污染与居民肺癌死亡率关系。建立肺癌死亡率与总悬浮颗粒物，降尘，氮氧化物和光化学氧化剂的最佳子集模型。利用岭迹图确定上述子集因素对肺癌效应的稳定。在ｋ＝０．３处，求得岭迹稳定的标准化变量表示的拟合方程：ｙ＝０．００１８Ｘ２＋０．０４７４Ｘ３＋０．０００３４２１Ｘ５＋０．３６１１３Ｘ６。方程的全相关系数为０．６８８０２８６，Ｍａｌｌｏｗｓ Ｃ…     

碘量法测定废水中硫化物值得注意的问题

从分析的观点出发，水和废水中的硫化物可分为３类：一是溶解的Ｈ２Ｓ和ＨＳ－，还有含在悬浮物中的酸性金属硫化物，在ｐＨ＞１０时，Ｓ２－的含量还不到溶解的硫化物的０．０５％，可忽略不计。硫化铜、硫化银几乎不溶，实际也忽略不计；二是未电离的硫化氢，实际也很少...     

低浓度气体检测管及其采样装置的研究

以微球硅胶、活性氧化铝和素陶瓷为截体，研制成ＣＯ、ＣＯ２、ＳＯ２、ＮＯ２、ＮＨ３和Ｈ２Ｓ６种低浓度有害气体检测管和与之配套使用的四通道自动采样器。可检测出环境空气中的上述有害气体。其最低检出限分别为：ＣＯ２．５ｍｇ·ｍ３；ＣＯ２０．０５％；ＳＯ２０．１５ｍｇ·ｍ３；ＮＯ２０．０８ｍｇ·ｍ３；ＮＨ３１．０ｍｇ·ｍ－３；Ｈ２Ｓ０．１ｍｇ·ｍ３，在现场应取得良好的效果。     

华枝睾吸虫病人治疗前后血清抗体的动态观察

用ＥＬＩＳＡ检测华支睾吸虫病人治疗前后血清特异性抗体ＩｇＧ，并进行动态观察，结果表明，ＥＬＩＳＡ的阳性符合率为９７％，抗体滴度在治疗后３、６和１２个月时不断下降。轻感组约６个月抗体降至正常；中感组１年左右；而重感组需１年半至２年。ＥＬＩＳＡ的阴转率随时间而增高。３、６和１２个月时间的阴转率，轻感组分别为３５％、８４．６％、９３．６％；中感组为１８％、５６．７％、８９．７％；重感组为０％、２５％５６     

中国汉族人群系统性红斑狼疮的遗传模式探讨

为探讨系统性红斑狼疮（ＳＬＥ）的遗传模式，应用Ｐｅｎｒｏｓｅ法、最大似然计方法和Ｆａｌｃｏｎ－ｅｒ法对２１５名ＳＬＥ病人及其家系进行了分离分析和遗传度计算，以探讨ＳＬＥ的可能遗传模式。研究结果表明，ＳＬＥ先证者家系一级亲属患病率为０．８５％，高于一般人群患病率（０．０３％）。应用Ｐｅｎｒｏｓｅ法计算，Ｓ／Ｐ接近１／Ｐ；用最大似然估计方法进行简单分离分析，其分离比θ＝０．０２９，经拟合优度χ２检验，χ２＝０．０００１，Ｐ＞０．０５；而经遗传度计算，ｈ２＝５６．７％，Ｐ＜０．０５。遗传模式分析提示，ＳＬＥ不符合单基因遗传模式，而可能是多因子疾病的遗传模式。     

护理人员关于艾滋病／HIV知识、态度、信念及行为的调查分析

对中日友好医院４６０名护理人员进行ＡＩＤＳ／ＨＩＶ知识、态度、信念及行为问卷（ＫＡＢＰ问卷）调查，发现知识平均分处于及格水平；对ＡＩＤＳ病原体及三大主要传播途径问题有较高答对率（８４．６％、９９．１％），但有２６．６～８２．３％的人错误地认为ＡＩＤＳ还可通过生活接触传播；对ＡＩＤＳ分期及临床表现问题，答对率仅为１４．２％；７０．９％及３９．２％的人对ＨＩＶ阳性及ＡＩＤＳ者存在恐惧及歧现心理。     

部队营区使用敌鼠钠盐和溴敌隆毒饵灭鼠效果研究

目的了解敌鼠钠盐（A区）和溴敌隆（B区）在海岛部队营区灭鼠效果。方法在现场采取回合式投药法。结果A试验区灭鼠前密度为：直观法36．62％，粉迹法43．57％；灭鼠后：直观法1，39％，粉迹法2．92％，分别下降96．20％和93．30％。B试验区灭鼠前密度为：直观法43．08％，粉迹法39．06％；灭鼠后：直观法1．61％，粉迹法2．38％，分别下降96．26％和93．91％。结论敌鼠钠盐和溴敌隆价格低廉，对鼠类适口性好．灭鼠效果比较显著。     

巴丹、易卫杀在大鼠胃匀浆中生物转化的研究

建立了胃匀浆中巴丹、易卫杀的ＧＣ－ＦＰＤ测定方法，并用此方法观察了巴丹、易卫杀在大鼠胃匀浆中的转化。添加巴丹的胃匀浆样品，经Ｎａ２Ｓ溶液转化生成沙蚕毒素，其回收率为１０３．１％［ｎ＝４，ＲＳＤ（％）＝０．７３］；添加易卫杀的胃匀浆样品，其回收率为１００．５％［ｎ＝４，ＲＳＤ（％）＝０．５４］。在大鼠胃匀浆中分别添加巴丹、易卫杀后，１ｍｉｎ时，分别有４９．７％和２８．８％的巴丹、易卫杀转化成沙蚕毒素；至１０ｍｉｎ时，加入的巴丹及易卫杀大部分转化生成沙蚕毒素。结果显示，巴丹和易卫杀在大鼠体内极易转化成沙蚕毒素。     

健康成人血清唾液酸含量及其相关因素的研究

测定年龄１７～７２岁（平均３４．７±１０．５）的５４２５名不同职业成人血清总唾液酸（Ｔｏｔｏｌｓｉａｌｉｃａｃｉｄ，ＴＳＡ）水平，平均含量为１．７４±０．３１ｍｍｏｌ／Ｌ，９５％可信区间１．７３～１．７５ｍｍｏｌ／Ｌ，同时发现ＴＳＡ含量与性别无关，但与年龄、从事交通警察职业、吸烟及饮酒有关（Ｐ＜０．０１）；多因素线性回归分析结果显示：（１）ＴＳＡ含量与年龄和从事交通警察职业有关；（２）男性和男性工人，ＴＳＡ含量除与年龄有关外．仍可见吸烟者有比不吸烟者增高的倾向，但不显著。而男性交警，ＴＳＡ含量均与年龄和日吸烟量有关，随两者的增加而增加．     

RSR法对水泥生产中粉尘危害程度的分级研究

采用ＲＳＲ对水泥生产中粉尘危害程度进行了分级研究。其结果表明：粉尘危害程度０级２个，占８．７％；Ⅰ级１２个，占５２．２％；Ⅱ级５个，占２１．７％；Ⅲ级４个，占１７．４％。同时采用Ｂａｒｔｌｅｔｔ检验，Ｘ２值为２．３３７４，Ｐ＞０．０５，各级别之间方差一致。经用ＡＮＯＶＡ、Ｎｅｗｍａｎ－Ｋｅｕｌｓｑ多重分析，Ｐ＜０．０１，各级别之间存在高显著性。据此，要重点突出Ⅱ、Ⅲ级作业场劳动条件改善和个人防护措施。     

多元岭回归方法在医院成本分析中的应用

目的：确定住院病人成本的影响因素,并对其进行定量测量。方法：采用ＳＰＳＳ,ＮｏＳＡ软件用最小二乘法建立住院病人总成本的多元线性回归模型,对其进行共线性诊断;与岭回归方法建立的回归模型进行了对比;在住院病人规模、利用等医院成本影响因素的相关分析;最后用岭回归方法建立了２３个变量的大型多元回归计量经济模型。结果：由于自变量间多元共线性的效应,使用最小二乘法建立的回归模型回归系数有较大的标准误,回归模型结果不稳定,用岭回归方法改善了多元共线性效应,降低了回归系数的标准误,使回归系数结果更为可靠。结论：确定了医院住院病人总成本影响因素,并提出了医院降低成本的途径。     

病例组合指数法在医院住院成本分析中的应用

目的：探讨住院病人成本的影响因素，并对其进行定量测量。方法：近照国际疾病ICD－9分类编码，采用病例组合指数法医院产出组成进行测量；彩和STAT，SPSS软件用最小二乘法，龄回归方法分别建立人均住院成本的回归模型并进行比较；对人均住院成本影响因素做相关分析；采用岭回归方法建立了引入病例组合指数等6个变量的人均住院成本的多元回归计量模型，结果：由于引入病例组合指数，考虑到了医院产出组成对人均住院成本的影响，使该成本分析更趋于合理；采用岭回归方法建立的回归模型相对于最小二乘法建立的回归模型而言，改善了自变量间多元共线性的效应，降低了回归系数的标准误，回归模型结果更稳定。结果：定量地测量了病例组合指数因素对人均住院成本的影响。     

低出生体重儿的影响因素研究

目的:应用描述性研究的方法,找出低体重儿的危险因素,为避免低体重儿的发生即优生优育提供可靠的理论依据。方法:符合纳入和排除标准的5842例确立为分析和研究的对象。结果:①通过低出生体重儿的影响因素单因素非条件Logistic回归分析发现:产次、孕次、孕周、产前空腹血糖、产前血压、季节、脐带长度有统计学意义(P<0.05),其中产次、孕次、孕周(37～40周)、产前血压是危险因素;秋季、脐带长度(30～70cm)是保护因素。②影响低出生体重儿的计量资料分析,通过成组t检验发现:产妇的产前体重、产妇的身高、胎盘重量有统计学意义,都对低出生体重儿有影响。③通过低体重儿多因素非条件Logistic回归结果发现:孕周、产前血压、秋季有统计学意义(P<0.05),其中孕周、秋季是保护因素,可避免低出生体重儿的发生;产前血压是危险因素,易导致低出生体重儿的发生。结论:孕妇的身高、体重、胎盘重量、孕次、产次、秋季是低出生体重儿的影响因素,其中孕周、秋季、产前空腹血糖、脐带长度是低出生体重儿的保护因素;产前血压是低出生体重儿的危险因素。     

胃癌危险因素研究中多因子共线性的logistic回归分析

目的 探索胃癌的危险因素,并探讨研究中存在的多因子共线性的处理方法。方法 采用病例对照方法,获得50名胃癌患者和50名对照的流行病学资料;PCR方法检测个体基因型;应用线性回归中的三个工具,对各研究因素进行共线性诊断：用主成分分析改进的方法,得出并解释最终的回归模型。结果 多因素logistic回归结果与单因素分析结果不一致,共线性诊断显示方差膨胀因子普遍较大,GSTM1基因型、肿瘤家族史等因素之间存在多因子共线性。应用主成分分析改进后的logistic回归模型拟合数据,不仅各回归系数的标准误均有减小,而且有更多的因素被选入模型。结论 遗传易感性和环境因素在胃癌的发生中共同起作用。对疾病危险因素进行logistic回归分析时,应首先进行原始变量的多重共线性诊断,并结合主成分分析得出更合理的回归模型。     

Collinear nutrients and the risk of colon cancer

The relationship between colon cancer risk and the relative contributions of fat and caloric intake are assessed. A lack of consensus exists regarding the role of each of these dietary factors in the development of colon cancer. This lack of agreement originates from the high correlations between the nutrients, as well as the manner in which researchers treat these dietary variables in their analyses. Four proposed methods are evaluated which attempt to address the collinearity problem in nutritional epidemiology: (1) exclude one or more collinear variables, (2) use the proportion of calories consumed attributable to each dietary component, (3) use a regression-adjustment approach to purge the collinearity correlated nutrients, and (4) ridge regression. Diagnostic tests are reported which assess the degree of collinearity on data collected for a case-control study of colon cancer conducted in Utah between 1979 and 1983. Using logistic regression analyses, we apply each of these methods to case-control data. We find that the risks associated with fat and caloric consumption are extremely sensitive to a priori analytic decisions made by epidemiologist about the underlying collinearity problem.     

Joint effects of nine polychlorinated biphenyl (PCB) congeners on breast cancer risk

BACKGROUND: Polychlorinated biphenyls (PCB) have been a major environmental health concern because of their wide distribution and persistence in the environment. Estimating joint effects of all congeners in a single analysis is complicated by correlation among exposure levels, and the resulting collinearity makes the results difficult to interpret. METHODS: Patients with breast-related surgery at Yale-New Haven Hospital were interviewed using a standardized questionnaire, and breast adipose tissue samples were analysed for nine PCB congeners (74, 118, 138, 153, 156, 170, 180, 183, 187). The study recruited 490 women (304 cases and 186 controls) between 1994 and 1997. Logistic ridge regression was used to analyse the instability caused by collinearity. RESULTS: Although total PCB did not appear to be associated with breast cancer risk, significant differences in effect were observed among the nine congeners. Logistic ridge regression demonstrated a protective effect on breast cancer risk for a potentially anti-oestrogenic and dioxin-like congener, 156, while two phenobarbital, CYP1A and CYP2B inducers had an adverse effect, 180 and 183. This analysis also suggested that a protective effect for another phenobarbital congener, 153, was largely explained by instability caused by collinearity. CONCLUSIONS: These results indicate that studies of PCB congeners and health require an in-depth statistical analysis in order to better understand the complex issues related to their collinearity.     

广东4月龄婴儿生长影响因素的多元回归分析

目的：对广东省７７７名城乡４月龄健康婴儿的生长与２８个环境和遗传因素的关系进行调查。方法：以ＷＨＯ推荐的儿童身高和体重标准作参考，采用美国疾病控制中心的Ａｎｔｈｒｏ软件计算年龄别身高Ｚ分（ＨＡＺ），年龄别体重Ｚ分（ＷＡＺ）和身高别体重Ｚ分（ＷＨＺ），进行多元回归分析。结果：城乡地区、婴儿出生体重、父亲年龄、父母亲身高和学历显著影响婴儿的ＨＡＺ（Ｐ＜０．０１）。婴儿出生体重、城乡地区、母亲身高、父亲籍贯、曾患过病显著影响婴儿的ＷＡＺ（Ｐ＜０．０１）。城乡地区、婴儿出生身长和体重、家庭收入、因病住过医院显著影响婴儿的ＷＨＺ（Ｐ＜０．０１）。结论：环境和遗传因素综合影响广东婴儿的生长。提高家长的文化水平，普及营养知识，加强教育是改善婴儿生长的重要措施，尤其是在农村地区更具实际意义     

Collinearity diagnosis for a relative risk regression analysis: an application to assessment of diet-cancer relationship in epidemiological studies.

In epidemiologic studies, two forms of collinear relationships between the intake of major nutrients, high correlations, and the relative homogeneity of the diet, can yield unstable and not easily interpreted regression estimates for the effect of diet on disease risk. This paper presents tools for assessing the magnitude and source of the corresponding collinear relationships among the estimated coefficients for relative risk regression models. I show how to extend three tools (condition indices, variance decomposition proportions, and standard inflation factors) for diagnosing collinearity in standard regression models to likelihood and partial likelihood estimation for logistic and proportional hazards models. This extension is based on the analogue role of the information matrix in such analyses and the cross-product matrix in the standard linear model. I apply the methodology to relative risk models that relate crude intakes (on the log scale) and nutrient densities to breast cancer cases in the NHANES-I follow-up study. The three diagnostic tools provide complementary evidence of the existence of a strong collinearity in all models that is due largely to homogeneity of the population with respect to our risk scale for the crude intakes. The analysis suggests that the non-significant relative risks for the crude intakes in these models may be due to their involvement in collinear relationships, while the nonsignificant relative risks for the nutrient densities are far less affected by multicollinearity.     

大气污染与肺癌关系的岭回归分析——徐州市1980～1991年大气污染与肺癌断面研究

采用岭回归模型拟合方法,分析徐州市1980～1991年大气污染与居民肺癌死亡率关系。建立肺癌死亡率与总悬浮颗粒物、降尘,氢氧化物和光化学氧化剂的最佳子集模型。利用岭迹图确定上述子集因素对肺癌效应的稳定性。在k=0.3处,求得岭迹稳定的标准化变量表示的拟合方程:y=0.0018_(X2)~-+0.0474_(X3)~-+0.0003421_(X5)~-+0.36113_(X6)~-。方程的全相关系数为0.680286,Mallows CP统计量为8.62(P<0.01)。大气污染物总悬浮颗粒物、降尘、氮氧化物和光化学氧化剂与居民肺癌死亡率呈正相关。其中总悬浮颗粒物作为肺癌高发危险因素意义最大。     

Childhood correlates of blood lead levels in Mumbai and Delhi

BACKGROUND: Lead exposure has previously been associated with intellectual impairment in children in a number of international studies. In India, it has been reported that nearly half of the children have elevated blood lead levels (BLLs). However, little is known about risk factors for these elevated BLLs. METHODS: We conducted a retrospective cross-sectional analysis of data from the Indian National Family Health Survey, a population-based study conducted in 1998-1999. We assessed potential correlates of BLLs in 1,081 children who were < 3 years of age and living in Mumbai or Delhi, India. We examined factors such as age, sex, religion, caste, mother's education, standard of living, breast-feeding, and weight/height percentile. RESULTS: Most children (76%) had BLLs between 5 and 20 microg/dL. Age, standard of living, weight/height percentile, and total number of children ever born to the mother were significantly associated with BLLs (log transformed) in multivariate regression models. Compared with children < or = 3 months of age, children 4-11 and 12-23 month of age had 84 and 146% higher BLLs, respectively (p < 0.001). A low standard of living correlated with a 32.3% increase in BLLs (p = 0.02). Children greater than the 95th percentile for their weight/height had 31% (p = 0.03) higher BLLs compared with those who were below the 5th percentile for their weight/height. CONCLUSIONS: Our study found various factors correlated with elevated BLLs in children. The correlation between greater than the 95th percentile weight/height and higher BLL may reflect an impact of lead exposure on body habitus. Our study may help in targeting susceptible populations and identifying correctable factors for elevated BLLs in Mumbai and Delhi.