纵向资料回归系数的新估计

本文研究纵向资料中回归系数的估计，借助于相依回归模型中的信息迭加法，给出了一个新估计，它改进了最小二乘估计．

Income Inequality in Mountain Areas: The Case of Agroforestry Farming Systems in Uluguru Mountains, Tanzania

Land degradation due to use of unsustainable agricultural practices has affected many communities in rural mountain areas rendering them to be more vulnerable to income poverty and inequality. In this case, agroforestry systems promise to offer great solutions as they can be developed in unfavourable conditions where other production systems would either rapidly degrade the land or otherwise would not be possible. However, little is known whether agroforestry can address issues of income inequality in mountain areas. Hence, we conducted a study to investigate the nature and determinants of income inequality in Uluguru Mountains, Tanzania. Specifically, we used the cross-sectional research design and we calculated the income percentile shares, Gini coefficients and the coefficient of variation (CV), to pinpoint the nature of income inequality in the study area. The determinants of income inequality were analysed using the step by step multiple linear model. The results of analysis suggested prevalence of income inequality. Crop production was the main source of income in the agroforestry systems of the study area. Earnings from crops and timber were decreasing income-inequality amongst smallholder farmers. Our disaggregated analysis showed that off-farm income was also decreasing income-inequality for farmers with farmlands located close to homestead, for female-headed households, for farmers who did not access extension services, and those who were members of community-based financial institutions. Estimated incomes increased with household assets, size of farmland, and age of household head. However, the same decreased with household size. We found gender disparity to be one of the key issues that need attention in formulating future policies to reduce inequality. We recommend promotion of livelihood diversification as well as the designing and implementation of tailor-made training and farm financing mechanism to help the less resource-endowed farmers in mountain areas to raise their economic portfolios and social status and combat income poverty and inequality.

Potential of roots and shoots of Napier grass for arresting soil erosion and runoff of mollisols soils of Himalayas

In this study, a soil filled Hydraulic Tilting Flume (HTF) was used as a test plot under simulated rainfallconditions. This flume was flled with mollisols soils (sandy loam in texture) collected from tarai regionof Himalayas. The effects of root and shoot characteristics of Napier grass in terms of leaf area index (LAI),shoot length (SL), number of leaves (NL), number of tillers (NT), shoot biomass (SB), root density (RD),root length (RL), root biomass (RB), and total biomass (TB) were investigated on runoff and sedimentoutflow at 90, 120 and 150 days after planting (DAP). Four simulated rainfall intensities namely 4.0, 6.5,8.3 and 9.4 cm/h over three land slopes of 1, 2 and 3% were selected. Runoff samples collected fromwhole plant plot and only root plot were analyzed for runoff and sediment outflow. Findings revealedthat Napier grasses were very effective to reduce runoff and sediment outflow and its efficacy increasedwith the extended growth stages. The reduction in runoff and sediment outflow at 90, 120 and 150 DAPwas obtained as 56% and 85%, 68% and 90%, and 74% and 96%, respectively, as compared to bare plotconditions. It was observed that the comparative contribution of shoots in runoff rate reduction washigher than the roots. On the contrary, the root part of the plant showed more contribution in sedimentrate reduction as compared to the shoot part. Step wise regression was attempted for the selection ofeffective input parameters to establish authentic runoff and sediment outflow models. Power form ofmultiple non-linear regression (MNLR) showed very satisfactory results for predicting runoff and sedimentoutflow with coefficient of determination (R^(2)) as 97.4% and 99.0%, respectively, root mean squareerror (RMSE) as 38.8 cc/m^(2)/min and 0.126 g/m^(2)/min, respectively, and coefficient of efficiency (CE) as93.9% and 96.7%, respectively, during testing period.

具有独立贡献的相依回归模型

考虑相依回归（ＳＵＲ）模型ｙｉ＝Ｘｉβｉ＿ｅｉ，ｉ＝１，２，…，ｍ，Ｅｅｉ＝０，ｉ，ｊ＝１；２，…ｍ，其中ｙｉ和ｅｉ是ｎ×１维随机向量，Ｘｉ是ｎ×ｐｉ已知矩阵，βｉ是ｐｉ×１维参数向量，∑＝（σｉｊ）ｍ×ｍ＞０．文中给出了两个概念：独立贡献和简洁估计．主要结果是如下五种叙述等价：（１）ＳＵＲ模型具有独立贡献；（２）βｉ的ＢＬＵＥ是简洁估计；（３）协方差改进估计是ＢＬＵＥＺ（４）βｉ的ＢＬＵＥ具有形式其中，ｊ＝１，２，…，ｍ；（５）ＰｋＮｉＮｊ＝０，ｉ≠ｊ，ｋ，Ｉ，ｊ＝１，２，…。