Zambian Financial Diaries Project 2015 - Zambia

Abstract
---------------------------

In 2014, Financial Sector Deepening Zambia (FSDZ) commissioned Microfinance Opportunities (MFO) to implement the Zambia Financial Diaries Project (FDP). The intention of this was to understand how low-income people in Zambia managed their cash flows and how they utilised transfers, savings, loans and insurance to do so.

Geographic coverage
---------------------------

Four provinces (Lusaka, Copperbelt, Eastern, Western) in districts with towns that could accommodate fieldworkers for a year that was withing one hour of all field sites.

Universe
---------------------------

The survey universe of the ZFDP 2015 is slightly unusual because of logistical constraints imposed on the sampling frame. These constraints meant that only certain districts from Copperbelt, Eastern, Lusaka, and Western Provinces could be selected. Districts within those provinces could then only be selected if there was a town with sufficient services to support a fieldwork team for a year that was within an hour and a half of all field sites. Enumerator areas were then drawn from those selected districts and households within those EAs were then selected using a random walk. The survey, then, covered all de jure household members within households in those enumerator areas in Zambia.

Kind of data
---------------------------

Event/transaction data [evn]

Sampling procedure
---------------------------

The sampling frame for the FDP was developed under certain logistical constraints. The priority was to develop a sample that, while not statistically representative, was still reflective of the varying levels of financial service access and livelihoods of low-income Zambians. Four provinces were selected — Copperbelt, Eastern, Lusaka, and Western Provinces — that contained a diverse mix of urban and rural respondents, various levels of financial access, and a preponderance of individuals involved in informal businesses (Lusaka Province), the mining sector (Copperbelt Province), or farming (Eastern and Western Provinces).''

From those provinces districts were selected based on further conditions. Chief amongst these was that any selected district needed to have a town with sufficient services to support a fieldwork team for a year that was within an hour and a half of all field sites. Once those constraints were satisfied standard enumerator areas (as drawn from the master sample developed in the Zambian 2010 Census) were randomly selected from the pruned set of districts in the provinces mentioned above. Households were then selected within those enumerator areas using a random walk. Respondents within households were chosen using a Kish grid as per and screened for eligibility with an enrolment questionnaire. This questionnaire had certain requirements that needed to be fulfilled for the respondent to be included in the sample. For example, if the respondent was going to be away for the majority of the year the interview was terminated and the respondent was excluded.

Mode of data collection
---------------------------

Face-to-face [f2f]

Research instrument
---------------------------

The financial diaries paper instrument: this data sheet was filled out weekly and then checked with respondents by enumerators at the end of each week for accuracy
Enrolment questionnaire: the enrolment questionnaire was used as a screen at the beginning of the data collection period
Cross-sectional survey questionnaire: the cross-sectional survey questionnaire was administered towards the end of the year of observation

Cleaning operations
---------------------------

The data was anonymised by DataFirst, encoded and cleaned. Some duplicates were removed.

Data appraisal
---------------------------

Transactions data:
Date start and date end variables are fuzzy (there are not always seven days in a week, the weeks don't always begin on the same day) which is most likely attributable to data capturing errors on the part of the fieldworker. Most of the week lengths, when evaluated, come to seven days (as expected) but not all. For the user the more reliable measure of the week of observation is the transact_week variable.

Roster data:
The wards variable seems to be imperfectly captured as many do not match lists of recorded Zambian electoral wards. Efforts have been made to make the entries more readable but are imperfect perfect. The phone access variable is also bit misleading. There are 58 missing values for the variable roster_phoneaccess_or_own which seem to have a corresponding follow-up response with variable roster_accessph_only. It is unclear what the roster_accessph_only} variable is meant to represent because it is not on the enrolment questionnaire.

Cross-section data:
There are two sets of duplicates in terms of RespID in the cross-sectional data file. Investigating further it was discovered that one set of duplicates is the apparent result of the same fieldworker visiting the same household twice (the second visit occurring eight days after the first). This policy adopted here was to choose the latest observed row in the data. Notably, there were a few variables that had different values between the two observations. These are easily attributable to actual dynamics within the household. There were no substantive differences between static household characteristics.

The other set of duplicates was slightly more complicated. It involved the apparent incorrect assignment of the RespID code (that is, the RespID code was assigned correctly for one entry and incorrectly for the other). Fortunately, it was possible to check the correct RespID using the other data files. It turned out that the incorrectly assigned entry was meant to be represented by another code entirely. This is most likely a data capturing error. Correcting the incorrectly coded RespID yielded another set of two duplicates. The correctly coded entry of these two duplicates was the one used in the final file.

摘要
---------------------------
2014年，赞比亚金融深化部门（FSDZ）委托微型金融机会（MFO）实施赞比亚金融日记项目（FDP）。此举旨在探究赞比亚低收入人群如何管理现金流，以及他们如何利用转账、储蓄、贷款和保险来实现这一目标。
地理覆盖范围
---------------------------
四个省份（卢萨卡、铜带、东部、西部）的城镇，这些城镇能够容纳现场工作人员一年，且所有现场地点均在半小时车程之内。
总体
---------------------------
2015年ZFDP的调查总体因抽样框架的物流限制而略显特殊。这些限制意味着只能选择铜带、东部、卢萨卡和西部省的某些地区。在这些省份内，只有当存在一个城镇拥有足够的服务以支持一个现场工作团队一年，且所有现场地点均在半小时车程之内时，才能选择该省份内的地区。然后从这些选定的地区中抽取调查员区域，并在这些调查员区域内的家庭中使用随机游走法选择家庭。
数据类型
---------------------------
事件/交易数据 [evn]
抽样程序
---------------------------
FDP的抽样框架在特定的物流限制下制定。优先考虑制定一个样本，虽然该样本不具有统计学意义，但仍能反映赞比亚低收入人群在金融服务获取和生活水平方面的差异。选择了四个省份——铜带、东部、卢萨卡和西部省——这些省份包含了多样化的城市和农村受访者，各种水平的金融服务获取，以及大量从事非正式商业（卢萨卡省）、采矿行业（铜带省）或农业（东部和西部省）的个人。
从这些省份中根据进一步的条件选择地区。其中最重要的条件是任何选定的地区都需要有一个城镇，该城镇拥有足够的服务以支持一个现场工作团队一年，且所有现场地点均在半小时车程之内。一旦满足这些条件，就从上述省份中随机选择标准调查员区域（如从赞比亚2010年人口普查中开发的母样本中抽取）。然后在这些调查员区域内使用随机游走法选择家庭。家庭内的受访者使用Kish网格选择，并使用登记问卷进行资格筛选。该问卷有某些要求需要满足，以便受访者被纳入样本。例如，如果受访者将在全年的大部分时间外出，则终止访谈，并将受访者排除在外。
数据收集方式
---------------------------
面对面 [f2f]
研究工具
---------------------------
金融日记论文工具：此数据表每周填写一次，并在每周结束时由调查员与受访者核对以确认准确性。
登记问卷：登记问卷在数据收集期开始时用作筛选。
横断面调查问卷：在观察年度结束时进行横断面调查问卷。
数据清洗操作
---------------------------
数据由DataFirst匿名化、编码和清洗。删除了一些重复项。
数据评估
---------------------------
交易数据：日期开始和日期结束变量模糊（一周中不总是有七天，周的开始日期也不总是相同），这很可能是由于现场工作人员在数据捕获方面的错误。大多数周长度在评估时都达到七天（如预期），但并非总是如此。对于用户来说，更可靠的观察周度量标准是transact_week变量。
名单数据：wards变量似乎被错误地捕获，因为许多与记录的赞比亚选区名单不匹配。已尽力使条目更易于阅读，但并不完美。phone access变量也有些误导。roster_phoneaccess_or_own变量有58个缺失值，似乎与变量roster_accessph_only的后续响应相对应。roster_accessph_only变量代表什么尚不清楚，因为它不在登记问卷中。
横断面数据：在横断面数据文件中，关于RespID存在两组重复项。进一步调查后发现，其中一组重复项是同一现场工作人员两次访问同一家庭的明显结果（第二次访问在第一次之后八天）。在此采取的政策是选择数据中的最新观察行。值得注意的是，有一些变量在两次观察之间有不同的值。这些变化很容易归因于家庭内部的实际情况。在静态家庭特征之间没有实质性差异。
另一组重复项稍微复杂一些。它涉及RespID代码的错误分配（即，对于一项条目，RespID代码被正确分配，而对于另一项条目，则被错误分配）。幸运的是，可以使用其他数据文件检查正确的RespID。结果是，错误分配的条目本应表示为另一个代码。这很可能是数据捕获错误。纠正错误编码的RespID产生了另一组两个重复项。这两个重复项中正确编码的条目被用于最终文件。