{"id":14,"date":"2018-02-08T20:36:57","date_gmt":"2018-02-09T03:36:57","guid":{"rendered":"https:\/\/blogs.ubc.ca\/gisinresearch\/?page_id=14"},"modified":"2018-04-17T19:51:43","modified_gmt":"2018-04-18T02:51:43","slug":"labs","status":"publish","type":"page","link":"https:\/\/blogs.ubc.ca\/gisinresearch\/labs\/","title":{"rendered":"Labs"},"content":{"rendered":"

Lab 1:<\/strong> Spatial stats using Modelbuilder tutorial<\/p>\n

Lab 1 involved an introduction to model building. Data was used from the CDC Wonder Data in order to create animated hotspot maps of hearth disease in the southern united states by county. A model was formed which allowed for18 individual feature classes to be created which were then animated. This was then produced into the final product which can be seen below.<\/p>\n

Lab 1-Map Animation<\/a><\/p>\n

\"\"<\/p>\n

Lab 2<\/strong>: Exploring Fragstats<\/p>\n

In lab 2 we envisioned ourselves as environmental consultants hired by the city council of Edmonton in order to produce a report demonstrating changes in the landscape metrics of the surrounding area. The goal of this lab was to observe how landscape change had occurred in Alberta between 1966 and 1976. Moreover, additional emphasis was placed on landscape metrics. In order to accomplish this goal we implored the use of Fragstats (a nifty tool which allows for complex statistical analysis of TIF files). We used fragstats in order to calculate a series of landscape metrics such as edge depth,area,percentage of landscape and shape index. In total 14 different landscape and class metrics were used. From there we used these results in order to create a transition matrix to show how the landscape changed. This involved the creation of rasters and a series of joins and relates.Lastly we created a pivot table in order to show in a simple to read way the results of the landscape change. All of these results can be viewed below.<\/p>\n

Land Use in Edmonton Alberta- Report<\/a><\/p>\n

Land Use in Edmonton Alberta-Map<\/a><\/p>\n

Lab 3<\/strong>: Introduction to Geographically Weighted Regression.<\/p>\n

Lab 3 dealt with issues related to geographically weighted regression. Within Vancouver variables such as language score, gender, and income were examined for their impact regarding childhood development.\u00a0 Furthermore, these variables were then examined spatially across the city as to observe possible patterns.<\/p>\n

Below is a summary of GWR and two maps from the final results which depict childhood language score and neighborhood income values. Geographically weighted regression (GWR) is a class of linear regression which is applied in order to examine local relationships. The most notable function of GWR is the modeling of the relationship between dependent and explanatory variables based on location. Unlike global models, a local model such as GWR is able to apply the explanatory and dependent variables on a case by case basis based upon locale. As such, GWR is able to model how variation occurs across an area of study. GWR as a form of spatial regression has many similarities to ordinary least squares models (OLS). In simplest terms OLS models are used to predict the unknown values in linear regression models.\u00a0 GWR requires two variables, respectively being the dependent and the explanatory variable. Explanatory variables though similar to independent variables are distinct due to outside variables effecting them.\u00a0 In other terms, explanatory variables are not completely independent from the effects of other variables, though they are not to be mistaken for a dependent variable. Additionally, dependent variables are those which respond to the effects of the explanatory variable.\u00a0 An example of this relationship would be looking at how the effect of income by neighborhood across an entire city effects crime. Returning to the previously mentioned OLS, a GWR is able to model a separate OLS for every point (or location) being examined.\u00a0 Another essential component of GWR is bandwidth. Bandwidth refers to the parameters related to kernel type, distance and number of neighbors. Important to note is that when the number of neighbors\u2019 parameter exceeds 1000, then only the nearest 1000 are incorporated in each equation (\u201cGeographically Weighted Regression,\u201d2016). Furthermore, GWR is restricted when applied to small data sets and when used with multipoint data. (\u201cGeographically Weighted Regression,\u201d2016) Due to the regression technique it is also important to consider the data being used. When using GWR it is crucial to avoid binary data that is data with only two possible outcomes such as 0 or 1. In turn GWR is only suitable for data which includes a variety of numeric values.<\/p>\n

Vancouver Neighbourhood Income Values-Standard Deviation<\/a><\/p>\n

Childhood Language Score-Standard Deviation<\/a><\/p>\n

Lab 4<\/strong>: Introduction to CrimeStat<\/p>\n

Lab four was a return to crime statistics which had been examined before in GEOB 370. Approaches taken in this lab extended on prior knowledge and were based in more advanced techniques. Moreover, the program Crime Stat was introduced in order to measure the statistical importance of results. Analysis revolved around nearest neighbor, fuzzy mode, hierarchical clustering, correlograms and risk adjusted models. Additionally, a knox index was run in order to test of temporal importance and to see if any patterns occurred throughout space and time. Two kernel density maps were as well produced which are attached below along with an example of the knox index.<\/p>\n

Primal Kernel Zoomed<\/a><\/p>\n

Dual Kernel Zoomed<\/a><\/p>\n

 <\/p>\n

 <\/p>\n

\"\"<\/a><\/p>\n

\"\"<\/a><\/p>\n

 <\/p>\n

Knox Index: Interaction of Space and Time\r\n\r\n\u00a0\u00a0 Sample size ...........:\u00a0 2152\r\n\r\n\u00a0\u00a0\u00a0 Measurement type ......:\u00a0 Direct\r\n\r\n\u00a0\u00a0\u00a0 Input units .... ......:\u00a0 Meters\r\n\r\n\u00a0\u00a0\u00a0 Time units ............:\u00a0 Hours\r\n\r\n\u00a0\u00a0\u00a0 Simulation runs .......:\u00a0 19\r\n\r\n\u00a0\u00a0\u00a0 Start time ............:\u00a0 09:46:37 AM, 03\/09\/2018\r\n\r\n\r\n\r\n\u00a0\u00a0\u00a0 \"Close\" time ........:\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 6.00000 hours\r\n\r\n\u00a0\u00a0\u00a0 \"Close\" distance ....:\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 5000.00000 m\r\n\r\n\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 | Close in space(1)\u00a0 | Not close in space(0) |\r\n\r\n\u00a0\u00a0\u00a0 ---------------------+--------------------+-----------------------+-----------------\r\n\r\n\u00a0\u00a0\u00a0 Close in time(1)\u00a0\u00a0\u00a0\u00a0 |\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 456592 |\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \u00a0\u00a0\u00a01421931 |\u00a0\u00a0\u00a0\u00a0\u00a0 1878523\r\n\r\n\u00a0\u00a0\u00a0 Not close in time(0) |\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 111845 |\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 324108 |\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 435953\r\n\r\n\u00a0\u00a0\u00a0 ---------------------+--------------------+-----------------------+-----------------\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 |\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 568437 |\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a01746039 |\u00a0\u00a0\u00a0\u00a0\u00a0 2314476\r\n\r\n\r\n\r\n\u00a0\u00a0\u00a0 Expected:\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 | Close in space(1)\u00a0 | Not close in space(0) |\r\n\r\n\u00a0\u00a0\u00a0 ---------------------+--------------------+-----------------------+-----------------\r\n\r\n\u00a0\u00a0\u00a0 Close in time(1)\u00a0\u00a0\u00a0\u00a0 |\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 461366.62404 |\u00a0\u00a0\u00a0 \u00a0\u00a0\u00a0\u00a0\u00a01417156.37596 | 1878523.00000\r\n\r\n\u00a0\u00a0\u00a0 Not close in time(0) |\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 107070.37596 |\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 328882.62404 | 435953.00000\r\n\r\n\u00a0\u00a0\u00a0 ---------------------+--------------------+-----------------------+-----------------\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 |\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 568437.00000 |\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 1746039.00000 | 2314476.00000\r\n\r\n\r\n\r\n\u00a0\u00a0\u00a0 Chi-square ..........:\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 347.73143\r\n\r\n\u00a0\u00a0\u00a0 P value of Chi-square:\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 0.00010\r\n\r\n\r\n\r\n\u00a0\u00a0\u00a0 End time ..............:\u00a0 09:46:38 AM, 03\/09\/2018\r\n\r\n\r\n\r\n\u00a0\u00a0\u00a0 Distribution of simulated index (percentile):\r\n\r\n\u00a0\u00a0\u00a0 Percentile\u00a0\u00a0\u00a0 \u00a0\u00a0Chi-square\r\n\r\n\u00a0\u00a0\u00a0 ---------- ---------------\r\n\r\n\u00a0\u00a0\u00a0\u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0min\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 0.00007\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 0.5\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 0.00007\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 1.0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 0.00007\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 2.5\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 0.00007\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 5.0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 0.00007\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 10.0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 0.01274\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 90.0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 1.79751\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 95.0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 2.42568\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 97.5\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 2.42568\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 99.0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 2.42568\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 99.5\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 2.42568\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 max\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 2.42568<\/pre>\n
 <\/p>\n","protected":false},"excerpt":{"rendered":"
Lab 1: Spatial stats using Modelbuilder tutorial Lab 1 involved an introduction to model building. Data was used from the…<\/p>\n","protected":false},"author":34610,"featured_media":0,"parent":0,"menu_order":2,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-14","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/blogs.ubc.ca\/gisinresearch\/wp-json\/wp\/v2\/pages\/14","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.ubc.ca\/gisinresearch\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/blogs.ubc.ca\/gisinresearch\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.ubc.ca\/gisinresearch\/wp-json\/wp\/v2\/users\/34610"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.ubc.ca\/gisinresearch\/wp-json\/wp\/v2\/comments?post=14"}],"version-history":[{"count":16,"href":"https:\/\/blogs.ubc.ca\/gisinresearch\/wp-json\/wp\/v2\/pages\/14\/revisions"}],"predecessor-version":[{"id":92,"href":"https:\/\/blogs.ubc.ca\/gisinresearch\/wp-json\/wp\/v2\/pages\/14\/revisions\/92"}],"wp:attachment":[{"href":"https:\/\/blogs.ubc.ca\/gisinresearch\/wp-json\/wp\/v2\/media?parent=14"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}