UCINET Visualization and Quantitative Analysis Tutorial
Session 1 Network Visualization Session 2 Quantitative Techniques Page 2
An Overview of UCINET (6.437) Page 3
Transferring Data from Excel (From Tab ConCoInfo) Page 4
Transferring Excel Matrix Data into UCINET Button To Open Spreadsheet Editor Step 1. Copy data from Excel Step 2. Open spreadsheet editor in UCINET Step 3. Paste into spreadsheet editor in UCINET Step 4. Save as info Page 5
Transferring Attribute Data into UCINET (From Tab: ConcoAttr) Button To Open Spreadsheet Editor Step 1. Copy data from Excel Step 2. Open spreadsheet editor in UCINET Step 3. Paste into spreadsheet editor in UCINET Step 4. Save as attrib Page 6
Opening NetDraw For Visualization Step 1. Click The NetDraw Button To Open Page 7
Opening Data in NetDraw Step 1. File > Open > Ucinet dataset > Network Step 2. Choose network dataset (info.##h) Page 8
Opening Data in NetDraw Step 1. Click - open folder icon Step 2. Choose network dataset (info.##h), then click OK. Page 9
Initial Visual in NetDraw Page 10
Dichotomizing in NetDraw Step 1. Click Relations Tab Step 2. Select Greater Than Operator Step 3. Insert The Number 3 Or Use The Plus Button To Get To 3 Page 11
Using Drawing Algorithm in NetDraw Step 1. Choose = option on tool bar Page 12
Using Attribute Data in NetDraw Step 1. Click - open folder icon Step 2. Choose attribute dataset (attrib.##h), then click Open. Step 3. Click OK On Matching Box And X Out Of Attribute Editor. Step 4. May need to re-set tie strength levels and click lightning bolt again. Page 13
Choosing Color Attribute in NetDraw Step 1. Select Nodes Step 2. Select Region Step 3. Place a check mark in the color box Page 14
Selecting Nodes in NetDraw Step 1. Default is all groups selected. To remove one group, e.g. group 2, remove check from box Page 15
Selecting Egonets in NetDraw Step 1. Select Ego Button On ToolBar Step 2. Ensure Geodesic distance FROM/TO ego is <= 1 Step 3. Select BM Step 4. De-Select AR Step 5. Select All Button and X Out Of Ego Net Viewer Page 16
Changing the Size of Nodes in NetDraw Step 1. Properties > Nodes > Symbols > Size > Attribute-based Step 2. Select gender and make minimum node size 8 and maximum 16 Page 17
Changing the Shape of Nodes in NetDraw Step 1. Properties > Nodes > Symbols > Shape > Attribute-based Step 2. Select attribute, e.g. hierarchy Page 18
Changing the Size of Lines in NetDraw Step 1. Properties > Lines > Size > Tie strength Step 2. Select minimum =1 and maximum = 5 Page 19
Changing the Color of Lines in NetDraw Step 1. Properties > Lines > Color > Node attribute-based Step 2. Select Region attribute, then choose within, between or both Step 3. Select Properties > Lines > Color > General to return to black lines Page 20
Deleting Isolates in NetDraw Step 1. Select Iso option on the toolbar Step 2. Select ~Nodes button to bring back removed nodes (click on Okay in pop-up box) Page 21
Resizing and Re-centering in NetDraw Step 1. Layout > Move/Rotate Step 2. Select Center option Page 22
Saving Pictures in NetDraw Step 1. File > Save diagram as > Jpeg Step 2. Choose file name, e.g. Example Jpeg File For Powerpoint Page 23
Session 1 Network Visualization Session 2 Quantitative Techniques Page 24
Dichotomizing Valued Data The survey data that we collect is usually valued data. Although we can use valued data in UCINET we prefer to take different cuts of the data. For example, we may want to examine the data where people only responded strongly agree to a question. To do this we dichotomize the data i.e. convert it to zeros and ones where one means strongly agree and zero means any other response. Step 1. Transform > Dichotomize Step 2. Choose input dataset (info.##h) Step 3. Choose cut-off op. and value (e.g. GE and 4) Step 4. Specify output data set (Info_GE_4) Page 25
Measures of Network Connection Network Connection Centrality Cross Boundary Analysis Density Shows overall level of connection within a network. We can also look at ties within and between groups. Distance Shows average distance for people to get to all other people. Shorter distances mean faster, more certain, more accurate transmission / sharing. Page 26
Density Network Connection Centrality Cross Boundary Analysis Low Density (25%) Avg. Dist. = 2.27 High Density (39%) Avg. Dist. = 1.76 Number of ties, expressed as percentage of the number of pairs Dense networks have more face-to-face relationships Page 27
Quantitative Analysis: Density Network Connection Centrality Cross Boundary Analysis Density of this network is 8%. Step 1. Network > Cohesion > Density > Density Overall Step 2. Input dataset Info_GE_4 Page 28
Distance Network Connection Centrality Cross Boundary Analysis Short average distance Long average distance Average number of steps to reach all network participants Lower scores reflect a group better able to leverage knowledge Page 29
Quantitative Analysis: Distance Network Connection Centrality Cross Boundary Analysis Average Distance is 3.545 Step 1. Network > Cohesion > Geodesic Distance (old) Step 2. Input dataset Info_GE_4 Page 30
Measures of Centrality Network Connection Centrality Cross Boundary Analysis Degree Centrality: How well connected each individual is. Betweenness Centrality: Extent to which individuals lie along short paths. Closeness Centrality: How far a person is from all others in the network. Page 31
Quantitative Analysis: Degree Centrality Network Connection Centrality Cross Boundary Analysis Step 1. Network > Centrality and Power > Degree Page 32
Quantitative Analysis: Degree Centrality Network Connection Centrality Cross Boundary Analysis Step 1. Input dataset Info_GE_4 Step 2. Choose whether to treat data as symmetric. I almost always select no. If you choose no it will calculate separate figures for the people you go to and the people that come to you. Page 33
Quantitative Analysis: Degree Centrality Network Connection Centrality Cross Boundary Analysis In-degree for HA is 7 Page 34
uantitative Analysis: Degree Centrality Network Connection Centrality Cross Boundary Analysis Average in-degree is 3.652 In-degree Network Centralization is 12.424% Page 35
Opportunities exist to re-distribute relational load. Focus on ways to delayer those in the top right quadrant (info access, decision rights, role) while also better leveraging those in the bottom quadrant From whom do you typically seek work-related information? 90.00 # People Receives Information From 80.00 70.00 60.00 50.00 40.00 High Info Sources 272 90 255 171 26 279 163 78 170 117 295 263 6 30.00 119 201 239 141 248177 160 5161 273 54299 266 8 300 178 19722 233 118 9 212 16 82 52 229 211 55 203 20.00 135 308 174 113 184 158 199 7 249 268 3 147 140 294 270 133 28 303 81 175 243 169 95 127 224 69 241 30 286 245189 126 191 202 105 45 265 230 14 198 217 35 132 234 39 3874 5 220 301 240 59 36 221 24 296 143 164 100 315 231 183 10.00 75 144 87 19 29 155 48 27 32 205 302 195 292 216 256 99 60 242 101 269 57 153 23 102 148176 210 92 131 56 185 91 264 213 258 1 317 257 89 237 47192 44 167 246 15 244 222 188 2316 106 209 312 149 223 206 120 43 280 34 247 139 314 116 281 193 67 111 50 276 311 145 136 0.00 93 275 278 53 0.00 10.00 20.00 30.00 40.00 50.00 60.00 70.00 80.00 90.00 # People Each Person Seeks Information From 173 37 187 Integrators 196 High Info Seekers 112 Page 36
ScatterPlot Step 1: Save Text File Network Connection Centrality Cross Boundary Analysis Step 1. Generate Degree Calc. Network > Centrality > Degree > Info_GE_4 Step 2. File > Save As > Degree Output Text Page 37
ScatterPlot Step 2: Save Text File Network Connection Centrality Cross Boundary Analysis Step 1. Open Excel Step 2. File > Open > Txt > Degree Output Text Step 3. Step 1 (In Text Import Wizard) > Next Step 4. Step 2 (Pictured) > Insert De-Limiter Between Names and Number. Step 5. Step 3 Finish Page 38
ScatterPlot Step 3: Insert Columns Back In UCINET Network Connection Centrality Cross Boundary Analysis Step 1. Open UCINET Spreadsheet Editor Step 2. Cut And Paste Relevant Headers And In/Out Degree Numbers Step 3. Save As A UCINET file titled, Scatterplot Page 39
ScatterPlot Step 4: Create Plot In UCINET Network Connection Centrality Cross Boundary Analysis Step 1. Tools > Scatterplot Step 2. Click on open file folder to open Scatterplot Step 3. Play with options (e.g., uniform axis) Page 40
Cross-boundary Analysis Network Connection Centrality Cross Boundary Analysis Density across boundaries: How connected are groups within themselves and with other pre-defined groups. This view can be used for different boundaries. We have used the following in our research: Function or other designation of skill or knowledge. Geographic location (even if only different floors). Hierarchical level. Time in organization or time in department. Personality traits. Gender (interesting though may be inflammatory). Brokers: Which individuals are the links between other groups. Brokers can be beneficial conduits of information but they can also hold up the flow of information. Page 41
Cross-boundary Analysis Network Connection Centrality Cross Boundary Analysis Information Network: Density as related to practice Please indicate how often you have turned to this person for information or advice on workrelated topics in the past three months (response of often or very often). Healthcare Government IT Oil & Gas Pharmaceuticals Industrial Healthcare 17% 0% 0% 7% 38% 0% Government 0% 17% 0% 0% 0% 10% IT 0% 0% 0% 0% 0% 6% Oil & Gas 4% 0% 0% 19% 3% 8% Pharmaceuticals 35% 0% 0% 1% 49% 0% Industrial 1% 9% 9% 12% 1% 8% Page 42
Density Across Practice Network Connection Centrality Cross Boundary Analysis Tip: Col 3 is the column that includes the practice attribute. You can select different columns for different attributes MAKE SURE TO USE THE DENSITY / AVERAGE VALUE WITHIN BLOCKS Step 1. Network > Cohesion > Density > Old Density Procedure Step 2. Input dataset Info_GE_4 Step 3. Click on to select Attrib file for Row Partitioning. Arrow to end to select col 3. Step 4. Column Partitioning will automatically be filled in with the same text as the Row Partition. Step 5. Scroll all the way down in output file for density matrix. Page 43
Broker Categories Network Connection Centrality Cross Boundary Analysis Coordinator - This person connects people within their group. A Ego B Gatekeeper - This person is a buffer between their own group and outsiders. Influential in information entering the group. A Ego B Representative - This person conveys information from their Ego group to outsiders. Influential in information sharing. A B Page 44
Quantitative Analysis: Broker Metrics Network Connection Centrality Cross Boundary Analysis Tip: Col 2 is the column that includes the gender attribute. You can select different columns for different attributes Step 1. Network > Ego networks > G&F Brokerage Step 2. Input dataset Info_GE_4 Step 3. Partition vector attrib col 2 Page 45
Additional Quantitative Analysis Symmetrization & Verification Combining Networks QAP Correlation and Regression Page 46
Symmetrizing Data Bill says he communicated with John last week, but John doesn t mention communicating with Bill Three options Bill John take the conservative option, and put no tie between John and Bill (minimum) take the liberal option, and put a tie between John and Bill (maximum) take the average, assigning a tie strength of 0.5 for the relationship between John and Bill (average) Page 47
Symmetrizing Data (Continued) Tip: See previous slide for how to choose the most applicable symmetrizing method. Step 1. Transform > Symmetrize Step 2. Input dataset Info_GE_4 Step 3. Symmetrizing method maximum Step 4. Output dataset Info_GE_4-Sym Page 48
Combining Networks In the picture to the left you can see the information network. In the picture below is the combined information and value network. Page 49
Combining Networks (Continued) Tip: The new matrix infovalue can now be used for various visual and quantitative analysis. Step 1. Tools > Matrix Algebra Step 2. In the Enter Command box type infovalue = mult(artcoinfo_ge_4,artcokase) Page 50
QAP Correlation Step 1. Tools > Testing Hypothesis > Dyadic (QAP) > QAP Correlation (old) Step 2. 1st Data Matrix ArtCoInfo_GE_4 Step 3. 2nd Data Matrix ArtCoKase (note that this file is already 1 s and 0 s so no need to dichotomize) Page 51
QAP Regression Step 1. Tools > Testing Hypothesis > Dyadic (QAP) > MR-QAP Linear Regression > Original (Y-permutation) method Page 52
QAP Regression (cont.) Adjusted R-Square of 0.133 indicates a moderate relationship between the two social relations. The probability of 0.000 indicates that it is statistically significant. Step 1. Enter dependent variable ArtCoInfo_GE_4 Step 2. Enter independent variable ArtCoKASE Page 53