HAS-Motion Software Documentation

User Tools

Site Tools

You are here: Main Page » sift » tutorials » Perform Statistical Parametric Mapping
sift:tutorials:perform_statistical_parametric_mapping

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
sift:tutorials:perform_statistical_parametric_mapping [2024/11/29 16:32] – wikisysopsift:tutorials:perform_statistical_parametric_mapping [2024/12/17 18:27] (current) – [Analysis] wikisysop
Line 1: Line 1:
 ====== Perform Statistical Parametric Mapping ====== ====== Perform Statistical Parametric Mapping ======
  
-This tutorial will show you how to perform an SPM analysis in Sift. An SPM analysis helps you gather statistical analysis contained in the original n-dimensional space as your data, ensuring the removal of potential biasing and allowing for easily understood visualizations. More information on SPM can be found in the [[Sift:Statistical_Parametric_Mapping:Using_Statistical_Parametric_Mapping_in_Biomechanics|SPM Page]]+This tutorial will show you how to perform an SPM analysis in Sift. An SPM analysis helps you gather statistical analysis contained in the original n-dimensional space as your data(commonly 101 normalized points in biomechanics), ensuring the removal of potential biasing and allowing for easily understood visualizations. More information on SPM can be found in the [[Sift:Statistical_Parametric_Mapping:Using_Statistical_Parametric_Mapping_in_Biomechanics|SPM Page]]
  
 ===== Research Question ===== ===== Research Question =====
  
-The question we will be trying to answer today is: "Is there a difference between how an OA patient walks and how a normal control group walks?". We will specifically look at identifying any differences there is in the flexion-extension of the right knee for our participants.+The question we will be trying to answer today is: "Is there a difference between how an Osteoarthritis (OA) patient walks and how a normal control (NC) group walks?". We will specifically look at identifying any differences there is in the flexion-extension of the right knee for our participants.
  
 ===== Data ===== ===== Data =====
Line 73: Line 73:
 We begin by creating a General Linear Model (GLM) of our data. This is a [[sift:statistical_parametric_mapping:using_statistical_parametric_mapping_in_biomechanics|necessary step]] to easily analyze our data and create statistical parametric maps. Since we are hoping to understand the (potential) differences between 2 groups of data, we can model it by crafting the design matrix within the GLM to suit our needs. Sift automatically creates a categorical design matrix, that is, one where each grouping is selected. This will lead to a regression which calculates the means, based on these groupings. The residual matrix can then be easily calculated, and we have obtained our GLM. We begin by creating a General Linear Model (GLM) of our data. This is a [[sift:statistical_parametric_mapping:using_statistical_parametric_mapping_in_biomechanics|necessary step]] to easily analyze our data and create statistical parametric maps. Since we are hoping to understand the (potential) differences between 2 groups of data, we can model it by crafting the design matrix within the GLM to suit our needs. Sift automatically creates a categorical design matrix, that is, one where each grouping is selected. This will lead to a regression which calculates the means, based on these groupings. The residual matrix can then be easily calculated, and we have obtained our GLM.
  
-{{ :GLM_Dialog.png?500}}+{{ :glm_dialog.png?500}}
  
 This process is completed through the following steps: This process is completed through the following steps:
 +
 +=== Original Data ===
  
   - On the SPM tab, within the [[Sift:application:Analyse_Page|Analyse Page]], select the groups and workspaces you want to include in your GLM   - On the SPM tab, within the [[Sift:application:Analyse_Page|Analyse Page]], select the groups and workspaces you want to include in your GLM
Line 82: Line 84:
   - Enter the following into the GLM Dialog:   - Enter the following into the GLM Dialog:
     * GLM Name: GLM     * GLM Name: GLM
 +    * Statistical Test: Two-Sample T-Test
     * Group By: Group     * Group By: Group
     * The Groups Selected should be OA and NC     * The Groups Selected should be OA and NC
 +    * Use Workspace Mean: Unchecked
   - Select Create GLM   - Select Create GLM
  
 You will then repeat this process for the registered data: You will then repeat this process for the registered data:
 +
 +=== Registered Data ===
  
   - On the SPM tab, within the [[Sift:application:Analyse_Page|Analyse Page]], select the groups and workspaces you want to include in your GLM   - On the SPM tab, within the [[Sift:application:Analyse_Page|Analyse Page]], select the groups and workspaces you want to include in your GLM
Line 93: Line 99:
   - Enter the following into the GLM Dialog:   - Enter the following into the GLM Dialog:
     * GLM Name: GLM_Registered     * GLM Name: GLM_Registered
 +    * Statistical Test: Two-Sample T-Test
     * Group By: Group     * Group By: Group
     * The Groups Selected should be OA_Registered and NC_Registered     * The Groups Selected should be OA_Registered and NC_Registered
 +    * Use Workspace Mean: Unchecked
   - Select Create GLM   - Select Create GLM
  
Line 110: Line 118:
  
 To complete these SPMs: To complete these SPMs:
 +
 +=== Original Data ===
  
   - Select GLM: GLM   - Select GLM: GLM
Line 116: Line 126:
     - For unregistered data:     - For unregistered data:
       * SPM Name: SPM       * SPM Name: SPM
-      * Statistic: t Statistic+      * Statistic: Two Sample T-Test
       * Group 1: OA       * Group 1: OA
       * Group 2: NC       * Group 2: NC
 +      * Threshold: 0.05
 +      * Two-Tailed: Checked
 +
 +=== Registered Data ===
  
   - Select GLM: GLM_Registered   - Select GLM: GLM_Registered
Line 125: Line 139:
     - For registered data:     - For registered data:
       * SPM Name: SPM_Registered       * SPM Name: SPM_Registered
-      * Statistic: t Statistic+      * Statistic: Two Sample T-Test
       * Group 1: OA_Registered       * Group 1: OA_Registered
       * Group 2: NC_Registered       * Group 2: NC_Registered
 +      * Threshold: 0.05
 +      * Two-Tailed: Checked
  
-We have now calculated two SPMs, which we can easily compare/contrast by selecting the GLM and SPM Results we want in the top bar of the SPM tab. Both SPMs provide us with similar insights: there is a statistical difference between the 2 groups, and it is most prominent during mid-stance(roughly 10%-25% of the gait cycle), as well as mid-swing (roughly 55%-85% of the gait cycle). For the given threshold (defaults to alpha=0.01), we have established that there is a difference between the 2 groups (more precisely, we determined that the null hypothesis that the 2 groups are from the same population sample is false at alpha<0.01).+We have now calculated two SPMs, which we can easily compare/contrast by selecting the GLM and SPM Results we want in the top bar of the SPM tab. Both SPMs provide us with similar insights: there is a statistical difference between the 2 groups, and it is most prominent during mid-stance(roughly 10%-25% of the gait cycle), as well as mid-swing (roughly 55%-85% of the gait cycle). For the given threshold (defaults to alpha=0.01), we have established that there is a difference between the 2 groups (more precisely, we determined that the null hypothesis that the 2 groups are from the same population sample is false at alpha<0.05).
  
  
 {{:SPM_Plot1.png?800}} {{:SPM_Plot1.png?800}}
  
-The difference between both SPMs is most apparent at ~65% of the gait cycle. Here we can see a significantly more pronounced t statistic (~10 vs ~12.5). While both are well above the specified threshold where alpha=0.01, this can show us how curve registration can be useful to correctly align our data, and get more meaningful results from our analysis. +The difference between both SPMs is most apparent at ~65% of the gait cycle. Here we can see a significantly more pronounced t statistic (~10 vs ~12.5). While both are well above the specified threshold where alpha=0.05, this can show us how curve registration can be useful to correctly align our data, and get more meaningful results from our analysis. 
  
 {{:SPM_Plot2.png?800}} {{:SPM_Plot2.png?800}}
sift/tutorials/perform_statistical_parametric_mapping.1732897960.txt.gz · Last modified: 2024/11/29 16:32 by wikisysop