diff --git a/Makefile b/Makefile
index 9057f37..a650ea7 100644
--- a/Makefile
+++ b/Makefile
@@ -1,4 +1,4 @@
-.PHONY: all clean coverage test
+.PHONY: all clean coverage test verbose
 
 all: clean
 
@@ -6,10 +6,10 @@ clean:
 	find . -name "*.so" -o -name "*.pyc" -o -name "*.pyx.md5" | xargs rm -f
 
 coverage:
-	nosetests code/utils data --with-coverage --cover-package=data  --cover-package=utils
+	nosetests code/utils/tests data/tests --with-coverage --cover-package=data/data.py  --cover-package=code/utils/functions
 
 test:
-	nosetests code/utils data
+	nosetests code/utils/tests data/tests
 
 verbose:
-	nosetests -v code/utils data
+	nosetests -v code/utils/tests data/tests
diff --git a/README.md b/README.md
index 4675049..8420983 100644
--- a/README.md
+++ b/README.md
@@ -1,5 +1,13 @@
-# project-template
+# UC Berkeley Stat 159/259 Fall 2015
+## Project-Theta
+
 [![Build Status](https://travis-ci.org/berkeley-stat159/project-theta.svg?branch=master)](https://travis-ci.org/berkeley-stat159/project-theta?branch=master)
 [![Coverage Status](https://coveralls.io/repos/berkeley-stat159/project-theta/badge.svg?branch=master)](https://coveralls.io/r/berkeley-stat159/project-theta?branch=master)
 
-Fall 2015 group project
+_**Group members:**_ Siyao Chang ([`changsiyao`](https://github.com/changsiyao)) , Boying Gong ([`boyinggong`](https://github.com/boyinggong)), Benjamin Hsieh ([`BenjaminHsieh`](https://github.com/BenjaminHsieh)), Brian Qiu ([`brianqiu`](https://github.com/brianqiu)), Jiang Zhu ([`pigriver123`](https://github.com/pigriver123))
+
+_**Topic:**_ [The Neural Basis of Loss Aversion in Decision Making Under Risk] (https://openfmri.org/dataset/ds000005/)
+[SOME SUMMARY OF PAPER]
+
+## Instructions
+[NEED TO ADD]
\ No newline at end of file
diff --git a/code/Makefile b/code/Makefile
index 8344e48..d4e3419 100644
--- a/code/Makefile
+++ b/code/Makefile
@@ -1,5 +1,7 @@
+.PHONY: test coverage
+
 test:
-	nosetests code/utils -w ..
+	nosetests code/utils/tests -w ..
 
 coverage:
-	nosetests code/utils -w .. --with-coverage --cover-package=utils 
+	nosetests code/utils/tests -w .. --with-coverage --cover-package=utils/functions
diff --git a/code/scripts/find_mask_threshold.py b/code/scripts/find_mask_threshold.py
index d834a66..0256ba4 100644
--- a/code/scripts/find_mask_threshold.py
+++ b/code/scripts/find_mask_threshold.py
@@ -2,7 +2,7 @@
 import matplotlib.pyplot as plt
 import numpy as np
 import sys
-sys.path.append('../utils')
+sys.path.append('../utils/functions')
 import smooth_gaussian
 import os
 
diff --git a/code/scripts/findoutlier.py b/code/scripts/findoutlier.py
index e29733a..ad08428 100644
--- a/code/scripts/findoutlier.py
+++ b/code/scripts/findoutlier.py
@@ -1,7 +1,7 @@
 import numpy as np
 import json
 import sys
-pathtofunction = '../utils'
+pathtofunction = '../utils/functions'
 # Append the sys path
 sys.path.append(pathtofunction)
 from outlierfunction import outlier
diff --git a/code/scripts/graph_lindiag_script.py b/code/scripts/graph_lindiag_script.py
index e3fed91..1e461fd 100644
--- a/code/scripts/graph_lindiag_script.py
+++ b/code/scripts/graph_lindiag_script.py
@@ -4,7 +4,7 @@
 import sys
 
 # Path to function
-pathtofunction = '../utils'
+pathtofunction = '../utils/functions'
 # Append path to sys
 sys.path.append(pathtofunction)
 
diff --git a/code/scripts/graphoutlier.py b/code/scripts/graphoutlier.py
index 787fbdf..38c695f 100644
--- a/code/scripts/graphoutlier.py
+++ b/code/scripts/graphoutlier.py
@@ -9,11 +9,17 @@
 # Paths
 pathtodata = '../../data/'
 pathtofig = '../../paper/figures/'
-pathtofunction = '../utils'
+pathtofunction = '../utils/functions'
+pathtographing = '../utils/graphing'
 # Append fuction path
 sys.path.append(pathtofunction)
 # Import function
-from graphoutlier_functions import loadnib_dict, loadtxt_dict, plot_dvars, plot_fd, plot_meanSig
+from basic_util import loadnib_dict, loadtxt_dict
+
+# Append graphing path
+sys.path.append(pathtographing)
+# Import function
+from graphoutlier_functions import plot_dvars, plot_fd, plot_meanSig
 
 
 # load outlier files
diff --git a/code/scripts/lme_script.py b/code/scripts/lme_script.py
index b5bb01f..0fbd080 100644
--- a/code/scripts/lme_script.py
+++ b/code/scripts/lme_script.py
@@ -5,12 +5,12 @@
 import sys
 
 # Path to function
-pathtofunction = '../utils'
+pathtofunction = '../utils/functions'
 # Append path to sys
 sys.path.append(pathtofunction)
 
 from behavtask_tr import events2neural_extend, merge_cond
-from regression_functions import hrf, getRegressor, calcBeta, calcMRSS, deleteOutliers
+from regression_functions import hrf, getRegressor, deleteOutliers
 from lme_functions import calcBetaLme, calcSigProp, calcAnov, anovStat
 
 n_vols=240
diff --git a/code/scripts/logistic.py b/code/scripts/logistic.py
index 7669426..4704aac 100644
--- a/code/scripts/logistic.py
+++ b/code/scripts/logistic.py
@@ -5,7 +5,7 @@
 import sys
 
 # Path to function
-pathtofunction = '../utils'
+pathtofunction = '../utils/functions'
 # Append path to sys
 sys.path.append(pathtofunction)
 
@@ -49,7 +49,16 @@
     logreg_proba = logreg.predict_proba(X)
     confusion = create_confusion(logreg_proba, y)
     addsub = fig.add_subplot(4, 4, i)
-    addsub, AUC = plot_roc(confusion, addsub, i)
+    addsub, ROC, AUC = plot_roc(confusion, addsub)
+    # Plot the ROC curve.
+    plt.plot(ROC[:,0], ROC[:,1], lw=2)
+    plt.xlim(-0.1,1.1)
+    plt.ylim(-0.1,1.1)
+    plt.xlabel('$FPR(t)$')
+    plt.ylabel('$TPR(t)$')
+    plt.grid()
+    plt.title('subject '+ str(i)+', AUC = %.4f'%AUC)
+    #------------------------------------------------------------------------#
     Min_thrs = np.append(Min_thrs, getMin_thrs(confusion))
     AUC_smr = np.append(AUC_smr, AUC)
 
diff --git a/code/scripts/make_smooth_graphs.py b/code/scripts/make_smooth_graphs.py
index cbd844b..877216a 100644
--- a/code/scripts/make_smooth_graphs.py
+++ b/code/scripts/make_smooth_graphs.py
@@ -2,7 +2,7 @@
 import matplotlib.pyplot as plt
 import nibabel as nib
 import sys
-sys.path.append('../utils')
+sys.path.append('../utils/functions')
 import smooth_gaussian
 
 #possibly put in os function to specify path later
diff --git a/code/scripts/regression_script.py b/code/scripts/regression_script.py
index b12d466..949f621 100644
--- a/code/scripts/regression_script.py
+++ b/code/scripts/regression_script.py
@@ -5,7 +5,7 @@
 import sys
 
 # Path to function
-pathtofunction = '../utils'
+pathtofunction = '../utils/functions'
 # Append path to sys
 sys.path.append(pathtofunction)
 
diff --git a/code/utils/functions/basic_util.py b/code/utils/functions/basic_util.py
new file mode 100644
index 0000000..01edebd
--- /dev/null
+++ b/code/utils/functions/basic_util.py
@@ -0,0 +1,53 @@
+"""
+A collection of basic utility functions for use in outlier detection/graphing
+of fd, dvars, and meanSignal, see graphoutlier_functions.py
+"""
+
+import numpy as np
+import nibabel as nib
+
+
+def loadtxt_dict(file_name, fig_name):
+    """
+    Input: 
+        Txt file specified by file_name
+        Name of figure file wish to output
+    
+    Output:
+        Dictonary that attached to file_name the np array after loading 
+    file_name
+    """
+    data = np.loadtxt(file_name)
+    dict_out = {fig_name: data}
+    return dict_out
+
+def loadnib_dict(file_name, fig_name):
+    """
+    Input: 
+        Bold file (bold.nii, bold.nii.gz) specified by file_name 
+        Name of figure file wish to output
+    
+    Output:
+    Dictonary that attached to file_name the np array after loading file_name
+    """
+    img = nib.load(file_name)
+    data = img.get_data()
+    dict_out = {fig_name: data}
+    return dict_out
+
+
+# Calculate mean
+def vol_mean(data):
+    """ Return mean across voxels for $D `data`
+    
+    Input:
+        np array of data
+    Output: np array of dim (T,)
+        mean of data across all but the last dimension
+    """
+    mean_list = []
+    # Loop over the each volume and outputs the mean of each dimension
+    for i in range(data.shape[-1]):
+        mean = np.mean(data[...,i])
+        mean_list.append(mean)
+    return np.asarray(mean_list)
diff --git a/code/utils/behavtask_tr.py b/code/utils/functions/behavtask_tr.py
similarity index 92%
rename from code/utils/behavtask_tr.py
rename to code/utils/functions/behavtask_tr.py
index 811ff24..73386f0 100644
--- a/code/utils/behavtask_tr.py
+++ b/code/utils/functions/behavtask_tr.py
@@ -70,10 +70,3 @@ def events2neural_extend(behav_task, tr, n_trs):
         time_course[on:on + dur,9] = RT
     return time_course
 
-def plot_time_course(time_course):
-    """
-    Simple function to plot time_course, an array from return of 
-    events2neural_extend
-    """
-    plt.plot(time_course[:,0])    
-    plt.show()
diff --git a/code/utils/lme_functions.py b/code/utils/functions/lme_functions.py
similarity index 96%
rename from code/utils/lme_functions.py
rename to code/utils/functions/lme_functions.py
index 87053d5..a09daa4 100644
--- a/code/utils/lme_functions.py
+++ b/code/utils/functions/lme_functions.py
@@ -3,8 +3,6 @@
 from scipy import stats  
 import pandas as pd
 import numpy as np
-from behavtask_tr import events2neural_extend, merge_cond
-from regression_functions import hrf, getRegressor, calcBeta, calcMRSS, deleteOutliers
 
 def calcBetaLme(data_full, gain_full, loss_full, linear_full, quad_full, run_group, thrshd=None):
     """ 
diff --git a/code/utils/logistic_function.py b/code/utils/functions/logistic_function.py
similarity index 85%
rename from code/utils/logistic_function.py
rename to code/utils/functions/logistic_function.py
index 00f8df1..e9fbe50 100644
--- a/code/utils/logistic_function.py
+++ b/code/utils/functions/logistic_function.py
@@ -8,8 +8,8 @@ def create_confusion(logreg_proba, y, thrs_inc=0.01):
         
         Parameters
         ----------
-        actual: Actual responses, 1-d array with values 0 or 1
-        fitted: Fitted probabilities, 1-d array with values between 0 and 1
+        y: Actual responses, 1-d array with values 0 or 1
+        logreg_proba: Fitted probabilities, 2-d array with values between 0 and 1 in second column
         thrs_inc: increment of threshold probability (default 0.05)
         
         Returns
@@ -52,7 +52,7 @@ def getMin_thrs(confusion):
         false_pos: number of incorrect trues
         false_neg: number of incorrect falses
         """
-    thrs_min = np.argmin(confusion[:,3]+ confusion[:,4])
+    thrs_min = np.min(confusion[:,3]+ confusion[:,4])
     col_out = confusion[thrs_min, :]
     thrs = col_out[0]
     false_pos = col_out[3]
@@ -60,7 +60,7 @@ def getMin_thrs(confusion):
     return thrs, false_pos, false_neg
 
 
-def plot_roc(confusion, fig, sub_i):
+def plot_roc(confusion, fig):
     """
         function to plot the ROC (receiver operating characteristic) curve and
         calculate the corresponding AUC (Area Under Curve).
@@ -83,19 +83,10 @@ def plot_roc(confusion, fig, sub_i):
         # Compute true  positive rate for current threshold.
         TPR_t = confusion[i, 1] / float(confusion[i, 1] + confusion[i, 4])
         ROC[i,1] = TPR_t
-    
-    # Plot the ROC curve.
-    plt.plot(ROC[:,0], ROC[:,1], lw=2)
-    plt.xlim(-0.1,1.1)
-    plt.ylim(-0.1,1.1)
-    plt.xlabel('$FPR(t)$')
-    plt.ylabel('$TPR(t)$')
-    plt.grid()
 
     AUC = 0.
     for i in range(confusion.shape[0]-1):
         AUC += (ROC[i+1,0]-ROC[i,0]) * (ROC[i+1,1]+ROC[i,1])
     AUC *= -0.5
     
-    plt.title('subject '+ str(sub_i)+', AUC = %.4f'%AUC)
-    return fig, AUC
+    return fig, ROC,  AUC
diff --git a/code/utils/outlierfunction.py b/code/utils/functions/outlierfunction.py
similarity index 100%
rename from code/utils/outlierfunction.py
rename to code/utils/functions/outlierfunction.py
diff --git a/code/utils/pearson.py b/code/utils/functions/pearson.py
similarity index 100%
rename from code/utils/pearson.py
rename to code/utils/functions/pearson.py
diff --git a/code/utils/regression_functions.py b/code/utils/functions/regression_functions.py
similarity index 97%
rename from code/utils/regression_functions.py
rename to code/utils/functions/regression_functions.py
index 426599c..fc8ed5d 100644
--- a/code/utils/regression_functions.py
+++ b/code/utils/functions/regression_functions.py
@@ -65,8 +65,7 @@ def calcBeta(data, gain, loss, linear_dr, quad_dr, threshold=None):
     design[:, 3] = quad_dr
     designp = npl.pinv(design)
     if threshold!=None:
-        mean_data = np.mean(data, axis=-1)
-        mask = mean_data > threshold
+        mask = np.mean(data, axis=-1) > threshold
         data[~mask]=0
     T = data.shape[-1]
     time_by_vox = np.reshape(data, (-1, T)).T
diff --git a/code/utils/smooth_gaussian.py b/code/utils/functions/smooth_gaussian.py
similarity index 100%
rename from code/utils/smooth_gaussian.py
rename to code/utils/functions/smooth_gaussian.py
diff --git a/code/utils/graph_lindiagnostics.py b/code/utils/graphing/graph_lindiagnostics.py
similarity index 100%
rename from code/utils/graph_lindiagnostics.py
rename to code/utils/graphing/graph_lindiagnostics.py
diff --git a/code/utils/graphoutlier_functions.py b/code/utils/graphing/graphoutlier_functions.py
similarity index 81%
rename from code/utils/graphoutlier_functions.py
rename to code/utils/graphing/graphoutlier_functions.py
index cc91e25..706eec7 100644
--- a/code/utils/graphoutlier_functions.py
+++ b/code/utils/graphing/graphoutlier_functions.py
@@ -1,38 +1,28 @@
 """
-A collection of utility functions for outlier detection/graphing
+A collection of  graphing  functions for outlier detection/graphing
 of fd, dvars, and meanSignal
 """
 import numpy as np
 import matplotlib.pyplot as plt
-import nibabel as nib
 
-def loadtxt_dict(file_name, fig_name):
-    """
-    Input: 
-        Txt file specified by file_name
-        Name of figure file wish to output
+# Calculate mean this is same as the one in basic_util.py 
+# Test already written, included here because graphing functions not tested
+# but need to use above: 
+def vol_mean(data):
+    """ Return mean across voxels for $D `data`
     
-    Output:
-        Dictonary that attached to file_name the np array after loading 
-    file_name
+    Input:
+        np array of data
+    Output: np array of dim (T,)
+        mean of data across all but the last dimension
     """
-    data = np.loadtxt(file_name)
-    dict_out = {fig_name: data}
-    return dict_out
+    mean_list = []
+    # Loop over the each volume and outputs the mean of each dimension
+    for i in range(data.shape[-1]):
+        mean = np.mean(data[...,i])
+        mean_list.append(mean)
+    return np.asarray(mean_list)
 
-def loadnib_dict(file_name, fig_name):
-    """
-    Input: 
-        Bold file (bold.nii, bold.nii.gz) specified by file_name 
-        Name of figure file wish to output
-    
-    Output:
-    Dictonary that attached to file_name the np array after loading file_name
-    """
-    img = nib.load(file_name)
-    data = img.get_data()
-    dict_out = {fig_name: data}
-    return dict_out
 
 # Graphing dvars: RMS signal derivative    
 def plot_dvars(dvars_dict, dvars_outliers, saveit=False):
@@ -64,6 +54,7 @@ def plot_dvars(dvars_dict, dvars_outliers, saveit=False):
         plt.savefig(dvars_dict.keys()[0])
         plt.close()
 
+
 # Graphing fd: Framewise displacement
 def plot_fd(fd_dict, fd_outliers, saveit=False):
     """
@@ -94,21 +85,6 @@ def plot_fd(fd_dict, fd_outliers, saveit=False):
         plt.savefig(fd_dict.keys()[0])
         plt.close()
 
-# Calculate mean
-def vol_mean(data):
-    """ Return mean across voxels for $D `data`
-    
-    Input:
-        np array of data
-    Output: np array of dim (T,)
-        mean of data across all but the last dimension
-    """
-    mean_list = []
-    # Loop over the each volume and outputs the mean of each dimension
-    for i in range(data.shape[-1]):
-        mean = np.mean(data[...,i])
-        mean_list.append(mean)
-    return np.asarray(mean_list)
 
 # Graphing mean signal	
 def plot_meanSig(bdata_dict, saveit = False):
@@ -141,4 +117,3 @@ def plot_meanSig(bdata_dict, saveit = False):
         plt.savefig(bdata_dict.keys()[0])
         plt.close()
 
-
diff --git a/code/utils/stimuli.py b/code/utils/stimuli.py
deleted file mode 100644
index 244607c..0000000
--- a/code/utils/stimuli.py
+++ /dev/null
@@ -1,37 +0,0 @@
-""" Functions to work with standard OpenFMRI stimulus files
-
-The functions have docstrings according to the numpy docstring standard - see:
-
-    https://github.com/numpy/numpy/blob/master/doc/HOWTO_DOCUMENT.rst.txt
-"""
-
-import numpy as np
-
-def events2neural(task_fname, tr, n_trs):
-    """ Return predicted neural time course from event file `task_fname`
-
-    Parameters
-    ----------
-    task_fname : str
-        Filename of event file
-    tr : float
-        TR in seconds
-    n_trs : int
-        Number of TRs in functional run
-
-    Returns
-    -------
-    time_course : array shape (n_trs,)
-        Predicted neural time course, one value per TR
-    """
-    task = np.loadtxt(task_fname)
-    # Check that the file is plausibly a task file
-    if task.ndim != 2 or task.shape[1] != 3:
-        raise ValueError("Is {0} really a task file?", task_fname)
-    # Convert onset, duration seconds to TRs
-    task[:, :2] = task[:, :2] / tr
-    # Neural time course from onset, duration, amplitude for each event
-    time_course = np.zeros(n_trs)
-    for onset, duration, amplitude in task:
-        time_course[onset:onset + duration] = amplitude
-    return time_course
diff --git a/code/utils/tests/test_graphoutlier_functions.py b/code/utils/tests/test_basic_util.py
similarity index 52%
rename from code/utils/tests/test_graphoutlier_functions.py
rename to code/utils/tests/test_basic_util.py
index 2f597dd..7a537c6 100644
--- a/code/utils/tests/test_graphoutlier_functions.py
+++ b/code/utils/tests/test_basic_util.py
@@ -1,31 +1,32 @@
 """
-Test graph_function module the following functions:
+Test basic_util module the following functions:
     loadtxt_dict
     loadnib_dict
     vol_mean
 
 Run with::
-
-    nosetests test_graph_functions.py
+   `make test` from code or project directory
 """
 # Loading modules.
 from __future__ import absolute_import, division, print_function
 import numpy as np
-import os
-import sys
+import sys, os
 from numpy.testing import assert_array_equal
+import nibabel as nib
 
 # Set path
-sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+sys.path.append(os.path.join(os.path.dirname(__file__), "../functions/"))
 
 # Load graph_functions:
-from graphoutlier_functions import loadtxt_dict, vol_mean
+from basic_util import loadtxt_dict, loadnib_dict, vol_mean
+
 
 # Test txt:
 np.savetxt('temp.txt', range(30))
 # Test np array, dim = 4
 # x1 = np.random.randn(100).reshape((2, 5, 2, 5))
-x2 = np.arange(64).reshape((2, 4, 2, 4)) 
+x2 = np.arange(64).reshape((2, 4, 2, 4))
+ 
 def test_loadtxt_dict():
     # Using loadtxt_dict
     mydict = loadtxt_dict('temp.txt', 'mytxt')
@@ -38,3 +39,14 @@ def test_vol_mean():
     mymean = vol_mean(x2)
     truemean = np.array([30., 31 ,32 ,33])
     assert_array_equal(mymean, truemean)    
+
+def test_loadnib_dict():
+    # create test img
+    t_data = np.array([1,2,3])
+    t_dict = {'testnib': t_data}
+    img = nib.Nifti1Image(t_data, np.eye(4))
+    nib.save(img,'testnib.nii.gz')
+    # my function
+    my_dict = loadnib_dict('testnib.nii.gz', 'testnib')
+    assert (list(t_dict.keys())[0] == list(my_dict.keys())[0])
+    assert_array_equal(list(t_dict.values())[0], list(my_dict.values())[0])
diff --git a/code/utils/tests/test_behavtask_tr.py b/code/utils/tests/test_behavtask_tr.py
new file mode 100644
index 0000000..902a4a6
--- /dev/null
+++ b/code/utils/tests/test_behavtask_tr.py
@@ -0,0 +1,55 @@
+"""
+Test behavtask_tr module the following functions:
+    merge_cond
+    events2neural_extend
+
+Run with::
+    **Run from project-theta directory with 'make test'
+
+"""
+# Loading modules.
+from __future__ import absolute_import, division, print_function
+import numpy as np
+import os
+import sys
+from numpy.testing import assert_allclose
+
+
+# Set path
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '../functions')))
+
+# Path to the first subject, first run, this is used as the test data for 
+pathtotest = 'code/utils/tests/' 
+
+# Load graph_functions:
+from behavtask_tr import merge_cond, events2neural_extend
+
+def test_mergecond():
+    # my function
+    my_merge = merge_cond(pathtotest+'test_behavdata.txt', pathtotest+'test_cond001.txt', pathtotest+'test_cond002.txt', pathtotest+'test_cond003.txt', pathtotest+'test_cond004.txt')
+    t_behav = np.loadtxt(pathtotest+'test_behavdata.txt', skiprows=1)
+    t_con1 = np.loadtxt(pathtotest+'test_cond001.txt')
+    t_con2 = np.loadtxt(pathtotest+'test_cond002.txt')    
+    t_con3 = np.loadtxt(pathtotest+'test_cond003.txt')
+    t_con4 = np.loadtxt(pathtotest+'test_cond004.txt')
+    
+    # assert
+    assert_allclose(t_behav[:,1:], my_merge[:,6:])
+    assert_allclose(t_con1, my_merge[:,:3])
+    assert_allclose(t_con2[:,-1], my_merge[:,3])
+    assert_allclose(t_con3[:,-1], my_merge[:,4])
+    assert_allclose(t_con4[:,-1], my_merge[:,5])
+    
+def test_events2neuarl_extend():
+    t_behav = np.array([np.arange(12)+1, np.arange(12)+2])
+    tr = 2
+    n_tr = 2
+    lame = np.array([1])
+    try:
+        events2neural_extend(lame, tr, n_tr)
+    except ValueError:
+        assert(True)
+    t_time = np.array([np.arange(3,13), np.arange(4,14)])
+    my_time = events2neural_extend(t_behav, tr, n_tr)
+    assert_allclose(t_time, my_time)
+    
diff --git a/code/utils/tests/test_lme_functions.py b/code/utils/tests/test_lme_functions.py
index 0b4d19f..afea34f 100644
--- a/code/utils/tests/test_lme_functions.py
+++ b/code/utils/tests/test_lme_functions.py
@@ -12,14 +12,14 @@
 # Loading modules.
 from __future__ import absolute_import, division, print_function
 import numpy as np
-import sys
+import sys, os
 from scipy import stats
 from sklearn import linear_model
 from numpy.testing import assert_almost_equal, assert_allclose
 
 
 # Append function path
-sys.path.append('..')
+sys.path.append(os.path.join(os.path.dirname(__file__), "../functions/"))
 
 # Path to the first subject, first run, this is used as the test data for 
 # getGainLoss:
@@ -28,8 +28,6 @@
 # Load graph_functions:
 from lme_functions import calcBetaLme, calcSigProp, calcAnov, anovStat
 
-
-
 def test_calcBetaLme():
     # Test data with large n = 1500
     X = np.ones((2000, 4))
@@ -45,9 +43,16 @@ def test_calcBetaLme():
     test_betas = regr.coef_
     # My function, should produce same results if groups are all the same:
     lme = calcBetaLme(Y, X[:,0], X[:,1], X[:,2], X[:,3], np.repeat(1,2000))
+    lme_thrs = calcBetaLme(Y, X[:,0], X[:,1], X[:,2], X[:,3], np.repeat(1,2000), -40000)
+    lme_thrs1 = calcBetaLme(Y, X[:,0], X[:,1], X[:,2], X[:,3], np.repeat(1,2000), 10)
     # Compare betas
     my_betas = lme.ravel()[[0,2]]
+    my_betas_thrs = lme_thrs.ravel()[[0,2]]
+    my_betas_thrs1 = lme_thrs1.ravel()[[0,2]]
     assert max(abs(my_betas - test_betas[:2])) < 0.005
+    assert max(abs(my_betas_thrs - test_betas[:2])) < 0.005
+    assert (test_betas != my_betas_thrs1)
+
     
 def test_calcSigProp():
     # Set up test betas
@@ -104,9 +109,13 @@ def ANOVA(G):
     test_anova = ANOVA(groups)
     # My function
     my_anova = calcAnov(t_data, run_group).ravel()
-
+    my_anova_thrs = calcAnov(t_data, run_group, -40000).ravel()
+    my_anova_thrs1 = calcAnov(t_data, run_group, 10).ravel()
     # Assert
     assert_allclose(test_anova, my_anova)
+    assert_allclose(test_anova, my_anova_thrs)
+    assert (test_anova != my_anova_thrs1).any()
+
 
 def test_anovStat():
     # create a test dataset
diff --git a/code/utils/tests/test_logistic_functions.py b/code/utils/tests/test_logistic_functions.py
new file mode 100644
index 0000000..9e15e02
--- /dev/null
+++ b/code/utils/tests/test_logistic_functions.py
@@ -0,0 +1,81 @@
+"""
+Test regression_function module the following functions:
+    create_confusion
+    getmin_thrs
+    plot_roc
+
+Run with::
+    **Run from project-theta or code directory with 'make test'
+
+"""
+# Loading modules.
+from __future__ import absolute_import, division, print_function
+import numpy as np
+import os
+import sys
+from numpy.testing import assert_allclose
+
+# Set path
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '../functions')))
+
+# Load graph_functions:
+from logistic_function import create_confusion, getMin_thrs, plot_roc
+
+def test_create_confusion():
+    # Sample data
+    actual = np.array([0,1,1,0,0,1])
+    fittedin = np.array([[0,0,0,0,0,0],[0.2, 0.6, 0.7, 0.1, 0.3, 0.9]])
+    fitted = np.array([0.2, 0.6, 0.7, 0.1, 0.3, 0.9])
+    # thrs_inc = 0.2
+    thrs_array = np.array([0, 0.2, 0.4, 0.6, 0.8, 1.0])
+    t_confusion = np.ones((len(thrs_array), 5))
+    t_confusion[:,0] = thrs_array
+    # thrs_inc = 0.2
+    for index, item in enumerate(thrs_array):
+        a = sum((actual == 1) & (fitted > item))
+        b = sum((actual == 0) & (fitted <= item))
+        c = sum((actual == 0) & (fitted > item))
+        d = sum((actual == 1) & (fitted <= item))
+        t_confusion[index, 1:5] = [a, b, c, d]
+    # my function
+    my_confusion = create_confusion(fittedin.T, actual, thrs_inc = 0.2)
+
+    # Assert
+    assert_allclose(t_confusion, my_confusion)
+
+def test_getMin_thrs():
+    # Test data
+    t_data = np.array([[0, 1, 2, 2, 3], [0.25, 1, 5, 1, 1], 
+                       [0.3, 3, 3, 1, 1], [0.5, 2, 3, 1, 3], 
+                       [1, 4, 1, 2, 1]])
+    # Should return the row with the lowest sum of 4th and 5th column values
+    # the 2nd row
+    t_result = t_data[2, :]
+    t_result = np.array([t_result[0], t_result[3], t_result[4]])
+    
+    my_thrs, my_fp, my_fn = getMin_thrs(t_data)
+    my_result = np.array([my_thrs, my_fp, my_fn])
+    
+    # Assert
+    assert_allclose(t_result, my_result)
+
+def test_plot_roc():
+    # test data
+    t_data = np.array([[0, 1, 2, 2, 3], [0.25, 1, 5, 1, 1], 
+                       [0.5, 2, 3, 1, 3],[1, 4, 1, 2, 1]])
+    fig = 111
+    # Calculating by hand: the roc matrix
+    # first column: 4th entry of each row / (4th + 3rd entries)
+    # second column: 2nd entry of each row / (2nd + 5th entries)
+    t_roc = np.array([[2/4, 1/4], [1/6, 1/2], [1/4, 2/5], [2/3, 4/5]])
+    dif1 = np.array([t_roc.T[0][i+1] - t_roc.T[0][i] for i in range(len(t_roc.T[0])-1)])
+    dif2 = np.array([t_roc.T[1][i+1] + t_roc.T[1][i] for i in range(len(t_roc.T[1])-1)])
+    t_AUC = sum(dif1*dif2)* (-0.5)
+
+    # my function
+    my_fig, my_ROC, my_AUC = plot_roc(t_data, fig)
+
+    # assert
+    assert (t_AUC == my_AUC)
+    assert (fig == my_fig)
+    assert_allclose(t_roc, my_ROC)
diff --git a/code/utils/tests/test_outlierfunction.py b/code/utils/tests/test_outlierfunction.py
index 03c657c..e544153 100644
--- a/code/utils/tests/test_outlierfunction.py
+++ b/code/utils/tests/test_outlierfunction.py
@@ -17,7 +17,7 @@
 import sys
 
 # Set path
-sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '../functions')))
 
 # Load function
 
diff --git a/code/utils/tests/test_pearson_1d.py b/code/utils/tests/test_pearson_1d.py
index 4eeb384..b87a0bc 100644
--- a/code/utils/tests/test_pearson_1d.py
+++ b/code/utils/tests/test_pearson_1d.py
@@ -28,7 +28,12 @@
 
 import numpy as np
 
-from .. import pearson
+import os, sys
+
+# Add path
+sys.path.append(os.path.join(os.path.dirname(__file__), "../functions/"))
+
+import pearson
 
 from numpy.testing import assert_almost_equal
 
diff --git a/code/utils/tests/test_pearson_2d.py b/code/utils/tests/test_pearson_2d.py
index 05e4cce..dcb5f87 100644
--- a/code/utils/tests/test_pearson_2d.py
+++ b/code/utils/tests/test_pearson_2d.py
@@ -10,7 +10,11 @@
 
 import numpy as np
 
-from .. import pearson
+import os, sys
+
+sys.path.append(os.path.join(os.path.dirname(__file__), "../functions/"))
+
+import pearson
 
 from numpy.testing import assert_almost_equal
 
diff --git a/code/utils/tests/test_regression_functions.py b/code/utils/tests/test_regression_functions.py
index 3afb5f6..0ebf91b 100644
--- a/code/utils/tests/test_regression_functions.py
+++ b/code/utils/tests/test_regression_functions.py
@@ -21,7 +21,7 @@
 
 
 # Set path
-sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '../functions')))
 
 # Path to the first subject, first run, this is used as the test data for 
 # getGainLoss:
@@ -179,6 +179,17 @@ def test_calcBeta():
     assert_allclose(t_by_v.ravel(), regr.predict(X))
     # assert design
     assert_allclose(X, design[:,:4])
+    
+    #--------------------------------------------------------------------------#
+    Y = X[:,0] + X[:,1]*2 + X[:,2] + X[:,3] + 1
+    # myfunction when thrs != None
+    design1, t_by_v1, my_beta1 = calcBeta(Y, X[:,0], X[:,1], X[:,2], X[:,3], 1)
+    # assert the threshold values are produce different betas and tbyv
+    assert (t_by_v.ravel() != t_by_v1.ravel()).any()
+    assert (my_beta.ravel() != my_beta1.ravel()).all()
+    # assert design still the same
+    assert_allclose(X, design1[:,:4])
+
 
 def test_calcMRSS():
     # Like above, create a test matrix of regressors
diff --git a/code/utils/tests/test_smoothing.py b/code/utils/tests/test_smoothing.py
index fc43884..ed834ed 100644
--- a/code/utils/tests/test_smoothing.py
+++ b/code/utils/tests/test_smoothing.py
@@ -15,7 +15,7 @@
 from numpy.testing import assert_allclose
 
 # Append function path
-sys.path.append('..')
+sys.path.append('../functions')
 
 # Path to the first subject, first run, this is used as the test data for 
 # getGainLoss:
diff --git a/data/Makefile b/data/Makefile
index a2d17fa..feb0a1e 100644
--- a/data/Makefile
+++ b/data/Makefile
@@ -1,8 +1,10 @@
+.PHONY: data validate unzip test
+
 data:
 	wget http://openfmri.s3.amazonaws.com/tarballs/ds005_raw.tgz
 	wget http://nipy.bic.berkeley.edu/rcsds/ds005_mnifunc.tar
 	wget http://nipy.bic.berkeley.edu/rcsds/mni_icbm152_nlin_asym_09c_2mm.tar.gz
-    
+
 validate:
 	python data.py
 
@@ -15,3 +17,6 @@ unzip:
 	rm mni_icbm152_nlin_asym_09c_2mm.tar.gz
 	mv mni_icbm152_nlin_asym_09c_2mm templates
 	mv templates/mni_icbm152_t1_tal_nlin_asym_09c_2mm.nii templates/mni_standard.nii
+
+test:
+	nosetests data/tests -w ..
diff --git a/data/README.md b/data/README.md
index 853e687..628b8b1 100644
--- a/data/README.md
+++ b/data/README.md
@@ -1,10 +1,11 @@
 The ds005 dataset, filtered ds005 dataset, and mni templates are stored here. Th
 e makefile is written such that:
  
-- 'make data' will pull in the appropriate data 
-- 'make unzip' will unzip, remove, and rename certain files
-- 'make validate' will run data.py to check the hashes of each downloaded file w
+- `make data` will pull in the appropriate data 
+- `make unzip` will unzip, remove, and rename certain files
+- `make validate` will run data.py to check the hashes of each downloaded file w
 ith a master hashlist included, ensuring all downloaded data is correct  
+- `make test` will run nosetest on the checking hashes function in data.py
 
 THE COMMANDS SHOULD BE DONE IN THIS ORDER to be successfully validated. The ds00
 5 folder contains subfolders for each subject, the most relevant of which are:
diff --git a/old_paper/.gitignore b/old_paper/.gitignore
deleted file mode 100644
index e69de29..0000000
diff --git a/old_paper/Makefile b/old_paper/Makefile
deleted file mode 100644
index 232a5dd..0000000
--- a/old_paper/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-TITLE="report"
-
-all:
-	pdflatex $(TITLE).tex
-	bibtex $(TITLE)
-	pdflatex $(TITLE).tex
-	pdflatex $(TITLE).tex
-
-
-clean:
-	rm -f *.{aux,log,bbl,lof,lot,blg,out}
diff --git a/old_paper/figures/dvars_sub1run1.png b/old_paper/figures/dvars_sub1run1.png
deleted file mode 100644
index e49afb4..0000000
Binary files a/old_paper/figures/dvars_sub1run1.png and /dev/null differ
diff --git a/old_paper/figures/dvars_sub9run1.png b/old_paper/figures/dvars_sub9run1.png
deleted file mode 100644
index a5c4e06..0000000
Binary files a/old_paper/figures/dvars_sub9run1.png and /dev/null differ
diff --git a/old_paper/figures/fd_sub1run1.png b/old_paper/figures/fd_sub1run1.png
deleted file mode 100644
index 6e192e8..0000000
Binary files a/old_paper/figures/fd_sub1run1.png and /dev/null differ
diff --git a/old_paper/figures/fd_sub9run1.png b/old_paper/figures/fd_sub9run1.png
deleted file mode 100644
index 9f8816d..0000000
Binary files a/old_paper/figures/fd_sub9run1.png and /dev/null differ
diff --git a/old_paper/figures/mean_sub1run1.png b/old_paper/figures/mean_sub1run1.png
deleted file mode 100644
index f5ed6af..0000000
Binary files a/old_paper/figures/mean_sub1run1.png and /dev/null differ
diff --git a/old_paper/figures/mean_sub9run1.png b/old_paper/figures/mean_sub9run1.png
deleted file mode 100644
index 1502b27..0000000
Binary files a/old_paper/figures/mean_sub9run1.png and /dev/null differ
diff --git a/old_paper/figures/qqplot.png b/old_paper/figures/qqplot.png
deleted file mode 100644
index 1f203e4..0000000
Binary files a/old_paper/figures/qqplot.png and /dev/null differ
diff --git a/old_paper/figures/res_fitted_log.png b/old_paper/figures/res_fitted_log.png
deleted file mode 100644
index da72d8f..0000000
Binary files a/old_paper/figures/res_fitted_log.png and /dev/null differ
diff --git a/old_paper/figures/res_fittedval.png b/old_paper/figures/res_fittedval.png
deleted file mode 100644
index 2aa43e5..0000000
Binary files a/old_paper/figures/res_fittedval.png and /dev/null differ
diff --git a/old_paper/project.bib b/old_paper/project.bib
deleted file mode 100644
index 79356c5..0000000
--- a/old_paper/project.bib
+++ /dev/null
@@ -1,9 +0,0 @@
-@article{Tom2007LossAversion,
-  title={The Neural Basis of Loss Aversion in Decision-Making Under Risk},
-  author={Tom, Sabrina M and others},
-  journal={Science},
-  volume={315},
-  pages={515--518},
-  year={2007},
-  publisher={American Association for the Advancement of Science}
-}
diff --git a/old_paper/report.pdf b/old_paper/report.pdf
deleted file mode 100644
index 1fc9fad..0000000
Binary files a/old_paper/report.pdf and /dev/null differ
diff --git a/old_paper/report.tex b/old_paper/report.tex
deleted file mode 100644
index 9c36ef7..0000000
--- a/old_paper/report.tex
+++ /dev/null
@@ -1,47 +0,0 @@
-\documentclass[11pt]{article}
-
-\usepackage[margin=0.75in]{geometry}
-\usepackage{indentfirst}
-\usepackage{graphicx}
-\usepackage{float}
-\bibliographystyle{siam}
-
-\title{The Neural Basis of Loss Aversion in Decision-Making Under Risk}
-\author{
-  Chang, Siyao \\
-  \texttt{changsiyao}
-  \and
-  Gong, Boying\\
-  \texttt{boyinggong}
-  \and
-  Hsieh, Benjamin\\
-  \texttt{BenjaminHsieh}
-  \and
-  Qiu, Brian\\
-  \texttt{brianqiu}
-  \and
-  Zhu, Jiang\\
-  \texttt{pigriver123}
-}
-
-
-
-\begin{document}
-\maketitle
-
-\abstract{\input{sections/abstract.tex}}
-
-\input{sections/introduction.tex}
-
-\input{sections/data.tex}
-
-\input{sections/methods.tex}
-
-\input{sections/results.tex}
-
-\input{sections/discussion_challenges.tex}
-
-
-\bibliography{project}
-
-\end{document}
diff --git a/old_paper/sections/abstract.tex b/old_paper/sections/abstract.tex
deleted file mode 100644
index fb8c779..0000000
--- a/old_paper/sections/abstract.tex
+++ /dev/null
@@ -1,13 +0,0 @@
-% Abstract
-\par Our paper is the \textit{Neural Basis of Loss Aversion in Decision-Making
-Under Risk} \cite{Tom2007LossAversion}. The experiment investigates the 
-phenomenon of loss aversion - where individuals decisions are influenced by the
-amount of potential loss more than they are by the amount of potential gains. 
-The experiment involved giving 16 subjects 256 combinations of gain/loss of 
-dollars with a 50/50 chance. The subject's decisions of whether to accept or 
-reject of each of the proposed gambles were measured as well as their brain 
-activity in the fMRI machine. The behavioral data file records the subjects 
-responses and to which combination of values, and the BOLD data file records 
-the subjects neurological reponse in 4-dimensional fMRI data. 
-
-
diff --git a/old_paper/sections/data.tex b/old_paper/sections/data.tex
deleted file mode 100644
index 8c3f44f..0000000
--- a/old_paper/sections/data.tex
+++ /dev/null
@@ -1,37 +0,0 @@
-\section{Data}
-\subsection{Overview}
-The study used 16 right-handed, healthy, English-speaking participants 
-recruited through ads posted on UCLA. Out of 16 subjects, 9 were female and 
-the mean age was 22 $ \pm $ 2.9 years. \cite{Tom2007LossAversion}
-
-\subsection{Behavorial Data}
-The behavioral data consists of each subject undergoing 3 trial runs for the 
-``gamble'' task, in which each subject is presented with a combination of 
-potential monetary gains and losses given a 50/50 chance of to win/loss. Each 
-trial run consists of 86 different combinations of rewards/penalities spread 
-out accross 474 seconds. Intervals between each onset of task range from 4 to 
-8 seconds. Subjects were given the 4 choices in reponse to each gambling 
-proposal:
-\begin{enumerate}
-  \item Strong Accept
-  \item Weak Accept
-  \item Weak Reject
-  \item Strong Reject
-\end{enumerate}
-The choices are recorded by denoting reponse numbers 1, 2, 3, and 4, 
-respectively. Furthermore, the response time for each gambling decision was 
-recorded in seconds. 
-\subsection{BOLD Data}
-Blood-oxygen-level dependent (BOLD) imaging data were collected from each 
-subject as he/she performed the gamble tasks. 240 time scans were done on each 
-run with a time between each scan of 2 seconds. So total scanning time is 480 
-seconds. Each scan consists of a snapshot consisting of a64 by 64 by 34 image 
-matrix. 
-
-There are also 4 model conditions, with events corresponding to 
-\begin{enumerate}
-  \item Task
-  \item Parametric Gain
-  \item Parametric Loss
-  \item Distance from Indifference
-\end{enumerate}
\ No newline at end of file
diff --git a/old_paper/sections/discussion_challenges.tex b/old_paper/sections/discussion_challenges.tex
deleted file mode 100644
index 336ae92..0000000
--- a/old_paper/sections/discussion_challenges.tex
+++ /dev/null
@@ -1,21 +0,0 @@
-% Subsection of Discussion
-\section{Discussion of Challenges}
-
-\par \indent One of the major challenges is trying to make this project as 
-reproducible as possible while following guidlines on documentation, testing 
-functions, and attempting to produce the results of the paper using our limited
-understanding of fMRI data. Travis CI bugs with various versions of python, 
-coverage failures, and errors with directory/path locations often hinder the 
-process of smooth workflows. Collaboration between five group members is no 
-doubt difficult as we found it hard to come up with an attainable final goal 
-that is still rewarding. 
-\par Technically, most of us are new to python programming and reseach using 
-git workflows, thus we have only a preliminary understanding of the various 
-python resources available for our use. Additionally, lack of statistical 
-understanding of some aspects of the paper has urged us to do independent 
-research. Yet the disconnent between theory and implementation has been a major 
-obstacle as we try to put our knowledge into practice. 
-\par Some problems can be solved or alleviated by defined checkpoints and making
-the effort to read and re-read the paper and ask questions. Further, as we 
-familiarize ourselves more and more  with various python modules and toolkits, 
-results can be easier to attain and interpret.
diff --git a/old_paper/sections/introduction.tex b/old_paper/sections/introduction.tex
deleted file mode 100644
index 0a93d75..0000000
--- a/old_paper/sections/introduction.tex
+++ /dev/null
@@ -1,8 +0,0 @@
-\section{Introduction}
-Most of the preliminary work we've done so far involves loading in the data 
-and running basic summary statistics. Our group has also written functions to 
-pull and graph the dvars (RMS of the signal derivatives) and the framewise 
-displacement. We use that in conjunction with the mean signal of the BOLD data 
-to identify outliers and use that in the near future to process our data 
-further. We have also begun rough functions to calculate the betas and begin 
-logistic regression. 
diff --git a/old_paper/sections/methods.tex b/old_paper/sections/methods.tex
deleted file mode 100644
index e8b81df..0000000
--- a/old_paper/sections/methods.tex
+++ /dev/null
@@ -1,211 +0,0 @@
-\section{Methods}
-
-\subsection{Models and analysis}
-
-We use linear models to find the relationship between behavioral and nueral 
-loss aversion cross participants as well as how participants react to different 
-loss and gain level. Below we illustrate our model using simple multiple linear 
-regression form. We may implement a mixed-effects model treating partipants as
-a random effect. Moreover, we may use the robust regression to reduce the 
-influence of outliers.
-
-\subsubsection{Behavioral analysis}
-
-We fit a Logistic regression model on the behavioral data to examine how the 
-response of individuals relates to the size of potential gain and loss of a 
-gamble. Following is the model:
-
-\begin{equation}
-logit(Y_{resp}) = \beta_0 + \beta_{loss} *X_{loss} + \beta_{gain} * X_{gain}  + 
-\epsilon
-\end{equation}
-
-where $X_{loss}$ and $X_{gain}$ are the potential loss and gain value 
-seperately, $Y_{resp}$ is a categorical independent variable representing 
-the subjects' decision on whether to accept or reject the gambles:
-
-\begin{displaymath}
-Y_{resp} = \left \{ \begin{array}{ll}
-1 & \textrm{If the subject accepted the gamble.} \\
-0 & \textrm{If the subject rejected the gamble.}
-\end{array} \right .
-\end{displaymath}
-
-Then we calculate the the behavioral loss aversion ($ \lambda $) for each 
-subject as follows, note that for simplicity, we collapse 3 runs into one model
-for each participant.
-
-\begin{equation}
-\lambda = -\beta_{loss} / \beta_{gain}
-\end{equation}
-
-We use $\lambda$ as the metric for the degree of loss aversion for each 
-participant. We have used R to fit the Logistic model, just as what the 
-authors did in the paper, and we achieved almost the same results as the paper 
-presented.
-
-\subsubsection{Linear Regression on BOLD data}
-
-For each voxel $i$, we fit a multiple linear model:
-
-\begin{equation}
-Y_{i} = \beta_{i, 0} + \beta_{i, loss} *X_{loss} + \beta_{i, gain} * X_{gain}  + 
-\epsilon_i
-\end{equation}
-
-where $Y_{i}$ is the BOLD data of voxel $i$. For each voxel, we calculate the 
-neural loss aversion $\eta_i$:
-
-\begin{equation}
-\eta_i = (-\beta_{loss}) - \beta_{gain}
-\end{equation}
-
-Using the voxelwise neural loss aversion, we do a region-specific analysis on 
-BOLD data for each participant. That is, we plot a heat map of $\eta_i$ and  
-$\beta_{i, loss}$, $ \beta_{i, gain}$ for each participant to find out the 
-regions with significant activation and regions which show a significant 
-positive or negative correlation with increasing loss or gain levels.
-
-\subsubsection{Whole brain analysis of correlation between 
-neural activity and behavioral response across participants}
-
-We then apply the above model on the standard brain to analysis the neural 
-activity and behavioral response across participants. For each participant, 
-we pick up several regions with highest activation level, calculate the mean 
-neural loss aversion $\bar{\eta}$ within these specific region. Thus we could 
-examine the relationship between neural activity and behavioral using the 
-following regression model:
-
-\begin{equation}
-\lambda = \alpha_0 + \alpha_1 * \eta + \epsilon
-\end{equation}
-
-where the sample size is the number of participants(16).
-
-\subsubsection{Cross-validation}
-
-We fit linear models for each voxel for each participant. For each linear
-model, we do a k-fold cross-validation. Since the sample size for each linear 
-regression model range from 80-90, we choose to use 10 fold cross-validation,
-which means the original sample is randomly pertitioned into 10 equal sized 
-subsamples. \\
-In the behavioral analysis using Logistic regression, since the responce 
-variables are binary, we calculate the misclassification error rate to 
-summarize the fit. In the neural linear regression model using BOLD data, we 
-use the mean squared error to summarize the errors.
-
-\subsubsection{Inferences on Data}
-
-After fitting regression models on our BOLD and behavioral data, we would try 
-assessing and validating our models. In order to do this, we would calculate 
-for the residual sum of squares for our model. We have to do three tests for 
-the model. The first one is that we calculate the t-statistics and p-value for 
-our beta coefficients to check whether our beta parameters are statistically 
-significant at a significance level of 5\%. The second one is that we calculate
-the residuals of this linear model and check whether it follows a normal 
-distribution. The third one is that we calculate the R-Squared value and the 
-adjusted R-squared value to see whether the values are good for the linear 
-regression model.\\
-
-
-\subsection{Explanation on model simplification}
-
-\subsubsection{Use of Data}
-\indent \indent First of all, for simplicity reasons, we are not using all the 
-regressors the paper used. The model in the paper performed regression on the 
-BOLD data with gain, loss and euclidean distance to indifference. In our model,
-we are leaving out the regressor euclidean distance to indifference. The paper 
-and its supplement material didn't document the exact way the authors 
-calculated this parameter; we are having a hard time reproducing this 
-parameter. Therefore, we decide to leave out this parameter when doing our own 
-regression.
-
-\subsubsection{Simplification of regression on BOLD data}
-
-\indent \indent We plan on simplifying the model on neural data. In the 
-original data analysis, the authors performed a mixed effect model when 
-regressing the potential gain and loss values against the BOLD data across 
-runs, since there are three different runs for each subject and the authors 
-were trying to incorporate all three runs into one model. The mixed effect 
-model adds a random effects term, which is associated with individual 
-experimental units drawn at random from a population. In this case, it 
-measures the difference between the average brain activation in run i and the 
-average brain activation in all three runs.
-
-We are simplifying the model because it is much easier to perform a simple 
-linear regression in python. In addition, we do not have a great deal of 
-understanding of fMRI data, so simple linear model would suffice when we are 
-only performing exploratory data analysis and looking for obvious pattern in 
-the data.
-
-After looking at the initial result from our linear regression model, we can 
-decide whether we want to further explore the relationship between the 
-dependent variable (BOLD data) and the independent variables (gain and loss) 
-and whether we want to continue to fit a mixed effect model.
-
-\subsection{Issues with analyses and potential solutions}
-
-\subsubsection{Selecting specific regions to further explore 
-correlation between neural and behavioral activity}
-
-\indent \indent Since we have no knowledge on the sections of brain that might 
-experience large difference in activation, it is hard for us to pick the 
-regions to deeper explore the correspondence between neural and behavioral loss 
-aversion.
-
-There are two potential ways to deal with this issue. The first one is to read 
-more paper and related articles to learn which parts of the brain are likely to 
-react in our given scenario -- faced with potential gain and loss combinations. 
-Another way to deal with the issue to to fit a regression for every part of the 
-brain and look for the areas with higher correspondence (higher slope). Then, 
-we select and graph a few areas with the most significant positive or negative 
-correlation between the parametric response to potential losses and behavioral 
-loss aversion (ln(λ)) across participants.
-
-\subsubsection{Producing heat map}
-
-\indent \indent Another issue that we are facing during our project is finding 
-the same region to plot for each participant. We see that each region of the 
-brain has its own standard coordinates. However, without much knowledge of 
-fMRI, we are not sure how to use these standard coordinates to locate the 
-regions of the brain.
-
-From our understanding, each subject's brain is mapped onto a standard brain 
-and we then use the coordinates for the standard brain to extract data from 
-the areas we are interested in. However, currently, we don't have the skill to 
-perform this step.
-
-\subsubsection{Further Research}
-
-We fit a linear regression model combining behavioral and BOLD data to examine 
-the relationship of correlation between neural activity and behavioral 
-response, we use another method which is different from what is mentioned in 
-the paper. We add the behavioral response to the regression model on BOLD data 
-as a predictor. We use the original 4-level response as stated below. \\ 
-
-Moreover, if the three tests we do for the linear regression model is bad. We 
-can plot the independents and the dependents on plots to see whether they fit a 
-model that is different from linear regression models. There may be another 
-reason why the performance of linear regression models are bad which is that we 
-simplify our model that we didn’t try a mixed model as the researchers in the 
-paper did.
-
-\begin{tabular}{lllll}
-\hline
-behavioral response & strongly accept & weakly accept & weakly reject & 
-strongly reject\\ 
-\hline
-$X_{behav}$ & 1 & 2 & 3 & 4 \\
-\hline
-\end{tabular}
-
-And the models are following:
-
-\begin{equation}
-Y_{i} = \beta_{i, 0} + \beta_{i, behav} * X_{behav} + \epsilon_i
-\end{equation}
-
-However, since the response and level of loss and gain are potentially 
-correlated, we might need to use stepwise regression to choose the best 
-predictor from the regression model presented above.
-
diff --git a/old_paper/sections/results.tex b/old_paper/sections/results.tex
deleted file mode 100644
index 4dd83a4..0000000
--- a/old_paper/sections/results.tex
+++ /dev/null
@@ -1,20 +0,0 @@
-\section{Results}
-
-\begin{figure}[H]
-    \centering
-        \includegraphics[scale=0.5]{figures/dvars_sub9run1.png}
-\end{figure}
-
-\begin{figure}[H]
-    \centering
-        \includegraphics[scale=0.5]{figures/mean_sub9run1.png}
-\end{figure}    
-
-\begin{figure}[H]
-    \centering
-        \includegraphics[scale = 0.5]{figures/fd_sub9run1.png}
-\end{figure}
-
-\begin{center}
-    Red points signify outliers in all three figures.
-\end{center}
diff --git a/paper/data_results/temp.txt b/paper/data_results/temp.txt
new file mode 100644
index 0000000..2f798ad
--- /dev/null
+++ b/paper/data_results/temp.txt
@@ -0,0 +1 @@
+Temp txt file, delete afterwards